Updated on 2026/03/05

写真a

 
OKUTOMI MASATOSHI
 
Organization
School of Engineering Specially Appointed Professor
Title
Specially Appointed Professor
External link

News & Topics

Degree

  • Doctor of Engineering ( Tokyo Institute of Technology )

Research Areas

  • Informatics / Perceptual information processing

Education

  • Tokyo Institute of Technology   Graduate School, Division of Science and Engineering

    - 1983

      More details

  • Tokyo Institute of Technology   Graduate School of Science and Engineering

    - 1983

      More details

    Country: Japan

    researchmap

  • The University of Tokyo   The Faculty of Engineering   Department of Mathematical Engineering and Information Physics

    - 1981

      More details

    Country: Japan

    researchmap

Research History

  • Tokyo Institute of Technology   School of Engineering   Professor

    2016.4

      More details

  • Tokyo Institute of Technology   Graduate School of Science and Engineering   Professor

    2002.4 - 2016.3

      More details

  • Tokyo Institute of Technology   Graduate School of Information Science and Engineering   Associate Professor

    1994.4 - 2002.3

      More details

  • キヤノン(株) 情報システム研究所 主任研究員

    1992 - 1994

      More details

  • カーネギーメロン大学 コンピュータサイエンス学科 客員研究員

    1987 - 1990

      More details

  • キヤノン(株) 中央研究所 研究員

    1983 - 1991

      More details

▼display all

Professional Memberships

▼display all

Committee Memberships

  • 日本学術振興会   科学研究費委員会専門委員  

    2017.4 - 2018.3   

      More details

  • 科学技術振興機構   マッチングプランナープログラム専門委員  

    2015.4 - 2017.3   

      More details

  • 光産業技術振興協会   入出力調査専門委員会委員長  

    2014.4 - 2018.3   

      More details

  • 画像情報教育振興協会   画像処理エンジニア教育推進委員会委員長  

    2011.4   

      More details

  • 情報処理学会コンピュータビジョンとイメージメディア研究会   主査  

    2010.4 - 2012.3   

      More details

  • 画像の認識・理解シンポジウム   実行委員長  

    2010 - 2011   

      More details

  • 画像の認識・理解シンポジウム   プログラム委員長  

    2009   

      More details

  • 画像センシングシンポジウム   実行委員長  

    2008   

      More details

  • 画像センシングシンポジウム   運営委員長  

    2007   

      More details

  • International Conference on Computer Vision   Publicity Chair  

    2007   

      More details

  • 計測自動制御学会   評議員  

    2006.3 - 2011.3   

      More details

  • 計測自動制御学会   国際委員会副委員長  

    2005.4 - 2006.3   

      More details

  • 画像センシング技術研究会   組織委員  

    2005   

      More details

  • SICE Annual Conference   Program Chair  

    2005   

      More details

  • 計測自動制御学会   常務理事  

    2004.3 - 2006.4   

      More details

    Committee type:Academic society

    計測自動制御学会

    researchmap

  • 情報処理学会コンピュータビジョンとイメージメディア研究会   運営委員  

    2002.4 - 2016.3   

      More details

  • 画像情報教育振興協会   ビジュアル情報処理テキスト編集委員長  

    2002   

      More details

  • 画像情報教育振興協会   ディジタル画像処理テキスト編集委員長  

    2002   

      More details

  • 画像センシングシンポジウム   プログラム委員長  

    1999   

      More details

  • 画像情報教育振興協会   画像処理検定問題選定委員会委員長  

    1996.4 - 2003.3   

      More details

▼display all

Papers

  • Development of Deep Learning-Based Virtual Lugol Chromoendoscopy for Superficial Esophageal Squamous Cell Carcinoma. International journal

    Yosuke Toya, Sho Suzuki, Yusuke Monno, Ryo Arai, Takahiro Dohmen, Makoto Eizuka, Masatoshi Okutomi, Takayuki Matsumoto

    Journal of gastroenterology and hepatology   2024.12

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    BACKGROUND: Lugol chromoendoscopy has been shown to increase the sensitivity of detection of esophageal squamous cell carcinoma (ESCC). We aimed to develop a deep learning-based virtual lugol chromoendoscopy (V-LCE) method. METHODS: We developed still V-LCE images for superficial ESCC using a cycle-consistent generative adversarial network (CycleGAN). Six endoscopists graded the detection and margins of ESCCs using white-light endoscopy (WLE), real lugol chromoendoscopy (R-LCE), and V-LCE on a five-point scale ranging from 1 (poor) to 5 (excellent). We also calculated and compared the color differences between cancerous and non-cancerous areas using WLE, R-LCE, and V-LCE. RESULTS: Scores for the detection and margins were significantly higher with R-LCE than V-LCE (detection, 4.7 vs. 3.8, respectively; p < 0.001; margins, 4.3 vs. 3.0, respectively; p < 0.001). There were nonsignificant trends towards higher scores with V-LCE than WLE (detection, 3.8 vs. 3.3, respectively; p = 0.089; margins, 3.0 vs. 2.7, respectively; p = 0.130). Color differences were significantly greater with V-LCE than WLE (p < 0.001) and with R-LCE than V-LCE (p < 0.001) (39.6 with R-LCE, 29.6 with V-LCE, and 18.3 with WLE). CONCLUSIONS: Our V-LCE has a middle performance between R-LCE and WLE in terms of lesion detection, margin, and color difference. It suggests that V-LCE potentially improves the endoscopic diagnosis of superficial ESCC.

    DOI: 10.1111/jgh.16843

    PubMed

    researchmap

  • Degraded Image Classification using Knowledge Distillation and Robust Data Augmentations

    Dinesh DAULTANI, Masayuki TANAKA, Masatoshi OKUTOMI, Kazuki ENDO

    IEICE Transactions on Information and Systems   E107.D ( 12 )   1517 - 1528   2024.12

     More details

    Publishing type:Research paper (scientific journal)   Publisher:Institute of Electronics, Information and Communications Engineers (IEICE)  

    DOI: 10.1587/transinf.2024edp7016

    researchmap

  • Neural Radiance Fields for Novel View Synthesis in Monocular Gastroscopy. International journal

    Zijie Jiang, Yusuke Monno, Masatoshi Okutomi, Sho Suzuki, Kenji Miki

    Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference   2024   1 - 5   2024.7

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    Enabling the synthesis of arbitrarily novel viewpoint images within a patient's stomach from pre-captured monocular gastroscopic images is a promising topic in stomach diagnosis. Typical methods to achieve this objective integrate traditional 3D reconstruction techniques, including structure-from-motion (SfM) and Poisson surface reconstruction. These methods produce explicit 3D representations, such as point clouds and meshes, thereby enabling the rendering of the images from novel viewpoints. However, the existence of low-texture and non-Lambertian regions within the stomach often results in noisy and incomplete reconstructions of point clouds and meshes, hindering the attainment of high-quality image rendering. In this paper, we apply the emerging technique of neural radiance fields (NeRF) to monocular gastroscopic data for synthesizing photo-realistic images for novel viewpoints. To address the performance degradation due to view sparsity in local regions of monocular gastroscopy, we incorporate geometry priors from a pre-reconstructed point cloud into the training of NeRF, which introduces a novel geometry-based loss to both pre-captured observed views and generated unobserved views. Compared to other recent NeRF methods, our approach showcases high-fidelity image renderings from novel viewpoints within the stomach both qualitatively and quantitatively.

    DOI: 10.1109/EMBC53108.2024.10782186

    PubMed

    researchmap

  • Diagnostic performance of deep-learning-based virtual chromoendoscopy in gastric neoplasms

    Sho Suzuki, Yusuke Monno, Ryo Arai, Masaki Miyaoka, Yosuke Toya, Mitsuru Esaki, Takuya Wada, Waku Hatta, Ayaka Takasu, Shigeaki Nagao, Fumiaki Ishibashi, Yohei Minato, Kenichi Konda, Takahiro Dohmen, Kenji Miki, Masatoshi Okutomi

    Gastric Cancer   27 ( 3 )   539 - 547   2024.5

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    BACKGROUNDS: Cycle-consistent generative adversarial network (CycleGAN) is a deep neural network model that performs image-to-image translations. We generated virtual indigo carmine (IC) chromoendoscopy images of gastric neoplasms using CycleGAN and compared their diagnostic performance with that of white light endoscopy (WLE). METHODS: WLE and IC images of 176 patients with gastric neoplasms who underwent endoscopic resection were obtained. We used 1,633 images (911 WLE and 722 IC) of 146 cases in the training dataset to develop virtual IC images using CycleGAN. The remaining 30 WLE images were translated into 30 virtual IC images using the trained CycleGAN and used for validation. The lesion borders were evaluated by 118 endoscopists from 22 institutions using the 60 paired virtual IC and WLE images. The lesion area concordance rate and successful whole-lesion diagnosis were compared. RESULTS: The lesion area concordance rate based on the pathological diagnosis in virtual IC was lower than in WLE (44.1% vs. 48.5%, p < 0.01). The successful whole-lesion diagnosis was higher in the virtual IC than in WLE images; however, the difference was insignificant (28.2% vs. 26.4%, p = 0.11). Conversely, subgroup analyses revealed a significantly higher diagnosis in virtual IC than in WLE for depressed morphology (41.9% vs. 36.9%, p = 0.02), differentiated histology (27.6% vs. 24.8%, p = 0.02), smaller lesion size (42.3% vs. 38.3%, p = 0.01), and assessed by expert endoscopists (27.3% vs. 23.6%, p = 0.03). CONCLUSIONS: The diagnostic ability of virtual IC was higher for some lesions, but not completely superior to that of WLE. Adjustments are required to improve the imaging system's performance.

    DOI: 10.1007/s10120-024-01469-7

    PubMed

    researchmap

  • Deep Sensing for Compressive Video Acquisition.

    Michitaka Yoshida, Akihiko Torii, Masatoshi Okutomi, Rin-Ichiro Taniguchi, Hajime Nagahara, Yasushi Yagi

    Sensors   23 ( 17 )   7535 - 7535   2023.9

     More details

    Publishing type:Research paper (scientific journal)  

    DOI: 10.3390/s23177535

    researchmap

  • Semantic Segmentation of Degraded Images Using Layer-Wise Feature Adjustor

    Kazuki Endo, Masayuki Tanaka, Masatoshi Okutomi

    2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)   3204 - 3212   2023.1

     More details

    Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    DOI: 10.1109/wacv56688.2023.00322

    researchmap

  • Learning-Based Depth and Pose Estimation for Monocular Endoscope with Loss Generalization. International journal

    Aji Resindra Widya, Yusuke Monno, Masatoshi Okutomi, Sho Suzuki, Takuji Gotoda, Kenji Miki

    Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference   2021   3547 - 3552   2021.11

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    Gastroendoscopy has been a clinical standard for diagnosing and treating conditions that affect a part of a patient's digestive system, such as the stomach. Despite the fact that gastroendoscopy has a lot of advantages for patients, there exist some challenges for practitioners, such as the lack of 3D perception, including the depth and the endoscope pose information. Such challenges make navigating the endoscope and localizing any found lesion in a digestive tract difficult. To tackle these problems, deep learning-based approaches have been proposed to provide monocular gastroendoscopy with additional yet important depth and pose information. In this paper, we propose a novel supervised approach to train depth and pose estimation networks using consecutive endoscopy images to assist the endoscope navigation in the stomach. We firstly generate real depth and pose training data using our previously proposed whole stomach 3D reconstruction pipeline to avoid poor generalization ability between computer-generated (CG) models and real data for the stomach. In addition, we propose a novel generalized photometric loss function to avoid the complicated process of finding proper weights for balancing the depth and the pose loss terms, which is required for existing direct depth and pose supervision approaches. We then experimentally show that our proposed generalized loss performs better than existing direct supervision losses.

    DOI: 10.1109/EMBC46164.2021.9630156

    PubMed

    researchmap

  • Recurrent RLCN-guided attention network for single image deraining

    Yizhou Li, Yusuke Monno, Masatoshi Okutomi

    Proceedings of MVA 2021 - 17th International Conference on Machine Vision Applications   2021.7

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:Institute of Electrical and Electronics Engineers Inc.  

    DOI: 10.23919/MVA51890.2021.9511405

    Scopus

    researchmap

  • 多露光カラーフィルタアレイを用いた深層学習によるスナップショットHDR画像生成 Reviewed

    岡本悠太郎, 須田武流, 田中正行, 紋野雄介, 奥富正敏

    第27回画像センシングシンポジウム(SSII2021)   SO1-23-1 - SO1-23-8   2021.6

     More details

    Authorship:Last author   Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • 多様な劣化水準に対応可能な劣化画像のクラス分類ネットワーク Reviewed

    遠藤和紀, 田中正行, 奥富正敏

    第27回画像センシングシンポジウム(SSII2021)   SO1-16-1 - SO1-16-8   2021.6

     More details

    Authorship:Last author   Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • Polarimetric MVIR: カラー偏光画像を用いたマルチビューインバースレンダリングによる高精細3次元復元 Reviewed

    趙 金雨, 紋野雄介, 奥富正敏

    第27回画像センシングシンポジウム(SSII2021)   SO1-04-1 - SO1-04-8   2021.6

     More details

    Authorship:Last author   Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • Spectral MVIR: Joint Reconstruction of 3D Shape and Spectral Reflectance Reviewed

    Chunyu Li, Yusuke Monno, Masatoshi Okutomi

    Proceedings of IEEE International Conference on Computational Photography (ICCP2021)   98 - 109   2021.5

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Gradient-domain image reconstruction framework using chroma-preserving intensity-range and base-structure constraints Reviewed

    Takashi Shibata, Masayuki Tanaka, Masatoshi Okutomi

    Journal of Electronic Imaging   30 ( 02 )   023032-1 - 023032-22   2021.4

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (scientific journal)   Publisher:SPIE-Intl Soc Optical Eng  

    DOI: 10.1117/1.jei.30.2.023032

    researchmap

  • VIO-Aided Structure from Motion Under Challenging Environments Reviewed

    Zijie Jiang, Hajime Taira, Naoyuki Miyashita, Masatoshi Okutomi

    Proceedings of the 22nd IEEE International Conference on Industrial Technology (ICIT2021)   2021.3

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Stomach 3D Reconstruction Using Virtual Chromoendoscopic Images Reviewed

    Aji Resindra Widya, Yusuke Monno, Masatoshi Okutomi, Sho Suzuki, Takuji Gotoda, Kenji Miki

    IEEE Journal of Translational Engineering in Health and Medicine   9   1700211-1 - 1700211-11   2021.2

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:Institute of Electrical and Electronics Engineers (IEEE)  

    DOI: 10.1109/jtehm.2021.3062226

    researchmap

  • Self-supervised monocular depth estimation in gastroendoscopy using GAN-augmented images Reviewed

    Aji Resindra Widya, Yusuke Monno, Masatoshi Okutomi, Sho Suzuki, Takuji Gotoda, Kenji Miki

    SPIE Medical Imaging, Proceedings of SPIE   11596   1159616-1 - 1159616-10   2021.2

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Human Segmentation with Dynamic LiDAR Data Reviewed

    Tao Zhong, Wonjik Kim, Masayuki Tanaka, Masatoshi Okutomi

    Proceedings of the 25th International Conference on Pattern Recognition (ICPR2020)   2021.1

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Adaptive Future Frame Prediction with Ensemble Network Reviewed

    Wonjik Kim, Masayuki Tanaka, Masatoshi Okutomi, Yoko Sasaki

    Proceedings of ICPR2020 Workshop : International Workshop on Pattern Forecasting (PATCAST)   2021.1

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • CNN-Based Classification of Degraded Images with Awareness of Degradation Levels Reviewed

    Kazuki Endo, Masayuki Tanaka, Masatoshi Okutomi

    IEEE Transactions on Circuits and Systems for Video Technology   1 - 1   2020.12

     More details

    Authorship:Last author   Publishing type:Research paper (scientific journal)   Publisher:Institute of Electrical and Electronics Engineers (IEEE)  

    DOI: 10.1109/tcsvt.2020.3045659

    researchmap

  • Deep Snapshot HDR Imaging Using Multi-Exposure Color Filter Array Reviewed

    Takeru Suda, Masayuki Tanaka, Yusuke Monno, Masatoshi Okutomi

    Proceedings of the 15th Asian Conference on Computer Vision (ACCV2020)   abs/2011.10232   353 - 370   2020.11

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

    Other Link: https://dblp.uni-trier.de/db/journals/corr/corr2011.html#abs-2011-10232

  • 3D Model Reconstruction of Whole Stomach from Standard Endoscope Video Reviewed

    Sho Suzuki, Kenji Miki, Takuji Gotoda, Aji Resindra Widya, Yusuke Monno, Masatoshi Okutomi

    Proceedings of the International Digestive Disease Forum (IDDF2020)   2020.11

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Spectral Reflectance Estimation Using Projector with Unknown Spectral Power Distribution Reviewed

    Hironori Hidaka, Yusuke Monno, Masatoshi Okutomi

    Proceedings of the Twenty-eighth Color and Imaging Conference (CIC28)   205 - 209   2020.11

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Long-Term Visual Localization Revisited Reviewed

    Carl Toft, Will Maddern, Akihiko Torii, Lars Hammarstrand, Erik Stenborg, Daniel Safari, Masatoshi Okutomi, Marc Pollefeys, Josef Sivic, Tomas Pajdla, Fredrik Kahl, Torsten Sattler

    IEEE Transactions on Pattern Analysis and Machine Intelligence   1 - 1   2020.10

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:Institute of Electrical and Electronics Engineers (IEEE)  

    DOI: 10.1109/tpami.2020.3032010

    researchmap

  • Monochrome and Color Polarization Demosaicking Using Edge-Aware Residual Interpolation Reviewed

    Miki Morimatsu, Yusuke Monno, Masayuki Tanaka, Masatoshi Okutomi

    Proceedings of IEEE International Conference on Image Processing(ICIP2020)   2571 - 2575   2020.10

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1109/ICIP40778.2020.9191085

    researchmap

    Other Link: https://dblp.uni-trier.de/db/conf/icip/icip2020.html#MorimatsuMTO20

  • Classifying Degraded Images Over Various Levels of Degradation Reviewed

    Kazuki Endo, Masayuki Tanaka, Masatoshi Okutomi

    Proceedings of IEEE International Conference on Image Processing(ICIP2020)   1691 - 1695   2020.10

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Pro-Cam SSfM: Projector-Camera System for Structure and Spectral Reflectance from Motion Invited

    Chunyu Li, Yusuke Monno, Hironori Hidaka, Masatoshi Okutomi

    2019 IEEE/CVF International Conference on Computer Vision(ICCV)   2414 - 2423   2020.8

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (conference, symposium, etc.)   Publisher:IEEE  

    DOI: 10.1109/ICCV.2019.00250

    researchmap

    Other Link: https://dblp.uni-trier.de/db/conf/iccv/iccv2019.html#LiMHO19

  • Polarimetric Multi-view Inverse Rendering Reviewed

    Jinyu Zhao, Yusuke Monno, Masatoshi Okutomi

    Proceedings of 16th European Conference on Computer Vision (ECCV2020)   85 - 102   2020.8

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1007/978-3-030-58586-0_6

    researchmap

    Other Link: https://dblp.uni-trier.de/db/conf/eccv/eccv2020-24.html#ZhaoMO20

  • Remote Heart Rate Estimation Based on 3D Facial Landmarks Reviewed

    Yuichiro Maki, Yusuke Monno, Masayuki Tanaka, Masatoshi Okutomi

    Proceedings of the 42nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC2020)   2634 - 2637   2020.7

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1109/EMBC44109.2020.9176563

    researchmap

    Other Link: https://dblp.uni-trier.de/db/conf/embc/embc2020.html#MakiMTO20

  • Stomach 3D Reconstruction Based on Virtual Chromoendoscopic Image Generation Reviewed International journal

    Aji Resindra Widya, Yusuke Monno, Masatoshi Okutomi, Sho Suzuki, Takuji Gotoda, Kenji Miki

    Proceedings of the 42nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC2020)   2020   1848 - 1852   2020.7

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Gastric endoscopy is a standard clinical process that enables medical practitioners to diagnose various lesions inside a patient's stomach. If any lesion is found, it is very important to perceive the location of the lesion relative to the global view of the stomach. Our previous research showed that this could be addressed by reconstructing the whole stomach shape from chromoendoscopic images using a structure-from-motion (SfM) pipeline, in which indigo carmine (IC) blue dye-sprayed images were used to increase feature matches for SfM by enhancing stomach surface's textures. However, spraying the IC dye to the whole stomach requires additional time, labor, and cost, which is not desirable for patients and practitioners. In this paper, we propose an alternative way to achieve whole stomach 3D reconstruction without the need of the IC dye by generating virtual IC-sprayed (VIC) images based on image-to-image style translation trained on unpaired real no-IC and IC-sprayed images. We have specifically investigated the effect of input and output color channel selection for generating the VIC images and found that translating no-IC green-channel images to IC-sprayed red-channel images gives the best SfM reconstruction result.

    DOI: 10.1109/EMBC44109.2020.9176016

    PubMed

    researchmap

  • Tunable Color Correction for Noisy Images Reviewed

    Ryo Yamakabe, Yusuke Monno, Masayuki Tanaka, Masatoshi Okutomi

    Journal of Electronic Imaging   Vol. 29 ( No. 3 )   033012-1 - 033012-24   2020.6

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (scientific journal)  

    DOI: 10.1117/1.JEI.29.3.033012

    researchmap

  • 内視鏡動画像からの胃の3次元形状復元 Reviewed

    紋野雄介, Widya Aji Resindra, 奥富正敏, 鈴木翔, 後藤田卓志, 三木健司

    第26回画像センシングシンポジウム(SSII2020)   IS3-29-1 - IS3-29-6   2020.6

     More details

    Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • 畳み込みニューラルネットワークを用いた劣化画像のクラス分類 Reviewed

    遠藤和紀, 田中正行, 奥富正敏

    第26回画像センシングシンポジウム(SSII2020)   IS1-10-1 - IS1-10-7   2020.6

     More details

    Authorship:Last author   Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • 3D Pipe Network Reconstruction Based on Structure from Motion with Incremental Conic Shape Detection and Cylindrical Constraint Reviewed

    Sho Kagami, Hajime Taira, Naoyuki Miyashita, Akihiko Torii, Masatoshi Okutomi

    Proceedings of 29th IEEE International Symposium on Industrial Electronics(ISIE2020)   1345 - 1352   2020.6

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • ステレオカメラのセルフキャリブレーションに対する解析と2フレーム手法の提案 Reviewed

    大石慎太郎, 奥富正敏

    第26回画像センシングシンポジウム(SSII2020)   IS3-26-1 - IS3-26-6   2020.6

     More details

    Authorship:Last author   Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • Pro-Cam SSfM:汎用プロジェクタとカメラを用いた分光3D計測 Reviewed

    李淳雨, 紋野雄介, 日高宏紀, 奥富正敏

    第26回画像センシングシンポジウム(SSII2020)   IS3-09-1 - IS3-09-6   2020.6

     More details

    Authorship:Last author   Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • Spatial-Spectral-Temporal Fusion for Remote Heart Rate Estimation Reviewed

    Shiika Kado, Yusuke Monno, Kazunori Yoshizaki, Masayuki Tanaka, Masatoshi Okutomi

    IEEE Sensors Journal   Vol. 20 ( No. 19 )   11688 - 11697   2020.5

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  • Learning-Based Human Segmentation and Velocity Estimation Using Automatic Labeled LiDAR Sequence for Training Reviewed

    Wonjik Kim, Masayuki Tanaka, Masatoshi Okutomi, Yoko Sasaki

    IEEE Access   Vol. 8   88443 - 88452   2020.5

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    DOI: 10.1109/ACCESS.2020.2993299

    researchmap

  • 内視鏡画像を基にした胃の3次元モデル表示法の開発

    鈴木翔, 三木健司, 後藤田卓志, Widya Aji Resindra, 紋野雄介, 奥富 正敏

    第16回日本消化管学会総会学術集会 ワークショップ11   2020.2

     More details

    Authorship:Last author   Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • CNN-based Classification of Degraded Images Reviewed

    Kazuki Endo, Masayuki Tanaka, Masatoshi Okutomi

    Proceedings of IS&T International Symposium on Electronic Imaging (EI2020)   028-1 - 028-6   2020.1

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • InLoc: Indoor Visual Localization with Dense Matching and View Synthesis Reviewed

    Hajime Taira, Masatoshi Okutomi, Torsten Sattler, Mircea Cimpoi, Marc Pollefeys, Josef Sivic, Tomas Pajdla, Akihiko Torii

    IEEE Transactions on Pattern Analysis and Machine Intelligence   43 ( 4 )   1293 - 1307   2019.11

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:Institute of Electrical and Electronics Engineers (IEEE)  

    DOI: 10.1109/tpami.2019.2952114

    researchmap

  • Whole Stomach 3D Reconstruction and Frame Localization from Monocular Endoscope Video International journal

    Aji Resindra Widya, Yusuke Monno, Masatoshi Okutomi, Sho Suzuki, Takuji Gotoda, Kenji Miki

    IEEE Journal of Translational Engineering in Health & Medicine   Vol. 7   3300310-1 - 3300310-10   2019.11

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    Gastric endoscopy is a common clinical practice that enables medical doctors to diagnose various lesions inside a stomach. In order to identify the location of a gastric lesion such as early cancer and a peptic ulcer within the stomach, this work addresses to reconstruct the color-textured 3D model of a whole stomach from a standard monocular endoscope video and localize any selected video frame to the 3D model. We examine how to enable structure-from-motion (SfM) to reconstruct the whole shape of a stomach from endoscope images, which is a challenging task due to the texture-less nature of the stomach surface. We specifically investigate the combined effect of chromo-endoscopy and color channel selection on SfM to increase the number of feature points. We also design a plane fitting-based algorithm for 3D point outliers removal to improve the 3D model quality. We show that whole stomach 3D reconstruction can be achieved (more than 90% of the frames can be reconstructed) by using red channel images captured under chromo-endoscopy by spreading indigo carmine (IC) dye on the stomach surface. In experimental results, we demonstrate the reconstructed 3D models for seven subjects and the application of lesion localization and reconstruction. The methodology and results presented in this paper could offer some valuable reference to other researchers and also could be an excellent tool for gastric surgeons in various computer-aided diagnosis applications.

    DOI: 10.1109/JTEHM.2019.2946802

    PubMed

    researchmap

  • 内視鏡画像を基にした胃の3次元モデル表示法の開発

    鈴木翔, 三木健司, 後藤田卓志, Widya Aji Resindra, 紋野雄介, 今堀公介, 奥富 正敏

    第27回日本消化器関連学会週間   2019.11

     More details

    Authorship:Last author   Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • Pro-Cam SSfM: Projector-Camera System for Structure and Spectral Reflectance From Motion Reviewed

    Chunyu Li, Yusuke Monno, Hironori Hidaka, Masatoshi Okutomi

    2019 IEEE/CVF International Conference on Computer Vision (ICCV)   2414 - 2423   2019.10

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    DOI: 10.1109/iccv.2019.00250

    researchmap

  • Is This the Right Place? Geometric-Semantic Pose Verification for Indoor Visual Localization Reviewed

    Hajime Taira, Ignacio Rocco, Jiri Sedlar, Masatoshi Okutomi, Josef Sivic, Tomas Pajdla, Torsten Sattler, Akihiko Torii

    2019 IEEE/CVF International Conference on Computer Vision (ICCV)   4372 - 4382   2019.10

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    DOI: 10.1109/iccv.2019.00447

    researchmap

  • Extraction of Degradation Parameters for Transparency of an Image Restoration Network Reviewed

    Kazutaka Uchida, Masayuki Tanaka, Masatoshi Okutomi

    2019 IEEE 8th Global Conference on Consumer Electronics (GCCE)   134 - 138   2019.10

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    DOI: 10.1109/gcce46687.2019.9015336

    researchmap

  • Are Large-Scale 3D Models Really Necessary for Accurate Visual Localization? Reviewed

    Akihiko Torii, Hajime Taira, Josef Sivic, Marc Pollefeys, Masatoshi Okutomi, Tomas Pajdla, Torsten Sattler

    IEEE Transactions on Pattern Analysis and Machine Intelligence   43 ( 3 )   814 - 829   2019.9

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:Institute of Electrical and Electronics Engineers (IEEE)  

    DOI: 10.1109/tpami.2019.2941876

    researchmap

  • Visible and Thermal Camera System for 360-degree Dynamic Panorama

    Thapanapong Rukkanchanunt, Takashi Shibata, Masayuki Tanaka, Masatoshi Okutomi

    Abstract Book of The 3rd Quantitative InfraRed Thermography Conference Asia (QIRT-Asia2019)   151 - 152   2019.7

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • 3D Reconstruction of Whole Stomach from Endoscope Video Using Structure-from-Motion Reviewed International journal

    Aji Resindra Widya, Yusuke Monno, Kosuke Imahori, Masatoshi Okutomi, Sho Suzuki, Takuji Gotoda, Kenji Miki

    2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)   2019   3900 - 3904   2019.7

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    Gastric endoscopy is a common clinical practice that enables medical doctors to diagnose the stomach inside a body. In order to identify a gastric lesion's location such as early gastric cancer within the stomach, this work addressed to reconstruct the 3D shape of a whole stomach with color texture information generated from a standard monocular endoscope video. Previous works have tried to reconstruct the 3D structures of various organs from endoscope images. However, they are mainly focused on a partial surface. In this work, we investigated how to enable structure-from-motion (SfM) to reconstruct the whole shape of a stomach from a standard endoscope video. We specifically investigated the combined effect of chromo-endoscopy and color channel selection on SfM. Our study found that 3D reconstruction of the whole stomach can be achieved by using red channel images captured under chromo-endoscopy by spreading indigo carmine (IC) dye on the stomach surface.

    DOI: 10.1109/embc.2019.8857964

    PubMed

    researchmap

  • Inter-Beat Interval Estimation from Facial Video Based on Reliability of BVP Signals Reviewed

    Yuichiro Maki, Yusuke Monno, Kazunori Yoshizaki, Masayuki Tanaka, Masatoshi Okutomi

    2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)   6525 - 6528   2019.7

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    DOI: 10.1109/embc.2019.8857081

    researchmap

  • DNNにより最適化されたピクセルコーディングCMOSイメージセンサによるハイスピード撮像

    吉田道隆, 鳥居秋彦, 奥富正敏, 遠藤健太, 杉山行信, 谷口倫一郎, 長原一

    第22回画像の認識・理解シンポジウム(MIRU2019)   2019.7

     More details

    Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • Full thermal panorama from a long wavelength infrared and visible camera system Reviewed

    Thapanapong Rukkanchanunt, Masayuki Tanaka, Masatoshi Okutomi

    Journal of Electronic Imaging   Vol. 28 ( No. 3 )   033028-1 - 033028-10   2019.6

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  • Improving Transparency of Deep Neural Inference Process Reviewed

    Hiroshi Kuwajima, Masayuki Tanaka, Masatoshi Okutomi

    Progress in Artificial Intelligence   Vol. 8 ( No. 2 )   273 - 285   2019.6

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  • 単板式カメラのための高画質イメージングパイプライン--本当にデモザイキングを最初に行うべきか?-- Reviewed

    山下部諒, 紋野雄介, 田中正行, 奥富正敏

    第25回画像センシングシンポジウム(SSII2019)   IS1-38-1 - IS1-38-3   2019.6

     More details

    Authorship:Last author   Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • 参照画像を用いたラインスキャン方式ハイパースペクトルカメラ画像の動き歪み補正 Reviewed

    大塚晃太郎, 田中正行, 奥富正敏

    第25回画像センシングシンポジウム(SSII2019)   IS1-35-1 - IS1-35-6   2019.6

     More details

    Authorship:Last author   Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • 時系列情報を用いたステレオカメラのセルフキャリブーション Reviewed

    篠﨑教志, 永原聡, 奥富正敏

    第25回画像センシングシンポジウム(SSII2019)   IS2-28-1 - IS2-28-4   2019.6

     More details

    Authorship:Last author   Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • 深層学習のための精密な人モデルに基づくラベル付きLiDARデータ生成 Reviewed

    金原稷, 田中正行, 奥富正敏, 佐々木洋子

    第25回画像センシングシンポジウム(SSII2019)   IS1-42-1 - IS1-42-4   2019.6

     More details

    Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • 大規模屋内環境における3Dマップを用いた自己位置推定 Reviewed

    田平創, Torsten Sattler, Josef Sivic, Tomas Pajdla, 鳥居秋彦, 奥富正敏

    第25回画像センシングシンポジウム(SSII2019)   IS3-34-1 - IS3-34-4   2019.6

     More details

    Authorship:Last author   Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • ノンブラインド型画像復元ネットワークによる頑健な画像復元 Reviewed

    内田和隆, 田中正行, 奥富正敏

    第25回画像センシングシンポジウム(SSII2019)   IS3-16-1 - IS3-16-6   2019.6

     More details

    Authorship:Last author   Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • Gradient-Based Low-Light Image Enhancement Reviewed

    Masayuki Tanaka, Takashi Shibata, Masatoshi Okutomi

    IEEE International Conference on Computational Photography (ICCP2019)   2019.5

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Joint optimization for compressive video sensing and reconstruction under hardware constraints

    Michitaka Yoshida, Akihiko Torii, Masatoshi Okutomi, Kenta Endo, Yukinobu Sugiyama, Rin-ichiro Taniguchi, Hajime Nagahara

    IEEE International Conference on Computational Photography (ICCP2019)   2019.5

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Automatic Labeled LiDAR Data Generation based on Precise Human Model Reviewed

    Wonjik Kim, Masayuki Tanaka, Masatoshi Okutomi, Yoko Sasaki

    2019 International Conference on Robotics and Automation (ICRA)   43 - 49   2019.5

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    DOI: 10.1109/icra.2019.8793916

    researchmap

  • Automatic Labeled LiDAR Data Generation and Distance-Based Ensemble Learning for Human Segmentation Reviewed

    Wonjik Kim, Masayuki Tanaka, Masatoshi Okutomi, Yoko Sasaki

    IEEE Access   Vol. 7   55132 - 55141   2019.5

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  • Non-blind Image Restoration Based on Convolutional Neural Network Reviewed

    Kazutaka Uchida, Masayuki Tanaka, Masatoshi Okutomi

    IEEE International Conference on Computational Photography (ICCP2019)   2019.5

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Pixelwise JPEG compression detection and quality factor estimation based on convolutional neural network Reviewed

    Kazutaka Uchida, Masayuki Tanaka, Masatoshi Okutomi

    Electronic Imaging, Image Processing: Algorithms and Systems XVII   2019 ( 11 )   276-1 - 276-7   2019.1

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:Society for Imaging Science & Technology  

    DOI: 10.2352/issn.2470-1173.2019.11.ipas-276

    researchmap

  • Gradient-Based Low-Light Image Enhancement Reviewed

    Masayuki Tanaka, Takashi Shibata, Masatoshi Okutomi

    2019 IEEE International Conference on Consumer Electronics (ICCE)   1 - 2   2019.1

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    DOI: 10.1109/icce.2019.8662059

    researchmap

  • Dual-arm construction robot with remote-control function

    Hiroshi Yoshinada, Keita Kurashiki, Daisuke Kondo, Keiji Nagatani, Seiga Kiribayashi, Masataka Fuchida, Masayuki Tanaka, Atsushi Yamashita, Hajime Asama, Takashi Shibata, Masatoshi Okutomi, Yoko Sasaki, Yasuyoshi Yokokohji, Masashi Konyo, Hikaru Nagano, Fumio Kanehiro, Tomomichi Sugihara, Genya Ishigami, Shingo Ozaki, Koich Suzumori, Toru Ide, Akina Yamamoto, Kiyohiro Hioki, Takeo Oomichi, Satoshi Ashizawa, Kenjiro Tadakuma, Toshi Takamori, Tetsuya Kimura, Robin R. Murphy, Satoshi Tadokoro

    Springer Tracts in Advanced Robotics   128   195 - 264   2019

     More details

    Publishing type:Part of collection (book)  

    DOI: 10.1007/978-3-030-05321-5_5

    Scopus

    researchmap

  • 遠赤外線カメラと可視カメラを利用した悪条件下における画像取得

    田中正行, 柴田剛志, 奥富正敏

    国際画像機器展2018 国際画像セミナー   2018.12

     More details

    Authorship:Last author   Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • DISPARITY MAP ESTIMATION FROM CROSS-MODAL STEREO Reviewed

    Thapanapong Rukkanchanunt, Takashi Shibata, Masayuki Tanaka, Masatoshi Okutomi

    2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP)   988 - 992   2018.11

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    DOI: 10.1109/globalsip.2018.8646523

    researchmap

  • Single-Sensor RGB-NIR Imaging: High-Quality System Design and Prototype Implementation Reviewed

    Yusuke Monno, Hayato Teranaka, Kazunori Yoshizaki, Masayuki Tanaka, Masatoshi Okutomi

    IEEE Sensors Journal   Vol. 19 ( No. 2 )   497 - 507   2018.10

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  • Unified Image Fusion Framework With Learning-Based Application-Adaptive Importance Measure Reviewed

    Takashi Shibata, Masayuki Tanaka, Masatoshi Okutomi

    IEEE Transactions on Computational Imaging   Vol. 5 ( No. 1 )   82 - 96   2018.10

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  • Non-blind Image Restoration Based on Convolutional Neural Network Reviewed

