KINDAI UNIVERSITY


*A space between the first name and last name, please enter

HABE Hitoshi

Profile

FacultyDepartment of Informatics / Graduate School of Science and Engineering Research
PositionAssociate Professor
DegreeDoctor of Informatics (Kyoto Uni
Commentator Guidehttps://www.kindai.ac.jp/meikan/473-habe-hitoshi.html
URLhttp://www.habe-lab.org/habe/
Mail
Last Updated :2020/09/30

Education and Career

Education

  •   1993 04  - 1997 03 , Kyoto University, Faculty of Engineering
  •   1997 04  - 1999 03 , Kyoto University, Graduate School of Engineering

Academic & Professional Experience

  •   2018 04 ,  - 現在, Associate Professor, Department of Informatics, Faculty of Engineering, Kindai University
  •   2012 04 ,  - 2018 03 , Lecturer, Dept. of Informatics, School of Engineering, Kinki University
  •   2011 12 ,  - 2012 03 , Specially Appointed Associate Professor, ISIR, Osaka University
  •   2007 04 ,  - 2011 11 , Assistant Professor, NAIST
  •   2010 03 ,  - 2011 02 , Visiting Scholar, Dept. of Engineering, University of Cambridge
  •   2006 12 ,  - 2007 03 , Assistant Professor, NAIST
  •   2003 04 ,  - 2006 11 , Assistant Professor, Graduate School of Engineering, Kyoto University
  •   2002 07 ,  - 2003 03 , Assistant Professor, ACMMS, Kyoto University
  •   1999 04 ,  - 2002 07 , Mitsubishi Electric

Research Activities

Research Areas

  • Informatics, Information networks
  • Informatics, Computer systems
  • Informatics, Intelligent informatics
  • Informatics, Intelligent robotics
  • Informatics, Perceptual information processing