    Kazutaka Uchida, Masayuki Tanaka, Masatoshi Okutomi

    2018 IEEE 7th Global Conference on Consumer Electronics (GCCE)   12 - 16   2018.10

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    DOI: 10.1109/gcce.2018.8574671

    researchmap

  • Coupled convolution layer for convolutional neural network

    Kazutaka Uchida, Masayuki Tanaka, Masatoshi Okutomi

    Neural Networks   105   197 - 205   2018.9

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:Elsevier Ltd  

    DOI: 10.1016/j.neunet.2018.05.002

    Scopus

    PubMed

    researchmap

  • Coupled convolution layer for convolutional neural network Reviewed

    Kazutaka Uchida, Masayuki Tanaka, Masatoshi Okutomi

    Neural Networks   Vol. 105   3548 - 3553   2018.9

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    Web of Science

    researchmap

  • ハードウェアの制約を考慮した圧縮ビデオセンシングにおける圧縮と再構成の同時最適化

    吉田道隆, 鳥居秋彦, 奥富正敏, 遠藤健太, 杉山行信, 谷口倫一郎, 長原一

    第21回画像の認識・理解シンポジウム(MIRU2018)   2018.8

     More details

    Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • Remote Heart Rate Measurement from RGB-NIR Video Based on Spatial and Spectral Face Patch Selection Reviewed

    Shiika Kado, Yusuke Monno, Kenta Moriwaki, Kazunori Yoshizaki, Masayuki Tanaka, Masatoshi Okutomi

    2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)   5676 - 5680   2018.7

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    DOI: 10.1109/embc.2018.8513464

    researchmap

  • Joint Optimization for Compressive Video Sensing and Reconstruction Under Hardware Constraints Reviewed

    Michitaka Yoshida, Akihiko Torii, Masatoshi Okutomi, Kenta Endo, Yukinobu Sugiyama, Rin-ichiro Taniguchi, Hajime Nagahara

    Computer Vision – ECCV 2018   649 - 663   2018.7

     More details

    Language:English   Publishing type:Part of collection (book)   Publisher:Springer International Publishing  

    DOI: 10.1007/978-3-030-01249-6_39

    researchmap

  • 2時刻間のカメラ運動推定を伴うステレオセルフキャリブレーション Reviewed

    洞山慶太, 鳥居秋彦, 奥富正敏

    第24回画像センシングシンポジウム(SSII2018)   SO1-IS1-29-1 - SO1-IS1-29-3   2018.6

     More details

    Authorship:Last author   Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • RGB-NIRカメラを用いた非接触心拍数推定 Reviewed

    角詩香, 紋野雄介, 森脇健太, 吉崎和徳, 田中正行, 奥富正敏

    第24回画像センシングシンポジウム(SSII2018)   SO3-IS3-18-1 - SO3-IS3-18-2   2018.6

     More details

    Authorship:Last author   Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • 汎用のカメラとプロジェクターを用いたキャリブレーションの不要な高精度3次元計測 Reviewed

    李淳雨, 鳥居秋彦, 奥富正敏

    第24回画像センシングシンポジウム(SSII2018)   SO3-IS3-10-1 - SO3-IS3-10-3   2018.6

     More details

    Authorship:Last author   Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • ノイズ増幅と色再現性のトレードオフを考慮した色補正手法 Reviewed

    山下部諒, 紋野雄介, 田中正行, 奥富正敏

    第24回画像センシングシンポジウム(SSII2018)   SO1-IS1-27-1 - SO1-IS1-27-5   2018.6

     More details

    Authorship:Last author   Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • InLoc: Indoor Visual Localization with Dense Matching and View Synthesis Reviewed

    Hajime Taira, Masatoshi Okutomi, Torsten Sattler, Mircea Cimpoi, Marc Pollefeys, Josef Sivic, Tomas Pajdla, Akihiko Torii

    2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition   7199 - 7209   2018.6

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    DOI: 10.1109/cvpr.2018.00752

    researchmap

  • 複数の長波長赤外線カメラを用いた広視野カメラシステムの開発 Reviewed

    荻野有加, 田中正行, 柴田剛志, 奥富正敏

    日本機械学会ロボティクス・メカトロニクス講演会2018(ROBOMECH2018)   2A1-J06-1 - 2A1-J06-3   2018.6

     More details

    Authorship:Last author   Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • Benchmarking 6DOF Outdoor Visual Localization in Changing Conditions Reviewed

    Torsten Sattler, Will Maddern, Carl Toft, Akihiko Torii, Lars Hammarstrand, Erik Stenborg, Daniel Safari, Masatoshi Okutomi, Marc Pollefeys, Josef Sivic, Fredrik Kahl, Tomas Pajdla

    2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition   8601 - 8610   2018.6

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    DOI: 10.1109/cvpr.2018.00897

    researchmap

  • 可視光・長波長赤外線カメラを用いたマルチモーダル広視野カメラシステムの開発 Reviewed

    荻野有加, 田中正行, 柴田剛志, 奥富正敏

    第24回画像センシングシンポジウム(SSII2018)   SO1-IS1-18-1 - SO1-IS1-18-3   2018.6

     More details

    Authorship:Last author   Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • 大規模visual localization の実用化に向けた評価用データセットの作成 Reviewed

    田平創, 荻野凌, 岩田健太郎, Torsten Sattler, Josef Sivic, Tomas Pajdla, 鳥居秋彦, 奥富正敏

    第24回画像センシングシンポジウム(SSII2018)   SO2-IS2-10-1 - SO2-IS2-10-3   2018.6

     More details

    Authorship:Last author   Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • 全方位画像を利用した疎なLiDARデータからの密な距離画像生成 Reviewed

    小池毅彦, 田中正行, 奥富正敏, 佐々木洋子

    第24回画像センシングシンポジウム(SSII2018)   SO3-IS3-02-1 - SO3-IS3-02-4   2018.6

     More details

    Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • Structure-from-motion using dense CNN features with keypoint relocalization Reviewed

    Aji Resindra Widya, Akihiko Torii, Masatoshi Okutomi

    IPSJ Transactions on Computer Vision and Applications   Vol. 10 ( 6 )   1 - 7   2018.5

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  • Depth map estimation with unknown fixed pattern projection Reviewed

    Masayuki Tanaka, Katsuhiro Fujita, Masatoshi Okutomi

    2018 IEEE International Conference on Consumer Electronics (ICCE)   446 - 448   2018.1

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    DOI: 10.1109/icce.2018.8326091

    researchmap

  • Accurate Plane Estimation Based on the Error Model of Time-of-Flight Camera Reviewed

    Yosuke Konno, Masayuki Tanaka, Masatoshi Okutomi, Yukiko Yanagawa, Koichi Kinoshita, Masato Kawade, Yuki Hasegawa

    2018 Second IEEE International Conference on Robotic Computing (IRC)   304 - 307   2018.1

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    DOI: 10.1109/irc.2018.00064

    researchmap

  • Robust, precise, and calibration-free shape acquisition with an off-the-shelf camera and projector Reviewed

    Chunyu Li, Akihiko Torii, Masatoshi Okutomi

    2018 IEEE International Conference on Consumer Electronics (ICCE)   952 - 957   2018.1

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    DOI: 10.1109/icce.2018.8326067

    researchmap

  • Adaptive residual interpolation for color and multispectral image demosaicking

    Yusuke Monno, Daisuke Kiku, Masayuki Tanaka, Masatoshi Okutomi

    Sensors (Switzerland)   17 ( 12 )   2017.12

     More details

    Publishing type:Research paper (scientific journal)  

    DOI: 10.3390/s17122787

    Scopus

    PubMed

    researchmap

  • Adaptive Residual Interpolation for Color and Multispectral Image Demosaicking Reviewed

    Yusuke Monno, Daisuke Kiku, Masayuki Tanaka, Masatoshi Okutomi

    Sensors   Vol. 17 ( No. 12 )   3861 - 3865   2017.12

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    Web of Science

    researchmap

  • Adaptive Residual Interpolation for Color and Multispectral Image Demosaicking

    Yusuke Monno, Daisuke Kiku, Masayuki Tanaka, Masatoshi Okutomi

    SENSORS   17 ( 12 )   2017.12

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    DOI: 10.3390/s17122787

    Web of Science

    researchmap

  • 遠赤外光を活用したマルチモーダル画像センシング技術とその応用

    柴田剛志, 田中正行, 奥富正敏

    ビジョンと技術の実利用ワークショップ(ViEW2017)   1 - 1   2017.12

     More details

    Authorship:Last author   Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • 3Dシーンの復元 --より精密に、より大規模に、より完全な情報を--

    奥富正敏

    3Dレーザスキャニング&イメージングシンポジウム 2017   2017.11

     More details

    Authorship:Lead author   Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • 入出力分野の最新動向

    奥富正敏

    光産業動向セミナー講演予稿集   29 - 34   2017.10

     More details

    Authorship:Lead author   Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • 次世代ヒューマンセンシングに向けたRGB-Xイメージングシステムの研究開発

    奥富正敏, 田中正行, 紋野雄介, 吉崎和徳, 菊地直, 福西宗憲

    ICTイノベーションフォーラム2017予稿集   28 - 29   2017.10

     More details

    Authorship:Lead author   Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • Misalignment-Robust Joint Filter for Cross-Modal Image Pairs Reviewed

    Takashi Shibata, Masayuki Tanaka, Masatoshi Okutomi

    2017 IEEE International Conference on Computer Vision (ICCV)   3315 - 3324   2017.10

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    DOI: 10.1109/iccv.2017.357

    researchmap

  • Tunable color correction between linear and polynomial models for noisy images Reviewed

    Ryo Yamakabe, Yusuke Monno, Masayuki Tanaka, Masatoshi Okutomi

    2017 IEEE International Conference on Image Processing (ICIP)   3125 - 3129   2017.9

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    DOI: 10.1109/icip.2017.8296858

    researchmap

  • Image Enhancement Framework for Low-resolution Thermal Images in Visible and LWIR Camera Systems Reviewed

    Thapanapong Rukkanchanunt, Masayuki Tanaka, Masatoshi Okutomi

    Proceedings of SPIE Security + Defence 2017   10438   1043809-1 - 1043809-10   2017.9

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1117/12.2277393

    Web of Science

    researchmap

  • Multi-View Inverse Rendering under Arbitrary Illumination and Albedo (ECCV2016)

    Kichang Kim, Akihiko Torii, Masatoshi Okutomi

    2017.8

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • 圧縮センシング動画のデコーディング手法の検討 Reviewed

    吉田道隆, 長原一, 鳥居秋彦, 奥富正敏, 谷口倫一郎

    第20回画像の認識・理解シンポジウム(MIRU2017)   1 - 4   2017.8

     More details

    Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • カラー画像と近赤外線画像を同時に撮影可能なイメージングシステム

    奥富正敏, 紋野雄介, 田中正行, 吉崎和徳, 福西宗憲, 小宮康宏

    日本光学会 光設計研究グループ 第62回研究会, 光設計研究グループ機関誌   ( 62 )   38 - 43   2017.7

     More details

    Authorship:Lead author   Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • Are Large-Scale 3D Models Really Necessary for Accurate Visual Localization? Reviewed

    Torsten Sattler, Akihiko Torii, Josef Sivic, Marc Pollefeys, Hajime Taira, Masatoshi Okutomi, Tomas Pajdla

    2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)   6175 - 6184   2017.7

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    DOI: 10.1109/cvpr.2017.654

    researchmap

  • 可視カメラと遠赤外線カメラの高精度キャリブレーションとその応用

    田中正行, 柴田剛志, 奥富正敏

    日本色彩学会 視覚情報基礎研究会 第31回研究発表会   1 - 4   2017.6

     More details

    Authorship:Last author   Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • カラー画像を同時取得可能なリアルタイム近赤外線蛍光イメージング Reviewed

    吉崎和徳, 福田弘之, 紋野雄介, 田中正行, 奥富正敏, 石原学, カムトーンキッティクン, チャイヤスィット

    第23回画像センシングシンポジウム(SSII2017)   SO1-IS1-20-1 - SO1-IS1-20-4   2017.6

     More details

    Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • 値域制約とベース構造制約を用いた勾配ベースの画像再構成 --マルチモーダル画像融合やHDR画像処理など様々な応用に向けて-- Reviewed

    柴田剛志, 田中正行, 奥富正敏

    第23回画像センシングシンポジウム(SSII2017)   SO1-IS1-06-1 - SO1-IS1-06-8   2017.6

     More details

    Authorship:Last author   Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • Multi-View Inverse Renderingによる高精細な3次元復元 Reviewed

    鳥居秋彦, 金杞昌, 奥富正敏

    第23回画像センシングシンポジウム(SSII2017)   SO1-IS1-35-1 - SO1-IS1-35-5   2017.6

     More details

    Authorship:Last author   Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • ノイズを含む画像に対する高精度な色補正パイプライン Reviewed

    紋野雄介, 高橋健太, 田中正行, 奥富正敏

    第23回画像センシングシンポジウム(SSII2017)   SO3-IS3-29-1 - SO3-IS3-29-5   2017.6

     More details

    Authorship:Last author   Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • 自己誘導型残差補間を用いた深度画像の高解像度化 Reviewed

    今野洋佑, 田中正行, 奥富正敏, 柳川由紀子, 木下航一, 川出雅人

    第23回画像センシングシンポジウム(SSII2017)   SO2-IS2-09-1 - SO2-IS2-09-6   2017.6

     More details

    Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • 可視画像と遠赤外線画像の画像融合技術

    田中正行, 柴田剛志, 奥富正敏

    精密工学会 画像応用技術専門委員会2017年度第1回研究会   2017.5

     More details

    Authorship:Last author   Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • SfMを用いた都市3Dモデルに対するカメラ位置姿勢推定

    加賀美翔, 田平創, 鳥居秋彦, 奥富正敏

    情報処理学会研究報告(コンピュータビジョンとイメージメディア(CVIM))   2017-CVIM-207 ( 8 )   1 - 6   2017.5

     More details

    Authorship:Last author   Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • 防塵性を考慮した可視光・遠赤外線同軸カメラシステムの開発 Reviewed

    荻野有加, 柴田剛志, 田中正行, 奥富正敏

    日本機械学会ロボティクス・メカトロニクス講演会(ROBOMECH2017)   2A1-P03-1 - 2A1-P03-3   2017.5

     More details

    Authorship:Last author   Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • ドローン搭載カメラを用いた3D復元

    奥富正敏

    OPTICS & PHOTONICS International Exhibition (OPIE'17)   2017.4

     More details

    Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • LWIR image visualization preserving local details and global distribution by gradient-domain image reconstruction. Reviewed

    Takashi Shibata, Masayuki Tanaka, Masatoshi Okutomi

    Proceedings of SPIE Defense + Commercial Sensing (DCS2017)   10178   101780X-1 - 101780X-11   2017.4

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1117/12.2261266

    Web of Science

    researchmap

  • Unified optimization framework for L2, L1, and/or L0 constrained image reconstruction Reviewed

    Masayuki Tanaka, Masatoshi Okutomi

    Proceedings of SPIE Defense + Commercial Sensing (DCS2017)   10222   102220J-1 - 102220J-10   2017.4

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Coaxial visible and FIR camera system with accurate geometric calibration Reviewed

    Yuka Ogino, Takashi Shibata, Masayuki Tanaka, Masatoshi Okutomi

    Proceedings of SPIE Defense + Commercial Sensing (DCS2017)   10214   1021415-1 - 1021415-6   2017.4

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • 複数視点魚眼映像による発生原理を考慮したオーロラの3次元形状計測と可視化 Reviewed

    竹内彰, 藤井浩光, 山下淳, 田中正行, 片岡龍峰, 三好由純, 奥富正敏, 淺間一

    第22回ロボティクスシンポジア講演予稿集   48 - 55   2017.3

     More details

    Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • 可視及び遠赤外カメラの高精度同時校正とその応用 Reviewed

    柴田剛志, 田中正行, 奥富正敏

    動的画像処理実利用化ワークショップ(DIA2017)講演論文集   50 - 57   2017.3

     More details

    Authorship:Last author   Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • 24/7 Place Recognition by View Synthesis

    Akihiko Torii, Relja Arandjelovic, Josef Sivic, Masatoshi Okutomi, Tomas Pajdla

    IEEE Transactions on Pattern Analysis and Machine Intelligence   Vol. 40 ( No. 2 )   2017.2

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  • Accurate Joint Geometric Camera Calibration of Visible and Far-Infrared Cameras Reviewed

    Takashi Shibata, Masayuki Tanaka, Masatoshi Okutomi

    Electronic Imaging   2017 ( 11 )   7 - 13   2017.1

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (scientific journal)   Publisher:Society for Imaging Science & Technology  

    DOI: 10.2352/issn.2470-1173.2017.11.imse-078

    researchmap

  • Toward robust reconstruction-based super-resolution

    Masayuki Tanaka, Masatoshi Okutomi

    Super-Resolution Imaging   219 - 246   2017.1

     More details

    Language:English   Publishing type:Part of collection (book)   Publisher:CRC Press  

    DOI: 10.1201/9781439819319

    Scopus

    researchmap

  • Joint Estimation of Depth, Albedo, and Illumination from a Single RGB-D Image

    Kichang Kim, Akihiko Torii, Masatoshi Okutomi

    IIEEJ Transactions on Image Electronics and Visual Computing   Vol. 4 ( No. 2 )   2016.12

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  • Interactive Stereoscopic Image Generation from Image Data Collection for Experiencing 360×180 Degree Real Environments

    Sakharin Buachan, Shigeki Sugimoto, Masatoshi Okutomi

    IIEEJ Transactions on Image Electronics and Visual Computing   Vol. 4 ( No. 2 )   2016.12

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  • 仮想視点生成によるパノラマ画像データベース拡張と位置・方位推定

    董亜飛, 鳥居秋彦, 奥富正敏

    電子情報通信学会論文誌D   Vol. 99 ( No. 8 )   2016.8

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • 回転するカメラを用いた高精度地表3D サーフェス推定

    杉本茂樹, 本岡昂馬, Doan Phuc Phan, 奥富正敏, 志磨健

    画像電子学会誌   Vol. 45 ( No. 3 )   2016.7

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • Beyond Color Difference: Residual Interpolation for Color Image Demosaicking Reviewed

    Daisuke Kiku, Yusuke Monno, Masayuki Tanaka, Masatoshi Okutomi

    IEEE Transactions on Image Processing   Vol. 25 ( No. 3 )   1288 - 1300   2016.3

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    DOI: 10.1109/TIP.2016.2518082

    Web of Science

    researchmap

  • 魚眼ステレオカメラを用いた全天周時系列画像からのオーロラ3次元計測

    竹内彰, 藤井浩光, 山下淳, 田中正行, 片岡龍峰, 三好由純, 奥富正敏, 淺間一

    日本機械学会論文集   Vol. 82 ( No. 834 )   2016.2

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • Versatile Visible and Near-Infrared Image Fusion Based on High Visibility Area Selection Reviewed

    Takashi Shibata, Masayuki Tanaka, Masatoshi Okutomi

    Journal of Electronic Imaging   Vol. 25 ( No. 1 )   2016.1

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    DOI: 10.1117/1.JEI.25.1.013016

    Web of Science

    researchmap

  • Depth map upsampling by self-guided residual interpolation

    Yosuke Konno, Masayuki Tanaka, Masatoshi Okutomi, Yukiko Yanagawa, Koichi Kinoshita, Masato Kawade

    Proceedings - International Conference on Pattern Recognition   1394 - 1399   2016.1

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:Institute of Electrical and Electronics Engineers Inc.  

    DOI: 10.1109/ICPR.2016.7899832

    Scopus

    researchmap

  • Robust Feature Matching by Learning Descriptor Covariance with Viewpoint Synthesis Reviewed

    Hajime Taira, Akihiko Torii, Masatoshi Okutomi

    2016 23RD INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)   1953 - 1958   2016

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Web of Science

    researchmap

  • Super High Dynamic Range Video Reviewed

    Yuka Ogino, Masayuki Tanaka, Takashi Shibata, Masatoshi Okutomi

    2016 23RD INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)   4208 - 4213   2016

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Web of Science

    researchmap

  • Gradient-Domain Image Reconstruction Framework with Intensity-Range and Base-Structure Constraints Reviewed

    Takashi Shibata, Masayuki Tanaka, Masatoshi Okutomi

    2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)   2745 - 2753   2016

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1109/CVPR.2016.300

    Web of Science

    researchmap

  • Single-sensor RGB and NIR image acquisition: Toward optimal performance by taking account of CFA pattern, demosaicking, and color correction Reviewed

    Hayato Teranaka, Yusuke Monno, Masayuki Tanaka, Masatoshi Okutomi

    IS and T International Symposium on Electronic Imaging Science and Technology   2016

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:Society for Imaging Science and Technology  

    DOI: 10.2352/ISSN.2470-1173.2016.18.DPMI-256

    Scopus

    researchmap

  • Multi-spectrum to RGB with direct structure-tensor reconstruction

    Takashi Shibata, Masayuki Tanaka, Masatoshi Okutomi

    IS and T International Symposium on Electronic Imaging Science and Technology   2016

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:Society for Imaging Science and Technology  

    DOI: 10.2352/ISSN.2470-1173.2016.18.DPMI-025

    Scopus

    researchmap

  • EFFECTIVE COLOR CORRECTION PIPELINE FOR A NOISY IMAGE Reviewed

    Kenta Takahashi, Yusuke Monno, Masayuki Tanaka, Masatoshi Okutomi

    2016 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)   4002 - 4006   2016

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Web of Science

    researchmap

  • 全球パノラマ画像を用いたSfMによる3次元復元と自己位置・方位推定への応用

    井上優希, 董亜飛, 田平創, 鳥居秋彦, 奥富正敏

    精密工学会誌   Vol. 81 ( No. 12 )   2015.12

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • Visual Place Recognition with Repetitive Structures

    Akihiko Torii, Josef Sivic, Masatoshi Okutomi, Tomas Pajdla

    IEEE Transactions on Pattern Analysis and Machine Intelligence   Vol. 37 ( No. 11 )   2015.11

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  • A Practical One-Shot Multispectral Imaging System Using a Single Image Sensor Reviewed

    Yusuke Monno, Sunao Kikuchi, Masayuki Tanaka, Masatoshi Okutomi

    IEEE Transactions on Image Processing   Vol. 24 ( No. 10 )   3048 - 3059   2015.10

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    DOI: 10.1109/TIP.2015.2436342

    Web of Science

    researchmap

  • Robust Feature Matching for Distorted Projection by Spherical Cameras

    Hajime Taira, Yuki Inoue, Akihiko Torii, Masatoshi Okutomi

    IPSJ Transactionas on Computer Vision and Applications   Vol. 7   2015.7

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  • 三次元画像センシングの新展開

    鳥居秋彦, 奥富正敏, 他

    2015.5

     More details

    Language:Japanese   Publishing type:Part of collection (book)   Publisher:NTS  

    researchmap

  • 全体最適性を保証した逐次的3次元サーフェス抽出法

    杉浦貴行, 鳥居秋彦, 奥富正敏

    電子情報通信学会論文誌D   Vol. J98-D ( No. 4 )   2015.4

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • 車載ステレオカメラを用いたロバストな3D地表サーフェスマップ生成

    杉本茂樹, 本岡昂馬, 奥富正敏, 志磨健

    電子情報通信学会論文誌D   Vol. J98-D ( No. 4 )   2015.4

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • UNIFIED IMAGE FUSION BASED ON APPLICATION-ADAPTIVE IMPORTANCE MEASURE Reviewed

    Takashi Shibata, Masayuki Tanaka, Masatoshi Okutomi

    2015 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)   1 - 5   2015

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Web of Science

    researchmap

  • Visible and Near-Infrared Image Fusion based on Visually Salient Area Selection Reviewed

    Takashi Shibata, Masayuki Tanaka, Masatoshi Okutomi

    DIGITAL PHOTOGRAPHY XI   9404   2015

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1117/12.2077050

    Web of Science

    researchmap

  • PSEUDO FOUR-CHANNEL IMAGE DENOISING FOR NOISY CFA RAW DATA Reviewed

    Hiroki Akiyama, Masayuki Tanaka, Masatoshi Okutomi

    2015 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)   4778 - 4782   2015

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Web of Science

    researchmap

  • N-to-sRGB Mapping for Single-Senor Multispectral Imaging Reviewed

    Yusuke Monno, Masayuki Tanaka, Masatoshi Okutomi

    2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOP (ICCVW)   66 - 73   2015

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1109/ICCVW.2015.18

    Web of Science

    researchmap

  • Practical Signal Dependent Noise Parameter Estimation From A Single Noisy Image Reviewed

    Xinhao Liu, Masayuki Tanaka, Masatoshi Okutomi

    IEEE Transactions on Image Processing   Vol. 23 ( No. 10 )   4361 - 4371   2014.10

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    DOI: 10.1109/TIP.2014.2347204

    Web of Science

    researchmap

  • Efficient Localization of Panoramic Images Using Tiled Image Descriptors

    Akihiko Torii, Yafei Dong, Masatoshi Okutomi, Josef Sivic, Tomas Pajdla

    IPSJ Transactionas on Computer Vision and Applications   Vol. 6   2014.7

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  • 位置ずれのあるノイジーカラー画像を用いた赤外線画像のカラリゼーション

    竹内広一, 田中正行, 奥富正敏

    画像電子学会誌   Vol. 43 ( No. 3 )   2014.7

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • A General and Simple Method for Camera Pose and Focal Length Determination Reviewed

    Yinqiang Zheng, Shigeki Sugimoto, Imari Sato, Masatoshi Okutomi

    2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)   430 - 437   2014

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1109/CVPR.2014.62

    Web of Science

    researchmap

  • Minimized-Laplacian Residual Interpolation for Color Image Demosaicking Reviewed

    Daisuke Kiku, Yusuke Monno, Masayuki Tanaka, Masatoshi Okutomi

    DIGITAL PHOTOGRAPHY X   9023   2014

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1117/12.2038425

    Web of Science

    researchmap

  • Simultaneous Capturing of RGB and Additional Band Images Using Hybrid Color Filter Array Reviewed

    Daisuke Kiku, Yusuke Monno, Masayuki Tanaka, Masatoshi Okutomi

    DIGITAL PHOTOGRAPHY X   9023   2014

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1117/12.2039396

    Web of Science

    researchmap

  • Robust Ground Surface Map Generation Using Vehicle-Mounted Stereo Camera Reviewed

    Kouma Motooka, Shigeki Sugimoto, Masatoshi Okutomi, Takeshi Shima

    2014 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS 2014)   2741 - 2748   2014

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Web of Science

    researchmap

  • A classification-and-reconstruction approach for a single image super-resolution by a sparse representation Reviewed

    YingYing Fan, Masayuki Tanaka, Masatoshi Okutomi

    DIGITAL PHOTOGRAPHY X   9023   2014

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1117/12.2038826

    Web of Science

    researchmap

  • A Novel Inference of a Restricted Boltzmann Machine Reviewed

    Masayuki Tanaka, Masatoshi Okutomi

    2014 22ND INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)   1526 - 1531   2014

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1109/ICPR.2014.271

    Web of Science

    researchmap

  • SIGNAL DEPENDENT NOISE REMOVAL FROM A SINGLE IMAGE Reviewed

    Xinhao Liu, Masayuki Tanaka, Masatoshi Okutomi

    2014 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)   2679 - 2683   2014

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Web of Science

    researchmap

  • MULTISPECTRAL DEMOSAICKING WITH NOVEL GUIDE IMAGE GENERATION AND RESIDUAL INTERPOLATION Reviewed

    Yusuke Monno, Daisuke Kiku, Sunao Kikuchi, Masayuki Tanaka, Masatoshi Okutomi

    2014 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)   645 - 649   2014

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Web of Science

    researchmap

  • Single-Image Noise Level Estimation for Blind Denoising Reviewed

    Xinhao Liu, Masayuki Tanaka, Masatoshi Okutomi

    IEEE Transactions on Image Processing   Vol. 22 ( No. 12 )   5226 - 5237   2013.12

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    DOI: 10.1109/TIP.2013.2283400

    Web of Science

    researchmap

  • ステレオ画像を用いた複数平面領域と平面パラメータの同時推定

    藤原将展, 杉本茂樹, 奥富正敏

    電子情報通信学会論文誌D   Vol. J96-D ( No. 8 )   2013.8

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • 適応的基底学習を利用したスパースコーディングに基づく一枚超解像

    櫻井歩, 田中正行, 奥富正敏

    電子情報通信学会論文誌D   Vol. J96-D ( No. 8 )   2013.8

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • オンライン撮影に適した実用的なSfMシステム

    半澤悠樹, 鳥居秋彦, 奥富正敏

    電子情報通信学会論文誌D   Vol. J96-D ( No. 8 )   2013.8

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • 適応的空間-スペクトル基底を利用したRAWデータからの直接分光反射率推定

    紋野雄介, 田中正行, 奥富正敏

    電子情報通信学会論文誌D   Vol. J96-D ( No. 8 )   2013.8

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • Fisher Vector based on Full-Covariance Gaussian Mixture Model Reviewed

    Masayuki Tanaka, Akihiko Torii, Masatoshi Okutomi

    IPSJ Transactions on Computer Vision and Applications   Vol. 5   50 - 54   2013.7

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    DOI: 10.2197/ipsjtcva.5.50

    Scopus

    researchmap

  • Direct Ground Surface Reconstruction from Stereo Images Reviewed

    Shigeki Sugimoto, Takaaki Kato, Kouma Motooka, Masatoshi Okutomi

    IPSJ Transactions on Computer Vision and Applications   Vol. 5   60 - 64   2013.7

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    DOI: 10.2197/ipsjtcva.5.60

    Scopus

    researchmap

  • ASPnP: An accurate and scalable solution to the perspective-n-point problem Reviewed

    Yinqiang Zheng, Shigeki Sugimoto, Masatoshi Okutomi

    IEICE Transactions on Information and Systems   Vol. E96-D ( No. 7 )   1525 - 1535   2013.7

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:The Institute of Electronics, Information and Communication Engineers  

    We propose an accurate and scalable solution to the perspective-n-point problem, referred to as ASPnP. Our main idea is to estimate the orientation and position parameters by directly minimizing a properly defined algebraic error. By using a novel quaternion representation of the rotation, our solution is immune to any parametrization degeneracy. To obtain the global optimum, we use the Gröbner basis technique to solve the polynomial system derived from the first-order optimality condition. The main advantages of our proposed solution lie in accuracy and scalability. Extensive experiment results, with both synthetic and real data, demonstrate that our proposed solution has better accuracy than the state-of-the-art noniterative solutions. More importantly, by exploiting vectorization operations, the computational cost of our ASPnP solution is almost constant, independent of the number of point correspondences n in the wide range from 4 to 1000. In our experiment settings, the ASPnP solution takes about 4 milliseconds, thus best suited for real-time applications with a drastically varying number of 3D-to-2D point correspondences.

    DOI: 10.1587/transinf.E96.D.1525

    researchmap

    Other Link: http://dblp.uni-trier.de/db/journals/ieicet/ieicet96d.html#journals/ieicet/ZhengSO13

  • ノンローカルPCAに基づく画像デノイジング

    山内啓大朗, 田中正行, 奥富正敏

    電子情報通信学会論文誌D   Vol. J96-D ( No. 3 )   2013.3

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • Revisiting the PnP Problem: A Fast, General and Optimal Solution Reviewed

    Yinqiang Zheng, Yubin Kuang, Shigeki Sugimoto, Kalle Astrom, Masatoshi Okutomi

    2013 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)   2344 - 2351   2013

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1109/ICCV.2013.291

    Web of Science

    researchmap

  • A Practical Rank-Constrained Eight-Point Algorithm for Fundamental Matrix Estimation. Reviewed

    Yinqiang Zheng, Shigeki Sugimoto, Masatoshi Okutomi

    2013 IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, USA, June 23-28, 2013   1546 - 1553   2013

     More details

    Publisher:IEEE  

    DOI: 10.1109/CVPR.2013.203

    researchmap

  • ESTIMATION OF SIGNAL DEPENDENT NOISE PARAMETERS FROM A SINGLE IMAGE Reviewed

    Xinhao Liu, Masayuki Tanaka, Masatoshi Okutomi

    2013 20TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP 2013)   79 - 82   2013

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Web of Science

    researchmap

  • RESIDUAL INTERPOLATION FOR COLOR IMAGE DEMOSAICKING Reviewed

    Daisuke Kiku, Yusuke Monno, Masayuki Tanaka, Masatoshi Okutomi

    2013 20TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP 2013)   2304 - 2308   2013

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Web of Science

    researchmap

  • Across-Resolution Adaptive Dictionary Learning for Single-Image Super-Resolution Reviewed

    Masayuki Tanaka, Ayumu Sakurai, Masatoshi Okutomi

    DIGITAL PHOTOGRAPHY IX   8660   2013

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1117/12.2002393

    Web of Science

    researchmap

  • Direct spatio-spectral datacube reconstruction from raw data using a spatially adaptive spatio-spectral basis Reviewed

    Yusuke Monno, Masayuki Tanaka, Masatoshi Okutomi

    DIGITAL PHOTOGRAPHY IX   8660   2013

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1117/12.2002292

    Web of Science

    researchmap

  • Direct Generation of Regular-Grid Ground Surface Map From In-Vehicle Stereo Image Sequences Reviewed

    Shigeki Sugimoto, Kouma Motooka, Masatoshi Okutomi

    2013 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW)   600 - 607   2013

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1109/ICCVW.2013.83

    Web of Science

    researchmap

  • Real-time Video Mosaicing using Non-rigid Registration

    Rafael Henrique Castanheira de Souza, Masatoshi Okutomi, Akihiko Torii

    IPSJ Transactions on Computer Vision and Applications   Vol. 4   2012.12

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  • Augmenting Moving Planar Surfaces Robustly with Video Projection and Direct Image Alignment Reviewed

    Samuel Audet, Masatoshi Okutomi, Masayuki Tanaka

    Virtual Reality (Springer) Special Issue on "Models for Mixed and Augmented Reality" (Online)   17 ( 2 )   157 - 168   2012.4

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    DOI: 10.1007/s10055-012-0210-9

    Web of Science

    researchmap

  • NOISE LEVEL ESTIMATION USING WEAK TEXTURED PATCHES OF A SINGLE NOISY IMAGE Reviewed

    Xinhao Liu, Masayuki Tanaka, Masatoshi Okutomi

    2012 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP 2012)   665 - 668   2012

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Web of Science

    researchmap

  • Generalizing Wiberg Algorithm for Rigid and Nonrigid Factorizations with Missing Components and Metric Constraints Reviewed

    Yinqiang Zheng, Shigeki Sugimoto, Shuicheng Yan, Masatoshi Okutomi

    2012 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)   2010 - 2017   2012

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1109/CVPR.2012.6247904

    Web of Science

    researchmap

  • Practical Low-Rank Matrix Approximation under Robust L-1-Norm Reviewed

    Yinqiang Zheng, Guangcan Liu, Shigeki Sugimoto, Shuicheng Yan, Masatoshi Okutomi

    2012 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)   1410 - 1417   2012

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1109/CVPR.2012.6247828

    Web of Science

    researchmap

  • Augmenting Moving Planar Surfaces Interactively with Video Projection and a Color Camera Reviewed

    Samuel Audet, Masatoshi Okutomi, Masayuki Tanaka

    IEEE VIRTUAL REALITY CONFERENCE 2012 PROCEEDINGS   111 - 112   2012

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Web of Science

    researchmap

  • Multispectral demosaicking using guided filter Reviewed

    Yusuke Monno, Masayuki Tanaka, Masatoshi Okutomi

    DIGITAL PHOTOGRAPHY VIII   8299   2012

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1117/12.906168

    Web of Science

    researchmap

  • OPTIMAL SPECTRAL SENSITIVITY FUNCTIONS FOR A SINGLE-CAMERA ONE-SHOT MULTISPECTRAL IMAGING SYSTEM Reviewed

    Yusuke Monno, Toshihiro Kitao, Masayuki Tanaka, Masatoshi Okutomi

    2012 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP 2012)   2137 - 2140   2012

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Web of Science

    researchmap

  • Camera Self Calibration Based on Direct Image Alignment Reviewed

    Shigeki Sugimoto, Masatoshi Okutomi

    2012 21ST INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR 2012)   3240 - 3243   2012

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Web of Science

    researchmap

  • 2足ロボットのためのステレオ画像による実時間段差エッジ推定

    淺谷南己, 杉本茂樹, 奥富正敏

    日本ロボット学会誌   Vol. 29 ( No. 10 )   2011.12

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • Monocular multi-view stereo imaging system

    Wei Jiang, Masao Shimizu, Masatoshi Okutomi

    Journal of the European Optical Society   Vol. 6   2011.11

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  • 色相関を利用した適応的カーネル回帰に基づく画像補間

    田中正行, 奥富正敏

    電子情報通信学会論文誌D   Vol. J94-D ( No. 8 )   2011.8

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • MULTISPECTRAL DEMOSAICKING USING ADAPTIVE KERNEL UPSAMPLING Reviewed

    Yusuke Monno, Masayuki Tanaka, Masatoshi Okutomi

    2011 18TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)   2011

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Web of Science

    researchmap

  • A Branch and Contract Algorithm For Globally Optimally Fundamental Matrix Estimation Reviewed

    Yinqiang Zheng, Shigeki Sugimoto, Masatoshi Okutomi

    2011 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)   2953 - 2960   2011

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1109/CVPR.2011.5995352

    Web of Science

    researchmap

  • Deterministically Maximizing Feasible Subsystem for Robust Model Fitting with Unit Norm Constraint Reviewed

    Yinqiang Zheng, Shigeki Sugimoto, Masatoshi Okutomi

    2011 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)   1825 - 1832   2011

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1109/CVPR.2011.5995640

    Web of Science

    researchmap

  • 3D Structure Refinement of Nonrigid Surfaces through Efficient Image Alignment Reviewed

    Yinqiang Zheng, Shigeki Sugimoto, Masatoshi Okutomi

    COMPUTER VISION - ACCV 2010, PT IV   6495   76 - 89   2011

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1007/978-3-642-19282-1_7

    Web of Science

    researchmap

  • Real-time Step Edge Estimation Using Stereo Images for Biped Robot Reviewed

    Minami Asatani, Shigeki Sugimoto, Masatoshi Okutomi

    2011 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS   4463 - 4468   2011

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Web of Science

    researchmap

  • Color Kernel Regression for Robust Direct Upsampling from Raw Data of General Color Filter Array Reviewed

    Masayuki Tanaka, Masatoshi Okutomi

    COMPUTER VISION - ACCV 2010, PT III   6494   290 - 301   2011

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Web of Science

    researchmap

  • Nonrigid Registration based on Projected Joint Entropy combined with Gradient Similarity

    RAFAEL HENRIQUE C DE SOUZA, Masao Shimizu, Masatoshi Okutomi, Shin Yoshimura

    Optical Engineering   Vol. 49 ( No. 12 )   2010.12

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  • Panoramic 3D Reconstruction Using Stereo Multi-perspective Panorama Reviewed

    Wei Jiang, Shigeki Sugimoto, Masatoshi Okutomi

    International Journal of Pattern Recognition and Artificial Intelligence   Vol. 24 ( No. 6 )   867 - 896   2010.9

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    DOI: 10.1142/S0218001410008226

    Web of Science

    researchmap

  • Toward Robust Reconstruction-Based Super-Resolution

    Masayuki Tanaka, Masatoshi Okutomi, et al

    2010.9

     More details

    Language:English   Publishing type:Part of collection (book)   Publisher:Super-Resolution Imaging  

    researchmap

  • バイラテラルフィルタとノンローカルミーンフィルタの統一的解釈とその発展へ向けて

    田中正行, 奥富正敏

    電子情報通信学会論文誌D   Vol. J93-D ( No. 8 )   1470 - 1479   2010.8

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • 多重像画像からの原画像の復元と重像間変位推定

    矢野高宏, 清水雅夫, 奥富正敏

    電子情報通信学会論文誌D   Vol. J93-D ( No. 8 )   1329 - 1339   2010.8

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • 複数フレームの累積情報を利用した高速ビデオ超解像処理

    魏大比, 田中正行, 奥富正敏

    電子情報通信学会論文誌D   Vol. J93-D ( No. 8 )   1480 - 1490   2010.8

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • 車載カメラによる道路認識(相対姿勢,障害物検出)

    杉本茂樹, 奥富正敏, 他編著

    2010.3

     More details

    Language:Japanese   Publishing type:Part of collection (book)   Publisher:ロボット情報学ハンドブック  

    researchmap

  • A Footstep-plan-based Floor Sensing Method Using Stereo Images for Stable Slope Walking of Biped Robot

    ASATANI Minami, SUGIMOTO Shigeki, OKUTOMI Masatoshi

    JRSJ   Vol. 28 ( No. 1 )   112 - 121   2010.1

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)   Publisher:The Robotics Society of Japan  

    It is important for autonomous control of a biped robot to obtain the 3D information of the ground on which the robot walks. When a biped robot traverses a floor including slopes, sensors should be able to detect a slope and precisely measure the angle of the slope, along with the positions of its beginning and end. In this paper, we propose a realtime floor sensing method using stereo cameras mounted on a biped robot. We detect a slope in the environment and estimate the inclination angle and the boundary by fitting a set of plane parameter vectors to a two-plane model. For obtaining the parameter vector set, we first determine multiple regions of interest (ROI) in a reference image by using footstep positions up to several steps, scheduled by a current footstep plan. Then the parameter vector of the floor with respect to each ROI are efficiently and accurately estimated by a fast direct method with motion compensation. The fitting result is feedback for stable walking by updating the footstep plan . The validity of the proposed method is demonstrated through online experiments using stereo cameras mounted on the body of a biped robot, Honda ASIMO, traversing a real slope.

    DOI: 10.7210/jrsj.28.112

    CiNii Books

    researchmap

    Other Link: https://jlc.jst.go.jp/DN/JALC/00346618624?from=CiNii

  • Latent Common Origin of Bilateral Filter and Non-Local Means Filter Reviewed

    Masayuki Tanaka, Masatoshi Okutomi

    IMAGE PROCESSING: ALGORITHMS AND SYSTEMS VIII   7532   2010

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1117/12.838772

    Web of Science

    researchmap

  • Disparity Estimation in a Layered Image for Reflection Stereo Reviewed

    Masao Shimizu, Masatoshi Okutomi, Wei Jiang

    COMPUTER VISION - ACCV 2009, PT III   5996   395 - +   2010

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Web of Science

    researchmap

  • Single-Camera Multi-baseline Stereo Using Fish-Eye Lens and Mirrors Reviewed

    Wei Jiang, Masao Shimizu, Masatoshi Okutomi

    COMPUTER VISION - ACCV 2009, PT II   5995   347 - 358   2010

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Web of Science

    researchmap

  • Direct Image Alignment of Projector-Camera Systems with Planar Surfaces Reviewed

    Samuel Audet, Masatoshi Okutomi, Masayuki Tanaka

    2010 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)   303 - 310   2010

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Web of Science

    researchmap

  • 超解像処理のための複数モーションに対応したロバストかつ高精度な位置合わせ手法

    矢口陽一, 田中正行, 奥富正敏

    電子情報通信学会論文誌D   Vol. J92-D ( No. 11 )   2033 - 2043   2009.11

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • 非均質なパッチベースMRFのための局所適応的学習

    田中正行, 奥富正敏

    電子情報通信学会論文誌D   Vol. J92-D ( No. 8 )   1084 - 1093   2009.8

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • ステレオ時系列画像を用いた直接法による高速・高精度モーション推定

    内田秀雄, 杉本茂樹, 奥富正敏

    電子情報通信学会論文誌D   Vol. J92-D ( No. 8 )   1414 - 1424   2009.8

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • 残差画像に基づく漸進的ぶれ画像復元

    田中正行, 神田崇史, 奥富正敏

    電子情報通信学会論文誌D   Vol. J92-D ( No. 8 )   1208 - 1220   2009.8

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • エントロピー最小化基準によるカラー画像の色チャンネル間における非剛体レジストレーション

    清水雅夫, 吉村真, 奥富正敏

    電子情報通信学会論文誌D   Vol. J92-D ( No. 8 )   1260 - 1269   2009.8

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • 多眼ステレオ画像を用いた高速平面パラメータ推定と仮想焦点面画像生成への応用

    杉本茂樹, 奥富正敏

    電子情報通信学会論文誌D   Vol. J92-D ( No. 5 )   671 - 682   2009.5

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • 位置ずれ量を考慮した画素選択に基づくロバスト超解像処理

    田中正行, 矢口陽一, 古川英治, 奥富正敏

    電子情報通信学会論文誌D   Vol. J92-D ( No. 5 )   650 - 660   2009.5

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • 顔らしさ分布を利用した顔検出

    高塚皓正, 田中正行, 奥富正敏

    情報処理学会論文誌:コンピュータビジョンとイメージメディア   Vol. 2 ( No. 1 )   42 - 52   2009.3

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • A User-Friendly Method to Geometrically Calibrate Projector-Camera Systems Reviewed

    Samuel Audet, Masatoshi Okutomi

    2009 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPR WORKSHOPS 2009), VOLS 1 AND 2   586 - 593   2009

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Web of Science

    researchmap

  • “Image Super-Resolution with Non-Rigid Motion of Hot-air Optical Turbulence”

    Masao Shimizu, Shin Yoshimura, Masayuki Tanaka, Masatoshi Oku-Tomi

    Journal of the Institute of Image Electronics Engineers of Japan   Vol. 37 ( No. 4 )   387 - 395   2008.7

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    DOI: 10.11371/iieej.37.387

    Scopus

    researchmap

  • リフレクションステレオのキャリブレーション

    清水雅夫, 奥富正敏

    情報処理学会論文誌:コンピュータビジョンとイメージメディア   Vol. 1 ( No. 2 )   124 - 135   2008.7

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • 両面ハーフミラー板の透過像を用いた単眼距離計測

    清水雅夫, 奥富正敏

    情報処理学会論文誌:コンピュータビジョンとイメージメディア   Vol. 1 ( No. 1 )   83 - 87   2008.6

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • 道路面情報に基づくステレオ動画像を用いた車両の前方環境認識

    関晃仁, 奥富正敏

    情報処理学会論文誌:コンピュータビジョンとイメージメディア   Vol. 1 ( No. 1 )   1 - 19   2008.6

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • 非同期ステレオ動画像を用いた同時最適化による位置とモーションの推定

    関晃仁, 奥富正敏

    情報処理学会論文誌:コンピュータビジョンとイメージメディア   Vol. 49 ( No. SIG6 (CVIM20) )   22 - 34   2008.3

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • アフィン空間拘束とエピポーラ拘束を利用した2組の時系列画像における画像間対応軌跡推定

    高橋秀和, 杉本茂樹, 奥富正敏

    情報処理学会論文誌:コンピュータビジョンとイメージメディア   Vol. 49 ( No. SIG6 (CVIM20) )   46 - 55   2008.3

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • A raw data compression for digital cameras with a color filter array Reviewed

    Masayuki Tanaka, Masatoshi Okutomi

    COLOR IMAGING XIII: PROCESSING, HARDCOPY, AND APPLICATIONS   6807   2008

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Web of Science

    researchmap

  • Locally adaptive learning for translation-variant MRF image priors Reviewed

    Masayuki Tanaka, Masatoshi Okutomi

    2008 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOLS 1-12   63 - 70   2008

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Web of Science

    researchmap

  • High-usability deblurring filter Reviewed

    Masayuki Tanaka, Kenichi Yoneji, Masatoshi Okutomi

    2008 IEEE INTERNATIONAL SYMPOSIUM ON CONSUMER ELECTRONICS, VOLS 1 AND 2   565 - 566   2008

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Web of Science

    researchmap

  • Virtual focusing image synthesis for user-specified image region using camera array

    Shigeki Sugimoto, Masatoshi Okutomi

    Proceedings - International Conference on Pattern Recognition   2008

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:Institute of Electrical and Electronics Engineers Inc.  

    DOI: 10.1109/icpr.2008.4761320

    Scopus

    researchmap

  • ROBUST AND ACCURATE ESTIMATION OF MULTIPLE MOTIONS FOR WHOLE-IMAGE SUPER-RESOLUTION Reviewed

    Masayuki Tanaka, Yoichi Yaguchi, Masatoshi Okutomi

    2008 15TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-5   649 - 652   2008

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Web of Science

    researchmap

  • Robust Obstacle Detection in General Road Environment Based on Road Extraction and Pose Estimation

    Akihito Seki, Masatoshi Okutomi

    Electronics and Communications in Japan, Part II   Vol. 90 ( No. 12 )   12 - 22   2007.12

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    DOI: 10.1002/ecjb.20413

    Web of Science

    researchmap

  • ステレオ画像からの高速な微小平面3Dサーフェス直接生成法

    杉本茂樹, 奥富正敏

    情報処理学会論文誌:コンピュータビジョンとイメージメディア   Vol. 48 ( No. SIG16(CVIM19) )   38 - 50   2007.11

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • 顔らしさの評価値分布を利用した顔検出の提案

    高塚皓正, 田中正行, 奥富正敏

    情報処理学会論文誌:コンピュータビジョンとイメージメディア   Vol. 48 ( No. SIG16(CVIM19) )   51 - 54   2007.11

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • ヒューマンフレンドリーな復元フィルタの提案

    米司健一, 田中正行, 奥富正敏

    電子情報通信学会論文誌D   Vol. J90-D ( No. 10 )   2830 - 2839   2007.10

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • Coding Algorithm for a Single-chip Color Image Sensor

    Masayuki Tanaka, Masatoshi Okutomi

    Journal of the Institute of Image Electronics Engineers of Japan   Vol. 36 ( No. 5 )   631 - 640   2007.9

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    DOI: 10.11371/iieej.36.631

    Scopus

    researchmap

  • 組合せ画素混合を利用した超解像処理

    田中正行, 奥富正敏

    電子情報通信学会論文誌D   Vol. J90-D ( No. 8 )   1948 - 1956   2007.8

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • A Fast Algorithm for Hyperplane-Intersection Method on Image Registration

    SoonKeun Chang, Masao Shimizu, Masatoshi Okutomi

    Systems and Computers in Japan   Vol. 38 ( No. 7 )   2007.6

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  • A Fast Algorithm for Reconstruction-Based Superresolution and Evaluation of Its Accuracy

    Masayuki Tanaka, Masatoshi Okutomi

    Systems and Computers in Japan   Vol. 38 ( No. 7 )   44 - 52   2007.6

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    DOI: 10.1002/scj.20662

    Scopus

    researchmap

  • 画像復元とレジストレーションの同時最適化の実験的検証

    後藤知将, 奥富正敏

    電子情報通信学会論文誌D   Vol. J90-D ( No. 6 )   1632 - 1635   2007.6

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • Omnidirectional 3D Reconstruction Using Rotating Camera with Mirrors

    Wei Jiang, Shigeki Sugimoto, Masatoshi Okutomi

    Systems and Computers in Japan   Vol. 38 ( No. 4 )   12 - 24   2007.4

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    DOI: 10.1002/scj.20606

    Scopus

    researchmap

  • ステレオ画像を用いた高速な平面パラメータ推定法

    杉本茂樹, 奥富正敏

    情報処理学会論文誌:コンピュータビジョンとイメージメディア   Vol. 48 ( No. SIG1 (CVIM17) )   24 - 34   2007.2

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • 領域選択を伴なう2段階レジストレーション

    張馴槿, 清水雅夫, 奥富正敏

    電子情報通信学会論文誌 D   Vol. J90-D ( No. 2 )   514 - 525   2007.2

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • Fast plane parameter estimation from stereo images

    Shigeki Sugimoto, Masatoshi Okutomi

    Proceedings of IAPR Conference on Machine Vision Applications, MVA 2007   567 - 570   2007

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Scopus

    researchmap

  • Reconstruction of a high dynamic range and high resolution image from a multisampled image sequence Reviewed

    Harald B. Haraldsson, Masayuki Tanaka, Masatoshi Okutomi

    14TH INTERNATIONAL CONFERENCE ON IMAGE ANALYSIS AND PROCESSING, PROCEEDINGS   303 - +   2007

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Web of Science

    researchmap

  • Distribution-based face detection using calibrated boosted cascade classifier Reviewed

    Hiromasa Takatsuka, Masayuki Tanaka, Masatoshi Okutomi

    14TH INTERNATIONAL CONFERENCE ON IMAGE ANALYSIS AND PROCESSING, PROCEEDINGS   351 - +   2007

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Web of Science

    researchmap

  • Simultaneous optimization of structure and motion in dynamic scenes using unsynchronized stereo cameras Reviewed

    Akihito Seki, Masatoshi Okutomi

    2007 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOLS 1-8   1451 - +   2007

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Web of Science

    researchmap

  • Motion blur parameter identification from a linearly blurred image Reviewed

    Masayuki Tanaka, Kenichi Yoneji, Masatoshi Okutomi

    ICCE: 2007 DIGEST OF TECHNICAL PAPERS INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS   441 - +   2007

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Web of Science

    researchmap

  • A direct and efficient method for piecewise-planar surface reconstruction from stereo images Reviewed

    Shigeki Sugimoto, Masatoshi Okutomi

    2007 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOLS 1-8   2150 - +   2007

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Web of Science

    researchmap

  • A footstep-plan-based floor sensing method using stereo images for biped robot control Reviewed

    Minami Asatani, Shigeki Sugimoto, Masatoshi Okutomi

    2007 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS, VOLS 1-9   913 - +   2007

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Web of Science

    researchmap

  • Neighbor Pixel Mixture and its Design Based on Condition Number

    Masayuki Tanaka, Masatoshi Okutomi

    Journal of the Institute of Image Electronics Engineers of Japan   Vol. 35 ( No. 5 )   461 - 468   2006.9

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    DOI: 10.11371/iieej.35.461

    Scopus

    researchmap

  • ステレオ画像を用いた道路シーン中の直線の検出

    田中健一, 奥富正敏

    電子情報通信学会論文誌 D   Vol. J89-D ( No. 8 )   1892 - 1896   2006.8

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • 道路面の抽出・姿勢推定をもとにした一般道路環境下におけるロバストな障害物検出

    関晃仁, 奥富正敏

    電子情報通信学会論文誌 D   Vol. J89-D ( No. 8 )   1859 - 1868   2006.8

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • 透明板に映る2重像を用いた1台のカメラによる距離計測手法

    清水雅夫, 奥富正敏

    情報処理学会論文誌:コンピュータビジョンとイメージメディア   Vol. 47 ( No. SIG10 (CVIM15) )   131 - 142   2006.7

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • 周波数領域最適化法によるMAP型超解像処理の高速化

    田中正行, 奥富正敏

    情報処理学会論文誌:コンピュータビジョンとイメージメディア   Vol. 47 ( No. SIG10 (CVIM15) )   12 - 22   2006.7

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • 直線的手ぶれ画像復元のためのPSFパラメータ推定手法

    米司健一, 田中正行, 奥富正敏

    情報処理学会論文誌:コンピュータビジョンとイメージメディア   Vol. 47 ( No. SIG9 (CVIM14) )   107 - 110   2006.6

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • ステレオ画像を用いた画質と視差推定精度の同時改善

    池田 薫, 清水 雅夫, 奥富正敏

    情報処理学会論文誌:コンピュータビジョンとイメージメディア   Vol. 47 ( No. SIG9 (CVIM14) )   111 - 114   2006.6

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • Multi-Parameter Simultaneous Estimation on Area-Based Matching

    Masao Shimizu, Masatoshi Okutomi

    International Journal of Computer Vision   Vol. 67 ( No. 3 )   2006.5

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  • ステレオ動画像を利用した道路面領域の抽出と追跡による自車両の運動推定

    関晃仁, 奥富正敏

    情報処理学会論文誌:コンピュータビジョンとイメージメディア   Vol. 47 ( No. SIG5 (CVIM13) )   90 - 99   2006.3

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • 再構成型超解像処理の理論限界に関する検討

    田中正行, 奥富正敏

    情報処理学会論文誌:コンピュータビジョンとイメージメディア   Vol. 47 ( No. SIG5 (CVIM13) )   80 - 89   2006.3

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • 画像のレジストレーションにおける超平面交差法の高速化手法

    張馴槿, 清水雅夫, 奥富正敏

    電子情報通信学会論文誌   Vol. J89-D ( No. 2 )   2006.2

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • Panoramic 3D reconstruction using rotational stereo camera with simple epipolar constraints Reviewed

    Wei Jiang, Masatoshi Okutomi, Shigeki Sugimoto

    Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition   1   371 - 378   2006

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1109/CVPR.2006.217

    Scopus

    researchmap

  • Super-resolution using a multi-mixture imaging system Reviewed

    Masayuki Tanaka, Masatoshi Okutomi

    2006 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP 2006, PROCEEDINGS   1725 - +   2006

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Web of Science

    researchmap

  • Neighbor pixel mixture Reviewed

    Masayuki Tanaka, Masatoshi Okutomi

    18TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 3, PROCEEDINGS   647 - +   2006

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Web of Science

    researchmap

  • Spatial merging for face detection Reviewed

    Hiromasa Takatsuka, Masayuki Tanaka, Masatoshi Okutomi

    2006 SICE-ICASE INTERNATIONAL JOINT CONFERENCE, VOLS 1-13   3722 - +   2006

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Web of Science

    researchmap

  • Robust and accurate image registration with pixel selection

    Masao Shimizu, SoonKeun Chang, Masatoshi Okutomi

    Sixth IEEE International Symposium on Signal Processing and Information Technology, ISSPIT   851 - 856   2006

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:Institute of Electrical and Electronics Engineers Inc.  

    DOI: 10.1109/ISSPIT.2006.270917

    Scopus

    researchmap

  • A fast MAP-based super-resolution algorithm for general motion Reviewed

    Masayuki Tanaka, Masatoshi Okutomi

    COMPUTATIONAL IMAGING IV   6065   2006

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Web of Science

    researchmap

  • Reflection stereo - Novel monocular stereo using a transparent plate

    Masao Shimizu, Masatoshi Okutomi

    Third Canadian Conference on Computer and Robot Vision, CRV 2006   2006   14 - 21   2006

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE Computer Society  

    DOI: 10.1109/CRV.2006.59

    Scopus

    researchmap

  • 再構成型超解像処理の高速化アルゴリズムとその精度評価

    田中正行, 奥富正敏

    電子情報通信学会論文誌 D-II   Vol. J88-D-II ( No. 11 )   2200 - 2209   2005.11

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • ミラー付き回転カメラによる全周3次元再構成

    Masatoshi Okutomi

    電子情報通信学会論文誌 D-II   J88-D-II ( 8 )   1508 - 1520   2005.8

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • Sub-pixel Estimation Error Cancellation on Area-Based Matching

    Masao Shimizu, Masatoshi Okutomi

    International Journal of Computer Vision   Vol. 63 ( No. 3 )   2005.7

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  • Super Resolution by Image Processing

    SUGIMOTO Shigeki, OKUTOMI Masatoshi

    JRSJ   23 ( 3 )   305 - 309   2005.4

     More details

    Language:Japanese   Publisher:The Robotics Society of Japan  

    DOI: 10.7210/jrsj.23.305

    CiNii Books

    researchmap

    Other Link: https://jlc.jst.go.jp/DN/JALC/00250148347?from=CiNii

  • 画像の超解像度化処理

    杉本茂樹, 奥富正敏

    日本ロボット学会誌   23 ( 3 )   33 - 37   2005.4

     More details

    Language:Japanese  

    researchmap

  • Two-Dimensional Simultaneous Sub-Pixel Estimation for Area-Based Matching

    Masao Shimizu, Masatoshi Okutomi

    Systems and Computers in Japan   Vol. 36 ( No. 2 )   2005.2

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  • Theoretical analysis on reconstruction-based super-resolution for an arbitrary PSF Reviewed

    Masayuki Tanaka, Masatoshi Okutomi

    Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005   II   947 - 954   2005

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE Computer Society  

    DOI: 10.1109/CVPR.2005.343

    Scopus

    researchmap

  • Color super-resolution using hand-held camera

    Masayuki Tanaka, Masatoshi Okutomi

    Proceedings of the SICE Annual Conference   2096 - 2100   2005

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Scopus

    researchmap

  • 画像変形を表すNパラメータの高精度同時推定法と超解像への応用

    清水雅夫, 矢野高宏, 奥富正敏

    情報処理学会論文誌:コンピュータビジョンとイメージメディア   Vol. 45 ( No. SIG13(CVIM10) )   83 - 98   2004.12

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • Moving Obstacle Segmentation Using MMW Radar and Image Sequence

    Shigeki Sugimoto, Hidekazu Takahashi, Masatoshi Okutomi

    International Journal of ITS Research   Vol. 2 ( No. 1 )   55 - 66   2004.10

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  • Omnidirectional 3-D Reconstruction Using Stereo Multi-Perspective Panoramas

    JIANG Wei, OKUTOMI Masatoshi, SUGIMOTO Shigeki

    The Journal of the Institute of Image Electronics Engineers of Japan   Vol. 33 ( No. 4-B )   565 - 575   2004.8

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)   Publisher:The Institute of Image Electronics Engineers of Japan  

    In this paper, we present a new approach for omnidirectional 3-D reconstruction using multi-perspective panoramas. We use two large collections of images taken by parallel stereo cameras whose motions are constrained to a planar concentric circle. The two collections of regular perspective images are resampled into four multi-perspective panoramas. Then we compute a depth map from three pairs of panoramas using multi-baseline algorithm with three types of epipolar constraints, that is horizontal, vertical and combination of them. Experimental results show that the proposed method can produce panoramic depth maps for omnidirectional 3D reconstruction.

    DOI: 10.11371/iieej.33.565

    CiNii Books

    researchmap

  • ステレオ動画像を利用した平面領域抽出による障害物検出

    関晃仁, 奥富正敏

    情報処理学会論文誌:コンピュータビジョンとイメージメディア   45 ( SIG13(CVIM10) )   1 - 10   2004

     More details

  • Obstacle detection using millimeter-wave radar and its visualization on image sequence Reviewed

    Shigeki Sugimoto, Hayato Tateda, Hidekazu Takahashi, Masatoshi Okutomi

    Proceedings - International Conference on Pattern Recognition   3   342 - 345   2004

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1109/ICPR.2004.1334537

    Scopus

    researchmap

  • 単板カラー撮像素子のRAWデータを利用した高精細画像復元

    後藤知将, 奥富正敏

    情報処理学会論文誌:コンピュータビジョンとイメージメディア   45 ( SIG 8(CVIM 9) )   15 - 25   2004

     More details

  • A simple stereo algorithm to recover precise object boundaries and smooth surfaces

    M Okutomi, Y Katayama, S Oka

    INTERNATIONAL JOURNAL OF COMPUTER VISION   47 ( 1-3 )   261 - 273   2002.4

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    DOI: 10.1023/A:1014510328154

    Web of Science

    researchmap

  • ステレオ動画像を用いた視覚誘導のための平面領域の連続推定

    奥富正敏, 中野勝之, 丸山純一, 原智章

    情報処理学会論文誌   43 ( 4 )   1061 - 1069   2002

     More details

  • A Proposal for Extracting an Object's Surface from Stereo Degree-of-Correspondence Space Considering Occlusions

    Yasuhiro Katayama, Masatoshi Okutomi

    Electronics and Communications in Japan (PartII: Electronics)   Vol. 84 ( No. 8 )   38 - 48   2001.8

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    DOI: 10.1002/ecjb.1048

    Web of Science

    researchmap

  • 領域ベースステレオマッチングにおけるバウンダリオーバリーチの解析

    片山保宏, 岡摂子, 奥富正敏

    電子情報通信学会論文誌 D-II   J84-D-II ( 3 )   596 - 602   2001

     More details

  • An Approach to Virtual-Viewpoint Image Generation Using Volume Rendering

    YAMAMOTO Tadashi, OKUTOMI Masatoshi

    The Journal of the Institute of Image Electronics Engineers of Japan   30 ( 4 )   371 - 378   2001

     More details

    Language:Japanese   Publisher:The Institute of Image Electronics Engineers of Japan  

    In this paper, we propose a new method for Image Based Rendering. Many studies using stereo vision techniques, which reconstruct shape of the objects, have been reported in the field of Image Based Rendering. However, these techniques cannot avoid difficulty in determining the positions of all object surfaces explicitly. Based on the thought that the problem of Image Based Rendering is estimation of the color of incident light into virtual viewpoint, our method divides the object space into voxels, and represents the probability of existence of the object as a continuous value calculated from the differences of colors projected onto input images, and directly perform rendering using the technique of Volume Rendering. Consequently, it can synthesize virtual viewpoint images without determining the surface depth explicitly by very simple algorithm.

    DOI: 10.11371/iieej.30.371

    CiNii Books

    researchmap

  • High-Definition Image Mosaicing Using Multiple Resolution Images and Its Interactive Display System

    Tomohisa Shidara, Kosuke Hayashi, Masatoshi Okutomi

    Journal of the Institute of Image Electronics Engineers of Japan   30 ( 5 )   613 - 618   2001

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    DOI: 10.11371/iieej.30.613

    Scopus

    researchmap

  • 物体境界と滑らかな表面形状を共に復元するステレオビジョン

    奥富正敏, 片山保宏, 横山敦

    画像電子学会誌   29 ( 5 )   445 - 451   2000

     More details

  • アクティブカメラによるイメージモザイキング

    中谷裕, 奥富正敏

    画像電子学会誌   29 ( 5 )   462 - 470   2000

     More details

  • Road-Region Detection by Computing Homography Matrix Using Stereo Images

    OKUTOMI Masatoshi, NOGUCHI Suguru, NAKANO Katsuyuki

    JRSJ   18 ( 8 )   1105 - 1111   2000

     More details

    Language:Japanese   Publisher:The Robotics Society of Japan  

    Detecting the road region in an observed image is an important technique for visual navigation of an autonomous vehicle. In this paper, we propose a road detection method using stereo images. The method does not rely on the existence of any specific road painting or texture. Instead, it supposes that a road (or a passable part) can be approximated by a plane. Then, a homography matrix which represents a geometric relation between the road plane and the stereo images can be computed from the stereo images. And the road region can be detected in the observed image by transforming one image by the homography matrix and simple matching. In this method, neither a predetermined geometric relation between the cameras and the road nor a strong camera calibration are necessary. Experimental results with real scenes have shown the effectiveness of the proposed method.

    DOI: 10.7210/jrsj.18.1105

    CiNii Books

    researchmap

    Other Link: https://jlc.jst.go.jp/DN/JALC/00070152555?from=CiNii

  • Shape recovery of rotating object using weighted voting of spacio-temporal images

    Masatoshi Okutomi, Shigeki Sugimoto

    Proceedings - International Conference on Pattern Recognition   15 ( 1 )   790 - 793   2000

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    Scopus

    researchmap

  • 時空間画像を用いた回転物体の形状復元

    杉本茂樹, 奥富正敏

    情報処理学会論文誌   Vol. 40 ( No. 6 )   2717 - 2724   1999.6

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • ステレオ対応度空間からのオクルージョンを考慮した表面抽出の試み

    片山保宏, 奥富正敏

    電子情報通信学会論文誌   Vol. J82-D-II ( No. 4 )   780 - 789   1999

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • Difficulties in Stereo Vision

    OKUTOMI Masatoshi

    JRSJ   16 ( 6 )   773 - 777   1998.9

     More details

    Language:Japanese   Publisher:The Robotics Society of Japan  

    DOI: 10.7210/jrsj.16.773

    CiNii Books

    researchmap

    Other Link: https://jlc.jst.go.jp/DN/JALC/00054827479?from=CiNii

  • ステレオがなぜ難しいか

    奥富正敏

    日本ロボット学会誌   Vol. 16 ( No. 6 )   39 - 43   1998

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • Calibration of a Pan/Tilt/ZoomCamera by a Simple Camera Model

    NUMAO Toshio, NAKATANI Yuu, OKUTOMI Masatoshi

    The Journal of the Institute of Television Engineers of Japan   Vol. 52 ( No. 9 )   1343 - 1350   1998

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)   Publisher:The Institute of Image Information and Television Engineers  

    We propose simple model for calibrating of our pan/tilt/zoom camera, which consists of two rotation stages, an electrically-controlled zoom lens, and a CCD camera. The simple model assumes that zoom changes do not cause any change in the optical axis, the image center, the position of the image plane of camera in world coordinates system, or the rotation axes of pan/tilt. We show that when our model is used, calibration can be achieved independently of the zoom setting and the number of parameters that must be estimated in calibration decreases.<BR>Because calibration of the pan/tilt/zoom camera was achieved, we can obtain the images by which the viewing angle and the magnification are set in an arbitrary value. And we show that the images are easily integrated using the position between the images derived from the estimated parameters.

    DOI: 10.3169/itej.52.1343

    CiNii Books

    researchmap

    Other Link: https://jlc.jst.go.jp/DN/JALC/00055972277?from=CiNii

  • コンピュータビジョン:技術評論と将来展望(分担)

    奥富正敏, 他

    Vol.   1998

     More details

    Language:Japanese   Publisher:新技術コミュニケーションズ  

    researchmap

  • 計測と制御

    奥富正敏, 他

    Vol.   1997

     More details

    Language:Japanese   Publisher:財団法人放送大学教育振興会  

    researchmap

  • Calibration accuracy and its dependence on target point arrangement for a zoom lens camera system

    Toshio Numao, Masatoshi Okutomi

    Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers   Vol. 51 ( No. 12 )   2126 - 2132   1997

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)   Publisher:Inst. of Image Information and Television Engineers  

    DOI: 10.3169/itej.51.2126

    Scopus

    researchmap

  • Stereo Matching algorithm with an Adaptive Window: Theory and Experiment

    Takeo Kanade, Masatoshi Okutomi

    IEEE Transactions on Pattern Analysis and Machine Intelligence   Vol. 16 ( No. 9 )   920 - 932   1994

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    DOI: 10.1109/34.310690

    Web of Science

    researchmap

  • Stereo vision based on mathematical modeling : toward adaptive and precise 3-D reconstruction from projected images

    MASATOSHI OKUTOMI

    1993.7

     More details

    Language:English   Publishing type:Doctoral thesis  

    researchmap

  • カラーステレオマッチングとその視神経乳頭3次元計測への応用

    奥富正敏, 吉崎修, 富田剛司

    電子情報通信学会論文誌(D-II)   Vol. J76-D-II ( No. 2 )   342 - 349   1993

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • A Stereo Matching Algorithm: An Adaptive Window Based on a Statistical Model

    Masatoshi Okutomi, Takeo Kanade

    Systems and Computers in Japan   Vol. 23 ( No. 8 )   26 - 35   1992.10

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    DOI: 10.1002/scj.4690230803

    Scopus

    researchmap

  • 複数の基線長を利用したステレオマッチング

    奥富正敏, 金出武雄

    電子情報通信学会論文誌(D-II)   Vol. J75-D-II ( No. 8 )   1317 - 1327   1992

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • A Locally Adaptive Window for Signal Matching

    Masatoshi Okutomi, Takeo Kanade

    International Journal of Computer Vision   Vol. 7 ( No. 2 )   143 - 162   1992

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    DOI: 10.1007/BF00128133

    Web of Science

    researchmap

  • 統計的モデルに基づく適応型ウィンドウによるステレオマッチング --- 1次元信号を用いた解析と実験

    奥富正敏, 金出武雄

    電子情報通信学会論文誌(D-II)   Vol. J74-D-II ( No. 6 )   669 - 677   1991.6

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • Decision of Robot's Movement by Means of Potential Field

    OKUTOMI Masatoshi, MORI Masahiro

    JRSJ   1 ( 3 )   226 - 232   1983

     More details

    Publisher:The Robotics Society of Japan  

    In this paper a method of deciding robot's movement by means of potential field is proposed and simple simulations using it are shown. Especially two concepts, "State space for robots" and "Oval potential", are unique.<BR>A robot which utilizes the proposed method has a potential field as what keeps informations about its surrounding situation. The field is formed in a space that represents the robot's state (state space) . And the robot's state that is a point in the space moves according to the potential distribution.<BR>The principal characteristics of this method are following.<BR>•As a robot's state is represented by a point, the decision of movement can be made simply.<BR>•And the oval potential is used for potential distribution, the robot's state moves successfully, the object is memorized by a little information and the calculation for the potential is easy.