Published Papers

  • Video scene detection of burst swimming by fry of farmed-raised bluefin tuna, Koji Abe, Masaru Tanaka, Hitoshi Habe, Yoshiaki Taniguchi, Nobukazu Iguchi, Proceedigns of ICFSP 2018, Proceedigns of ICFSP 2018, 105 - 109, Sep. 2018 , Refereed
  • Depth Error Correction for Projector-Camera Based Consumer Depth Camera, Hirotake Yamazoe, Hitoshi Habe, Ikuhisa Mitsugami, Yasushi Yagi, Computational Visual Media, Computational Visual Media, 4(2), 1 - 9, Mar. 14 2018 , Refereed
  • Multiple fish tracking with an NACA airfoil model for collective behavior analysis, Kei Terayama, Hitoshi Habe, Masa-aki Sakagami, IPSJ Transaction on Computer Vision and Applications, IPSJ Transaction on Computer Vision and Applications, 8(4), Aug. 2016 , Refereed
    Summary:We propose a visual tracking method with an NACA airfoil model for dense fish schools in which occlusions occur frequently. Although much progress has been made for tracking multiple objects, it remains a challenging task to track individuals due to factors such as occlusion and target appearance variation. In this paper, we first introduce a NACA airfoil model as a deformable appearance model of fish. For occluded fish, we estimate their positions, angles, and postures with template matching and simulated annealing algorithms to effectively optimize their parameters. To improve performance of tracking, we repeatedly track fish with the parameter estimation algorithm forwards and backwards. We prepared two real fish scenes in which the average number of fish is over 25 in each frame and multiple fish superimpose over 50 times. Experimental results for the scenes show that fish are practically tracked with our method compared to a tracking method based on a mixture particle filter. Over 75 % of fish in each scene have been tracked throughout the scene, and the average difference is less than 4 % of the mean body length of the school.
  • Foreground Extraction by Pseudo-synchronization of Camera and Range Sensor(Real World Imaging), Nakajima Hozuma, Mitsugami Ikuhisa, Yamazoe Hirotake, Habe Hitoshi, Makihara Yasushi, Yagi Yasushi, Transactions of the Virtual Reality Society of Japan, Transactions of the Virtual Reality Society of Japan, 17(3), 209 - 217, Sep. 2012 , Refereed
    Summary:Existing background subtraction methods often fail to extract a foreground region whose color is similar to that of the background. When we use a co-located camera and range sensor, by which we can obtain both a color image and depth map simultaneously, it is expected to get a better foreground region by integrating the two kind of images. However, it is not straightforward when a moving object is observed because the camera and range sensor do not capture the scene synchronously. In this paper, we propose a novel method that pseudo-synchronize the camera and range sensor and integrate the ...
  • Video Analysis for Generating Informative Composite Image of Target Object, Hitoshi Habe, Shota Makiyama, Masatsugu Kidode, The transactions of the Institute of Electrical Engineers of Japan, The transactions of the Institute of Electrical Engineers of Japan, 131(4), 557 - 564, Apr. 2011 , Refereed
  • Distortion Compensation of Light Reflection on Concave Screen Based on Image-Based Light Transport, HABE Hitoshi, SAEKI Nobuo, MATSUYAMA Takashi, The IEICE transactions on information and systems (Japanese edetion), The IEICE transactions on information and systems (Japanese edetion), 91(11), 2684 - 2695, Nov. 01 2008
    Summary:没入型投影ディスプレイシステムなどで用いられる凹面スクリーン上に映像を投影したとき,相互反射や表面反射特性の影響で,入力された映像の明暗パターンがひずんで鑑賞者へ提示される.本論文では,これらの影響を補償し意図する映像を忠実に再現する手法を提案する.原理的には,プロジェクタ(光源)からスクリーン,鑑賞者とたどるライトトランスポートを求め,その逆変換を施すことで反射ひずみ補償が達成され,いくつかの例が提案されている.しかし,それらは本来面積をもった画素同士の対応であるライトトランスポートを,点同士の対応関係として近似的に定式化しているため,近似誤差によって反射ひずみを正しく補償できない場合がある.提案手法は,単純な点対応で生じる,単位入射光を投影したときの直接反射と相互反射の境界部分の急激な明度変化が観測できないという問題に対し,プロジェクタとカメラの間の幾何的対応関係をとり,幾何変換を行った上でライトトランスポートを求める.これにより,凹面スクリーンの幾何形状に応じたコンパクトなライトトランスポートで反射ひずみ補償が可能となった.
  • 3D Information Measuring Using Multiple Illuminations, HABE Hitoshi, SHIROUZU Kensuke, KOBAYASHI Toshihiko, MATSUYAMA Takashi, The IEICE transactions on information and systems (Japanese edetion), The IEICE transactions on information and systems (Japanese edetion), 89(9), 2065 - 2074, Sep. 01 2006