    DOI: 10.7210/jrsj.1.3_226

    researchmap

  • ポテンシャル場を用いたロボットの動作決定

    奥富正敏, 森政弘

    日本ロボット学会誌   1 ( 3 )   66 - 72   1983

     More details

▼display all

Books

  • ディジタル画像処理[改訂第二版]

    奥富正敏, 他編( Role: Joint editor)

    公益財団法人画像情報教育振興協会(CG-ARTS協会)  2020.2  ( ISBN:9784903474649

     More details

    Total pages:479p   Language:Japanese  

    CiNii Books

    researchmap

  • センサフュージョン技術の開発と応用事例

    柴田剛志, 田中正行, 奥富正敏, 他著( Role: Joint author第7章第2節 可視カメラと遠赤外カメラの同時校正技術)

    技術情報協会  2019.1  ( ISBN:9784861047367

     More details

    Total pages:528p   Language:Japanese  

    CiNii Books

    researchmap

  • Disaster Robotics, Results from the ImPACT Tough Robotics Challenge

    Masayuki Tanaka, Takashi Shibata, Masatoshi Okutomi et. al( Role: Joint authorChapter5 [Dual-Arm Construction Robot with Remote-Control Function])

    2019.1 

     More details

  • ビジュアル情報処理 -CG・画像処理入門- [改訂新版]

    奥富正敏, 他編

    公益財団法人画像情報教育振興協会(CG-ARTS協会)  2017.3 

     More details

  • 三次元画像センシングの新展開 : リアルタイム・高精度に向けた要素技術から産業応用まで

    鳥居秋彦, 奥富正敏 他著, 岩堀祐之 監修( Role: Joint author第3章 三次元復元技術)

    エヌ・ティー・エス  2015.5  ( ISBN:9784860434281

     More details

    Total pages:ii, viii, 358, viip, 図版21p   Language:Japanese  

    CiNii Books

    researchmap

  • コンピュータグラフィックス[改訂新版]

    奥富正敏, 他編( Role: Joint editor)

    公益財団法人画像情報教育振興協会(CG-ARTS協会)  2015.3 

     More details

  • ディジタル画像処理[改訂新版]

    奥富正敏, 他編著( Role: Joint editor)

    公益財団法人画像情報教育振興協会(CG-ARTS協会)  2015.3 

     More details

  • Super-Resolution Imaging

    Masayuki Tanaka, Masatoshi Okutomi( Role: Joint authorToward Robust Reconstruction-Based Super-Resolution)

    CRC Press  2010.9 

     More details

  • ロボット情報学ハンドブック

    杉本茂樹, 奥富正敏他編著( Role: Joint author車載カメラによる道路認識(相対姿勢,障害物検出))

    ナノオプトニクス・エナジー出版局  2010.3 

     More details

  • ビジュアル情報処理-CG・画像処理入門-

    財団法人画像情報教育振興協会(CG-ARTS協会)  2004 

     More details

  • ディジタル画像処理

    財団法人画像情報教育振興協会(CG-ARTS協会)  2004 

     More details

  • コンピュータグラフィックス

    財団法人画像情報教育振興協会(CG-ARTS協会)  2004 

     More details

  • コンピュータビジョン:技術評論と将来展望(分担)

    新技術コミュニケーションズ  1998 

     More details

  • 計測と制御

    財団法人放送大学教育振興会  1997 

     More details

▼display all

MISC

  • 畳み込みニューラルネットワークを用いた劣化画像のクラス分類

    遠藤和紀, 田中正行, 奥富正敏

    画像ラボ   32 ( 3 )   52 - 58   2021.3

     More details

    Authorship:Last author   Language:Japanese  

    researchmap

  • 内視鏡動画像からの胃の3次元モデル復元

    紋野雄介, Widya Aji Resindra, 奥富正敏, 鈴木翔, 後藤田卓志, 三木健司

    O plus E誌 2020年11・12月号, アドコム・メディア   42 ( 6 )   755 - 760   2020.11

     More details

    Language:Japanese   Publisher:アドコム・メディア  

    researchmap

  • 可視光と近赤外光を同時に撮像可能な撮像素子

    紋野雄介, 田中正行, 奥富正敏, 吉崎和徳, 福西宗憲, 小宮康宏

    O plus E誌 2018年7・8月号, アドコム・メディア   560 - 065   2018.7

     More details

  • 可視及び遠赤外カメラの同時校正技術とその応用

    柴田剛志, 田中正行, 奥富正敏

    画像ラボ   29 ( 4 )   2018.4

     More details

    Authorship:Last author  

    researchmap

  • カラー画像と近赤外線画像を同時撮影可能なイメージングシステム

    紋野雄介, 田中正行, 奥富正敏, 吉崎和徳, 福西宗憲, 小宮康宏

    O plus E   2016.10

     More details

    Language:Japanese   Publisher:アドコム・メディア  

    researchmap

  • リアルタイムマルチバンドイメージングシステム ー RGBカラーイメージングを超えて ー

    紋野雄介, 田中正行, 奥富正敏, 菊地直, 吉崎和徳, 小宮康宏

    画像ラボ   2016.6

     More details

    Language:Japanese   Publisher:日本工業出版  

    researchmap

  • 車載ステレオカメラによる地表サーフェスマップ生成

    杉本茂樹, 本岡昂馬, 奥富正敏, 志磨健

    画像ラボ   2016.2

     More details

    Language:Japanese   Publisher:日本工業出版  

    researchmap

  • 様々な広視野カメラを利用可能なオンラインSfMシステムの構築

    井上優希, 鳥居秋彦, 奥富正敏

    研究報告コンピュータビジョンとイメージメディア(CVIM)   2014 ( 25 )   1 - 7   2014.5

     More details

    Language:Japanese   Publisher:一般社団法人情報処理学会  

    Structure from Motion(SfM) の発展により,撮影対象の 3D モデルの復元やカメラの位置姿勢推定を,画像から容易に行うことが可能になりつつある.本論文では,広範囲を撮影できるカメラを利用することで効率よくシーンを撮影し,オンラインで復元を行う SfM システムを提案する.投影モデルが異なる様々な広視野カメラを単一のシステムで利用可能にするため,各投影モデルを表す投影関数と逆投影関数を一様な形で表現することで,カメラの種類に依らないシステムの構築を行った.さらに,実装上の工夫として,処理時間の大部分を占める特徴点検出と特徴点マッチングを画像ごとに並列化することで,効率のよいシステムを実現した.また,広視野カメラで屋内,屋外のシーンを撮影して復元を行い,実験を通して提案システムの有効性を示す.

    CiNii Books

    researchmap

  • 逐次的四面体カービング法を用いた3Dモデリング

    鳥居秋彦, 杉浦貴行, 奥富正敏

    研究報告コンピュータビジョンとイメージメディア(CVIM)   2013 ( 6 )   1 - 7   2013.11

     More details

    Language:Japanese   Publisher:一般社団法人情報処理学会  

    画像が次々と入力され,Structure from Motion (SfM) によって疎な 3D 点群とカメラポーズが与えられる場合,逐次的に効率良くサーフェス生成を行う手法を提案する.提案手法では,四面体を削り出すサーフェス抽出法を,視線と四面体の交差の効率的な検出方法と,ダイナミックグラフカットを適用したサーフェス抽出によって,逐次的処理が可能な手法へと発展する.これらにより,追加の入力に対して効率の良い処理でありながら,常に全体最適性を保証することが可能である.従って,提案手法で抽出されるサーフェスは,既存のバッチ処理によるサーフェス抽出手法を,入力毎に始めから繰り返す場合と,完全に同一のものとなる.実験では,数種類の既存手法と比較を行い,提案手法の効果を示す.

    CiNii Books

    researchmap

  • インクリメンタル四面体カービング法による三次元サーフェス生成

    杉浦貴行, 鳥居秋彦, 奥富正敏

    研究報告コンピュータビジョンとイメージメディア(CVIM)   2013 ( 7 )   1 - 5   2013.5

     More details

    Language:Japanese  

    Structure from Motion (SfM) 手法により,単眼カメラ画像からその画像を撮影したカメラの位置姿勢と 3D 点の推定が可能である.SfM によって得られる点群から平面やテクスチャ情報を付加できるサーフェスを生成することは,点群では表現しがたい遮蔽関係や変化の検出など,様々な応用上重要である.本論文では,特に逐次的な入力に対して,単純に毎フレーム始めから処理を繰り返すようなサーフェス生成ではなく,サーフェスの一部が拡張・更新されるインクリメンタルサーフェス生成の手法を提案する.提案手法の特徴は,インクリメンタル処理による効率化を図りながら,全体最適性の保たれたサーフェスを生成できる点にある.

    CiNii Books

    researchmap

  • 時系列ステレオ画像を用いた直接法による広範囲な地表面サーフェスマップ生成

    本岡昂馬, 杉本茂樹, 奥富正敏

    研究報告コンピュータビジョンとイメージメディア(CVIM)   2013 ( 9 )   1 - 5   2013.5

     More details

    Language:Japanese  

    本論文では,ステレオ時系列画像を利用した地表面の 3 次元サーフェスとカメラ運動を同時に推定する手法を提案する.提案手法では,地上座標系において高さゼロの平面上に三角パッチで構成されるメッシュを定め,地表面を異なる時刻で観測したステレオ画像 2 組から,メッシュ頂点の高さと,時刻間のカメラ運動を推定する.この推定には,ダイレクトイメージアライメントの考え方を利用し,2 組のステレオ画像間のパッチ内領域の画素値差分を表すコスト関数を最小化する.サーフェスとカメラ運動を同時に推定することで,各時刻でのサーフェス推定結果を合わせた,広範囲なサーフェスマップ生成が可能となる.また,提案手法では,カメラの自動露光補正などによって生じる時系列画像間の輝度の変化に対し,その変化を同時に求めることで推定の安定性を向上させている.提案手法を実画像に用い,広範囲なサーフェスマップ生成を行うことにより,提案手法の有効性を示す.

    CiNii Books

    researchmap

  • 近傍パッチの情報に基づく重みを利用したスパース再構成による一枚超解像

    牧野賢吾, 櫻井歩, 田中正行, 奥富正敏

    研究報告コンピュータビジョンとイメージメディア(CVIM)   2013 ( 16 )   1 - 6   2013.5

     More details

    Language:Japanese  

    画像の一枚超解像手法について,スパースコーディングを用いたものが近年成果を挙げている.スパースコーディングを用いた画像再構成 (スパース再構成) では,画像をパッチに切り分け,各パッチを少数の基底の線形結合によって表現する.この時,線形結合の係数を決める際に基底に重みを与えることで再構成結果が向上することが知られている.本論文ではパッチとその近傍パッチの概形からクラスタリングを行い,クラスタに応じた重みを与えてスパース再構成を行う手法を提案する.従来のスパース再構成ではパッチは独立に処理されていたが,提案手法では近傍のパッチの情報も利用して再構成を行っており,一枚超解像の結果から,提案手法の性能の有効性が確認された.

    CiNii Books

    researchmap

  • BoFの分割表現を用いた画像検索による自己位置・方位推定

    董亜飛, 鳥居秋彦, 奥富正敏

    研究報告コンピュータビジョンとイメージメディア(CVIM)   2013 ( 15 )   1 - 6   2013.5

     More details

    Language:Japanese  

    本研究では,パノラマ画像をデータベースとする画像検索にもとづいて,撮影した画像の自己位置・方位を推定するための手法を提案する.画像検索にもとづいて方位推定を実現するためには,パノラマ画像から各方位に対応するカットアウト画像を複数生成し,それぞれの BoF を用意する必要がある.提案手法では,画像を縦長のタイル状に分割し,各タイル領域から BoF を抽出することで,隣り合う画像間で情報重複のない BoF データベースを構成する.同時にデータベースが疎のためサイズが小さく計算コストが低い.実験で提案手法が複数画像を生成した場合と同等あるいはそれ以上の精度で位置推定が可能なことを示す.

    CiNii Books

    researchmap

  • 焦点距離が未知の入力画像群に対する3次元復元の安定化

    野沢和輝, 鳥居秋彦, 奥富正敏

    研究報告コンピュータビジョンとイメージメディア(CVIM)   2012 ( 19 )   1 - 8   2012.5

     More details

    Language:Japanese  

    本研究では焦点距離が未知の画像集合に対して,安定した3次元復元を行うためのアルゴリズムを提案する.Steweniusらが提案した6点アルゴリズムを用いることで,画像ペアからカメラ間の相対的な運動と焦点距離が推定可能である.カメラ内部校正を前提条件とするNisterらの5点アルゴリズムに比べ汎用であるものの,撮影したシーン,カメラ運動に対する幾何学的縮退条件が多く,不安定なものであった.本論文では,縮退が起きている画像ペアの検出アルゴリズムを新たに提案することで3次元復元システムの安定化を図る.これにより,近年広く用いられているBundlerなどのストラクチャーフロムモーションが必要とする焦点距離が既知という制約がなくなり,3次元復元に用いる入力画像の自由度が広がる.

    CiNii Books

    researchmap

  • Spatial Super-resolution and Gray Level Super-quantization

    Journal of the Japan Society for Precision Engineering   77 ( 12 )   1099 - 1103   2011.12

     More details

    Language:Japanese   Publisher:The Japan Society for Precision Engineering  

    DOI: 10.2493/jjspe.77.1099

    researchmap

  • H-011 Fast KNN algorithm using PatchMatch

    FAN YingYing, TANAKA Masayuki, OKUTOMI Masatoshi

    10 ( 3 )   125 - 126   2011.9

     More details

    Language:Japanese   Publisher:Forum on Information Technology  

    CiNii Books

    researchmap

  • ノンローカルPCAによるブラインドデノイジング

    山内啓大朗, 田中正行, 奥富正敏

    画像の認識・理解シンポジウム(MIRU2011)論文集   2011   432 - 439   2011.7

     More details

    Language:Japanese  

    researchmap

  • 赤外フラッシュと1台のカメラを利用した低照度シーンのカラー画像生成

    ゴウキムシン, 田中正行, 奥富正敏

    画像の認識・理解シンポジウム(MIRU2011)論文集   2011   1034 - 1041   2011.7

     More details

    Language:Japanese  

    researchmap

  • 安定・高精度なオンラインSfM

    鳥居秋彦, 奥富正敏

    画像の認識・理解シンポジウム(MIRU2011)論文集   2011   1719 - 1720   2011.7

     More details

    Language:Japanese  

    researchmap

  • 単板撮像素子を用いたワンショット撮影によるマルチスペクトル画像生成

    紋野雄介, 田中正行, 奥富正敏

    画像の認識・理解シンポジウム(MIRU2011)論文集   2011   1042 - 1049   2011.7

     More details

    Language:Japanese  

    researchmap

  • High resolution color image interpolation using color correlation

    2011 ( 25 )   1 - 8   2011.5

     More details

    Language:Japanese  

    CiNii Books

    researchmap

  • Robust and Fast Super-Resolution

    TANAKA Masayuki, OKUTOMI Masatoshi

    IEICE technical report. Image engineering   110 ( 217 )   55 - 55   2010.9

     More details

    Language:Japanese   Publisher:The Institute of Electronics, Information and Communication Engineers  

    CiNii Books

    researchmap

  • A Direct Method for Camera Calibration from Planar Scene

    SUGIMOTO SHIGEKI, OKUTOMI MASATOSHI

    2010 ( 4 )   1 - 8   2010.8

     More details

  • 誰にでもわかる画像超解像

    奥富正敏

    O plus E   2010.8

     More details

    Language:Japanese   Publisher:アドコム・メディア株式会社  

    researchmap

  • Recent Trends in Image Super-resolution

    OKUTOMI Masatoshi, TANAKA Masayuki, TAKESHIMA Hidenori, MATSUMOTO Nobuyuki

    The Journal of the Institute of Electronics, Information and Communication Engineers   93 ( 8 )   693 - 698   2010.8

     More details

    Language:Japanese   Publisher:The Institute of Electronics, Information and Communication Engineers  

    CiNii Books

    researchmap

  • 複数フレーム超解像処理のためのロバストかつ高精度な位置合わせ処理

    田中正行, 奥富正敏, 矢口陽一

    画像ラボ   21 ( 6 )   1 - 6   2010.6

     More details

    Language:Japanese   Publisher:日本工業出版  

    CiNii Books

    researchmap

  • Stabilization of Poisson Equation for Gradient-Based Image Composing

    KAMIO RYO, TANAKA MASAYUKI, OKUTOMI MASATOSHI

    2010 ( 9 )   1 - 7   2010.5

     More details

  • Natural Image prior model using adaptive multi-variate Gaussian distribution

    YAMAUCHI KEITARO, TANAKA MASAYUKI, OKUTOMI MASATOSHI

    2010 ( 10 )   1 - 8   2010.5

     More details

  • 高速平面姿勢推定を利用した多眼ステレオからの仮想焦点面画像生成

    杉本茂樹, 奥富正敏

    画像ラボ   21 ( 1 )   6 - 11   2010.1

     More details

    Language:Japanese   Publisher:日本工業出版  

    researchmap

  • Color image interpolation using kernel regression

    IEICE technical report   109 ( 182 )   127 - 134   2009.8

     More details

    Language:Japanese  

    researchmap

  • Color Image Interpolation using Kernel Regression

    TANAKA Masayuki, OKUTOMI Masatoshi

    2009 ( 20 )   1 - 8   2009.8

     More details

  • Range Estimation Using Uncalibrated Double Layered Image

    FUJIWARA MASANOBU, SHIMIZU MASAO, OKUTOMI MASATOSHI

    2009 ( 20 )   1 - 7   2009.6

     More details

  • A Direct Method for 3D Reconstruction from Multi-View Stereo

    SHIOTA YOSUKE, SUGIMOTO SHIGEKI, OKUTOMI MASATOSI

    2009 ( 19 )   1 - 8   2009.6

     More details

  • リフレクションステレオを構成する技術 ― 2重像間変位の計測 ―

    清水雅夫, 奥富正敏

    画像ラボ   20 ( 4 )   28 - 33   2009.4

     More details

    Language:Japanese   Publisher:日本工業出版  

    CiNii Books

    researchmap

  • Blur Image Restoration with Reducing Ringing

    KANDA Takafumi, TANAKA Masayuki, OKUTOMI Masatoshi

    IPSJ SIG Notes. CVIM   2008 ( 36 )   99 - 104   2008.5

     More details

    Language:Japanese   Publisher:Information Processing Society of Japan (IPSJ)  

    Camera shake during exposure blurs images. The blurring process can be modeled as an image convolution by point spread function (PSF) which describes the motion path. A deblurring from a single blurred image is challenging problem, even if the PSF is known. The deblurred images usually include unexpected ringing artifacts. In this paper, we proposed a progressive image deconvolution method using a residual image. In the proposed method, the input blurred image is decomposed into the reference image and the residual image. Then, the blurred residual image is deblurred instead of the input blurred image. The reference image is updated based on the deblurred residual image. We demonstrate the effectiveness of the proposed method using synthetic images and real images.

    CiNii Books

    researchmap

    Other Link: http://id.nii.ac.jp/1001/00051813/

  • Technologies leading to the next-generation digital cameras and movies (3); super-resolution: high-resolution image reconstruction from multiple low-resolution images

    Masayuki Tanaka, Masatoshi Okutomi

    Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers   62 ( 3 )   337 - 342   2008.3

     More details

    Language:Japanese   Publisher:Inst. of Image Information and Television Engineers  

    DOI: 10.3169/itej.62.337

    Scopus

    researchmap

  • 使いやすさを考慮した復元フィルタの設計 --直感的に復元効果を調整できる復元フィルタとは?--

    田中正行, 奥富正敏, 米司健一

    画像ラボ   19 ( 3 )   1 - 5   2008.3

     More details

    Language:Japanese   Publisher:日本工業出版  

    CiNii Books

    researchmap

  • ステレオ画像からの微小平面サーフェス生成 -- 三角ポリゴンメッシュを直接生成するステレオ3次元再構成 --

    杉本茂樹, 奥富正敏

    画像ラボ   18 ( 12 )   42 - 47   2007.12

     More details

    Language:Japanese   Publisher:日本工業出版  

    CiNii Books

    researchmap

  • Image Registration Method of Multiple Motion-Regions and Its Applications

    CHANG SoonKeun, SHIMIZU Masao, OKUTOMI Masatoshi

    IEICE technical report   107 ( 281 )   57 - 62   2007.10

     More details

    Language:English   Publisher:The Institute of Electronics, Information and Communication Engineers  

    In this study, we propose an accurate method of registering an input image to a reference image with detecting automatically the multiple motion-regions from an image sequence taken with a hand-held camera. In the first step of the proposed method, detecting the most dominant motion-region from the reference image is performed by setting the whole image as ROI (region of interest). Subsequently, the second dominant motion-region is detected from the remaining region ; the multiple motion-regions are extracted automatically by repeating this process. The proposed method can accurately estimate motion parameters associated with the motion-regions to align the input image to the reference image. Additionally, we present applications of the proposed method. The validity of the proposed method is confirmed by performing experiments on real images.

    CiNii Books

    researchmap

  • H-059 Image Registration Technique for Sequential Images with Multiple Motion Regions

    Chang SoonKeun, Shimizu Masao, Okutomi Masatoshi

    6 ( 3 )   141 - 144   2007.8

     More details

    Language:Japanese   Publisher:Forum on Information Technology  

    CiNii Books

    researchmap

  • Interactive Stereo Vision for Three-Dimensional Measurement

    SAITOU Yuuji, SHIMIZU Masao, OKUTOMI Masatoshi

    IPSJ SIG Notes. CVIM   2007 ( 42 )   121 - 124   2007.5

     More details

    Language:Japanese   Publisher:Information Processing Society of Japan (IPSJ)  

    In this study, we have realized an interactive stereo system with two cameras and active lighting to measure a stationary object shape. Any lighting condition changes including a moving electric flashlight or a moving shadow of a stick can be used for the active lighting. A time domain window is adopted to detect the correspondences between the stereo images. The time domain window dispenses with the use of the spatial local support that is usually employed in the stereo matching. The system displays the measurement results interactively to encourage the user to light up the region which does not show a good result. Experimental results demonstrate the effectiveness of our proposed system.

    CiNii Books

    researchmap

    Other Link: http://id.nii.ac.jp/1001/00052031/

  • Robust Super-Resolution under Occlusion and Illumination Change

    YAGUCHI Youichi, TANAKA Masayuki, OKUTOMI Masatoshi

    IPSJ SIG Notes. CVIM   2007 ( 42 )   51 - 56   2007.5

     More details

    Language:Japanese   Publisher:Information Processing Society of Japan (IPSJ)  

    A super-resolution requires accurate registration between low-resolution images. However, occlusions or an insufficient motion model degrade the accuracy of the registration. The inaccurate registration yields visible artifacts in super-resolution images. We propose the robust super-resolution against the registration error. The proposed method verifies each pixel based on a similarity and a registration error. Then, the super-resolution image is reconstructed from only validated pixels. We also propose an illumination correction method to improve the super-resolution image. Experiments demonstrate effectiveness the proposed method.

    CiNii Books

    researchmap

    Other Link: http://id.nii.ac.jp/1001/00052022/

  • Road Scene Understanding Using Sequential Stereo Images

    SEKI Akihito, OKUTOMI Masatoshi

    IPSJ SIG Notes. CVIM   2007 ( 42 )   1 - 16   2007.5

     More details

    Language:Japanese   Publisher:Information Processing Society of Japan (IPSJ)  

    In this paper, we propose methods of road scene understanding of vehicle front view using sequential vehicle-mounted stereo images. To understand road scene, we notice the issue that road surface information is fundamental because vehicles run on the road. Therefore, road surface is detected using sequential stereo images at beginning. First, we propose dangerous region detection method which is derived from checking edges of road region in real space. Second, obstacle detection method is proposed. Obstacles which are the 3D objects on the road surface are detected and measured using this road information. Third proposed method is ego-motion estimation. This is done by using road information and vehicle motion constraints on road surface. Final proposed method is simultaneous depth and 3D motion estimation. We present experimental results to demonstrate the effectiveness of our methods at each chapter.

    CiNii Books

    researchmap

    Other Link: http://id.nii.ac.jp/1001/00052018/

  • 透明板に映る2重像を用いた1台のカメラによる距離計測

    清水雅夫, 奥富正敏

    画像ラボ, 日本工業出版   18 ( 4 )   28 - 33   2007.4

     More details

    Language:Japanese  

    researchmap

  • 3-D Reconstruction of Staircase Using Stereo Images

    TANAKA Kenichi, OKUTOMI Masatoshi

    IPSJ SIG Notes. CVIM   2007 ( 31 )   63 - 70   2007.3

     More details

    Language:Japanese   Publisher:Information Processing Society of Japan (IPSJ)  

    We propose a method for 3-D reconstruction of a staircase using stereo images. In the images of a staircase, there are many similar patterns along edges and poor textures on the surface of each step. Therefore mis-correspondences will very likely occur when doing stereo matching. In the proposed method, we model a staircase using several parameters. These parameters are estimated by using extracted lines of the staircase and optimized to minimize the displacement between the projected model and extracted edges on each image. Consequently, it is not necessary to search the correspondence between images.

    CiNii Books

    researchmap

    Other Link: http://id.nii.ac.jp/1001/00052058/

  • Calibration of Boosted Cascade Classifier and Distribution-based Face Detection

    TAKATSUKA Hiromasa, TANAKA Masayuki, OKUTOMI Masatoshi

    IEICE technical report   106 ( 539 )   49 - 54   2007.2

     More details

    Language:Japanese   Publisher:The Institute of Electronics, Information and Communication Engineers  

    Face detection is a useful technique in computer vision. Many researches have been developed in the literature. These existing studys have focused on subwindows and could not integrate the information over image space and scale in their framework. We found the classifier value around the interesting points keep high on the true face and have proposed the distribution-based face detection framework in a previous report. In this report, we propose a distribution-based method using the boosted cascade classifier. The output of the boosted cascade classifier is independent between each stage. We propose the novel calibration method for the boosted cascade classifier. Finally, we evaluate the local face likelihood distribuiton over space and scale by distribution-based framework. Experimental results using 170 input scenes, which might or might not include faces, show that the proposed framework improves the detection rate by about 5%.

    CiNii Books

    researchmap

  • Simultaneous Estimation of 3D Position and Motion in Dynamic Scene Using Unsynchronized Stereo Image Sequence

    SEKI Akihito, OKUTOMI Masatoshi

    IPSJ SIG Notes. CVIM   2007 ( 1 )   177 - 184   2007.1

     More details

    Language:Japanese   Publisher:Information Processing Society of Japan (IPSJ)  

    In this paper, we propose a simultaneous estimation method of structure and motion in dynamic scenes. Usual methods for getting structure and motion using stereo cameras need two kinds of operations: stereo correspondence and tracking. Therefore, we had to separately get correspondence between stereo images and sequential images. Our first contribution is the method of corresponding all stereo images and sequential images at once. On the other hand, most of stereo correspondence algorithms are limited under synchronized status. In the stereo rig by using unsynchronized cameras, the structure can't be obtained by stereo correspondence and triangulation because of unknown time offset between cameras. Then, our second contribution is the method of estimating structure, motion, and time offset simultaneously by using unsynchronized stereo cameras. This is done by taking advantage of the first contribution scheme. Finally, we present some experimental results.

    CiNii Books

    researchmap

    Other Link: http://id.nii.ac.jp/1001/00052107/

  • Elimination of Fluctuations from Sequential Images with Non-Rigid Motion Model

    YOSHIMURA Shin, SHIMIZU Masao, TANAKA Masayuki, OKUTOMI Masatoshi

    IPSJ SIG Notes. CVIM   2007 ( 1 )   169 - 176   2007.1

     More details

    Language:Japanese   Publisher:Information Processing Society of Japan (IPSJ)  

    A stable and highly accurate image registration technique is required for sequential image processing. Affine and projective transforms are often used for motion models of the image registration, but some objects cannot be modeled with the motion models using such a limited number of parameters. In this paper we discuss a non-rigid registration that utilizes a B-Spline image transformation with a parameter-set of the control vertex positions. The parameter-set can be estimated using a gradient-based parameter optimization method. The optimization method is, however, sometimes unstable at texture-less regions with image noise. We have introduced a stabilization term that varies with the magnitude of image gradient to the cost function, which allows estimating a stable and accurate parameter-set even if the image has a weak texture. In the experiments, we have applied the stable non-rigid registration technique to eliminate two types of fluctuations in image sequences; an atmospheric fluctuation and afluctuation through a watter surface. A deformation-eliminated reference image is obtained by averaging image frames in the sequence, and then each frame is non-rigidly registered to the reference image. The experimental results demonstrate the stability and accuracy of the proposed non-rigid image registration technique.

    CiNii Books

    researchmap

    Other Link: http://id.nii.ac.jp/1001/00052106/

  • Image Correspondence Estimation from Subspace Constraint and Epipolar Constraint on a Pair of Image Sequences

    TAKAHASHI Hidekazu, SUGIMOTO Shigeki, OKUTOMI Masatoshi

    IPSJ SIG Notes. CVIM   2006 ( 115 )   163 - 170   2006.11

     More details

    Language:Japanese   Publisher:Information Processing Society of Japan (IPSJ)  

    In this paper, we propose a novel approach for image correspondence estimation using a pair of synchronized image sequences. In the proposed approach, after tracking the feature points in each image sequence over several frames, we utilize the consistent epipolar constraints on the image pairs for fitting each trajectory in one image sequence to the motion subspace derived from all trajectories in the other sequence. Then the stereo correspondence of each trajectory is obtained. Dissimilarly to the conventional stereo correspondence estimation based on matching using pixel values, the proposed approach enables us to obtain the image correspondences even though the trajectories are observed in only one image sequence. The validity of the proposed approache is shown by the experiments using synthetic and real images.

    CiNii Books

    researchmap

    Other Link: http://id.nii.ac.jp/1001/00052133/

  • A Direct and Efficient Method for Piecewise-Planar Surface Reconstruction from Stereo Images

    SUGIMOTO Shigeki, OKUTOMI Masatoshi

    IPSJ SIG Notes. CVIM   2006 ( 115 )   109 - 116   2006.11

     More details

    Language:Japanese   Publisher:Information Processing Society of Japan (IPSJ)  

    In this paper, we propose a direct method for 3D surface reconstruction from stereo images. In the proposed method, we reconstruct a 3D surface by estimating the depths of all vertices of piecewise triangular patches which composes a mesh generated on the reference image. We express the SSD (sum of squared differences) value between a single patch region in the reference and the corresponding region in the input as a function of three depths of the vertices of the patch. Then all depths are estimated by minimizing the accumulated SSD value with respect to all patches by Gauss-Newton optimization. For reducing the iterative computational costs for depth estimation, we incorporate an ICIA (inverse compositional image alignment) manner for expressing the SSD function. The validity of the proposed method is shown by some experiments using synthetic and real images.

    CiNii Books

    researchmap

    Other Link: http://id.nii.ac.jp/1001/00052127/

  • Raw data decodable JPEG data

    TANAKA Masayuki, OKUTOMI Masatoshi

    IPSJ SIG Notes. CVIM   2006 ( 115 )   125 - 132   2006.11

     More details

    Language:Japanese   Publisher:Information Processing Society of Japan (IPSJ)  

    A single color CCD with color filter array has been became very popular. An effective compression of the raw data captured by the single color CCD is highly demanded. This paper proposes a novel raw data compression. We show the concept of the JPEG data from which the raw data can be extracted. An preview functionality is realized by using this JPEG data. We can preview by the normal JPEG decorder. Experiments using standard image and real image demonstrate that the proposed method can effectively compress the raw data.

    CiNii Books

    researchmap

    Other Link: http://id.nii.ac.jp/1001/00052129/

  • Synthesizing High-Resolution Virtual-Focal-Plane Image from Multiple Images with Different View Points

    IKEDA Kaoru, SHIMIZU Masao, OKUTOMI Masatoshi

    IPSJ SIG Notes. CVIM   2006 ( 115 )   101 - 108   2006.11

     More details

    Language:Japanese   Publisher:Information Processing Society of Japan (IPSJ)  

    This paper presents a new method to synthesize a virtual high-resolution image from multiple images with different view points. First, a disparity map of the captured scene for the reference image is obtained using the multiple stereo matching. Next, a virtual focal plane in the disparity space is estimated corresponding to a user- established rectangle area in the reference image. Finally, all images are warped into the virtual focal plane by using estimated homography warp parameters for each image. The synthesized virtual-focal-plane image is an in-focus, high-resolution and less-noisy image for the virtual focal plane. The paper also demonstrates experimental results using both synthetic and real images.

    CiNii Books

    researchmap

    Other Link: http://id.nii.ac.jp/1001/00052126/

  • 車載ステレオカメラによる自車両の運動推定

    関晃仁, 奥富正敏

    画像ラボ,日本工業出版   17 ( 10 )   37 - 41   2006.10

     More details

    Language:Japanese  

    researchmap

  • Face Detection Algorithm using Face Likelihood Distribution

    TAKATSUKA Hiromasa, TANAKA Masayuki, OKUTOMI Masatoshi

    IPSJ SIG Notes. CVIM   2006 ( 93 )   73 - 80   2006.9

     More details

    Language:Japanese   Publisher:Information Processing Society of Japan (IPSJ)  

    Face detection is a useful technique in computer vision. Many face detectors have been developed in the literature. Almost all approaches for face detection focus on the face detectors which classify a given sub-window into face or non-face. However, in face detection process, since the detectors also evaluate the scanned sub-windows independently, non-faces with high face likelihood are often misdetected. In this paper, we propose a novel face detection algorithm which explicitly uses difference of face likelihood distribution between faces and non-faces. The proposed algorithm can correctly classify the non-faces misdetected by the existing algorithm. The face likelihood distribution is generated and integrated to emphasize the difference between faces and non-faces. Experiments with pre-scanned data set and real-world images show that the proposed algorithm improves the detection rate approximately by 20% and 10%, respectively.

    CiNii Books

    researchmap

    Other Link: http://id.nii.ac.jp/1001/00052146/

  • Face Detection Algorithm using Face Likelihood Distribution

    TAKATSUKA Hiromasa, TANAKA Masayuki, OKUTOMI Masatoshi

    IEICE technical report   106 ( 229 )   73 - 80   2006.9

     More details

    Language:Japanese   Publisher:The Institute of Electronics, Information and Communication Engineers  

    Face detection is a useful technique in computer vision. Many face detectors have been developed in the literature. Almost all approaches for face detection focus on the face detectors which classify a given sub-window into face or non-face. However, in face detection process, since the detectors also evaluate the scanned sub-windows independently, non-faces with high face likelihood are often misdetected. In this paper, we propose a novel face detection algorithm which explicitly uses difference of face likelihood distribution between faces and non-faces. The proposed algorithm can correctly classify the non-faces misdetected by the existing algorithm. The face likelihood distribution is generated and integrated to emphasize the difference between faces and non-faces. Experiments with pre-scanned data set and real-world images show that the proposed algorithm improves the detection rate approximately by 20% and 10%, respectively.

    CiNii Books

    researchmap

  • Human-Friendly Restoration Filter

    YONEJI Kenichi, TANAKA Masayuki, OKUTOMI Masatoshi

    IEICE technical report   105 ( 674 )   107 - 114   2006.3

     More details

    Language:Japanese   Publisher:The Institute of Electronics, Information and Communication Engineers  

    Images axe blurred by camera shakes or moving objects. When the PSF (Point Spread Function) which is a degradation function of blurring can be obtained from a degraded image, there are many techniques for image restoration using the relation between a degradation image and PSF. However, we must appropriately set some parameters, which affect the restoration image materially. In this paper, we propose a restoration technique which enables us to select the appropriate parameter easily. We call this restoration technique "human-friendly restoration". This papaer shows necessary conditions to make a human-friendly restoration. Moreover, one example of a human-friendly restoration filter is shown, and it's effect is demonstrated through experiments using synthetic images and real images.

    CiNii Books

    researchmap

  • Multi-mixture Imaging and Its Application to Super-resolution

    TANAKA Masayuki, OKUTOMI Masatoshi

    IPSJ SIG Notes. CVIM   2006 ( 25 )   271 - 278   2006.3

     More details

    Language:Japanese   Publisher:Information Processing Society of Japan (IPSJ)  

    Pixel mixture reduces a read-out time of an image, but it lowers the resolution. Although super-resolution is well-kown as a technique for improving the resolution, it can not improve a lot for the pixel mixture images because the pixel mixture images are low-passed to reduce aliasing. Therefore, we propose a novel imaging method that we call "multi-mixture". The proposed imaging method generates two types of image sequences. This paper demonstrates that super-resolution using the multi-mixture imaging can greatly improve the image resolution.

    CiNii Books

    researchmap

    Other Link: http://id.nii.ac.jp/1001/00052249/

  • Multi-mixture Imaging and Its Application to Super-resolution

    TANAKA Masayuki, OKUTOMI Masatoshi

    IEICE technical report   105 ( 674 )   99 - 106   2006.3

     More details

    Language:Japanese   Publisher:The Institute of Electronics, Information and Communication Engineers  

    Pixel mixture reduces a read-out time of an image, but it lowers the resolution. Although super-resolution is well-kown as a technique for improving the resolution, it can not improve a lot for the pixel mixture images because the pixel mixture images are low-passed to reduce aliasing. Therefore, we propose a novel imaging method that we call "multi-mixture". The proposed imaging method generates two types of image sequences. This paper demonstrates that super-resolution using the multi-mixture imaging can greatly improve the image resolution.

    CiNii Books

    researchmap

  • Human-Friendly Restoration Filter

    YONEJI Kenichi, TANAKA Masayuki, OKUTOMI Masatoshi

    IPSJ SIG Notes. CVIM   2006 ( 25 )   279 - 286   2006.3

     More details

    Language:Japanese   Publisher:Information Processing Society of Japan (IPSJ)  

    Images are blurred by camera shakes or moving objects. When the PSF (Point Spread Function) which is a degradation function of blurring can be obtained from a degraded image, there are many techniques for image restoration using the relation between a degradation image and PSF. However, we must appropriately set some parameters, which affect the restoration image materially. In this paper, we propose a restoration technique which enables us to select the appropriate parameter easily. We call this restoration technique "human-friendly restoration". This papaer shows necessary conditions to make a human-friendly restoration. Moreover, one example of a human-friendly restoration filter is shown, and it's effect is demonstrated through experiments using synthetic images and real images.

    CiNii Books

    researchmap

    Other Link: http://id.nii.ac.jp/1001/00052250/

  • Editor's Message to Special Section on Advanced Sensing Technologies for Computer Vision

    SUMI K., OKUTOMI M.

    47 ( 5 )   i - ii   2006.3

     More details

    Language:Japanese   Publisher:Information Processing Society of Japan (IPSJ)  

    CiNii Books

    researchmap

  • Direct Plane Parameter Estimation using Stereo Camera and Its Extension to Multi-view Application

    SUGIMOTO Shigeki, OKUTOMI Masatoshi

    IPSJ SIG Notes. CVIM   2005 ( 112 )   131 - 138   2005.11

     More details

    Language:Japanese   Publisher:Information Processing Society of Japan (IPSJ)  

    To estimate 3D plane parameters (the distance to a plane and its plane normal) is an important issue for realizing computer-aided control of vehicles or mobile robots which move around on a plane such as road and floor, because the plane parameters vary as the vehicle changes its pose relative to the plane. In this paper, we study about a Gauss-Newton-based fast estimation method for the plane parameters using calibrated stereo camera. Since the plane parameters are involved in homography warp parameters, we incorporate the inverse compositional algorithm (recently proposed by Baker et al. for fast homography warp parameter estimation), in order to reduce computational costs of Hessian matrix in each iteration procedure. We also re-formulate an estimation method suitable for multi-view applications which realize more robust estimation than binocular stereo. The validity of the presented methods is shown through comparative experiments.

    CiNii Books

    researchmap

    Other Link: http://id.nii.ac.jp/1001/00052314/

  • 高速カラー超解像処理システムの実現

    田中正行, 奥富正敏, 清水雅夫, 後藤知将

    画像ラボ, 日本工業出版   16 ( 11 )   41 - 44   2005.11

     More details

    Language:Japanese  

    researchmap

  • Neighbor Pixel Mixture Based on Condition Number

    TANAKA Masayuki, OKUTOMI Masatoshi

    Technical report of IEICE. PRMU   105 ( 302 )   113 - 118   2005.9

     More details

    Language:Japanese   Publisher:The Institute of Electronics, Information and Communication Engineers  

    Pixel mixture is a technique to reduce read-out time of an image by mixing multiple pixel values on an imager. Values of same color pixels are mixed by ordinary pixel mixture methods. However, the same color pixels are not neighboring on widely-used Bayer pattern. This degrades the resolution of the pixel mixture image. In this paper, we propose a neighbor pixel mixture method. The proposed method mixes neighboring pixels by using a linear combination. We also discuss a guideline for designing the coefficients of the linear combination.

    CiNii Books

    researchmap

  • Robust Obstacle Detection in General Road Environment Based on Road-Region Extraction and Pose Estimation Method

    SEKI Akihito, OKUTOMI Masatoshi

    2005 ( 89 )   13 - 18   2005.9

     More details

    Language:Japanese   Publisher:Information Processing Society of Japan (IPSJ)  

    In this paper, we propose the method for obstacle detection using vehicle-mounted stereo cameras. We have to measure the position from road plane for the purpose of deviding road patterns or obstacles in the image. But, the state of general road is worse than that of highway, a vehicle sometimes vibrates larger in the road. We first dynamically estimate road region and position. Subsequently, we measure 3D position of points within non-road region using stereo images. Next, segmentation method is applied about the possible space of vehicle's passing and we detect obstacles. Finally, we present the experimental results of obstacle detection with our method.

    CiNii Books

    researchmap

    Other Link: http://id.nii.ac.jp/1001/00045639/

  • Robust Obstacle Detection in General Road Environment Based on Road-Region Extraction and Pose Estimation Method

    SEKI Akihito, OKUTOMI Masatoshi

    105 ( 259 )   13 - 18   2005.9

     More details

    Language:Japanese   Publisher:The Institute of Electronics, Information and Communication Engineers  

    In this paper, we propose the method for obstacle detection using vehicle-mounted stereo cameras. We have to measure the position from road plane for the purpose of deviding road patterns or obstacles in the image. But, the state of general road is worse than that of highway, a vehicle sometimes vibrates larger in the road. We first dynamically estimate road region and position. Subsequently, we measure 3D position of points within non-road region using stereo images. Next, segmentation method is applied about the possible space of vehicle's passing and we detect obstacles. Finally, we present the experimental results of obstacle detection with our method.

    CiNii Books

    researchmap

  • Simultaneous Improvement of Image Quality and Depth Estimation using Stereo Images

    IKEDA Kaoru, SHIMIZU Masao, OKUTOMI Masatoshi

    IPSJ SIG Notes. CVIM   2005 ( 38 )   77 - 82   2005.5

     More details

    Language:Japanese   Publisher:Information Processing Society of Japan (IPSJ)  

    In this report, a method to simultaneously improve the depth estimation accuracy of stereo measurement and the image quality of the input stereo images is studied. Firstly, the correspondences between the stereo image pair are obtained. Secondly, each image is warped onto another image and averaged images are generated to reduce noise. Thirdly, an improved correspondences between the noise reduced image pair is obtained to improve the disparity. The iterative computation provides both higher quality images and accurate depth estimation. The method can be extended to the multi-camera stereo to obtain a higher resolution image. Experimental results using both synthetic and real images are shown to demonstrate the effectiveness of the method.

    CiNii Books

    researchmap

    Other Link: http://id.nii.ac.jp/1001/00052350/

  • PSF Parameter Estimation for Restoration of Linear Motion Blurred Image

    YONEJI Kenichi, TANAKA Masayuki, OKUTOMI Masatoshi

    IPSJ SIG Notes. CVIM   2005 ( 38 )   47 - 52   2005.5

     More details

    Language:Japanese   Publisher:Information Processing Society of Japan (IPSJ)  

    An image is degraded by hand blurring or moving object. That degradation can be expressed by PSF (Point Spread Function). The PSF has two parameters of width and the angle, approximating the motion is uniform. An amplitude spectrum of blurred image has a feature based on PSF parameters. PSF parameters can estimate from this feature. This paper presents a new method to estimate PSF parameters from the amplitude spectrum of blurred image. The effect of the proposed method is confirmed by experiments.

    CiNii Books

    researchmap

    Other Link: http://id.nii.ac.jp/1001/00052346/

  • Theoretical Analysis about Limitations on Reconstruction-Based Super-Resolution

    TANAKA Masayuki, OKUTOMI Masatoshi

    IPSJ SIG Notes. CVIM   2005 ( 4 )   147 - 154   2005.1

     More details

    Language:Japanese   Publisher:Information Processing Society of Japan (IPSJ)  

    This study presents and proves a condition number theorem for super-resolution (SR). The SR condition number theorem provides the condition number for an arbitrary space-invariant point spread function (PSF) when using an infinite number of low resolution images. A gradient restriction is also derived for maximum likelihood (ML) method. The gradient restriction is presented as an inequality which shows that the power spectrum of the PSF suppresses the spatial frequency component of the gradient of ML cost function. A Box PSF and a Gaussian PSF are analyzed with the SR condition number theorem. Effects of the gradient restriction on super-resolution results are shown using synthetic images.

    CiNii Books

    researchmap

    Other Link: http://id.nii.ac.jp/1001/00052427/

  • An Efficient Algorithm for Multi-Parameter Simultaneous Estimation on Image Registration

    CHANG SoonKeun, SHIMIZU Masao, OKUTOMI Masatoshi

    IPSJ SIG Notes. CVIM   2005 ( 4 )   51 - 58   2005.1

     More details

    Language:Japanese   Publisher:Information Processing Society of Japan (IPSJ)  

    This paper proposes a fast algorithm of simultaneous motion parameter estimation method, intended for sequential image motion estimation. The simultaneous motion parameter estimation method can estimate a set of highly precise motion parameters among images using area-based image matching. This method offers advantages of non-iterative computation and a nonrestricted shape of the region of interest. The fast algorithm proposed in this paper is about 8.5 times faster than the previous simultaneous method. This paper also compares the computational cost and the accuracy of the estimated parameters of the proposed fast algorithm with the gradient descent method (the so-called Lucas-Kanade method), which is widely used to estimate motion parameters. The computational cost of the proposed fast algorithm is slightly lower than a fast version of the gradient descent method, and their accuracies are almost equal. Experiments using a synthesized motion sequence and a real image sequence are performed to confirm the comparisons.

    CiNii Books

    researchmap

    Other Link: http://id.nii.ac.jp/1001/00052415/

  • 古くて新しい画像間の高精度マッチング技術 -第2回 高精度サブピクセル2次元変位の推定-

    清水雅夫, 奥富正敏

    画像ラボ,日本工業出版   16 ( 1 )   67 - 71   2005.1

     More details

    Language:Japanese  

    researchmap

  • Precise Simultaneous Estimation of Image Deformation N - Parameter with Its Application on Super - Resolution

    45 ( 13 )   93 - 98   2004.12

     More details

    Language:Japanese  

    CiNii Books

    researchmap

  • 古くて新しい画像間の高精度マッチング技術 -第1回 サブピクセル推定誤差キャンセル手法-

    清水雅夫, 奥富正敏

    画像ラボ,日本工業出版   15 ( 12 )   67 - 71   2004.12

     More details

    Language:Japanese  

    researchmap

  • Fast Algorithm for Reconstruction -based Super- resolution

    TANAKA Masayuki, OKUTOMI Masatoshi

    IPSJ SIG Notes. CVIM   2004 ( 113 )   97 - 104   2004.11

     More details

    Language:Japanese   Publisher:Information Processing Society of Japan (IPSJ)  

    A super-resolution process produces a high-resolution image from a set of low-resolution images. Reconstruction-based algorithms to produce the high-resolution image which minimizes the difference between observed images and images estimated from the high-resolution image with a camera model has been developed. The reconstruction-based algorithm requires iterative calculation and large calculation cost because the reconstruction-based super-resolution is a large scale problem. In this report, a fast algorithm for the reconstruction-based super-resolution is newly proposed. The proposed method is to reduce the number of observed pixel value estimations from the high-resolution image, using an average of pixel values in a divide region. Effect of our proposed algorithm is demonstrated with synthetic images and actual images. The results show that the proposed method is about 1.3 - 5.0 times faster than a conventional method.

    CiNii Books

    researchmap

    Other Link: http://id.nii.ac.jp/1001/00052443/

  • Ego - Motion Estimation by Matching Road Patterns Extracted Using Stereo Images

    SEKI Akihito, OKUTOMI Masatoshi

    IPSJ SIG Notes. CVIM   2004 ( 113 )   89 - 96   2004.11

     More details

    Language:Japanese   Publisher:Information Processing Society of Japan (IPSJ)  

    In this paper , we propose the method for ego-motion estimation using the stereo cameras mounted on a vehicle. Estimating ego-motion using the cameras requires to extract the static regions in the images. We first estimate planar regions which might be static area using stereo images. And so then, to match the time series of the road patterns in the extracted regions is equivalent to estimating ego-motion. We use car-movement-model and consider the matching method , so we easily and accurately get the motion. Finally, we present the experimental results of ego-motion estimation with our method.

    CiNii Books

    researchmap

    Other Link: http://id.nii.ac.jp/1001/00052442/

  • D-12-143 Omnidirectinal 3-D Reconstruction Using Rotating Camera with Separated Field of View

    Wei Jiang, Sugimoto Shigeki, Okutomi Masatoshi

    Proceedings of the IEICE General Conference   2004 ( 2 )   309 - 309   2004.3

     More details

    Language:Japanese   Publisher:The Institute of Electronics, Information and Communication Engineers  

    CiNii Books

    researchmap

  • Precise Simultaneous Estimation of Deformation N - Parameters Extended from Two - Dimentional Simultaneous Estimation

    SHIMIZU Masao, YANO Takahiro, OKUTOMI Masatoshi

    IPSJ SIG Technical Report 2004-CVIM-143   2004 ( 26 )   81 - 88   2004.3

     More details

    Language:Japanese   Publisher:Information Processing Society of Japan (IPSJ)  

    This paper presents a new method to obtain simultaneously precise N parameters of image deformation with non-iterative calculation by extending area-based matching and sub-pixel estimation. Although area-based matching and similarity interpolation for sub-pixel displacement estimation are commonly used in many areas as a fundamental procedure, they are bound to simple translation. The proposed method is based on a practical similarity model in N-dimensional parameter space. Using similarity measures obtained at discrete positions in the parameter space, our method provides a highly accurate maximum position of similarity in sub-sampling resolution ; that position corresponds to image deformation parameters. Experimental results using both synthetic and real images demonstrate that our method can estimate parameters more accurately than previous methods.

    CiNii Books

    researchmap

    Other Link: http://id.nii.ac.jp/1001/00052519/

  • Extraction of Planar Region and Obstacle Detection Using Stereo Images

    SEKI Akihito, OKUTOMI Masatoshi

    IPSJ SIG Notes. CVIM   2004 ( 26 )   17 - 24   2004.3

     More details

    Language:Japanese   Publisher:Information Processing Society of Japan (IPSJ)  

    In this paper, we propose the method for an obstacle detection on the road plane using the stereo cameras mounted on a vehicle. We first estimate planar regions using projective transformation matrix. By singular value decomposition of the matrix, we get the normal vector of the planar regions and the distance from the optical center of the primary camera to the plane. Then, we make a virtual projection plane (VPP) image which is equivalent to the top view of the road scene. Obstacles are detected by checking the change of the planar regions using the VPP image. Finally, we present the experimental results of obstacle detection with our method.

    CiNii Books

    researchmap

    Other Link: http://id.nii.ac.jp/1001/00052511/

  • Two-Dimensional Simultaneous Sub-Pixel Estimation for Area-Based Matching

    SHIMIZU Masao, OKUTOMI Masatoshi

    The Transactions of the Institute of Electronics,Information and Communication Engineers.   87 ( 2 )   554 - 564   2004.2

     More details

    Language:Japanese   Publisher:The Institute of Electronics, Information and Communication Engineers  

    CiNii Books

    researchmap

  • Omnidirectinal 3-D Reconstruction Using Stereo Multi-Perspective Panoramas

    JIANG Wei, OKUTOMI Masatoshi, SUGIMOTO Shigeki

    Technical report of IEICE. PRMU   103 ( 585 )   77 - 82   2004.1

     More details

    Language:Japanese   Publisher:The Institute of Electronics, Information and Communication Engineers  

    In this paper, we present a new approach for omnidirectinal 3-D reconstruction using multi-perspective panoramas. We use two large collections of images taken by parallel stereo cameras whose motions are constrained to a planar concentric circle. The two collections of regular perspective images are resampled into four multi-perspective panoramas. Then we compute a depth map from three pairs of the panoramas using multi-baseline algorithm with three types of epipolar constraints,that of horizontal,vertical and combination of them.Experimental results show that the proposed method produces omnidirectional depth maps and 3D reconstruction.

    CiNii Books

    researchmap

  • Application of 2D Simultaneous Sub - Pixel Estimation for Multi - Image Super - Resolution from Bayer CFA Data

    SHIMIZU Masao, GOTOH Tomomasa, YANO Takahiro, OKUTOMI Masatoshi

    IPSJ SIG Notes. CVIM   2003 ( 88 )   79 - 86   2003.9

     More details

    Language:Japanese   Publisher:Information Processing Society of Japan (IPSJ)  

    Area-based matching is a fundamental image processing to obtain displacement between images. Also, the similarity interpolation method to estimate sub-pixel displacement is commonly used to enhance resolution. This paper explains a novel two-dimensional simultaneous sub-pixel estimation method based on similarity interpolation. The method requires no "a priori" knowledge over 2D similarity, or images at all. It adopts no iteration. On the other hand, it is necessary to estimate the highly precise sub-pixel displacement between low-resolution Bayer CFA images for direct multi-image super-resolution applications. The application directly re-constructs a high-resolution full color RGB image from a set of low-resolution Bayer CFA images. In this paper, we have investigated the usage of Bayer CFA image data for the highly precise and effective image matching and sub-pixel estimation. Based on the result, an experiment on the super-resolution processing was performed utilizing real image sequences for verification of the two-dimensional simultaneous estimation method.

    CiNii Books

    researchmap

    Other Link: http://id.nii.ac.jp/1001/00052570/

  • Highly Precise Two-Dimensional Sub-Pixel Estimation Method on Area-Based Image Matching based on Similarity Model

    SHIMIZU Masao, OKUTOMI Masatoshi

    Technical report of IEICE. PRMU   103 ( 151 )   31 - 38   2003.6

     More details

    Language:Japanese   Publisher:The Institute of Electronics, Information and Communication Engineers  

    Area-based matching is a fundamental image processing to obtain displacement between images. Also, the similarity interpolation method to estimate sub-pixel displacement is commonly used to enhance resolution. Conventionally, similarity interpolation estimation is performed by assuming that horizontal and vertical displacements are independent. Almost no investigations on estimation error over the conventional method have been done, but it is inferred experientially that sub-pixel estimation with image interpolation or gradient-based methods is more precise than the similarity interpolation method. This paper proposes a novel 2D sub-pixel displacement estimation method based on similarity interpolation through modeling 2D self-similarity. The proposed method requires no "a priori" knowledge over 2D similarity, or images at all. It adopts no iteration. Furthermore, the proposed method requires only slightly higher calculation costs than the conventional similarity interpolation method. The proposed method can obtain more precise estimation not only than the conventional similarity interpolation method, but also than the image interpolation method through comparison of sub-pixel estimation accuracy. Moreover, an experiment using actual images demonstrates effectiveness of the proposed method.

    CiNii Books

    researchmap

  • High Resolution Color Image Reconstruction from a Single CCD

    GOTOH Tomomasa, OKUTOMI Masatoshi

    IPSJ SIG Notes. CVIM   2003 ( 41 )   223 - 230   2003.5

     More details

    Language:Japanese   Publisher:Information Processing Society of Japan (IPSJ)  

    Limitation in the physical resolution of CCD image sensors has provided motivation to enhance the resolution of images. Super-resolution has been applied mainly to grayscale images, and producing a high resolution color image from a single CCD sensor has not been discussed thoroughly. This work aims at producing a high resolution color image directly from "color mosaic" images obtained by a single-CCD with a color filter array. This method is based on a generalized formulation of super-resolution which performs both resolution enhancement and demosaicking simultaneously. Verification of the proposed method is conducted through experiments using synthetic and real images.

    CiNii Books

    researchmap

    Other Link: http://id.nii.ac.jp/1001/00052632/

  • Significance and Attributes of Sub-Pixel Estimation on Area-Based Matching

    SHIMIZU Masao, OKUTOMI Masatoshi

    The Transactions of the Institute of Electronics,Information and Communication Engineers.   85 ( 12 )   1791 - 1800   2002.12

     More details

    Language:Japanese   Publisher:The Institute of Electronics, Information and Communication Engineers  

    CiNii Books

    researchmap

  • Robust estimation of planar regions for visual navi-gation using sequential stereo images

    OKUTOMI M.

    ICRA   4   3321 - 3327   2002

     More details

  • An Application of New Precise Sub-Pixel Estimation Method to PIV Images

    SHIMIZU Masao, OKUTOMI Masatoshi

    Journal of the Visualization Society of Japan   21   35 - 38   2001.7

     More details

    Language:Japanese  

    CiNii Books

    researchmap

  • Precise Sub-Pixel Estimation on Area-Based Matching

    SHIMIZU Masao, OKUTOMI Masatoshi

    The Transactions of the Institute of Electronics,Information and Communication Engineers.   84 ( 7 )   1409 - 1418   2001.7

     More details

    Language:Japanese   Publisher:The Institute of Electronics, Information and Communication Engineers  

    CiNii Books

    researchmap

  • Precise Sub-Pixel Estimation on Area-Based Matching

    SHIMIZU Masao, OKUTOMI Masatoshi

    Technical report of IEICE. PRMU   100 ( 634 )   1 - 8   2001.2

     More details

    Language:Japanese   Publisher:The Institute of Electronics, Information and Communication Engineers  

    Area-based matching is a common procedure in various fields like image-based measurements, stereo image processing, and fluidics. Sub-pixel estimation using parabola fitting over three points with their similarity measures is also a common method to increase the resolution of matching. However, few investigations or studies concerning the characteristics of this estimation are reported. In this paper, we have analyzed the sub-pixel estimation error by using an approximate image function and three kinds of similarity measures for matching. The result illustrates some inherent phenomena like so called "pixel-locking". Additionally, we propose a new algorithm to greatly reduce the sub-pixel estimation error. This method is independent from the similarity measure and quite simple to implement. The advantage of our novel method is confirmed through experiments using two different types of images.

    CiNii Books

    researchmap

  • Continuous Estimation of Planar Region for Visual Navigation Using Sequential Stereo Images

    OKUTOMI Masatoshi, MARUYAMA Junichi, NAKANO Katsuyuki

    IPSJ SIG Notes. CVIM   2000 ( 82 )   17 - 24   2000.9

     More details

    Language:Japanese   Publisher:Information Processing Society of Japan (IPSJ)  

    In this paper, we propose a robust method to estimate planar regions using sequential stereo images for visual navigation of an autonomous vehicle. The proposed method estimates projective transformations, which represent the plane in space, for both stereo images and sequential images. This can be done robustly by utilizing sequential information, i. e. previous estimation of both the transformations and the planar region. The experimental results, using sequential stereo images taken from a moving vehicle, show that the proposed method can work even in the conditions of undulation of the road and rolling and pitching of the vehicle.

    CiNii Books

    researchmap

    Other Link: http://id.nii.ac.jp/1001/00052894/

  • A Study of Boundary Overreach on Area - Based Stereo Matching

    OKA Setsuko, KATAYAMA Yasuhiro, OKUTOMI Masatoshi

    IPSJ SIG Notes. CVIM   2000 ( 82 )   9 - 15   2000.9

     More details

    Language:Japanese   Publisher:Information Processing Society of Japan (IPSJ)  

    In area-based stereo matching, it is known that there is a problem called "boundary ovenreach". That is, the estimated positions of the object boundaries tend to be rnislocated and, in general, an object in front of a background tends to become larger than its actual size. However, no theoretical analysis, such that why it happens and how much the amount of the boundary overreach is expected, has been shown so far. In this paper, we make them clear by theoretically and experimentally.

    CiNii Books

    researchmap

    Other Link: http://id.nii.ac.jp/1001/00052893/

  • About Windows for Stereo Matching.

    KATAYAMA Yasuhiro, KAWAGUCHI Yoshihiro, OKUTOMI Masatoshi

    58   3 - 4   1999.3

     More details

    Language:Japanese  

    CiNii Books

    researchmap

  • Calibration of a Pan/Tilt/Zoom Camera by a Simple Camera Model

    NUMAO Toshio, NAKATANI Yuu, OKUTOMI Masatoshi

    Technical report of IEICE. PRMU   97 ( 596 )   65 - 72   1998.3

     More details

    Language:Japanese   Publisher:The Institute of Electronics, Information and Communication Engineers  

    A simple model for calibration of pan/tilt/zoom camera which consists of two rotation stages, an electrically-controlled zoom lens, and a CCD camera is proposed. The simple model is the one assuming that neither the optical axis nor the image center change by the zoom change and neither the position of image plane of the camera in the world coordinates systems nor the rotation axes of pan/tilt are changed by the zoom change. We show that it is shown to be able to achieve calibration without depending on the zoom setting according to this model and the number of parameters which should be estimated in calibration decreases according to that. Moreover, we show that images of arbitrary viewing angle and an arbitrary magnification can be easily integrated because of a geometrical relation by calibrated parameters.

    CiNii Books

    researchmap

  • ステレオ視 (Stereo Vision)

    奥富正敏

    コンピュータビジョン : 技術評論と将来展望   1998

     More details

    Publisher:新技術コミュニケーションズ  

    researchmap

  • ズームレンズのキャリブレーション

    沼尾利夫, 奥富正敏

    画像ラボ   9 ( 12 )   6 - 12   1998

     More details

    Language:Japanese  

    researchmap

  • Computation of Homography Matrix for Road Plane Using Stereo Images

    NOGUCHI Suguru, OKUTOMI Masatoshi

    IPSJ SIG Notes. CVIM   1997 ( 114 )   23 - 30   1997.11

     More details

    Language:Japanese   Publisher:Information Processing Society of Japan (IPSJ)  

    Extracting the road region in an image is an important technique for visual navigation of an autonomous vehicle. We propose a road extraction method using stereo images. We suppose that a road can be approximated by a plane. Then we can compute the homography matrix for the road plane using stereo images. In the proposed method, we don't have to know the geometric relation between two images and a road plane. In this paper, we describe mainly the method to compute the homography matrix of the road plane automatically. Also, some experimental results are presented to show the effectiveness of the method for real scenes.

    CiNii Books

    researchmap

  • Calibration Accuracy and its Target Points Arrangement for an Active Camera System with Zoom Lens

    NUMAO Toshio, OKUTOMI Masatoshi

    Technical report of IEICE. PRMU   97 ( 112 )   71 - 78   1997.6

     More details

    Language:Japanese   Publisher:The Institute of Electronics, Information and Communication Engineers  

    To achieve the input of an accurate magnification image, calibration of the focal length is needed in an active camera system which can control the viewing angle (pan and tilt), zoom, focus, and iris. It is shown that, by the calibration with a zoom lens camera model we propose, good estimation can be made even when the number of the measurement points on a single plane is small and the error of image coordinates is large. In addition, we demonstrate that we can integrate the multi-magnification images at the image center easily by using the calibration results of our camera system.

    CiNii Books

    researchmap

  • Road Region Extraction using Stereo Images

    Noguchi Suguru, Okutomi Masatoshi

    Proceedings of the Society Conference of IEICE   276 - 276   1997

     More details

    Language:Japanese   Publisher:The Institute of Electronics, Information and Communication Engineers  

    CiNii Books

    researchmap

  • Dense Shape Recovery of Rotating Object by Weighted Voting

    Ueda Hiroyuki, Okutomi Masatoshi

    Proceedings of the IEICE General Conference   370 - 370   1996

     More details

    Language:Japanese   Publisher:The Institute of Electronics, Information and Communication Engineers  

    CiNii Books

    researchmap

  • Position Estimation from Images with Continuous Mapping by Neural Network

    Sugimoto Shigeki, Numao Thoshio, Okutomi Masatoshi

    IEICE technical report. Pattern recognition and understanding   95 ( 365 )   1 - 4   1995.11

     More details

    Language:Japanese   Publisher:The Institute of Electronics, Information and Communication Engineers  

    We are aiming for real-time estimation of an object position in real images using continuous mapping of a three-layered neural network with back-propagation algorithm. This method could be available for any object with arbitrary texture unless the same pattern exists in images for each position. We clarify the problems for obtaining practical position estimation in terms of both training and interpolated data under a limited number of the units through the experiments using 2-dimensional movement of a flat object, and show the accuracy could be improved using a low-pass filter and the principal component analysis.

    CiNii Books

    researchmap

  • A Multiple-Baseline Stereo

    Masatoshi Okutomi, Takeo Kanade

    IEEE Transactions on Pattern Analysis and Machine Intelligence   Vol. 15 ( No. 4 )   353 - 363   1993

     More details

    Language:English  

    DOI: 10.1109/34.206955

    Scopus

    researchmap

  • マルチベースラインステレオ法による3次元計測

    金出武雄, 中原智治, 奥富正敏

    画像ラボ   4 ( 9 )   53 - 57   1993

     More details

    Language:Japanese  

    researchmap

  • A STEREO MATCHING ALGORITHM WITH AN ADAPTIVE WINDOW - THEORY AND EXPERIMENT

    T KANADE, M OKUTOMI

    1991 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1-3   CMU-CS-90-120 ( No. )   1088 - 1095   1991

     More details

    Language:English  

    Web of Science

    researchmap

  • A Multiple-Baseline Stereo

    Masatoshi Okutomi, Takeo Kanade

    CMU-CS-90-189 ( No. )   pp.   1990.11

     More details

    Language:English   Publisher:CMU Technical Report  

    researchmap

  • A Locally Adaptive Window for Signal Matching

    Masatoshi Okutomi, Takeo Kanade

    THIRD INTERNATIONAL CONFERENCE ON COMPUTER VISION   CMU-CS-90-178 ( No. )   190 - 199   1990.10

     More details

    Language:English  

    Web of Science

    researchmap

  • A Stereo Matching Algorithm with an Adaptive Window: Theory and Experiment

    Takeo Kanade, Masatoshi Okutomi

    CMU Technical Report   CMU-CS-90-120 ( No. )   pp.   1990.4

     More details

    Language:English   Publisher:CMU Technical Report  

    researchmap

  • A Multiple-Baseline Stereo

    Masatoshi Okutomi, Takeo Kanade

    CMU Technical Report   CMU-CS-90-189 ( No. )   pp.   1990

     More details

  • Decision of Robot Movement by means of a Potential Field

    Masatoshi Okutomi, Masahiro Mori

    Advanced Robotics   Vol. 1 ( No. 2 )   131 - 141   1986

     More details

  • Decision of Robot Movement By Means of a Potential Field

    Masatoshi Okutomi, Masahiro Mori

    Advanced Robotics   1 ( 2 )   131 - 141   1986

     More details

▼display all

Presentations

  • 多様な劣化水準に対応可能な劣化画像のクラス分類ネットワーク

    遠藤和紀, 田中正行, 奥富正敏

    第27回画像センシングシンポジウム(SSII2021)  2021.6 

     More details

    Event date: 2021.6

    Language:Japanese  

    researchmap

  • 多露光カラーフィルタアレイを用いた深層学習によるスナップショットHDR画像生成

    岡本悠太郎, 須田武流, 田中正行, 紋野雄介, 奥富正敏

    第27回画像センシングシンポジウム(SSII2021)  2021.6 

     More details

    Event date: 2021.6

    Language:Japanese  

    researchmap

  • Polarimetric MVIR: カラー偏光画像を用いたマルチビューインバースレンダリングによる高精細3次元復元

    趙 金雨, 紋野雄介, 奥富正敏

    第27回画像センシングシンポジウム(SSII2021)  2021.6 

     More details

    Event date: 2021.6

    Language:Japanese  

    researchmap

  • ロバストで高精度な3次元再構成に向けて Invited

    奥富正敏

    動体計測研究会  2021.5 

     More details

    Event date: 2021.5

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    researchmap

  • Spectral MVIR: Joint Reconstruction of 3D Shape and Spectral Reflectance

    Chunyu Li, Yusuke Monno, Masatoshi Okutomi

    Proceedings of IEEE International Conference on Computational Photography (ICCP2021)  2021.5 

     More details

    Event date: 2021.5

    Language:English  

    researchmap

  • VIO-Aided Structure from Motion Under Challenging Environments

    Zijie Jiang, Hajime Taira, Naoyuki Miyashita, Masatoshi Okutomi

    Proceedings of the 22nd IEEE International Conference on Industrial Technology (ICIT2021)  2021.3 

     More details

    Event date: 2021.3

    Language:English  

    researchmap

  • Self-supervised monocular depth estimation in gastroendoscopy using GAN-augmented images

    Aji Resindra Widya, Yusuke Monno, Masatoshi Okutomi, Sho Suzuki, Takuji Gotoda, Kenji Miki

    SPIE Medical Imaging, Proceedings of SPIE  2021.2 

     More details

    Event date: 2021.2

    Language:English  

    researchmap

  • Adaptive Future Frame Prediction with Ensemble Network

    Wonjik Kim, Masayuki Tanaka, Masatoshi Okutomi, Yoko Sasaki

    Proceedings of ICPR2020 Workshop : International Workshop on Pattern Forecasting (PATCAST)  2021.1 

     More details

    Event date: 2021.1

    Language:English  

    researchmap

  • Deep Snapshot HDR Imaging Using Multi-Exposure Color Filter Array

    Takeru Suda, Masayuki Tanaka, Yusuke Monno, Masatoshi Okutomi

    Proceedings of the 15th Asian Conference on Computer Vision (ACCV2020)  2020.11 

     More details

    Event date: 2020.11

    Language:English  

    researchmap

  • 3D Model Reconstruction of Whole Stomach from Standard Endoscope Video

    Sho Suzuki, Kenji Miki, Takuji Gotoda, Aji Resindra Widya, Yusuke Monno, Masatoshi Okutomi

    Proceedings of the International Digestive Disease Forum (IDDF2020)  2020.11 

     More details

    Event date: 2020.11

    Language:English  

    researchmap

  • Spectral Reflectance Estimation Using Projector with Unknown Spectral Power Distribution

    Hironori Hidaka, Yusuke Monno, Masatoshi Okutomi

    Proceedings of the Twenty-eighth Color and Imaging Conference (CIC28)  2020.11 

     More details

    Event date: 2020.11

    Language:English  

    researchmap

  • Monochrome and Color Polarization Demosaicking Using Edge-Aware Residual Interpolation

    Miki Morimatsu, Yusuke Monno, Masayuki Tanaka, Masatoshi Okutomi

    Proceedings of IEEE International Conference on Image Processing(ICIP2020)  2020.10 

     More details

    Event date: 2020.10

    Language:English  

    researchmap

  • Classifying Degraded Images Over Various Levels of Degradation

    Kazuki Endo, Masayuki Tanaka, Masatoshi Okutomi

    Proceedings of IEEE International Conference on Image Processing(ICIP2020)  2020.10 

     More details

    Event date: 2020.10

    Language:English  

    researchmap

  • Pro-Cam SSfM: Projector-Camera System for Structure and Spectral Reflectance from Motion Invited

    Chunyu Li, Yusuke Monno, Hironori Hidaka, Masatoshi Okutomi

    2020.8 

     More details

    Event date: 2020.8

    Language:English  

    researchmap

  • Polarimetric Multi-view Inverse Rendering

    Jinyu Zhao, Yusuke Monno, Masatoshi Okutomi

    Proceedings of 16th European Conference on Computer Vision (ECCV2020)  2020.8 

     More details

    Event date: 2020.8

    Language:English  

    researchmap

  • Stomach 3D Reconstruction Based on Virtual Chromoendoscopic Image Generation

    Aji Resindra Widya, Yusuke Monno, Masatoshi Okutomi, Sho Suzuki, Takuji Gotoda, Kenji Miki

    Proceedings of the 42nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC2020)  2020.7 

     More details

    Event date: 2020.7

    Language:English  

    researchmap

  • Remote Heart Rate Estimation Based on 3D Facial Landmarks

    Yuichiro Maki, Yusuke Monno, Masayuki Tanaka, Masatoshi Okutomi

    Proceedings of the 42nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC2020)  2020.7 

     More details

    Event date: 2020.7

    Language:English  

    researchmap

  • 内視鏡動画像からの胃の3次元形状復元

    紋野雄介, Widya Aji Resindra, 奥富正敏, 鈴木翔, 後藤田卓志, 三木健司

    第26回画像センシングシンポジウム(SSII2020)  2020.6 

     More details

    Event date: 2020.6

    Language:Japanese  

    researchmap

  • 畳み込みニューラルネットワークを用いた劣化画像のクラス分類

    遠藤和紀, 田中正行, 奥富正敏

    第26回画像センシングシンポジウム(SSII2020)  2020.6 

     More details

    Event date: 2020.6

    Language:Japanese  

    researchmap

  • 3D Pipe Network Reconstruction Based on Structure from Motion with Incremental Conic Shape Detection and Cylindrical Constraint

    Sho Kagami, Hajime Taira, Naoyuki Miyashita, Akihiko Torii, Masatoshi Okutomi

    Proceedings of 29th IEEE International Symposium on Industrial Electronics(ISIE2020)  2020.6 

     More details

    Event date: 2020.6

    Language:English  

    researchmap

  • ステレオカメラのセルフキャリブレーションに対する解析と2フレーム手法の提案

    大石慎太郎, 奥富正敏

    第26回画像センシングシンポジウム(SSII2020)  2020.6 

     More details

    Event date: 2020.6

    Language:Japanese  

    researchmap

  • Pro-Cam SSfM:汎用プロジェクタとカメラを用いた分光3D計測

    李淳雨, 紋野雄介, 日高宏紀, 奥富正敏

    第26回画像センシングシンポジウム(SSII2020)  2020.6 

     More details

    Event date: 2020.6

    Language:Japanese  

    researchmap

  • 内視鏡画像を基にした胃の3次元モデル表示法の開発

    鈴木翔, 三木健司, 後藤田卓志, Widya Aji Resindra, 紋野雄介, 奥富 正敏

    第16回日本消化管学会総会学術集会 ワークショップ11  2020.2 

     More details

    Event date: 2020.2

    Language:Japanese  

    researchmap

  • CNN-based Classification of Degraded Images

    Kazuki Endo, Masayuki Tanaka, Masatoshi Okutomi

    Proceedings of IS&T International Symposium on Electronic Imaging (EI2020)  2020.1 

     More details

    Event date: 2020.1

    Language:English  

    researchmap

  • 内視鏡画像を基にした胃の3次元モデル表示法の開発

    鈴木翔, 三木健司, 後藤田卓志, Widya Aji Resindra, 紋野雄介, 今堀公介, 奥富 正敏

    第27回日本消化器関連学会週間  2019.11 

     More details

    Event date: 2019.11

    Language:Japanese  

    researchmap

  • Pro-Cam SSfM: Projector-Camera System for Structure and Spectral Reflectance From Motion

    Chunyu Li, Yusuke Monno, Hironori Hidaka, Masatoshi Okutomi

    2019 IEEE/CVF International Conference on Computer Vision (ICCV)  2019.10  IEEE

     More details

    Event date: 2019.10

    Language:English  

    researchmap

  • Extraction of Degradation Parameters for Transparency of an Image Restoration Network

    Kazutaka Uchida, Masayuki Tanaka, Masatoshi Okutomi

    2019 IEEE 8th Global Conference on Consumer Electronics (GCCE)  2019.10  IEEE

     More details

    Event date: 2019.10

    Language:English  

    researchmap

  • Inter-Beat Interval Estimation from Facial Video Based on Reliability of BVP Signals

    Yuichiro Maki, Yusuke Monno, Kazunori Yoshizaki, Masayuki Tanaka, Masatoshi Okutomi

    2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)  2019.7  IEEE

     More details

    Event date: 2019.7

    Language:English  

    researchmap

  • 3D Reconstruction of Whole Stomach from Endoscope Video Using Structure-from-Motion

    Aji Resindra Widya, Yusuke Monno, Kosuke Imahori, Masatoshi Okutomi, Sho Suzuki, Takuji Gotoda, Kenji Miki

    2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)  2019.7  IEEE

     More details

    Event date: 2019.7

    Language:English  

    researchmap

  • Visible and Thermal Camera System for 360-degree Dynamic Panorama

    Thapanapong Rukkanchanunt, Takashi Shibata, Masayuki Tanaka, Masatoshi Okutomi

    Abstract Book of The 3rd Quantitative InfraRed Thermography Conference Asia (QIRT-Asia2019)  2019.7 