    Summary:画像計測において,単独の画像では得られない情報を補う手法として,多重画像の利用が広く行われている.その中で,本論文では多重光源画像を用いた2種類の画像計測手法を提案する.多重光源画像を用いた従来手法では,正確な形状計測を行うため,表面の反射特性の厳密なモデル化や大掛りな装置が必要とされており,実環境への適用は容易ではない.それに対し本論文では,精密なモデルを用いず,多重光源画像での明度変化に着目して計測対象の大まかな三次元情報を計測する手法を提案する.まず第一の手法では,光源位置を変化させたときの画素値の変化からトンネル壁画のひび割れを検出する.第二の手法では,鉄道道床でのステレオマッチングの精度を向上させるために,様々な方向から照明を照射した画像を統合して利用する.本論文ではこれらの手法の原理及びアルゴリズムを述べ,実画像を用いた実験でその有効性を示す.
  • Skin-off: Texture-oriented 2-D plane mapping for 3-D video compression, Yosuke Katsura, Hitoshi Habe, Takashi Matsuyama, Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers, Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers, 60(4), 553 - 560, Apr. 2006
    Summary:3-D video records dynamic 3-D visual events as is. Applications of 3-D video include wide varieties of human activities. For promoting these applications in everyday life, a standardized compression scheme for 3-D video is required. We developed a practical and effective scheme for representing and compressing 3-D video named "skin-off," in which both the geometric and visual information are efficiently represented by cutting a 3-D mesh and mapping it onto a 2-D array. Skin-off has much in common with geometry images proposed by Gu et al. However, while geometry images use only 3-D surface shape information to generate 2-D images, skin-off uses both 3-D shape and texture information to generate them. This enables us to achieve higher image quality with limited bandwidth. Experimental results demonstrate the effectiveness of skin-off.
  • Accurate Sub-Pixel Matching Using Spatial Structure of Images, HABE Hitoshi, SUMI Kazuhiko, MATSUYAMA Takashi, The IEICE transactions on information and systems (Japanese edetion), The IEICE transactions on information and systems (Japanese edetion), 89(2), 393 - 398, Feb. 01 2006
    Summary:2枚のディジタル画像の変位をサブピクセル精度で得るために様々な手法が用いられている.ここではブロック間の相違度を補間して変位を推定する手法を取り上げ,マッチング対象画像の空間構造に着目することでその精度を向上する手法を提案する.
  • Compression Method for Omnidirectional Video Using Polyhedral Representations, HABE Hitoshi, YAMAZAWA Kazumasa, NOMURA Toshio, KATSURA Yosuke, MATSUYAMA Takashi, The Transactions of the Institute of Electronics, Information and Communication Engineers. A, The Transactions of the Institute of Electronics, Information and Communication Engineers. A, 88(9), 1074 - 1084, Sep. 01 2005
    Summary:人の住む三次元世界をそのまま映像化する三次元映像メディアに関する研究が活発に行われているが, 大量のデータを効率的に扱い, 放送・配信・アーカイブに広く利用するためには, 統一されたデータ圧縮手法の確立が不可欠になる. そこでは従来の映像情報に含まれない三次元幾何情報を同時に効率良く扱うことが課題となる. 本論文では, 三次元映像メディアの一つである全方位ビデオに着目し, 多面体表現を利用した圧縮手法を提案する. そこでは, 1)全方位ビデオの多面体表面への投影, 2)多面体の平面への展開, 3)通常の二次元平面映像に対する圧縮法の適用, によって, データ表現の効率が良く, 既存の技術との親和性の高い圧縮手法を実現する. 本論文においては, 全方位ビデオの撮影・伝送・表示のシステム全体を考慮したときの提案手法の優位性を明らかにし, 実映像及びシミュレーション映像を用いた実験によって, 既存の全方位ビデオの表現法との定量的な比較を行う. 更に, 効率良い表現のための多面体の選択指針を明らかにする.
  • Background Subtraction under Varying Illumination, MATSUYAMA Takashi, WADA Toshikazu, HABE Hitoshi, TANAHASHI Kazuya, The transactions of the Institute of Electronics, Information and Communication Engineers. D-II, The transactions of the Institute of Electronics, Information and Communication Engineers. D-II, 84(10), 2201 - 2211, Oct. 01 2001
    Summary:背景差分は, 画像中の移動対象を検出する有効な手法として広く利用されている.しかし, 背景差分を行うには, 背景部分での画像の変化が観測されないという前提条件が必要であるため, その適用範囲は限られている.本論文では, 照明変化による背景部分の画像の変化が起きた場合にも適用可能な背景差分による移動対象検出法を提案する.本手法は, 異なった考え方に基づく二つの対象検出法に基づいている.一方は, 照明に不変な特徴を用いて背景画像と観測画像の比較を行う手法である.他方は, 背景差分を行う前に観測画像の照明条件を推定し, 輝度の正規化を行う手法である.これら二つの手法は互いに相補的であり, 最終的に双方の検出結果を統合することで精度の高い検出結果を得ることができる.実験の結果, 実画像に対する本手法の有効性が示された.
  • Behavior understanding based on intention-gait model, Yasushi Yagi, Ikuhisa Mitsugami, Satoshi Shioiri, Hitoshi Habe, Human-Harmonized Information Technology, Human-Harmonized Information Technology, 2, 139 - 172, Apr. 20 2017 , Refereed
    Summary:Gait is known as one of biometrics, and there have been many studies on gait authentication. In those studies, it is implicitly assumed that the gait of a certain person is always constant. It is, however, untrue in reality a person usually walks differently according to their mood and physical/mental conditions, which we call "inertial states."Motivated by this fact, we organized the research project "Behavior Understanding based on Intention-Gait Model", whichwas supported by JST-CREST from 2010 to 2017. The goal of this project was to map "gait", in the broad sense of the term, to inertial states such as attention, social factors, and cognitive ability. In this chapter, we provide an overview of the three kinds of estimation technologies considered in this project: attention, social factors, and cognitive ability.