     More details

    Event date: 2019.7

    Language:English  

    researchmap

  • DNNにより最適化されたピクセルコーディングCMOSイメージセンサによるハイスピード撮像

    吉田道隆, 鳥居秋彦, 奥富正敏, 遠藤健太, 杉山行信, 谷口倫一郎, 長原一

    第22回画像の認識・理解シンポジウム(MIRU2019)  2019.7 

     More details

    Event date: 2019.7

    Language:Japanese  

    researchmap

  • 参照画像を用いたラインスキャン方式ハイパースペクトルカメラ画像の動き歪み補正

    大塚晃太郎, 田中正行, 奥富正敏

    第25回画像センシングシンポジウム(SSII2019)  2019.6 

     More details

    Event date: 2019.6

    Language:Japanese  

    researchmap

  • 大規模屋内環境における3Dマップを用いた自己位置推定

    田平創, Torsten Sattler, Josef Sivic, Tomas Pajdla, 鳥居秋彦, 奥富正敏

    第25回画像センシングシンポジウム(SSII2019)  2019.6 

     More details

    Event date: 2019.6

    Language:Japanese  

    researchmap

  • 時系列情報を用いたステレオカメラのセルフキャリブーション

    篠﨑教志, 永原聡, 奥富正敏

    第25回画像センシングシンポジウム(SSII2019)  2019.6 

     More details

    Event date: 2019.6

    Language:Japanese  

    researchmap

  • ノンブラインド型画像復元ネットワークによる頑健な画像復元

    内田和隆, 田中正行, 奥富正敏

    第25回画像センシングシンポジウム(SSII2019)  2019.6 

     More details

    Event date: 2019.6

    Language:Japanese  

    researchmap

  • 単板式カメラのための高画質イメージングパイプライン--本当にデモザイキングを最初に行うべきか?--

    山下部諒, 紋野雄介, 田中正行, 奥富正敏

    第25回画像センシングシンポジウム(SSII2019)  2019.6 

     More details

    Event date: 2019.6

    Language:Japanese  

    researchmap

  • 深層学習のための精密な人モデルに基づくラベル付きLiDARデータ生成

    金原稷, 田中正行, 奥富正敏, 佐々木洋子

    第25回画像センシングシンポジウム(SSII2019)  2019.6 

     More details

    Event date: 2019.6

    Language:Japanese  

    researchmap

  • Non-blind Image Restoration Based on Convolutional Neural Network

    Kazutaka Uchida, Masayuki Tanaka, Masatoshi Okutomi

    IEEE International Conference on Computational Photography (ICCP2019)  2019.5 

     More details

    Event date: 2019.5

    Language:English  

    researchmap

  • Joint optimization for compressive video sensing and reconstruction under hardware constraints

    Michitaka Yoshida, Akihiko Torii, Masatoshi Okutomi, Kenta Endo, Yukinobu Sugiyama, Rin-ichiro Taniguchi, Hajime Nagahara

    IEEE International Conference on Computational Photography (ICCP2019)  2019.5 

     More details

    Event date: 2019.5

    Language:English  

    researchmap

  • Gradient-Based Low-Light Image Enhancement

    Masayuki Tanaka, Takashi Shibata, Masatoshi Okutomi

    IEEE International Conference on Computational Photography (ICCP2019)  2019.5 

     More details

    Event date: 2019.5

    Language:English  

    researchmap

  • Automatic Labeled LiDAR Data Generation based on Precise Human Model

    Wonjik Kim, Masayuki Tanaka, Masatoshi Okutomi, Yoko Sasaki

    2019 International Conference on Robotics and Automation (ICRA)  2019.5  IEEE

     More details

    Event date: 2019.5

    Language:English  

    researchmap

  • Pixelwise JPEG compression detection and quality factor estimation based on convolutional neural network

    Kazutaka Uchida, Masayuki Tanaka, Masatoshi Okutomi

    Electronic Imaging, Image Processing: Algorithms and Systems XVII  2019.1  Society for Imaging Science & Technology

     More details

    Event date: 2019.1

    Language:English  

    researchmap

  • Gradient-Based Low-Light Image Enhancement

    Masayuki Tanaka, Takashi Shibata, Masatoshi Okutomi

    2019 IEEE International Conference on Consumer Electronics (ICCE)  2019.1  IEEE

     More details

    Event date: 2019.1

    Language:English  

    researchmap

  • 遠赤外線カメラと可視カメラを利用した悪条件下における画像取得 Invited

    田中正行, 柴田剛志, 奥富正敏

    国際画像機器展2018 国際画像セミナー  2018.12 

     More details

    Event date: 2018.12

    Language:Japanese  

    researchmap

  • DISPARITY MAP ESTIMATION FROM CROSS-MODAL STEREO

    Thapanapong Rukkanchanunt, Takashi Shibata, Masayuki Tanaka, Masatoshi Okutomi

    2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP)  2018.11  IEEE

     More details

    Event date: 2018.11

    Language:English  

    researchmap

  • Non-blind Image Restoration Based on Convolutional Neural Network

    Kazutaka Uchida, Masayuki Tanaka, Masatoshi Okutomi

    2018 IEEE 7th Global Conference on Consumer Electronics (GCCE)  2018.10  IEEE

     More details

    Event date: 2018.10

    Language:English  

    researchmap

  • ハードウェアの制約を考慮した圧縮ビデオセンシングにおける圧縮と再構成の同時最適化

    吉田道隆, 鳥居秋彦, 奥富正敏, 遠藤健太, 杉山行信, 谷口倫一郎, 長原一

    第21回画像の認識・理解シンポジウム(MIRU2018)  2018.8 

     More details

    Event date: 2018.8

    Language:Japanese  

    researchmap

  • Remote Heart Rate Measurement from RGB-NIR Video Based on Spatial and Spectral Face Patch Selection

    Shiika Kado, Yusuke Monno, Kenta Moriwaki, Kazunori Yoshizaki, Masayuki Tanaka, Masatoshi Okutomi

    2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)  2018.7  IEEE

     More details

    Event date: 2018.7

    Language:English  

    researchmap

  • Joint Optimization for Compressive Video Sensing and Reconstruction Under Hardware Constraints

    Michitaka Yoshida, Akihiko Torii, Masatoshi Okutomi, Kenta Endo, Yukinobu Sugiyama, Rin-ichiro Taniguchi, Hajime Nagahara

    Computer Vision – ECCV 2018  2018.7  Springer International Publishing

     More details

    Event date: 2018.7

    Language:English  

    researchmap

  • 可視光・長波長赤外線カメラを用いたマルチモーダル広視野カメラシステムの開発

    荻野有加, 田中正行, 柴田剛志, 奥富正敏

    第24回画像センシングシンポジウム(SSII2018)  2018.6 

     More details

    Event date: 2018.6

    Language:Japanese  

    researchmap

  • 2時刻間のカメラ運動推定を伴うステレオセルフキャリブレーション

    洞山慶太, 鳥居秋彦, 奥富正敏

    第24回画像センシングシンポジウム(SSII2018)  2018.6 

     More details

    Event date: 2018.6

    Language:Japanese  

    researchmap

  • 大規模visual localization の実用化に向けた評価用データセットの作成

    田平創, 荻野凌, 岩田健太郎, Torsten Sattler, Josef Sivic, Tomas Pajdla, 鳥居秋彦, 奥富正敏

    第24回画像センシングシンポジウム(SSII2018)  2018.6 

     More details

    Event date: 2018.6

    Language:Japanese  

    researchmap

  • 全方位画像を利用した疎なLiDARデータからの密な距離画像生成

    小池毅彦, 田中正行, 奥富正敏, 佐々木洋子

    第24回画像センシングシンポジウム(SSII2018)  2018.6 

     More details

    Event date: 2018.6

    Language:Japanese  

    researchmap

  • Benchmarking 6DOF Outdoor Visual Localization in Changing Conditions

    Torsten Sattler, Will Maddern, Carl Toft, Akihiko Torii, Lars Hammarstrand, Erik Stenborg, Daniel Safari, Masatoshi Okutomi, Marc Pollefeys, Josef Sivic, Fredrik Kahl, Tomas Pajdla

    2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  2018.6  IEEE

     More details

    Event date: 2018.6

    Language:English  

    researchmap

  • InLoc: Indoor Visual Localization with Dense Matching and View Synthesis

    Hajime Taira, Masatoshi Okutomi, Torsten Sattler, Mircea Cimpoi, Marc Pollefeys, Josef Sivic, Tomas Pajdla, Akihiko Torii

    2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  2018.6  IEEE

     More details

    Event date: 2018.6

    Language:English  

    researchmap

  • RGB-NIRカメラを用いた非接触心拍数推定

    角詩香, 紋野雄介, 森脇健太, 吉崎和徳, 田中正行, 奥富正敏

    第24回画像センシングシンポジウム(SSII2018)  2018.6 

     More details

    Event date: 2018.6

    Language:Japanese  

    researchmap

  • 複数の長波長赤外線カメラを用いた広視野カメラシステムの開発

    荻野有加, 田中正行, 柴田剛志, 奥富正敏

    日本機械学会ロボティクス・メカトロニクス講演会2018(ROBOMECH2018)  2018.6 

     More details

    Event date: 2018.6

    Language:Japanese  

    researchmap

  • ノイズ増幅と色再現性のトレードオフを考慮した色補正手法

    山下部諒, 紋野雄介, 田中正行, 奥富正敏

    第24回画像センシングシンポジウム(SSII2018)  2018.6 

     More details

    Event date: 2018.6

    Language:Japanese  

    researchmap

  • 汎用のカメラとプロジェクターを用いたキャリブレーションの不要な高精度3次元計測

    李淳雨, 鳥居秋彦, 奥富正敏

    第24回画像センシングシンポジウム(SSII2018)  2018.6 

     More details

    Event date: 2018.6

    Language:Japanese  

    researchmap

  • Robust, precise, and calibration-free shape acquisition with an off-the-shelf camera and projector

    Chunyu Li, Akihiko Torii, Masatoshi Okutomi

    2018 IEEE International Conference on Consumer Electronics (ICCE)  2018.1  IEEE

     More details

    Event date: 2018.1

    Language:English  

    researchmap

  • Depth map estimation with unknown fixed pattern projection

    Masayuki Tanaka, Katsuhiro Fujita, Masatoshi Okutomi

    2018 IEEE International Conference on Consumer Electronics (ICCE)  2018.1  IEEE

     More details

    Event date: 2018.1

    Language:English  

    researchmap

  • Accurate Plane Estimation Based on the Error Model of Time-of-Flight Camera

    Yosuke Konno, Masayuki Tanaka, Masatoshi Okutomi, Yukiko Yanagawa, Koichi Kinoshita, Masato Kawade, Yuki Hasegawa

    2018 Second IEEE International Conference on Robotic Computing (IRC)  2018.1  IEEE

     More details

    Event date: 2018.1

    Language:English  

    researchmap

  • 遠赤外光を活用したマルチモーダル画像センシング技術とその応用 Invited

    柴田剛志, 田中正行, 奥富正敏

    ビジョンと技術の実利用ワークショップ(ViEW2017)  2017.12 

     More details

    Event date: 2017.12

    Language:Japanese  

    researchmap

  • 3Dシーンの復元 --より精密に、より大規模に、より完全な情報を-- Invited

    奥富正敏

    3Dレーザスキャニング&イメージングシンポジウム 2017  2017.11 

     More details

    Event date: 2017.11

    Language:Japanese  

    researchmap

  • 次世代ヒューマンセンシングに向けたRGB-Xイメージングシステムの研究開発

    奥富正敏, 田中正行, 紋野雄介, 吉崎和徳, 菊地直, 福西宗憲

    ICTイノベーションフォーラム2017予稿集  2017.10 

     More details

    Event date: 2017.10

    Language:Japanese  

    researchmap

  • Misalignment-Robust Joint Filter for Cross-Modal Image Pairs

    Takashi Shibata, Masayuki Tanaka, Masatoshi Okutomi

    2017 IEEE International Conference on Computer Vision (ICCV)  2017.10  IEEE

     More details

    Event date: 2017.10

    Language:English  

    researchmap

  • 入出力分野の最新動向 Invited

    奥富正敏

    光産業動向セミナー講演予稿集  2017.10 

     More details

    Event date: 2017.10

    Language:Japanese  

    researchmap

  • Image Enhancement Framework for Low-resolution Thermal Images in Visible and LWIR Camera Systems

    Thapanapong Rukkanchanunt, Masayuki Tanaka, Masatoshi Okutomi

    Proceedings of SPIE Security + Defence 2017  2017.9  SPIE-INT SOC OPTICAL ENGINEERING

     More details

    Event date: 2017.9

    Language:English  

    Infrared (IR) thermography camera became an essential tool for monitoring applications such as pedestrian detection and equipment monitoring. Most commonly used IR cameras are Long Wavelength Infrared (LWIR) cameras due to their suitable wavelength for environmental temperature. Even though the cost of LWIR cameras had been on a decline, the affordable ones only provided low-resolution images. Enhancement techniques that could be applied to visible images often failed to perform correctly on low-resolution LWIR images. Many attempts on thermal image enhancement had been on high-resolution images. Stereo calibration between visible cameras and LWIR cameras had recently been improved in term of accuracy and ease of use. Recent visible cameras and LWIR cameras are bundled into one device, giving the capability of simultaneously taking visible and LWIR images. However, few works take advantage of this camera systems. In this work, image enhancement framework for visible and LWIR camera systems is proposed. The proposed framework consists of two inter-connected modules: visible image enhancement module and LWIR image enhancement module. The enhancement technique that will be experimented is image stitching which serves two purposes: view expansion and super-resolution. The visible image enhancement module follows a regular workflow for image stitching. The intermediate results such as homography and seam carvings labels are passed to LWIR image enhancement module. The LWIR image enhancement module aligns LWIR images to visible images using stereo calibrations results and utilizes already computed homography from visible images to avoid feature extraction and matching on LWIR images. The framework is able to handle difference in image resolution between visible images and LWIR images by performing sparse pixel-to-pixel version of image alignment and image projection. Experiments show that the proposed framework leads to richer image stitching's results comparing to the results from an existing commercial software.

    researchmap

  • Tunable color correction between linear and polynomial models for noisy images

    Ryo Yamakabe, Yusuke Monno, Masayuki Tanaka, Masatoshi Okutomi

    2017 IEEE International Conference on Image Processing (ICIP)  2017.9  IEEE

     More details

    Event date: 2017.9

    Language:English  

    researchmap

  • 圧縮センシング動画のデコーディング手法の検討

    吉田道隆, 長原一, 鳥居秋彦, 奥富正敏, 谷口倫一郎

    第20回画像の認識・理解シンポジウム(MIRU2017)  2017.8 

     More details

    Event date: 2017.8

    Language:Japanese  

    researchmap

  • Multi-View Inverse Rendering under Arbitrary Illumination and Albedo (ECCV2016) Invited

    Kichang Kim, Akihiko Torii, Masatoshi Okutomi

    2017.8 

     More details

    Event date: 2017.8

    Language:English  

    researchmap

  • Are Large-Scale 3D Models Really Necessary for Accurate Visual Localization?

    Torsten Sattler, Akihiko Torii, Josef Sivic, Marc Pollefeys, Hajime Taira, Masatoshi Okutomi, Tomas Pajdla

    2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  2017.7  IEEE

     More details

    Event date: 2017.7

    Language:English  

    researchmap

  • カラー画像と近赤外線画像を同時に撮影可能なイメージングシステム Invited

    奥富正敏, 紋野雄介, 田中正行, 吉崎和徳, 福西宗憲, 小宮康宏

    日本光学会 光設計研究グループ 第62回研究会, 光設計研究グループ機関誌  2017.7 

     More details

    Event date: 2017.7

    Language:Japanese  

    researchmap

  • ノイズを含む画像に対する高精度な色補正パイプライン

    紋野雄介, 高橋健太, 田中正行, 奥富正敏

    第23回画像センシングシンポジウム(SSII2017)  2017.6 

     More details

    Event date: 2017.6

    Language:Japanese  

    researchmap

  • カラー画像を同時取得可能なリアルタイム近赤外線蛍光イメージング

    吉崎和徳, 福田弘之, 紋野雄介, 田中正行, 奥富正敏, 石原学, カムトーンキッティクン, チャイヤスィット

    第23回画像センシングシンポジウム(SSII2017)  2017.6 

     More details

    Event date: 2017.6

    Language:Japanese  

    researchmap

  • 値域制約とベース構造制約を用いた勾配ベースの画像再構成 --マルチモーダル画像融合やHDR画像処理など様々な応用に向けて--

    柴田剛志, 田中正行, 奥富正敏

    第23回画像センシングシンポジウム(SSII2017)  2017.6 

     More details

    Event date: 2017.6

    Language:Japanese  

    researchmap

  • 自己誘導型残差補間を用いた深度画像の高解像度化

    今野洋佑, 田中正行, 奥富正敏, 柳川由紀子, 木下航一, 川出雅人

    第23回画像センシングシンポジウム(SSII2017)  2017.6 

     More details

    Event date: 2017.6

    Language:Japanese  

    researchmap

  • Multi-View Inverse Renderingによる高精細な3次元復元

    鳥居秋彦, 金杞昌, 奥富正敏

    第23回画像センシングシンポジウム(SSII2017)  2017.6 

     More details

    Event date: 2017.6

    Language:Japanese  

    researchmap

  • 可視カメラと遠赤外線カメラの高精度キャリブレーションとその応用 Invited

    田中正行, 柴田剛志, 奥富正敏

    日本色彩学会 視覚情報基礎研究会 第31回研究発表会  2017.6 

     More details

    Event date: 2017.6

    Language:Japanese  

    researchmap

  • 防塵性を考慮した可視光・遠赤外線同軸カメラシステムの開発

    荻野有加, 柴田剛志, 田中正行, 奥富正敏

    日本機械学会ロボティクス・メカトロニクス講演会(ROBOMECH2017)  2017.5 

     More details

    Event date: 2017.5

    Language:Japanese  

    researchmap

  • 可視画像と遠赤外線画像の画像融合技術 Invited

    田中正行, 柴田剛志, 奥富正敏

    精密工学会 画像応用技術専門委員会2017年度第1回研究会  2017.5 

     More details

    Event date: 2017.5

    Language:Japanese  

    researchmap

  • SfMを用いた都市3Dモデルに対するカメラ位置姿勢推定

    加賀美翔, 田平創, 鳥居秋彦, 奥富正敏

    情報処理学会研究報告(コンピュータビジョンとイメージメディア(CVIM))  2017.5 

     More details

    Event date: 2017.5

    Language:Japanese  

    researchmap

  • Unified optimization framework for L2, L1, and/or L0 constrained image reconstruction

    Masayuki Tanaka, Masatoshi Okutomi

    Proceedings of SPIE Defense + Commercial Sensing (DCS2017)  2017.4 

     More details

    Event date: 2017.4

    Language:English  

    researchmap

  • Coaxial visible and FIR camera system with accurate geometric calibration

    Yuka Ogino, Takashi Shibata, Masayuki Tanaka, Masatoshi Okutomi

    Proceedings of SPIE Defense + Commercial Sensing (DCS2017)  2017.4 

     More details

    Event date: 2017.4

    Language:English  

    researchmap

  • LWIR image visualization preserving local details and global distribution by gradient-domain image reconstruction.

    Takashi Shibata, Masayuki Tanaka, Masatoshi Okutomi

    Proceedings of SPIE Defense + Commercial Sensing (DCS2017)  2017.4  SPIE-INT SOC OPTICAL ENGINEERING

     More details

    Event date: 2017.4

    Language:English  

    Recent developments of long wave infrared (LWIR) devices and LWIR sensor technologies enable us to obtain an LWIR image with high bit depth and low signal-noise ratio. To exploit these recent developments, we propose a novel temperature visualization method that can simultaneously represent global distribution and local details of the input temperature. The global temperature distribution is represented by pseudo color. On the other hand, to manipulate the local temperature details, the output luminance is generated by gradient-domain image reconstruction. Experimental results on real LWIR images show the effectiveness of the proposed method.

    researchmap

  • ドローン搭載カメラを用いた3D復元 Invited

    奥富正敏

    OPTICS & PHOTONICS International Exhibition (OPIE'17)  2017.4 

     More details

    Event date: 2017.4

    Language:Japanese  

    researchmap

  • 可視及び遠赤外カメラの高精度同時校正とその応用

    柴田剛志, 田中正行, 奥富正敏

    動的画像処理実利用化ワークショップ(DIA2017)講演論文集  2017.3 

     More details

    Event date: 2017.3

    Language:Japanese  

    researchmap

  • 複数視点魚眼映像による発生原理を考慮したオーロラの3次元形状計測と可視化

    竹内彰, 藤井浩光, 山下淳, 田中正行, 片岡龍峰, 三好由純, 奥富正敏, 淺間一

    第22回ロボティクスシンポジア講演予稿集  2017.3 

     More details

    Event date: 2017.3

    Language:Japanese  

    researchmap

  • Accurate Joint Geometric Camera Calibration of Visible and Far-Infrared Cameras

    Takashi Shibata, Masayuki Tanaka, Masatoshi Okutomi

    Electronic Imaging  2017.1  Society for Imaging Science & Technology

     More details

    Event date: 2017.1

    Language:English  

    researchmap

  • Robust Feature Matching by Learning Descriptor Covariance with Viewpoint Synthesis

    Hajime Taira, Akihiko Torii, Masatoshi Okutomi

    2016 23RD INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)  2016  IEEE COMPUTER SOC

     More details

    Event date: 2016

    Language:English  

    For images taken from very different viewpoints, we propose a new feature matching algorithm that provides accurate matches while preserving high matchability. Our method first synthesizes images by simulating the viewpoint changes. It then learns variation of local feature descriptors induced by the viewpoint changes. Finally, we robustly match feature descriptors by measuring the similarity using the learned variation. Our method is particularly useful for matching new query images to target image archived in a database. We demonstrate the benefits of the proposed method in terms of accuracy and computational time through experiments using several wide-baseline image datasets.

    researchmap

  • EFFECTIVE COLOR CORRECTION PIPELINE FOR A NOISY IMAGE

    Kenta Takahashi, Yusuke Monno, Masayuki Tanaka, Masatoshi Okutomi

    2016 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)  2016  IEEE

     More details

    Event date: 2016

    Language:English  

    Color correction is an essential image processing operation that transforms a camera-dependent RGB color space to a standard color space, e.g., the XYZ or the sRGB color space. The color correction is typically performed by multiplying the camera RGB values by a color correction matrix, which often amplifies image noise. In this paper, we propose an effective color correction pipeline for a noisy image. The proposed pipeline consists of two parts; the color correction and denoising. In the color correction part, we utilize spatially varying color correction (SVCC) that adaptively calculates the color correction matrices for each local image block considering the noise effect. Although the SVCC can effectively suppress the noise amplification, the noise is still included in the color corrected image, where the noise levels spatially vary for each local block. In the denoising part, we propose an effective denoising framework for the color corrected image with spatially varying noise levels. Experimental results demonstrate that the proposed color correction pipeline outperforms existing algorithms for various noise levels.

    researchmap

  • Gradient-Domain Image Reconstruction Framework with Intensity-Range and Base-Structure Constraints

    Takashi Shibata, Masayuki Tanaka, Masatoshi Okutomi

    2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)  2016  IEEE

     More details

    Event date: 2016

    Language:English  

    This paper presents a novel unified gradient-domain image reconstruction framework with intensity-range constraint and base-structure constraint. The existing method for manipulating base structures and detailed textures are classifiable into two major approaches: i) gradient-domain and ii) layer-decomposition. To generate detail-preserving and artifact-free output images, we combine the benefits of the two approaches into the proposed framework by introducing the intensity-range constraint and the base-structure constraint. To preserve details of the input image, the proposed method takes advantage of reconstructing the output image in the gradient domain, while the output intensity is guaranteed to lie within the specified intensity range, e.g. 0-to-255, by the intensity-range constraint. In addition, the reconstructed image lies close to the base structure by the base-structure constraint, which is effective for restraining artifacts. Experimental results show that the proposed framework is effective for various applications such as tone mapping, seamless image cloning, detail enhancement, and image restoration.

    researchmap

  • Super High Dynamic Range Video

    Yuka Ogino, Masayuki Tanaka, Takashi Shibata, Masatoshi Okutomi

    2016 23RD INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)  2016  IEEE COMPUTER SOC

     More details

    Event date: 2016

    Language:English  

    High dynamic range (HDR) imaging is highly demanded in computer vision algorithms. An HDR image is composed with several low dynamic range (LDR) images, which usually have some disparities. In many HDR imaging algorithms, the disparities are estimated based on the texture information of the LDR images. However, the texture information is often lost completely if scenes include extremely bright and dark regions simultaneously. Recently, super high dynamic range (SHDR) imaging algorithm has been proposed where the disparities are estimated based on the segment shapes instead of the textures for handling such extreme scenes. In this paper, we extend the SHDR imaging algorithm to SHDR video generation introducing temporal smoothness terms. The temporal smoothness terms improve the temporal stability and the precision of the disparity estimation. Quantitative and qualitative evaluations demonstrate that the proposed algorithm outperforms existing algorithms.

    researchmap

  • Single-sensor RGB and NIR image acquisition: Toward optimal performance by taking account of CFA pattern, demosaicking, and color correction

    Hayato Teranaka, Yusuke Monno, Masayuki Tanaka, Masatoshi Okutomi

    IS and T International Symposium on Electronic Imaging Science and Technology  2016  Society for Imaging Science and Technology

     More details

    Event date: 2016

    Language:English  

    In recent years, many applications using a pair of RGB and near-infrared (NIR) images have been proposed in computer vision and image processing communities. Thanks to recent progress of image sensor technology, it is also becoming possible to manufacture an image sensor with a novel spectral filter array, which has RGB plus NIR pixels for one-shot acquisition of the RGB and the NIR images. In such a novel filter array, half of the G pixels in the standard Bayer color filter array (CFA) are typically replaced with the NIR pixels. However, its performance has not fully been investigated in the pipeline of single-sensor RGB and NIR image acquisition. In this paper, we present an imaging pipeline of the single-sensor RGB and NIR image acquisition and investigate its optimal performance by taking account of the filter array pattern, demosaicking and color correction. We also propose two types of filter array patterns and demosaicking algorithms for improving the quality of acquired RGB and NIR images. Based on the imaging pipeline we present, the performance of different filter array patterns and demosaicking algorithms is evaluated. In experimental results, we demonstrate that our proposed filter array patterns and demosaicking algorithms outperform the existing ones.

    researchmap

  • N-to-sRGB Mapping for Single-Senor Multispectral Imaging

    Yusuke Monno, Masayuki Tanaka, Masatoshi Okutomi

    2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOP (ICCVW)  2015  IEEE

     More details

    Event date: 2015

    Language:English  

    Visualization of a multispectral image in a standard color space, typically the sRGB space, is an important task for human color perception. When we reproduce the sRGB image from the multispectral image with N spectral bands, an N-to-sRGB mapping is required. The challenge of the N-to-sRGB mapping in single-sensor multispectral imaging with a multispectral filter array (MSFA) is to reduce demosaicking error amplification and propagation across different spectral bands, which are not trivial because of very sparse sampling of multiple spectral bands in a single image sensor. In this paper, we propose a novel N-to-sRGB mapping pipeline for effectively suppressing the demosaicking error amplification and propagation. Our idea is to apply guided filtering in the mapped sRGB space using one of input N band images before the amplification and propagation as a guide image. Experimental results demonstrate that our proposed pipeline improves the mapping accuracy for various MSFA types.

    researchmap

  • UNIFIED IMAGE FUSION BASED ON APPLICATION-ADAPTIVE IMPORTANCE MEASURE

    Takashi Shibata, Masayuki Tanaka, Masatoshi Okutomi

    2015 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)  2015  IEEE

     More details

    Event date: 2015

    Language:English  

    This paper presents a novel unified image fusion framework based on an application-adaptive importance measure. In the proposed method, an important area is selected pixel-by-pixel using the importance measure which is designed for each image type in each application. Then, the fused intensity is generated by a Poisson image editing. The main contribution is to provide a generalized image fusion framework enables us to deal with various different types of images for many applications. Experimental results show that the proposed method is effective for various applications including depth-perceptible image enhancement, temperature-preserving image fusion, optical flow fusion, and haze removal.

    researchmap

  • PSEUDO FOUR-CHANNEL IMAGE DENOISING FOR NOISY CFA RAW DATA

    Hiroki Akiyama, Masayuki Tanaka, Masatoshi Okutomi

    2015 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)  2015  IEEE

     More details

    Event date: 2015

    Language:English  

    Most demosaicking algorithms only focus on handling noise-free CFA raw data. In practice, the CFA raw data are corrupted by noise, which degrades demosaicking performance. Full-color image quality strongly depends on the performance of the demosaicking. Here, we propose a CFA raw data denoising algorithm. In the proposed algorithm, the CFA raw data is converted to a pseudo four-channel image by rearranging pixels. Then, the four-channel data are transformed based on the principal component analysis (PCA). Existing high-performance gray image denoising algorithm is applied to each transformed image. Finally, the denoised data is rearranged to obtain denoised CFA raw data. We evaluate both the denoised CFA raw data as well as the full-color image reconstructed with the noisy CFA raw data. Experimental comparisons demonstrate that the proposed algorithm outperforms existing state-of-the-art algorithms.

    researchmap

  • Visible and Near-Infrared Image Fusion based on Visually Salient Area Selection

    Takashi Shibata, Masayuki Tanaka, Masatoshi Okutomi

    DIGITAL PHOTOGRAPHY XI  2015  SPIE-INT SOC OPTICAL ENGINEERING

     More details

    Event date: 2015

    Language:English  

    This paper presents a novel image fusion algorithm for a visible image and a near infrared (NIR) image. For the proposed fusion, the image is selected pixel-by-pixel based on local saliency. In this paper, the local saliency is measured by a local contrast. Then, the gradient information is fused and the output image is constructed by a Poisson image editing which preserves the gradient information of both images. The effectiveness of the proposed fusion algorithm is demonstrated in various applications including denoising, dehazing, and image enhancement.

    researchmap

  • A General and Simple Method for Camera Pose and Focal Length Determination

    Yinqiang Zheng, Shigeki Sugimoto, Imari Sato, Masatoshi Okutomi

    2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)  2014  IEEE

     More details

    Event date: 2014

    Language:English  

    In this paper, we revisit the pose determination problem of a partially calibrated camera with unknown focal length, hereafter referred to as the PnPf problem, by using n (n &gt;= 4) 3D-to-2D point correspondences. Our core contribution is to introduce the angle constraint and derive a compact bivariate polynomial equation for each point triplet. Based on this polynomial equation, we propose a truly general method for the PnPf problem, which is suited both to the minimal 4-point based RANSAC application, and also to large scale scenarios with thousands of points, irrespective of the 3D point configuration. In addition, by solving bivariate polynomial systems via the Sylvester resultant, our method is very simple and easy to implement. Its simplicity is especially obvious when one needs to develop a fast solver for the 4-point case on the basis of the characteristic polynomial technique. Experiment results have also demonstrated its superiority in accuracy and efficiency when compared with the existing state-of-the-art solutions.

    researchmap

  • Minimized-Laplacian Residual Interpolation for Color Image Demosaicking

    Daisuke Kiku, Yusuke Monno, Masayuki Tanaka, Masatoshi Okutomi

    DIGITAL PHOTOGRAPHY X  2014  SPIE-INT SOC OPTICAL ENGINEERING

     More details

    Event date: 2014

    Language:English  

    A color difference interpolation technique is widely used for color image demosaicking. In this paper, we propose a minimized-laplaeian residual interpolation (MLRI) as an alternative to the color difference interpolation, where the residuals are the differences between observed and tentatively estimated pixel values. In the MLRI, we estimate the tentative pixel values by minimizing the Laplacian energies of the residuals. This residual image transformation makes the interpolation process more precise than the standard color difference transformation. We incorporate the proposed MLRI into the gradient based threshold free (GBTF) algorithm, which is one of current state-of-the-art Bayer demosaicking algorithms. Experimental results demonstrate that our proposed demosaicking algorithm can outperform the state-of-the-art algorithms for the 30 images of the IMAX and the Kodak datasets.

    researchmap

  • A classification-and-reconstruction approach for a single image super-resolution by a sparse representation

    YingYing Fan, Masayuki Tanaka, Masatoshi Okutomi

    DIGITAL PHOTOGRAPHY X  2014  SPIE-INT SOC OPTICAL ENGINEERING

     More details

    Event date: 2014

    Language:English  

    A sparse representation is known as a very powerful tool to solve image reconstruction problem such as denoising and the single image super-resolution. In the sparse representation, it is assumed that an image patch or data can be approximated by a linear combination of a few bases selected from a given dictionary. A single over-complete dictionary is usually learned with training patches. Dictionary learning methods almost are concerned about building a general over-complete dictionary on the assumption that the bases in dictionary can represent everything. However, using more appropriate dictionary, the sparse representation of patch can obtain better results. In this paper, we propose a classification-and-reconstruction approach with multiple dictionaries. Before learning dictionary for reconstruction, some representative bases can be used to classify all training patches from database and multiple dictionaries for reconstruction can be learned by classified patches respectively. In reconstruction phase, the patch of input image can be classified and the adaptive dictionary can be selected to use. We demonstrate that the proposed classification-and-reconstruction approach outperforms existing sparse representation with the single dictionary.

    researchmap

  • Robust Ground Surface Map Generation Using Vehicle-Mounted Stereo Camera

    Kouma Motooka, Shigeki Sugimoto, Masatoshi Okutomi, Takeshi Shima

    2014 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS 2014)  2014  IEEE

     More details

    Event date: 2014

    Language:English  

    We propose a robust method for incrementally estimating a regular-grid ground surface map from stereo image sequences captured by nearly front-looking vehiclemounted stereo cameras. The method simultaneously estimates a camera ego-motion and vertex heights of a regular mesh, which is composed of piecewise triangular patches drawn on a level plane in the ground coordinate system, by minimizing pixel value differences over the ground surface. The method combinationally uses feature-based approach and pixel-based approach for robustly estimating ego-motion parameters. We also show that this combination is beneficial for removing outlier pixels, which mainly represent the edge of the selfshadow area on the ground surface. The validity of the proposed method is demonstrated through experiments using real images.

    researchmap

  • SIGNAL DEPENDENT NOISE REMOVAL FROM A SINGLE IMAGE

    Xinhao Liu, Masayuki Tanaka, Masatoshi Okutomi

    2014 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)  2014  IEEE

     More details

    Event date: 2014

    Language:English  

    State-of-the-art image denoising algorithms usually assume additive white Gaussian noise (AWGN), although they have achieved outstanding performance, modeling and removing real signal dependent noise from a single image still remains a challenging problem. In this paper we propose a segmentation-based image denoising algorithm for signal dependent noise. Incorporating a noise identification algorithm, we integrate these two modules into a full blind, end-to-end denoising algorithm for signal dependent noise. First, we identify the noise level function for a given single noisy image. Then, after initial denoising, segmentation is applied to the pre-filtered image. Assuming the noise level of each segment is constant, we apply AWGN denoising algorithm to each segment. We obtain a final denoised image by composing the denoised segments. Various experimental results on synthetic and real noisy images show that our algorithm outperforms state-of-the-art denoising algorithms in removing real signal dependent noise.

    researchmap

  • A Novel Inference of a Restricted Boltzmann Machine

    Masayuki Tanaka, Masatoshi Okutomi

    2014 22ND INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)  2014  IEEE COMPUTER SOC

     More details

    Event date: 2014

    Language:English  

    A deep neural network (DNN) pre-trained via stacking restricted Boltzmann machines (RBMs) demonstrates high performance. The binary RBM is usually used to construct the DNN. However, a continuous probability of each node is used as real value state, although the state of the binary RBM's node should be represented by a random binary variable. One of main reasons of this abuse is that it works. One of others is to reduce a computational cost. In this paper, we propose a novel inference of the RBM, considering that the input of the RBM is the random binary variable. Straight forward derivation of the proposed inference is intractable. Then, we also propose the closed-form approximation of it. We convince that the proposed inference is more reasonable than a conventional algorithm of the RBM. Experimental comparisons demonstrate that the proposed inference improves the performance of the DNN.

    researchmap

  • MULTISPECTRAL DEMOSAICKING WITH NOVEL GUIDE IMAGE GENERATION AND RESIDUAL INTERPOLATION

    Yusuke Monno, Daisuke Kiku, Sunao Kikuchi, Masayuki Tanaka, Masatoshi Okutomi

    2014 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)  2014  IEEE

     More details

    Event date: 2014

    Language:English  

    A one-shot multispectral imaging system using a multispectral filter array (MSFA) provides a practical solution for compact, low-cost, and real-time multispectral imaging. However, multispectral demosaicking is a challenging problem because each spectral band is significantly undersampled in the MSFA. In this paper, we propose a novel demosaicking algorithm for the MSFA proposed in [1, 2]. Main contributions of this paper are (i) we utilize multispectral correlations for generating a guide image, which is effectively used for interpolation preserving image structures, and (ii) we effectively use residual interpolation (RI) [3] for generating the guide image and interpolating each spectral band. Experimental results demonstrate that our proposed algorithm significantly outperforms existing state-of-the-art algorithms.

    researchmap

  • Simultaneous Capturing of RGB and Additional Band Images Using Hybrid Color Filter Array

    Daisuke Kiku, Yusuke Monno, Masayuki Tanaka, Masatoshi Okutomi

    DIGITAL PHOTOGRAPHY X  2014  SPIE-INT SOC OPTICAL ENGINEERING

     More details

    Event date: 2014

    Language:English  

    Extra band information in addition to the RGB, such as the near-infrared (NIR) and the ultra-violet, is valuable for many applications. In this paper, we propose a novel color filter array (CFA), which we call "hybrid CFA," and a demosaicking algorithm for the simultaneous capturing of the RGB and the additional band images. Our proposed hybrid CFA and demosaicking algorithm do not rely on any specific correlation between the RGB and the additional band. Therefore, the additional band can be arbitrarily decided by users. Experimental results demonstrate that our proposed demosaicking algorithm with the proposed hybrid CFA can provide the additional band image while keeping the RGB image almost the same quality as the image acquired by using the standard Bayer CFA.

    researchmap

  • RESIDUAL INTERPOLATION FOR COLOR IMAGE DEMOSAICKING

    Daisuke Kiku, Yusuke Monno, Masayuki Tanaka, Masatoshi Okutomi

    2013 20TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP 2013)  2013  IEEE

     More details

    Event date: 2013

    Language:English  

    A color difference interpolation technique is widely used for color image demosaicking. In this paper, we propose residual interpolation as an alternative to the color difference interpolation, where the residual is a difference between an observed and a tentatively estimated pixel value. We incorporate the proposed residual interpolation into the gradient based threshold free (GBTF) algorithm, which is one of current state-of-the-art demosaicking algorithms. Experimental results demonstrate that our proposed demosaicking algorithm using the residual interpolation can give state-of-the-art performance for the 30 images of Kodak and IMAX datasets.

    researchmap

  • Direct Generation of Regular-Grid Ground Surface Map From In-Vehicle Stereo Image Sequences

    Shigeki Sugimoto, Kouma Motooka, Masatoshi Okutomi

    2013 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW)  2013  IEEE

     More details

    Event date: 2013

    Language:English  

    We propose a direct method for incrementally estimating a regular-grid ground surface map from stereo image sequences captured by nearly front-looking stereo cameras, taking illumination changes on all images into consideration. At each frame, we simultaneously estimate a camera motion and vertex heights of the regular mesh, composed of piecewise triangular patches, drawn on a level plane in the ground coordinate system, by minimizing a cost representing the differences of the photometrically transformed pixel values in homography-related projective triangular patches over three image pairs in a two-frame stereo image sequence. The data term is formulated by the Inverse Compositional trick for high computational efficiency. The main difficulty of the problem formulation lies in the instability of the height estimation for the vertices distant from the cameras. We first develop a stereo ground surface reconstruction method where the stability is effectively improved by the combinational use of three complementary techniques, the use of a smoothness term, update constraint term, and a hierarchical meshing approach. Then we extend the stereo method for incremental ground surface map generation. The validity of the proposed method is demonstrated through experiments using real images.

    researchmap

  • ESTIMATION OF SIGNAL DEPENDENT NOISE PARAMETERS FROM A SINGLE IMAGE

    Xinhao Liu, Masayuki Tanaka, Masatoshi Okutomi

    2013 20TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP 2013)  2013  IEEE

     More details

    Event date: 2013

    Language:English  

    The additive white Gaussian noise (AWGN) is usually assumed in many image processing algorithms. However, these algorithms cannot effectively deal with the noise from actual cameras which is better modeled as signal dependent noise (SDN). In this paper, we focus on the SDN model and propose an algorithm to accurately estimate its parameters without any assumption of the noise types. The noise parameters are estimated by using the selected weak textured patches from a single noisy image. Experiments on synthetic noisy images are conducted to test the algorithm, which show that our noise parameter estimation outperforms the existing algorithms. And based on our estimation, the performance of image processing applications like Wiener filter can be effectively improved.

    researchmap

  • Direct spatio-spectral datacube reconstruction from raw data using a spatially adaptive spatio-spectral basis

    Yusuke Monno, Masayuki Tanaka, Masatoshi Okutomi

    DIGITAL PHOTOGRAPHY IX  2013  SPIE-INT SOC OPTICAL ENGINEERING

     More details

    Event date: 2013

    Language:English  

    Spectral reflectance is an inherent property of objects that is useful for many computer vision tasks. The spectral reflectance of a scene can be described as a spatio-spectral (SS) datacube, in which each value represents the reflectance at a spatial location and a wavelength. In this paper, we propose a novel method that reconstructs the SS datacube from raw data obtained by an image sensor equipped with a multispectral filter array. In our proposed method, we describe the SS datacube as a linear combination of spatially adaptive SS basis vectors. In a previous method, spatially invariant SS basis vectors are used for describing the SS datacube. In contrast, we adaptively generate the SS basis vectors for each spatial location. Then, we reconstruct the SS datacube by estimating the linear coefficients of the spatially adaptive SS basis vectors from the raw data. Experimental results demonstrate that our proposed method can accurately reconstruct the SS datacube compared with the method using spatially invariant SS basis vectors.

    researchmap

  • A Practical Rank-Constrained Eight-Point Algorithm for Fundamental Matrix Estimation.

    Yinqiang Zheng, Shigeki Sugimoto, Masatoshi Okutomi

    2013 IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, USA, June 23-28, 2013  2013  IEEE

     More details

    Event date: 2013

    researchmap

  • Augmenting Moving Planar Surfaces Interactively with Video Projection and a Color Camera

    Samuel Audet, Masatoshi Okutomi, Masayuki Tanaka

    IEEE VIRTUAL REALITY CONFERENCE 2012 PROCEEDINGS  2012  IEEE

     More details

    Event date: 2012

    Language:English  

    researchmap

  • Multispectral demosaicking using guided filter

    Yusuke Monno, Masayuki Tanaka, Masatoshi Okutomi

    DIGITAL PHOTOGRAPHY VIII  2012  SPIE-INT SOC OPTICAL ENGINEERING

     More details

    Event date: 2012

    Language:English  

    Multispectral imaging is highly demanded for precise color reproduction and for various computer vision applications. Multispectral imaging with a multispectral color filter array (MCFA), which can be considered as a multispectral extension of commonly used consumer RGB cameras, could be a simple, low-cost, and practical system. A challenge of the multispectral imaging with the MCFA is multispectral demosaicking because each spectral component of the MCFA is severely undersampled. In this paper, we propose a novel multispectral demosaicking algorithm using a guided filter. The guided filter is recently proposed as an excellent structure-preserving filter. The guided filter requires so-called a guide image. A main issue of the guided filter is how to obtain an effective guide image. In our proposed algorithm, we generate the guide image from the most densely sampled spectral component in the MCFA. Then, ohter spectral components are interpolated by the guided filter. Experimental results demonstrate that our proposed algorithm outperforms other existing demosaicking algorithms both visually and quantitatively.

    researchmap

  • NOISE LEVEL ESTIMATION USING WEAK TEXTURED PATCHES OF A SINGLE NOISY IMAGE

    Xinhao Liu, Masayuki Tanaka, Masatoshi Okutomi

    2012 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP 2012)  2012  IEEE

     More details

    Event date: 2012

    Language:English  

    A patch-based noise level estimation algorithm is proposed in this paper, with patches generated from a single noisy image. One can easily estimate the noise level from image patches using principal component analysis (PCA) if the image comprises only weak textured patches. The challenge for patch-based noise level estimation is how to select weak textured patches from a noisy image. As described in this paper, we propose a novel algorithm to select weak textured patches from a single noisy image based on the gradients of the patches and their statistics. Then we estimate the noise level from the selected weak textured patches using PCA. We demonstrate experimentally that the proposed noise level estimation algorithm outperforms the state-of-the-art algorithm.

    researchmap

  • OPTIMAL SPECTRAL SENSITIVITY FUNCTIONS FOR A SINGLE-CAMERA ONE-SHOT MULTISPECTRAL IMAGING SYSTEM

    Yusuke Monno, Toshihiro Kitao, Masayuki Tanaka, Masatoshi Okutomi

    2012 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP 2012)  2012  IEEE

     More details

    Event date: 2012

    Language:English  

    Multispectral imaging is highly demanded for precise color reproduction and for various computer vision applications. Recently, a single-camera one-shot multispectral imaging (SCOS) system that uses a single image sensor equipped with a multispectral filter array (MSFA) has been proposed. In this paper, we develop optimal spectral sensitivity functions (SSFs) for the SCOS system, in which multispectral image quality depends strongly on the performance of multispectral demosaicking. First, we propose a simple optimization algorithm that can incorporate a high-performance multispectral demosaicking algorithm. Then, we experimentally demonstrate that the optimized SSFs by our proposed algorithm improve the performance of spectral reflectance estimation and the accuracy of color reproduction.

    researchmap

  • Camera Self Calibration Based on Direct Image Alignment

    Shigeki Sugimoto, Masatoshi Okutomi

    2012 21ST INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR 2012)  2012  IEEE

     More details

    Event date: 2012

    Language:English  

    We propose a camera self calibration method based on direct image alignment (DIA) for estimating camera parameters including lens-distortion components from planar scenes. We formulate a cost function without the inverse of the lens distortion function for avoiding the difficulty in the image alignment between two lens-distorted images. We also use a backward warp cost for improving the convergence instability due to inherent ambiguities in calibration parameters and blurring effects through image warps. We show our method leads to a comparable performance with the de-facto standard Matlab toolbox for non-self calibration, even though the proposed method is for self calibration.

    researchmap

  • Real-time Step Edge Estimation Using Stereo Images for Biped Robot

    Minami Asatani, Shigeki Sugimoto, Masatoshi Okutomi

    2011 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS  2011  IEEE

     More details

    Event date: 2011

    Language:English  

    A state-of-the-arts biped robot can take footsteps such that its heels always overhang corner edges while ascending stairs, as humans naturally do. The overhanging footstep is advantageous in terms of relaxation of restrictions on gait planning. However, in a man-made environment without geometry information, the overhanging footstep requires the estimation of the exact step-edge position in real-time. In this paper we propose a real-time method for estimating step edge positions using stereo images. We find a straight edge line, which divides a view area into two regions representing the upper and lower step-able planes at the target edge. The edge line is obtained by minimizing a cost function composed of pixel-value-difference images, which are computed from the two stereo images and the geometry parameters of the planes, estimated by an efficient direct method in high precision. The validity of the proposed method is demonstrated through online experiments using stereo cameras mounted on the body of a biped robot traversing real stairs.

    researchmap

  • MULTISPECTRAL DEMOSAICKING USING ADAPTIVE KERNEL UPSAMPLING

    Yusuke Monno, Masayuki Tanaka, Masatoshi Okutomi

    2011 18TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)  2011  IEEE

     More details

    Event date: 2011

    Language:English  

    Multispectral demosaicking, which estimates full multispectral images from raw data observed using a single image sensor with a color filter array (CFA), is a challenging task because each spectral component is severely undersampled. In this paper, we propose a novel multispectral demosaicking algorithm. We extend existing upsampling algorithms to adaptive kernel upsampling algorithms using an adaptive kernel as a spatial weight and apply them to multispectral demosaicking. We also propose a new CFA and a direct adaptive kernel estimation from the raw data of the proposed CFA. Experimental results with real multispectral images demonstrate the effectiveness of the proposed algorithm.

    researchmap

  • Color Kernel Regression for Robust Direct Upsampling from Raw Data of General Color Filter Array

    Masayuki Tanaka, Masatoshi Okutomi

    COMPUTER VISION - ACCV 2010, PT III  2011  SPRINGER-VERLAG BERLIN

     More details

    Event date: 2011

    Language:English  

    Upsampling with preserving image details is highly demanded image operation. There are various upsampling algorithms. Many upsampling algorithms focus on the gray image. For color images, those algorithms are usually applied to a luminance component only, or independently applied channel by channel. However, we can not observe the full-color image by a single image sensor equipped in a common digital camera. The data observed by the single image sensor is called raw data. The raw data is converted into the full-color image by demosaicing. Upsampling from the raw data requires sequential processes of demosaicing and upsampling. In this paper, we propose direct upsampling from the raw data based on a kernel regression. Although the kernel regression is known as powerful denoising and interpolation algorithm, the kernel regression has been also proposed for the gray image. We extend to the color kernel regression which can generate the full-color image from any kind of raw data. Second key point of the proposed color kernel regression is a local density parameter optimization, or kernel size optimization, based on the stability of the linear system associated to the kernel regression. We also propose a novel iteration framework for the upsampling. The experimental results demonstrate that the proposed color kernel regression outperforms existing sequential approaches, reconstruct ion approaches, and existing kernel regression.

    researchmap

  • Theoretical analysis on reconstruction-based super-resolution for an arbitrary PSF

    Masayuki Tanaka, Masatoshi Okutomi

    Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005  2005  IEEE Computer Society

     More details

    Event date: 2005

    Language:English  

    This study presents and proves a condition number theorem for super-resolution (SR). The SR condition number theorem provides the condition number for an arbitrary space-invariant point spread function (PSF) when using an infinite number of low resolution images. A gradient restriction is also derived for maximum likelihood (ML) method. The gradient restriction is presented as an inequality which shows that the power spectrum of the PSF suppresses the spatial frequency component of the gradient of ML cost function. A Box PSF and a Gaussian PSF are analyzed with the SR condition number theorem. Effects of the gradient restriction on super-resolution results are shown using synthetic images.

    researchmap

  • Obstacle detection using millimeter-wave radar and its visualization on image sequence

    Shigeki Sugimoto, Hayato Tateda, Hidekazu Takahashi, Masatoshi Okutomi

    Proceedings - International Conference on Pattern Recognition  2004 

     More details

    Event date: 2004

    Language:English  

    Sensor fusion of millimeter-wave radar and a camera is beneficial for advanced driver assistance functions such as obstacle avoidance and Stop&amp
    Go. However, millimeter-wave radar has low directional resolution which engenders low measurement accuracy of object position and difficulty of calibration between radar and camera. In this paper, we first propose a calibration method between millimeter-wave radar and CCD camera using homography. The proposed method does not require estimation of rotation and translation between them, or intrinsic parameters of the camera. Then, we propose an obstacle detection method which consists of an occupancy-grid representation, and a segmentation technique which divides data acquired by radar into clusters(obstacles)
    thereafter we display them as an image sequence using calibration results. We demonstrate the validity of the proposed methods, through experiments using sensors that are mounted on a vehicle.

    researchmap

  • A LOCALLY ADAPTIVE WINDOW FOR SIGNAL MATCHING

    M OKUTOMI, T KANADE

    THIRD INTERNATIONAL CONFERENCE ON COMPUTER VISION  1990  I E E E, COMPUTER SOC PRESS

     More details

    Event date: 1990

    Language:English  

    researchmap

  • Simultaneous Optimization of Structure and Motion in Dynamic Scenes Using Unsynchronized Stereo Cameras

    IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR2007)  2007 

     More details

    Presentation type:Poster presentation  

    researchmap

  • リアルタイム平面パラメータ計測システム

    第13回画像センシングシンポジウム(SSII2007)  2007 

     More details

  • 実時間動画像超解像処理の実現へ向けて

    第13回画像センシングシンポジウム(SSII2007)  2007 

     More details

  • 透過型リフレクションステレオ -両面ハーフミラー板透過像を使った単眼距離計測-

    第13回画像センシングシンポジウム(SSII2007)  2007 

     More details

  • ステレオ画像からの高速な微小平面3Dサーフェス直接生成法

    第13回画像センシングシンポジウム(SSII2007)  2007 

     More details

  • Fast Plane Parameter Estimation From Stereo Images

    IAPR Conference on Machine Vision Applications (MVA2007)  2007 

     More details

  • Monocular Range Estimation through a Double-Sided Half-Mirror Plate

    Fourth Canadian Conference on Computer and Robot Vision (CRV2007)  2007 

     More details

    Presentation type:Poster presentation  

    researchmap

  • A Footstep-Plan-Based Floor Sensing Method Using Stereo Images for Biped Robot Control

    the 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS2007)  2007 

     More details

  • Microscopic Surface Shape Estimation of a Transparent Plate Using a Complex Image

    8th Asian Conference on Computer Vision (ACCV2007)  2007 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Image Correspondence from Motion Subspace Constraint and Epipolar Constraint

    8th Asian Conference on Computer Vision (ACCV2007)  2007 

     More details

    Presentation type:Poster presentation  

    researchmap

  • カスケード型識別器のキャリブレーションと尤度分布を利用した顔検出

    電子情報通信学会 パターン認識・メディア理解研究会(PRMU)  2007 

     More details

  • ステレオ画像を利用した階段の空間位置推定

    第158回コンピュータビジョンとイメージメディア研究会  2007 

     More details

  • Motion Blur Parameter Identification from a Linearly Blurred Image

    International Conference on Consumer Electronics  2007 

     More details

  • Image Registration Technique for Sequential Images Including Multiple Motion Regions

    3rd TokyoTech-KAIST Joint Workshop for Mechanical Engineering Students in Tokyo  2007 

     More details

  • 非剛体レジストレーションによる時系列画像中の揺らぎ除去

    第157回コンピュータビジョンとイメージメディア研究会  2007 

     More details

  • 非同期ステレオ動画像を用いた動的シーンの位置とモーションの同時推定

    第157回コンピュータビジョンとイメージメディア研究会  2007 

     More details

  • Near-real-time Video-to-video Super-resolution

    8th Asian Conference on Computer Vision (ACCV2007)  2007 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Image Super Resolution and Related Techniques

    2007 

     More details

  • Virtual Focusing Image Synthesis for User-specified Image Region Using Camera Array

    The 19th International Conference on Pattern Recognition (ICPR2008)  2008 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Motion Blur Parameter Identification from a Linearly Blurred Image

    International Conference on Consumer Electronics  2007 

     More details

  • Image Registration Technique for Sequential Images Including Multiple Motion Regions

    3rd TokyoTech-KAIST Joint Workshop for Mechanical Engineering Students in Tokyo  2007 

     More details

  • Distribution-Based Face Detection using Calibrated Boosted Cascade Classifier

    14th International Conference on Image Analysis and Processing (ICIAP2007)  2007 

     More details

  • Image Registration Method of Multiple Motion-Regions and Its Applications

    the second Korean Japan Joint Workshop on Pattern Recognition (KJPR2007)  2007 

     More details

  • Introduction of Our Researches on Super Resolution

    MIRU International Workshop on Computer Vision  2007 

     More details

  • Reconstruction of a High Dynamic Range and High Resolution Image from a Multisampled Image Sequence

    14th International Conference on Image Analysis and Processing (ICIAP2007)  2007 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Simultaneous Optimization of Structure and Motion in Dynamic Scenes Using Unsynchronized Stereo Cameras

    IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR2007)  2007 

     More details

    Presentation type:Poster presentation  

    researchmap

  • A Direct and Efficient Method for Piecewise-Planar Surface Reconstruction from Stereo Images

    IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR2007)  2007 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Fast Plane Parameter Estimation From Stereo Images

    IAPR Conference on Machine Vision Applications (MVA2007)  2007 

     More details

  • Monocular Range Estimation through a Double-Sided Half-Mirror Plate

    Fourth Canadian Conference on Computer and Robot Vision (CRV2007)  2007 

     More details

    Presentation type:Poster presentation  

    researchmap

  • ステレオ時系列画像を用いたロバストかつ高速なモーション推定

    第11回画像の認識・理解シンポジウム(MIRU2008)  2008 

     More details

    Presentation type:Poster presentation  

    researchmap

  • 部分空間に射影したジョイントヒストグラムのエントロピーを用いたカラー画像の色チャンネル間における非剛体レジストレーション

    第11回画像の認識・理解シンポジウム(MIRU2008)  2008 

     More details

  • 非均質なパッチベースMRFのための局所適応的学習

    第11回画像の認識・理解シンポジウム(MIRU2008)  2008 

     More details

  • Locally Adaptive High-Order Markov Random Field Image Priors

    Mathematical Aspects of Image Processing and Computer Vision 2008 (MAIPCV)  2008 

     More details

  • 画像超解像処理

    ビジョン技術の実利用ワークショップ(ViEW2008)  2008 

     More details

  • Robust and Precise Registration for Super-Resolution in the Presence of Multiple Motions

    MIRU International Workshop on Computer Vision 2008 (MIRU-IWCV2008)  2008 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Robust and Accurate Estimation of Multiple Motions for Whole-Image Super-Resolution

    15th IEEE International Conference on Image Processing (ICIP2008)  2008 

     More details

  • Progressive Deconvolution Method with Residual Image

    MIRU International Workshop on Computer Vision 2008 (MIRU-IWCV2008)  2008 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Efficient and Robust Motion Estimation Using Stereo Image Sequence

    MIRU International Workshop on Computer Vision 2008 (MIRU-IWCV2008)  2008 

     More details

    Presentation type:Poster presentation  

    researchmap

  • 超解像処理のための複数モーションに対応したロバストかつ高精度位置合わせ手法

    第11回画像の認識・理解シンポジウム(MIRU2008)  2008 

     More details

    Presentation type:Poster presentation  

    researchmap

  • 25眼カメラを用いたユーザ指定画像領域に対する準実時間仮想焦点画像生成

    第11回画像の認識・理解シンポジウム(MIRU2008)  2008 

     More details

    Presentation type:Poster presentation  

    researchmap

  • High-Uasbility Deblurring Filter

    The 12th Annual IEEE International Symposium on Consumer Electronics (ISCE2008)  2008 

     More details

  • リンギングの発生を抑えたブラー画像復元

    情報処理学会:第163回コンピュータビジョンとイメージメディア研究会  2008 

     More details

  • 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR2007) 報告

    情報処理学会:第161回コンピュータビジョンとイメージメディア研究会  2008 

     More details

  • A Raw Data Compression for Digital Cameras with a Color Filter Array

    IS&T/SPIE 19th Annual Symposium Electronic Imaging (EI2008)  2008 

     More details

  • Calibration and Rectification for Reflection Stereo

    IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR2008)  2008 

     More details

    Presentation type:Poster presentation  

    researchmap

  • リンギングを考慮した漸進的ブラー画像復元

    第11回画像の認識・理解シンポジウム(MIRU2008)  2008 

     More details

  • Locally Adaptive Learning for Translation-Variant MRF Image Priors

    IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR2008)  2008 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Super-Resolution from Image Sequence under Influence of Hot-Air Optical Turbulence

    IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR2008)  2008 

     More details

    Presentation type:Poster presentation  

    researchmap

  • 全自動全画面超解像 --ワンセグ放送への適用--

    第14回画像センシングシンポジウム(SSII2008)  2008 

     More details

  • カメラアレイを利用した任意画像領域に対する仮想焦点画像生成

    第14回画像センシングシンポジウム(SSII2008)  2008 

     More details

  • リフレクションステレオの2重像に対する対応位置探索法

    第14回画像センシングシンポジウム(SSII2008)  2008 

     More details

  • Calibration and Rectification for Reflection Stereo

    IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR2008)  2008 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Locally Adaptive Learning for Translation-Variant MRF Image Priors

    IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR2008)  2008 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Super-Resolution from Image Sequence under Influence of Hot-Air Optical Turbulence

    IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR2008)  2008 

     More details

    Presentation type:Poster presentation  

    researchmap

  • A Raw Data Compression for Digital Cameras with a Color Filter Array

    IS&T/SPIE 19th Annual Symposium Electronic Imaging (EI2008)  2008 

     More details

  • High-Uasbility Deblurring Filter

    The 12th Annual IEEE International Symposium on Consumer Electronics (ISCE2008)  2008 

     More details

  • Locally Adaptive High-Order Markov Random Field Image Priors

    Mathematical Aspects of Image Processing and Computer Vision 2008 (MAIPCV)  2008 

     More details

  • Virtual Focusing Image Synthesis for User-specified Image Region Using Camera Array

    The 19th International Conference on Pattern Recognition (ICPR2008)  2008 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Robust and Precise Registration for Super-Resolution in the Presence of Multiple Motions

    MIRU International Workshop on Computer Vision 2008 (MIRU-IWCV2008)  2008 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Robust and Accurate Estimation of Multiple Motions for Whole-Image Super-Resolution

    15th IEEE International Conference on Image Processing (ICIP2008)  2008 

     More details

  • Progressive Deconvolution Method with Residual Image

    MIRU International Workshop on Computer Vision 2008 (MIRU-IWCV2008)  2008 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Efficient and Robust Motion Estimation Using Stereo Image Sequence

    MIRU International Workshop on Computer Vision 2008 (MIRU-IWCV2008)  2008 

     More details

    Presentation type:Poster presentation  

    researchmap

  • ステレオ動画像を用いた車両の前方環境認識

    第159回コンピュータビジョンとイメージメディア研究会  2007 

     More details

  • 超解像ディスプレイ

    画像電子学会第247回研究会  2009 

     More details

  • Single-Camera Multi-Baseline Stereo using Fish-Eye Lens and Mirrors

    the 9th Asian Conference on Computer Vision (ACCV2009)  2009 

     More details

  • Disparity Estimation in a Layered Image for Reflection Stereo

    the 9th Asian Conference on Computer Vision (ACCV2009)  2009 

     More details

  • Fast and Robust Video Super-Resolution

    The 12th IEEE International Conference on Computer Vision (ICCV2009) (Demo)  2009 

     More details

  • 隣接フレーム間情報に基づく複数枚を利用した高速ビデオ超解像処理

    第12回画像の認識・理解シンポジウム(MIRU2009)  2009 

     More details

  • 魚眼レンズとミラーを使った単眼マルチステレオシステム

    第12回画像の認識・理解シンポジウム(MIRU2009)  2009 

     More details

  • A User-Friendly Method to Geometrically Calibrate Projector-Camera Systems

    IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR2009) Workshop, IEEE International Workshop on Projector-Camera Systems (PROCAMS2009)  2009 

     More details

  • 多重像画像からの原画像の復元と重像間変位推定

    第12回画像の認識・理解シンポジウム(MIRU2009)  2009 

     More details

  • Bootstrap Algorithm for Dynamic Stereo Vision

    IEEE Sixth Workshop on Multidimensional Signal Processing  1989 

     More details

  • A Locally Adaptive Window for Signal Matching

    Proceedings of the Third International Conference on Computer Vision  1990 

     More details

  • Bootstrap Algorithm for Dynamic Stereo Vision

    IEEE Sixth Workshop on Multidimensional Signal Processing  1989 

     More details

  • A Bayesian Foundation for Active Stereo Vision

    Proceedings of SPIE Conference 1198, Sensor Fusion II: Human and Machine Strategies  1989 

     More details

  • 画像処理ワークステーションのためのソフトウェア環境(2) --- 画像メモリの動的管理機構

    情報処理学会第36回全国大会予稿集  1988 

     More details

  • A Bayesian Foundation for Active Stereo Vision

    Proceedings of SPIE Conference 1198, Sensor Fusion II: Human and Machine Strategies  1989 

     More details

  • 導体管壁を持つ電磁流量計

    第20回SICE講演会  1981 

     More details

  • A Stereo Matching Algorithm with an Adaptive Window: Theory and Experiment

    International Conference on Robotics and Automation  1991 

     More details

  • CVPR91会議報告

    情報処理学会コンピュータビジョン研究会  1991 

     More details

  • A Multiple-Baseline Stereo

    IEEE Computer Society Conference on Computer Vision and Pattern Recognition  1991 

     More details

  • 適応型ウィンドウによるステレオマッチングアルゴリズム

    情報処理学会コンピュータビジョン'90シンポジウム論文集  1990 

     More details

  • A Locally Adaptive Window for Signal Matching

    Proceedings of the Third International Conference on Computer Vision  1990 

     More details

  • A Stereo Matching Algorithm with an Adaptive Window: Theory and Experiment

    Proceedings of DARPA Image Understanding Workshop  1990 

     More details

  • カラーステレオマッチングと、その視神経乳頭3次元形状計測への応用

    第22回画像工学コンファレンス論文集  1991 

     More details

  • 視神経乳頭3次元表示画像の動画的呈示による経時変化の観察

    日本眼光学学会予稿集  1991 

     More details

  • A Stereo Matching Algorithm with an Adaptive Window: Theory and Experiment

    Proceedings of DARPA Image Understanding Workshop  1990 

     More details

  • Color Stereo Matching and Its Application to 3-D Measurement of Optic Nerve Head

    the Eleventh IAPR International Conference on Pattern Recognition  1992 

     More details

  • A Multi-Baseline Stereo Method

    DARPA Image Understanding Workshop  1992 

     More details

  • A Stereo Matching Algorithm with an Adaptive Window: Theory and Experiment

    International Conference on Robotics and Automation  1991 

     More details

  • 複数解像度の距離画像を用いた三角形パッチによる物体表面の再構成

    画像工学コンファレンス論文集  1992 

     More details

  • 複数の基線長を利用したステレオマッチング

    電子情報通信学会技術研究報告  1991 

     More details

  • A Multiple-Baseline Stereo

    IEEE Computer Society Conference on Computer Vision and Pattern Recognition  1991 

     More details

  • A Multi-Baseline Stereo Method

    DARPA Image Understanding Workshop  1992 

     More details

  • Surface Reconstruction with Triangular Patches from Multiscale Range Images

    IAPR Workshop on Machine Vision Applications  1992 

     More details

  • Surface Reconstruction with Triangular Patches from Multiscale Range Images

    IAPR Workshop on Machine Vision Applications  1992 

     More details

  • Color Stereo Matching and Its Application to 3-D Measurement of Optic Nerve Head

    the Eleventh IAPR International Conference on Pattern Recognition  1992 

     More details

  • アクティブカメラのズームレンズのキャリブレーションにおけるターゲットと精度

    電子情報通信学会技術研究報告 PRMU97  1997 

     More details

  • GAを用いた表面探索によるステレオ視---1次元信号を用いた解析と実験

    画像の認識・理解シンポジウム講演論文集I  1996 

     More details

  • 重み付投票による回転物体の密な形状復元

    電子情報通信学会1996年総合大会講演論文集 情報・システム2  1996 

     More details

  • 連続写像型ニューラルネットワークを用いた物体の位置推定

    電子情報通信学会技術研究報告  1995 

     More details

  • CVCV-WG 特別報告:コンピュータビジョンにおける技術評論と将来展望(X) --- ステレオ視

    情報処理学会研究報告 96-CVIM-102  1996 

     More details

  • ステレオ画像からの道路平面に対する射影変換行列の導出

    情報処理学会研究報告 97-CVIM-108  1997 

     More details

  • ステレオ画像による道路領域の抽出

    電子情報通信学会 情報・システムソサイエティ大会講演論文集  1997 

     More details

  • 遺伝的アルゴリズムを用いた表面探索によるステレオ視

    情報処理学会第52回全国大会講演論文集(2)  1996 

     More details

  • ステレオ視の新たな展開

    東京工業大学総合研究館講演会予稿集  1997 

     More details

  • マルチベースラインステレオ法による3次元計測

    INTERMAC'93 SICEシンポジウム予稿集  1993 

     More details

  • Extraction of Road Region Using Stereo Images

    Proceedings of the 14th International Conference on Pattern Recognition  1998 

     More details

  • 時系列画像を用いた回転物体の3次元形状復元

    東京工業大学ベンチャービジネスラボラトリー公開シンポジウム98  1998 

     More details

  • 時空間濃淡画像からの重み付投票を用いた回転物体の形状復元法の解析

    情報処理学会第54回全国大会講演論文集(2)  1997 

     More details

  • ズームレンズのキャリブレーションと複数任意倍率画像の統合処理

    情報処理学会第54回全国大会講演論文集(2)  1997 

     More details

  • ステレオ対応度空間内の視差勾配に対する制約を考慮した物体表面再構成

    第4回画像センシングシンポジウム講演論文集  1998 

     More details

  • 時空間濃淡画像からの回転物体の形状復元

    第4回画像センシングシンポジウム講演論文集  1998 

     More details

  • 第14回パターン認識国際会議(ICPR’98)報告

    電子情報通信学会技術研究報告 PRMU98  1998 

     More details

  • イメージベーストボリュームレンダリング --- 多視点画像からの新たな任意視点画像生成の試み

    知能情報メディアシンポジウム  1998 

     More details

  • 表面探索による多眼ステレオ3次元再構成

    第3回画像センシングシンポジウム講演論文集  1997 

     More details

  • アクティブカメラのキャリブレーションとズーム画像の統合

    第3回画像センシングシンポジウム講演論文集  1997 

     More details

  • パン・チルト・ズームカメラの簡易モデルによるキャリブレーション

    電子情報通信学会技術研究報告 PRMU97  1998 

     More details

  • ステレオ3次元画像センシング

    第4回画像センシングシンポジウム  1998 

     More details

  • 焦点はずれ画像の復元パラメータの推定

    電子情報通信学会 総合大会講演論文集 情報・システム2  1998 

     More details

  • 多視点画像からの任意視点画像の非モデル復元型生成

    情報処理学会第56回全国大会講演論文集(2)  1998 

     More details

  • 時空間画像を用いた回転物体の3次元形状復元 --- 透視投影モデルへの拡張

    情報処理学会第58回全国大会講演論文集(4)  1999 

     More details

  • Extraction of Road Region Using Stereo Images

    Proceedings of the 14th International Conference on Pattern Recognition  1998 

     More details

  • ステレオマッチングにおけるウィンドウの及ぼす影響についての検討

    情報処理学会第58回全国大会講演論文集(2)  1999 

     More details

  • キャリブレーションされたパン・チルト・ズームカメラによる複数画像のマッピングとその利用

    第4回画像センシングシンポジウム講演論文集  1998 

     More details

  • 多視点画像からの任意視点画像の非モデル復元型生成法の提案

    第4回画像センシングシンポジウム講演論文集  1998 

     More details

  • ステレオ画像を用いた道路領域の抽出

    第4回画像センシングシンポジウム講演論文集  1998 

     More details

  • 領域ベースステレオマッチングにおけるバウンダリオーバーリーチの解析と定量化

    情報処理学会研究報告 2000-CVIM-123  2000 

     More details

  • Shape Recovery of Rotating Object Using Weighted Voting of Spacio-Temporal Images

    Proceedings of the 15th International Conference on Pattern Recognition: Volume 1: Computer Vision and Image Analysis  2000 

     More details

  • A Statistical Method for Color Object Detection and Application to Localization

    Proceedings of International Conference on Industrial Electronics, Control and Instrumentation  2000 

     More details

  • ステレオ動画像を用いた視覚誘導のための平坦部の連続推定

    情報処理学会研究報告 2000-CVIM-123  2000 

     More details

  • Three-Color Fiducial for Pose Estimation

    Proceedings of the Fourth Asian Conference on Computer Vision  2000 

     More details

  • アクティブカメラによるイメージモザイキング

    第6回画像センシングシンポジウム講演論文集  2000 

     More details

  • 対応度空間のフィルタリングによるステレオマッチングにおける local support の検討

    第5回画像センシングシンポジウム講演論文集  1999 

     More details

  • Parallel Image Processing for Visual Navigation

    Sixth International Conference on Control, Automation, Robotics, and Computer Vision  2000 

     More details

  • 任意視点位置から撮影可能な回転物体の3次元形状復元

    東京工業大学ベンチャービジネスラボラトリー公開シンポジウム99  1999 

     More details

  • 透視投影モデルによる時空間画像を用いた回転物体の3次元形状復元

    第5回画像センシングシンポジウム講演論文集  1999 

     More details

  • 物体境界と滑らかな表面形状を共に復元するステレオビジョンシステム

    東京工業大学ベンチャービジネスラボラトリー公開シンポジウム'00  2000 

     More details

  • Parallel Image Processing for Visual Navigation

    Sixth International Conference on Control, Automation, Robotics, and Computer Vision  2000 

     More details

  • 時系列ステレオ画像を用いた平面領域の連続推定

    情報処理学会第60回全国大会講演論文集  2000 

     More details

  • ビジュアルナビゲーションのための研究開発環境の構築

    情報処理学会第60回全国大会講演論文集(2)  2000 

     More details

  • A Statistical Method for Color Object Detection and Application to Localization

    Proceedings of International Conference on Industrial Electronics, Control and Instrumentation  2000 

     More details

  • 時空間画像を用いた回転物体の表面形状の推定とモデリング

    第6回画像センシングシンポジウム講演論文集  2000 

     More details

  • マルチスレッドを利用したビジュアルナビゲーション研究開発環境

    第5回ロボティクスシンポジア  2000 

     More details

  • ステレオ視におけるテクスチャを考慮した対応評価について

    情報処理学会第60回全国大会講演論文集(2)  2000 

     More details

  • 物体境界と滑らかな表面形状を共に復元するステレオビジョン

    第6回画像センシングシンポジウム講演論文集  2000 

     More details

  • 時系列ステレオ画像を利用した道路領域のロバストな連続推定

    第6回画像センシングシンポジウム講演論文集  2000 

     More details

  • Near-real-time Video-to-video Super-resolution

    8th Asian Conference on Computer Vision (ACCV2007)  2007 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Image Super Resolution and Related Techniques

    2007 

     More details

  • Microscopic Surface Shape Estimation of a Transparent Plate Using a Complex Image

    8th Asian Conference on Computer Vision (ACCV2007)  2007 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Image Correspondence from Motion Subspace Constraint and Epipolar Constraint

    8th Asian Conference on Computer Vision (ACCV2007)  2007 

     More details

    Presentation type:Poster presentation  

    researchmap

  • A Footstep-Plan-Based Floor Sensing Method Using Stereo Images for Biped Robot Control

    the 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS2007)  2007 

     More details

  • Panoramic 3D Reconstruction Using Rotational Stereo Camera with Simple Epipolar Constraints

    IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR2006)  2006 

     More details

    Presentation type:Poster presentation  

    researchmap

  • A Fast MAP-Based Super-Resolution Algorithm for General Motion

    2006 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Ego-Motion Estimation by Matching Dewarped Road Regions Using Stereo Images

    Proceedings of the IEEE International Conference on Robotics and Automation  2006 

     More details

  • 2重反射像を用いた透明板の顕微鏡的表面形状推定

    ビジョン技術の実利用ワークショップ(ViEW2007)  2007 

     More details

  • Similarity-Independent and Non-Iterative Algorithm for Sub-Pixiel Motion Estimation

    Proceedings of SPIE-IS&T Electronic Imaging 2006, Visual Communications and Image Processing 2006  2006 

     More details

  • 非剛体変形を利用した揺らぎ除去と高解像度画像生成

    画像の認識・理解シンポジウム(MIRU2007)  2007 

     More details

  • 両面ハーフミラー板の形状推定によるリフレクションステレオのキャリブレーション

    画像の認識・理解シンポジウム(MIRU2007)  2007 

     More details

  • A Direct and Efficient Method for Piecewise-Planar Surface Reconstruction from Stereo Images

    IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR2007)  2007 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Introduction of Our Researches on Super Resolution

    MIRU International Workshop on Computer Vision  2007 

     More details

  • 複数モーション領域を含む時系列画像の分割レジストレーション

    第6回情報科学技術フォーラム(FIT2007)  2007 

     More details

  • Image Registration Method of Multiple Motion-Regions and Its Applications

    the second Korean Japan Joint Workshop on Pattern Recognition (KJPR2007)  2007 

     More details

  • Reconstruction of a High Dynamic Range and High Resolution Image from a Multisampled Image Sequence

    14th International Conference on Image Analysis and Processing (ICIAP2007)  2007 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Distribution-Based Face Detection using Calibrated Boosted Cascade Classifier

    14th International Conference on Image Analysis and Processing (ICIAP2007)  2007 

     More details

  • 準実時間超解像処理

    画像の認識・理解シンポジウム(MIRU2007)  2007 

     More details

  • 二足歩行ロボットのための歩行計画に基づくステレオ画像センシング

    画像の認識・理解シンポジウム(MIRU2007)  2007 

     More details

  • オクルージョンや明るさ変化にロバストな超解像処理

    第159回コンピュータビジョンとイメージメディア研究会  2007 

     More details

  • インタラクティブなステレオ3次元計測

    第159回コンピュータビジョンとイメージメディア研究会  2007 

     More details

  • 複数枚画像を利用した超解像処理

    第15回 Future of Radiology  2009 

     More details

  • 非均質マルコフ確率場を利用した自然画像のモデル化

    第13回画像の認識・理解シンポジウム(MIRU2010)  2010 

     More details

  • 誰にでもわかる「画像超解像」

    画像センシング展2010  2010 

     More details

  • Egomotion Estimation Using Planar and Non-planar Constraints

    2010 IEEE Intelligent Vehicles Symposium (IV 2010)  2010 

     More details

  • Direct Image Alignment of Projector-Camera Systems with Planar Surfaces

    The 23rd IEEE Conference on Computer Vision and Pattern Recognition (CVPR2010)  2010 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Non-Rigid Registration between Color Channels based on Joint-Histogram Entropy in Subspace

    Second Workshop on Non-Rigid Shape Analysis and Deformable Image Alignment (NORDIA'09)  2009 

     More details

  • 平面を利用した直接法によるカメラキャリブレーション

    情報処理学会第173回コンピュータビジョンとイメージメディア研究会  2010 

     More details

  • A User-Friendly Method to Geometrically Calibrate Projector-Camera Systems

    IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR2009) Workshop, IEEE International Workshop on Projector-Camera Systems (PROCAMS2009)  2009 

     More details

  • Interactive Video Projection on a Moving Planar Surface of Arbitrary Texture Tracked with a Color Camera

    2010 

     More details

  • Progressive MAP-Based Deconvolution with Pixel-Dependent Gaussian Prior

    20th International Conference on Pattern Recognition (ICPR2010)  2010 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Progressive MAP-Based Deconvolution with Pixel-Dependent Gaussian Prior

    20th International Conference on Pattern Recognition (ICPR2010)  2010 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Fast Video Super-Resolution Based on Pixel Information Accumulated from Past Frames

    IIEEJ Image Electronics and Visual Computing Workshop (IEVC2010)  2010 

     More details

  • Egomotion Estimation Using Planar and Non-planar Constraints

    2010 IEEE Intelligent Vehicles Symposium (IV 2010)  2010 

     More details

  • Interactive Video Projection on a Moving Planar Surface of Arbitrary Texture Tracked with a Color Camera

    2010 

     More details

  • 複数フレームを利用したリアルタイムビデオ超解像処理

    第16回画像センシングシンポジウム(SSII2010)  2010 

     More details

  • Image Restoration and Disparity Estimation from an Uncalibrated Multi-Layered Image

    The 23rd IEEE Conference on Computer Vision and Pattern Recognition (CVPR2010)  2010 

     More details

    Presentation type:Poster presentation  

    researchmap

  • 勾配情報と輝度情報に基づくシームレス画像合成

    第16回画像センシングシンポジウム(SSII2010)  2010 

     More details

  • ダイレクトステレオイメージアライメントによる3 次元実時間推定

    第16回画像センシングシンポジウム(SSII2010)  2010 

     More details

  • 勾配情報に基づく画像合成のためのポアソン方程式安定化

    第172回コンピュータビジョンとイメージメディア研究会  2010 

     More details

  • 適応的な多変量正規分布による自然画像の事前確率モデル

    第172回コンピュータビジョンとイメージメディア研究会  2010 

     More details

  • Direct Image Alignment of Projector-Camera Systems with Planar Surfaces

    The 23rd IEEE Conference on Computer Vision and Pattern Recognition (CVPR2010)  2010 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Fast Video Super-Resolution Based on Pixel Information Accumulated from Past Frames

    IIEEJ Image Electronics and Visual Computing Workshop (IEVC2010)  2010 

     More details

  • Image Restoration and Disparity Estimation from an Uncalibrated Multi-Layered Image

    The 23rd IEEE Conference on Computer Vision and Pattern Recognition (CVPR2010)  2010 

     More details

    Presentation type:Poster presentation  

    researchmap

  • 射影変換を利用した特徴点抽出とカメラキャリブレーションへの応用

    情報処理学会第62回全国大会講演論文集(2)  2001 

     More details

  • 射影変換を利用した特徴点抽出処理とカメラキャリブレーション

    第7回画像センシングシンポジウム講演論文集  2001 

     More details

  • ステレオマッチングに基づく奥行き情報を利用したより自然な画像合成

    情報処理学会第62回全国大会講演論文集(2)  2001 

     More details

  • 時系列ステレオ画像を利用した道路領域抽出とその高速化

    情報処理学会第62回全国大会講演論文集(2)  2001 

     More details

  • Three-Color Fiducial for Pose Estimation

    Proceedings of the Fourth Asian Conference on Computer Vision  2000 

     More details

  • Shape Recovery of Rotating Object Using Weighted Voting of Spacio-Temporal Images

    Proceedings of the 15th International Conference on Pattern Recognition: Volume 1: Computer Vision and Image Analysis  2000 

     More details

  • A Simple Stereo Algorithm to Recover Precise Object Boundaries and Smooth Surfaces

    Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition  2001 

     More details

  • A Simple Stereo Algorithm to Recover Precise Object Boundaries and Smooth Surfaces

    Proceedings of IEEE Workshop on Stereo and Multi-Baseline Vision  2001 

     More details

  • 色情報による領域分割を利用したステレオマッチング

    第7回画像センシングシンポジウム講演論文集  2001 

     More details

  • Precise Sub-Pixel Estimation on Area-Based Matching

    Proceedings of the 8th IEEE International Conference on Computer Vision  2001 

     More details

  • Camera Calibration with Precise Extraction of Feature Points Using Projective Transformation

    Proceedings of 2002 IEEE International Conference on Robotics and Automation  2002 

     More details

  • An Analysis of Sub-Pixel Estimation Error on Area-Based Image Matching

    Proceedings of 14th International Conference on Digital Signal Processing  2002 

     More details

  • Robust Estimation of Planar Regions for Visual Navigation Using Sequential Stereo Images

    Proceedings of 2002 IEEE International Conference on Robotics and Automation  2002 

     More details

  • ステレオマッチングと領域分割による正確な物体境界抽出

    情報処理学会第62回全国大会講演論文集(2)  2001 

     More details

  • A Simple Stereo Algorithm to Recover Precise Object Boundaries and Smooth Surfaces

    Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition  2001 

     More details

  • A Simple Stereo Algorithm to Recover Precise Object Boundaries and Smooth Surfaces

    Proceedings of IEEE Workshop on Stereo and Multi-Baseline Vision  2001 

     More details

  • An Analysis of Sub-Pixel Estimation Error on Area-Based Image Matching

    Proceedings of 14th International Conference on Digital Signal Processing  2002 

     More details

  • Precise Sub-Pixel Estimation on Area-Based Matching

    Proceedings of the 8th IEEE International Conference on Computer Vision  2001 

     More details

  • Robust Estimation of Planar Regions for Visual Navigation Using Sequential Stereo Images

    Proceedings of 2002 IEEE International Conference on Robotics and Automation  2002 

     More details

  • Camera Calibration with Precise Extraction of Feature Points Using Projective Transformation

    Proceedings of 2002 IEEE International Conference on Robotics and Automation  2002 

     More details

  • Omnidirectional 3-D Reconstruction Using Stereo Multi-Perspective Panoramas

    In Proceedings of SICE Annual Conference 2004  2004 

     More details

  • Super-Resolution under Image Deformation

    Proceedings of 17th International Conference on Pattern Recognition (ICPR2004)  2004 

     More details

  • Obstacle Detection Using Millimeter-wave Radar and Its Visualization on Image Sequence

    Proceedings of 17th International Conference on Pattern Recognition (ICPR2004)  2004 

     More details

  • Color Super Resolution from a Single-CCD

    Proceedings(CD-ROM) of the IEEE Workshop on Color and Photometric Methods in Computer Vision  2003 

     More details

  • ミリ波レーダとCCDカメラのセンサフュージョンのための キャリブレーションおよび統合表示法

    電気学会研究会資料 ITS研究会  2003 

     More details

  • 単板CCDからの高解像度カラー画像の生成

    情報処理学会研究報告 2003-CVIM-138  2003 

     More details

  • 2次元同時サブピクセル推定法のBayer配列への適用と超解像への応用

    情報処理学会研究報告 2003-CVIM-140  2003 

     More details

  • 再構成型超解像処理の高速化アルゴリズム

    情報処理学会研究報告(コンピュータビジョンとイメージメディア 2004-CVIM-146)  2004 

     More details

  • Color Super Resolution from a Single-CCD

    Proceedings(CD-ROM) of the IEEE Workshop on Color and Photometric Methods in Computer Vision  2003 

     More details

  • ミラー付き回転カメラによる全周3次元再構成

    映像情報メディア学会技術報告  2004 

     More details

  • ステレオ動画像を利用した道路面パターン抽出による自車両の運動推定

    情報処理学会研究報告(コンピュータビジョンとイメージメディア 2004-CVIM-146)  2004 

     More details

  • ステレオマルチパースペクティブパノラマによる全方位3次元再構成

    電子情報通信学会技術研究報告PRMU2004  2004 

     More details

  • Two-Dimensional Simultaneous Sub-Pixel Estimation on Area-Based Image Matching

    Proceedings of Asian Conference on Computer Vision (ACCV2004)  2004 

     More details

  • ステレオ動画像を利用した平面領域抽出による障害物検出

    情報処理学会研究報告2003-CVIM-143  2004 

     More details

  • ミリ波レーダとCCDカメラを利用した障害物検出

    画像の認識・理解シンポジウム(MIRU2004)論文集I  2004 

     More details

  • 画像間モーションパラメータ同時推定法と超解像への応用

    第7回画像の認識・理解シンポジウム(MIRU2004)論文集  2004 

     More details

  • 単板CCD画像データからのダイレクトカラースーパーレゾリューション

    第10回画像センシングシンポジウム(SSII2004)講演論文集  2004 

     More details

  • Precise Simultaneous Estimation of Image Deformation Parameters

    Second IEEE Workshop on Image and Video Registration  2004 

     More details

  • ミリ波レーダとCCDカメラを利用した障害物検出

    電子情報通信学会2004年総合大会講演論文集  2004 

     More details

  • Direct Super-Resolution and Registration Using Raw CFA Images

    Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR2004)  2004 

     More details

  • 2次元サブピクセル同時推定法を拡張した画像変形Nパラメータ同時推定法

    情報処理学会研究報告2003-CVIM-143  2004 

     More details

  • ミラーにより視野分割された回転カメラを利用した全方位3次元再構成

    電子情報通信学会2004年総合大会講演論文集  2004 

     More details

  • ステレオ画像を利用した平面姿勢推定手法と多眼カメラへの拡張

    情報処理学会研究報告(コンピュータビジョンとイメージメディア 2005-CVIM-151)  2005 

     More details

  • Panoramic 3D Reconstruction Using Rotating Camera with Planar Mirrors

    2005 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Region Extraction and Tracking of Moving Objects in Image Sequence

    Proceedings of 1st Tokyo Tech.-POSTECH-KNU Joint Workshop on Mechanical Engineering  2005 

     More details

  • Super-Resolution under Image Deformation

    Proceedings of 17th International Conference on Pattern Recognition (ICPR2004)  2004 

     More details

  • Obstacle Detection Using Millimeter-wave Radar and Its Visualization on Image Sequence

    Proceedings of 17th International Conference on Pattern Recognition (ICPR2004)  2004 

     More details

  • Precise Simultaneous Estimation of Image Deformation Parameters

    Second IEEE Workshop on Image and Video Registration  2004 

     More details

  • Omnidirectional 3-D Reconstruction Using Stereo Multi-Perspective Panoramas

    In Proceedings of SICE Annual Conference 2004  2004 

     More details

  • Direct Super-Resolution and Registration Using Raw CFA Images

    Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR2004)  2004 

     More details

  • Direct Color Super-Resolution from Bayer CFA Data

    2004 

     More details

  • Two-Dimensional Simultaneous Sub-Pixel Estimation on Area-Based Image Matching

    Proceedings of Asian Conference on Computer Vision (ACCV2004)  2004 

     More details

  • ステレオ画像を用いた画像の品質と奥行き推定精度の同時改善

    情報処理学会研究報告(コンピュータビジョンとイメージメディア 2005-CVIM-149)  2005 

     More details

  • ステレオ画像を用いた道路シーン中の直線の抽出と識別

    情報処理学会研究報告(コンピュータビジョンとイメージメディア 2005-CVIM-149)  2005 

     More details

  • 全方位3次元カメラシステム

    東京工業大学ベンチャー・ビジネス・ラボラトリー シンポジウム2004  2005 

     More details

  • 直線的手ぶれ画像復元のためのPSFパラメータ推定手法

    情報処理学会研究報告(コンピュータビジョンとイメージメディア 2005-CVIM-149)  2005 

     More details

  • 平面の検出・姿勢推定を利用した一般道路環境下におけるロバストな障害物検出

    電子情報通信学会技術研究報告(ITS2005)  2005 

     More details

  • 条件数に基づく近傍画素混合の設計

    電子情報通信学会技術研究報告 (パターン認識・メディア理解研究会(PRMU2005))  2005 

     More details

  • 手持ちカメラによる高速カラー超解像処理

    画像の認識・理解シンポジウム(MIRU2005)  2005 

     More details

  • Color Super-Resolution using Hand-Held Camera

    Proceedings of SICE Annual Conference 2005  2005 

     More details

  • 高速超解像処理システムの実現

    第11回画像センシングシンポジウム(SSII2005)講演論文集  2005 

     More details

  • 周波数領域最適化法によるMAP型超解像処理の高速化

    画像の認識・理解シンポジウム(MIRU2005)  2005 

     More details

  • Theoretical Analysis on Reconstruction-Based Super-Resolution for an Arbitrary PSF

    2005 

     More details

    Presentation type:Poster presentation  

    researchmap

  • カーネル回帰に基づくカラー画像補間

    第168回コンピュータビジョンとイメージメディア研究会  2009 

     More details

  • Non-Rigid Registration between Color Channels based on Joint-Histogram Entropy in Subspace

    Second Workshop on Non-Rigid Shape Analysis and Deformable Image Alignment (NORDIA'09)  2009 

     More details

  • 複数枚を利用した実時間ビデオ超解像処理システムの実現

    第12回画像の認識・理解シンポジウム(MIRU2009)  2009 

     More details

  • ステレオ時系列画像を用いた直接法による実時間モーション推定

    第12回画像の認識・理解シンポジウム(MIRU2009)  2009 

     More details

  • バイラテラルフィルタとノンローカルミーンフィルタの隠された意味とその発展へ向けて

    第12回画像の認識・理解シンポジウム(MIRU2009)  2009 

     More details

  • グラフカットを利用したステレオ画像からの平面領域抽出

    第12回画像の認識・理解シンポジウム(MIRU2009)  2009 

     More details

  • サンプリングした画素を用いた勾配法による画像位置合わせの高精度化

    第13回画像の認識・理解シンポジウム(MIRU2010)  2010 

     More details

  • Raw dataを復号可能なJPEGデータの生成方法 -- 新しいRaw data圧縮 --

    第156回コンピュータビジョンとイメージメディア研究会  2006 

     More details

  • 部分空間拘束とエピポーラ拘束を利用した2組の時系列画像における画像間対応推定

    第156回コンピュータビジョンとイメージメディア研究会  2006 

     More details

  • 撮影位置の異なる複数の画像を用いた高解像仮想焦点面画像生成

    第156回コンピュータビジョンとイメージメディア研究会  2006 

     More details

  • ステレオ画像からの直接的かつ高速な微小平面3Dサーフェス生成法

    第156回コンピュータビジョンとイメージメディア研究会  2006 

     More details

  • 画像のレジストレーションにおける同時推定法の高速化手法

    情報処理学会研究報告(コンピュータビジョンとイメージメディア 2005-CVIM-147)  2005 

     More details

  • 再構成型超解像処理の理論限界に関する検討

    情報処理学会研究報告(コンピュータビジョンとイメージメディア 2005-CVIM-147)  2005 

     More details

  • Panoramic 3D Reconstruction Using Rotating Camera with Planar Mirrors

    2005 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Region Extraction and Tracking of Moving Objects in Image Sequence

    Proceedings of 1st Tokyo Tech.-POSTECH-KNU Joint Workshop on Mechanical Engineering  2005 

     More details

  • Theoretical Analysis on Reconstruction-Based Super-Resolution for an Arbitrary PSF

    2005 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Color Super-Resolution using Hand-Held Camera

    Proceedings of SICE Annual Conference 2005  2005 

     More details

  • ステレオ動画像を用いた動的シーンのモーションと奥行きの同時推定

    画像の認識・理解シンポジウム(MIRU2006)  2006 

     More details

  • 組合せ画素混合を利用した超解像処理

    画像の認識・理解シンポジウム(MIRU2006)  2006 

     More details

  • Reflection Stereo -- Novel Monocular Stereo using a Transparent Plate --

    Proceedings of Third Canadian Conference on Computer and Robot Vision (CRV2006)  2006 

     More details

  • Robust Obstacle Detection in General Road Environment Based on Road Extraction and Pose Estimation

    2006 

     More details

    Presentation type:Poster presentation  

    researchmap

  • 道路面の抽出・姿勢推定に基づく一般道路環境下におけるロバストな障害物検出

    第12回画像センシングシンポジウム(SSII2006)予稿集  2006 

     More details

  • 近傍画素混合~高解像度な画素混合手法~

    第12回画像センシングシンポジウム(SSII2006)予稿集  2006 

     More details

  • Super-Resolution Using a Multi-Mixture Imaging System

    International Conference on Image Processing (ICIP2006)  2006 

     More details

  • Spatial Merging for Face Detection

    SICE-ICASE International Joint Conference 2006 (SICE-ICCAS)  2006 

     More details

  • Neighbor Pixel Mixture

    the 18th International Conference on Pattern Recognition  2006 

     More details

    Presentation type:Poster presentation  

    researchmap

  • 顔らしさ分布を利用した顔検出手法

    情報処理学会研究報告(コンピュータビジョンとイメージメディア 2006-CVIM-155)  2006 

     More details

  • Robust and Accurate Image Registration with Pixel Selection

    the 6th IEEE International Symposium on Signal Processing and Information Technology (ISSPIT2006)  2006 

     More details

  • 組合せ画素混合と超解像処理への応用

    情報処理学会研究報告(コンピュータビジョンとイメージメディア 2006-CVIM-153)  2006 

     More details

  • A Fast MAP-Based Super-Resolution Algorithm for General Motion

    2006 

     More details

    Presentation type:Poster presentation  

    researchmap

  • 透明板の透過と反射による多重像を用いた1台のカメラによる距離計測手法の研究

    2005年度東京工業大学ベンチャー・ビジネス・ラボラトリー シンポジウム  2006 

     More details

  • Spatial Merging for Face Detection

    SICE-ICASE International Joint Conference 2006 (SICE-ICCAS)  2006 

     More details

  • Similarity-Independent and Non-Iterative Algorithm for Sub-Pixiel Motion Estimation

    Proceedings of SPIE-IS&T Electronic Imaging 2006, Visual Communications and Image Processing 2006  2006 

     More details

  • Neighbor Pixel Mixture

    the 18th International Conference on Pattern Recognition  2006 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Super-Resolution Using a Multi-Mixture Imaging System

    International Conference on Image Processing (ICIP2006)  2006 

     More details

  • Panoramic 3D Reconstruction Using Rotational Stereo Camera with Simple Epipolar Constraints

    IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR2006)  2006 

     More details

    Presentation type:Poster presentation  

    researchmap

  • 直線的手ぶれ画像からの画像復元

    第12回画像センシングシンポジウム(SSII2006)予稿集  2006 

     More details

  • ヒューマンフレンドリーな復元フィルタの提案

    情報処理学会研究報告(コンピュータビジョンとイメージメディア 2006-CVIM-153)  2006 

     More details

  • Ego-Motion Estimation by Matching Dewarped Road Regions Using Stereo Images

    Proceedings of the IEEE International Conference on Robotics and Automation  2006 

     More details

  • Robust Obstacle Detection in General Road Environment Based on Road Extraction and Pose Estimation

    2006 

     More details

    Presentation type:Poster presentation  

    researchmap

  • Robust and Accurate Image Registration with Pixel Selection

    the 6th IEEE International Symposium on Signal Processing and Information Technology (ISSPIT2006)  2006 

     More details

  • Reflection Stereo -- Novel Monocular Stereo using a Transparent Plate --

    Proceedings of Third Canadian Conference on Computer and Robot Vision (CRV2006)  2006 

     More details

  • 画像超解像処理の最新技術

    第3回新画像システム・情報フォトニクス研究討論会  2009 

     More details

  • 多眼ステレオカメラを用いた直接法による全周サーフェス生成

    第167回コンピュータビジョンとイメージメディア研究会  2009 

     More details

  • Disparity Estimation in a Layered Image for Reflection Stereo

    the 9th Asian Conference on Computer Vision (ACCV2009)  2009 

     More details

  • 複数枚の画像を利用した超解像処理技術

    映像情報メディア学会メディア工学シンポジウム  2009 

     More details

  • Fast and Robust Video Super-Resolution

    The 12th IEEE International Conference on Computer Vision (ICCV2009) (Demo)  2009 

     More details

  • Single-Camera Multi-Baseline Stereo using Fish-Eye Lens and Mirrors

    the 9th Asian Conference on Computer Vision (ACCV2009)  2009 

     More details

  • 超広角撮影の周辺視野を使った単眼高精度マルチステレオシステム

    第15回画像センシングシンポジウム(SSII2009)  2009 

     More details

  • 実時間動画像超解像処理システム

    第15回画像センシングシンポジウム(SSII2009)  2009 

     More details

    Presentation type:Poster presentation  

    researchmap

  • 未校正2重反射画像からの3次元計測

    第167回コンピュータビジョンとイメージメディア研究会  2009 

     More details

  • 複数画像からの「超」解像技術

    第15回画像センシングシンポジウム(SSII2009)  2009 

     More details

▼display all

Works

  • 高解像画像生成技術の研究

    2005 - 2006

     More details

    Work type:Artistic work  

    researchmap

  • 走路・障害物を検出する画像処理技術の共同研究

    2005

     More details

    Work type:Artistic work  

    researchmap

  • 道路環境認識のための画像処理技術の研究

    2003 - 2004

     More details

    Work type:Artistic work  

    researchmap

  • デジタル画像の超解像度化手法とその応用システムの開発

    2003

     More details

    Work type:Artistic work  

    researchmap

  • レーダの信号処理アルゴリズムの研究

    2002 - 2003

     More details

    Work type:Artistic work  

    researchmap

Awards

  • 東京都功労者表彰(技術振興功労)

    2021.10  

     More details

  • 第26回画像センシングシンポジウム(SSII2020) 最優秀学術賞

    2021.6  

    李 淳雨, 紋野雄介, 日高宏紀, 奥富正敏

     More details

  • 第25回画像センシングシンポジウム(SSII2019) 優秀学術賞

    2020.6  

    田平創, Torsten Sattler, Josef Sivic, Tomas Pajdla, 鳥居秋彦, 奥富正敏

     More details

  • 第26回画像センシングシンポジウム(SSII2020) オーディエンス賞

    2020.6  

    遠藤和紀, 田中正行, 奥富正敏

     More details

  • 第35回電気通信普及財団賞(テレコムシステム技術賞)

    2020.3  

    紋野雄介, 寺中駿人, 吉崎和徳, 田中正行, 奥富正敏

     More details

  • 第25回画像センシングシンポジウム(SSII2019) オーディエンス賞

    2019.6  

    田平創, Torsten Sattler, Josef Sivic, Tomas Pajdla, 鳥居秋彦, 奥富正敏

     More details

  • 第24回画像センシングシンポジウム(SSII2018) オーディエンス賞

    2018.6  

    李淳雨, 鳥居秋彦, 奥富正敏

     More details

  • 日本機械学会賞(論文)

    2018.4  

    竹内彰, 藤井浩光, 山下淳, 田中正行, 片岡龍峰, 三好由純, 奥富正敏, 淺間一

     More details

  • 計測自動制御学会 システムインテグレーション部門 部門研究奨励賞

    2017.12  

    竹内彰, 藤井浩光, 山下淳, 田中正行, 片岡龍峰, 三好由純, 奥富正敏, 淺間一

     More details

  • 第2回 IEEE Signal Processing Society (SPS) Japan Best Paper Award

    2017.11  

    紋野雄介, 菊地直, 田中正行, 奥富正敏

     More details

  • 第23回画像センシングシンポジウム(SSII2017) オーディエンス賞

    2017.6  

    鳥居秋彦, 金杞昌, 奥富正敏

     More details

  • 第22回画像センシングシンポジウム(SSII2016) 優秀学術賞

    2017.6  

    石黒耀, 井上優希, 杉本茂樹, 鳥居秋彦, 奥富正敏

     More details

  • 動的画像処理実利用化ワークショップ(DIA2017) 研究奨励賞

    2017.3  

    柴田剛志, 田中正行, 奥富正敏

     More details

  • 第1回 IEEE Signal Processing Society (SPS) Japan Best Paper Award

    2016.11  

    劉新豪, 田中正行, 奥富正敏

     More details

  • 第22回画像センシングシンポジウム(SSII2016) オーディエンス賞

    2016.6  

    石黒耀, 井上優希, 杉本茂樹, 鳥居秋彦, 奥富正敏

     More details

  • International Conference on Advanced Mechatronics (ICAM2015), ICAM 2015 Honorable Mention

    2015.12  

    今野洋佑, 紋野雄介, 禧久大輔, 田中正行, 奥富正敏

     More details

  • 情報処理学会論文賞 (2014年度)

    2015.6  

    Rafael Henrique Castanheira de Souza, 奥富正敏, 鳥居秋彦

     More details

  • 第20回画像センシングシンポジウム 優秀学術賞

    2015.6  

    速水健人, 田中正行, 奥富正敏, 柴田剛志, 仙田修司

     More details

  • 第20回画像センシングシンポジウム(SSII2014) デモンストレーション賞

    2014.6  

    菊地 直,吉崎和徳,小宮康宏,紋野雄介,金 昌熙,田中正行,奥富正敏

     More details

  • 画像センシング技術研究会 感謝状

    2014.6  

     More details

  • 第20回画像センシングシンポジウム(SSII2014) 高木賞

    2014.6  

    奥富正敏, 田中正行, 後藤知将, 清水雅夫, 矢口陽一, 魏 大比

     More details

  • 第19回画像センシングシンポジウム 優秀学術賞

    2014.6  

    鳥居秋彦, 杉浦貴行, 阿達大地, 奥富正敏

     More details

  • 第14回計測自動制御学会システムインテグレーション部門 講演会(SI2013)SI2013優秀講演賞

    2013.12  

    久保 尭之, 山下 淳, 田中 正行, 片岡 龍峰, 三好 由純, 奥富 正敏, 淺間 一

     More details

  • 第19回画像センシングシンポジウム(SSII2013) オーディエンス賞

    2013.6  

    鳥居秋彦, 杉浦貴行, 阿達大地, 奥富正敏

     More details

  • 第18回画像センシングシンポジウム(SSII2012) デモンストレーション賞

    2012.6  

    鳥居秋彦, 半澤悠樹, 金杞昌, 阿達大地, 杉本茂樹, 奥富正敏

     More details

  • 第15回画像センシングシンポジウム最優秀学術賞

    2010  

     More details

    Country:Japan

    researchmap

  • 画像電子学会優秀論文賞

    2010  

     More details

    Country:Japan

    researchmap

  • 第15回画像センシングシンポジウムオーディエンス賞

    2009  

     More details

    Country:Japan

    researchmap

  • 手島記念研究賞(発明賞)

    2009  

     More details

    Country:Japan

    researchmap

  • 第14回画像センシングシンポジウム優秀学術賞

    2009  

     More details

    Country:Japan

    researchmap

  • 第14回画像センシングシンポジウムオーディエンス賞

    2008  

     More details

    Country:Japan

    researchmap

  • 映像情報メディア学会誌3月号ベストオーサー

    2008  

     More details

    Country:Japan

    researchmap

  • 第12回画像センシングシンポジウム優秀論文賞

    2007  

     More details

    Country:Japan

    researchmap

  • 第10回画像の認識・理解シンポジウム優秀論文賞

    2007  

     More details

    Country:Japan

    researchmap

  • 第11回画像センシングシンポジウム論文賞

    2006  

     More details

    Country:Japan

    researchmap

  • 第9回画像の認識・理解シンポジウムインタラクティブセッション優秀賞

    2006  

     More details

    Country:Japan

    researchmap

  • 第10回画像センシングシンポジウム論文賞

    2005  

     More details

    Country:Japan

    researchmap

  • 手島記念研究賞(発明賞)

    2005  

     More details

    Country:Japan

    researchmap

  • 画像の認識・理解シンポジウムMIRU長尾賞(最優秀論文賞)

    2005  

     More details

    Country:Japan

    researchmap

  • 情報処理学会論文賞

    2005  

     More details

    Country:Japan

    researchmap

  • 第7回画像センシングシンポジウム論文賞

    2002  

     More details

    Country:Japan

    researchmap

  • 情報処理学会 山下記念研究賞

    2001  

     More details

    Country:Japan

    researchmap

  • 第4回画像センシングシンポジウム論文賞

    1999  

     More details

    Country:Japan

    researchmap

▼display all

Research Projects

  • Detailed 3D Reconstruction of Whole Environment Including Shape, Illumination, and Reflectance

    Grant number:17H00744  2017.4 - 2021.3

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research (A)

    Okutomi Masatoshi

      More details

    Grant amount:\44330000 ( Direct Cost: \34100000 、 Indirect Cost:\10230000 )

    In this study, we have developed novel multi-view inverse rendering (MVIR) methods called Spectral MVIR and Polarimetric MVIR, where detailed 3D shape, illumination, and reflectance of the scene can be estimated simultaneously from multi-view input images.
    Spectral MVIR enables us to estimate detailed 3D shape and precise spectral reflectance of the scene using an off-the-shelf LED bulb/projector and a standard RGB camera. Polarimetric MVIR enables us to acquire more detailed 3D shape compared with standard MVIR by exploiting the polarization information of reflected light obtained using a polarization camera.
    These achievements have been published in major journals or conferences, such as The Visual Computer, ECCV, and ICCP.

    researchmap

  • Vision-Based Online 3D Modeling with Visual Feedbacks

    Grant number:25240025  2013.4 - 2016.3

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research (A)

    Okutomi Masatoshi, Shimizu Masao, Torii Akihiko, Sugimoto Shigeki

      More details

    Grant amount:\46410000 ( Direct Cost: \35700000 、 Indirect Cost:\10710000 )

    We have developed an incremental tetrahedra carving algorithm, where the tetrahedra-carving-based surface extraction algorithm was extended to the incremental fashion by efficiently detecting ray-tetrahedra intersections and the dynamic graph cut. Then we have built an online 3D modeling system using aerial images, where the user can immediately confirm the 3D model updated by the aerial images captured by the camera mounted on a drone operated by remote control. In addition, we have developed a method for refining the 3D model estimated by the online 3D modeling system, where we estimate not only 3D surface parameters but also illumination parameters and surface albedo. These achievements have been awarded the SSII Audience prize and Academic prize at SSII2013, and the SSII Audience prize at SSII2016.

    researchmap

  • Precise 3D Measurement of Aurora Using Fish-Eye Stereo Camera

    Grant number:25540114  2013.4 - 2015.3

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research  Grant-in-Aid for Challenging Exploratory Research

    YAMASHITA Atsushi, TANAKA Masayuki, KATAOKA Ryuho, MIYOSHI Yoshizumi, OKUTOMI Masatoshi, ASAMA Hajime

      More details

    Grant amount:\3770000 ( Direct Cost: \2900000 、 Indirect Cost:\870000 )

    In this study, a methodology for 3D measurement and visualization of aurora were proposed. To analyze auroras, two fish-eye cameras were set in Poker Flat Research Range, Alaska, USA. The feature points were detected from a pair of images captured by fish-eye cameras, the three-dimensional points were triangulated, and 3D aurora shapes were visualized in 3D space.

    researchmap

  • Real-time Progressive Surface Generation

    Grant number:21240015  2009 - 2012

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research (A)

    OKUTOMI Masatoshi, SHIMIZU Masao, TORII Akihiko

      More details

    Grant amount:\46150000 ( Direct Cost: \35500000 、 Indirect Cost:\10650000 )

    We developed a progressive surface generation technique using stereo image sequences, based on the development of a method for simultaneously estimating a surface and inter-frame camera motion. Several component techniques, including stereo surface reconstruction and simultaneous estimation of plane parameters and inter-frame motion, were implemented into real-time demonstration systems. We also developed a method for progressively generating a surface from the camera positions and 3D point clouds obtained by an incremental Structure from Motion technique, enabling us to confirm in real-time the surface reconstruction result at every picture-taken time instance while taking pictures. We won the best demonstration prize in SSII2012 on the latter demonstration system.

    researchmap

  • Real-time Reflection Stereo

    Grant number:19300057  2007 - 2008

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research (B)

    SHIMIZU Masao, OKUTOMI Masatosi

      More details

    Grant amount:\19110000 ( Direct Cost: \14700000 、 Indirect Cost:\4410000 )

    researchmap

  • 3-D Reconstruction by Using Arrayd Cameras

    Grant number:08650481  1996 - 1997

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research (C)

    OKUTOMI Masatoshi

      More details

    Grant amount:\2200000 ( Direct Cost: \2200000 )

    (a) We introduced a new data structure, "stereo DOC (Degree of Correspondence) space", in order to integrate the image information obtained from multiple cameras and to extract 3-D structure robustly.
    (b) We investigated the characteristics of the stereo DOC space and the constraints which an actual object surface must satisfy.
    (c) We introduced the following two methods to search the object surface in the stereo DOC space.
    ・A method to obtain the 3-D surface model directly which consists of arbitrary-shaped trianglar patches using a genetic algorithm (GA)
    ・A method to identify the planes which correspond to the object surfaces and the borders of the planes using Hough transform
    (d) We showed the effectiveness and the current problems of the obove methods by the experiments using synthesized and real images.
    (e) Based on the obove results, we proposed a method to generate a virtual camera image with an arbitrary point of view using multiple real images.
    (f) As another application, we proposed a method to detect road regions in the observed image for visual navigation of an autonomous land vehicle.
    (g) Also, we made a technical survey for stereo methods.

    researchmap

  • Color Super-Resolution

      More details

    Grant type:Competitive

    researchmap

  • 3-D Reconstraction Using Multi-Viewpoint Images and Its Applications

      More details

    Grant type:Competitive

    researchmap

  • 自律移動車のための視覚誘導

      More details

    Grant type:Competitive

    researchmap

  • カラースーパーレゾリューション

      More details

    Grant type:Competitive

    researchmap

  • 多視点画像からの3次元復元とその応用

      More details

    Grant type:Competitive

    researchmap

  • Visual Navigation for Autonomous Vehicle

      More details

    Grant type:Competitive

    researchmap

▼display all