  • Spatial and Temporal Segmented Dense Trajectories for Gesture Recognition, Kaho Yamada, Takeshi Yoshida, Kazuhiko Sumi, Hitoshi Habe, Ikuhisa Mitsugami, THIRTEENTH INTERNATIONAL CONFERENCE ON QUALITY CONTROL BY ARTIFICIAL VISION 2017, THIRTEENTH INTERNATIONAL CONFERENCE ON QUALITY CONTROL BY ARTIFICIAL VISION 2017, 10338, 2017 , Refereed
    Summary:Recently, dense trajectories [1] have been shown to be a successful video representation for action recognition, and have demonstrated state-of-the-art results with a variety of datasets. However, if we apply these trajectories to gesture recognition, recognizing similar and fine-grained motions is problematic. In this paper, we propose a new method in which dense trajectories are calculated in segmented regions around detected human body parts. Spatial segmentation is achieved by body part detection [2]. Temporal segmentation is performed for a fixed number of video frames. The proposed method removes background video noise and can recognize similar and fine-grained motions. Only a few video datasets are available for gesture classification; therefore, we have constructed a new gesture dataset and evaluated the proposed method using this dataset. The experimental results show that the proposed method outperforms the original dense trajectories.
  • A video scene detection of the instantaneous motion by farmed fry, Koji Abe, Ryota Shimizu, Hitoshi Habe, Yoshiaki Taniguchi, Nobukazu Iguchi, ACM International Conference Proceeding Series, ACM International Conference Proceeding Series, 6 - 10, Nov. 21 2016 , Refereed
    Summary:As a method for supporting fish farming, this paper presents a video scene detection when farmed fry start instantaneously in a tank due to environmental stimuli. Although some environmental stimuli such as sound noises or lighting startle the fry and the stimuli bring about the instantaneous response, actual situations around the tanks in which the stimuli occur are unclear in detail. From the fact the fry often die due to crashes to the tank's wall and between the fry by the response, a monitoring system for the fry and situation around the pool could find causes of the stimuli, and it could result in decrease of the death number of the fry. In this research, the fry which swim in a tank are monitored by a video cam- era and the video scenes at the response are detected by a SVM with a feature value which represents fry's acceleration using sequential frames of the moving image. Preparing the moving images which include scenes of the response by fish in a tank, performances of the proposed method were examined. From experimental results, accuracy ratios of the recall and the precision for the scene detection have shown more than 80% on average and 100% under normal illuminances (108.5 lux on average), respectively.
  • Flexible Screen Sharing System between PC and Tablet for Collaborative Activities, Hiroyuki Masaki, Hitoshi Habe, Nobukazu Iguchi, PROCEEDINGS OF 2016 10TH INTERNATIONAL CONFERENCE ON COMPLEX, INTELLIGENT, AND SOFTWARE INTENSIVE SYSTEMS (CISIS), PROCEEDINGS OF 2016 10TH INTERNATIONAL CONFERENCE ON COMPLEX, INTELLIGENT, AND SOFTWARE INTENSIVE SYSTEMS (CISIS), 569 - 571, 2016 , Refereed
    Summary:We have developed a screen sharing system to share contents between two persons, and applicable to one-to-one remote teaching. The screen of a PC at one side is shared with the screen of a tablet at the other side through the network to convey instructions from an operator to a collaborator. This system makes it possible to arbitrarily select a part of the screen of the PC at the operator side. The selected screen is presented in the tablet at the collaborator side. The collaborator can adjust the scale of contents, and capture the screen. By analyzing such operations, the system can understand and record which parts of the contents the collaborator paid attention to. In addition, the camera of the tablet can be used as a simple scanner to digitize paper documents easily. Further, characters and symbols drawn with a finger or a pen on the tablet screen can be presented on the PC at the other side.
  • Calibration of Multiple Kinects with Little Overlap Regions, Mitsuru Nakazawa, Ikuhisa Mitsugami, Hitoshi Habe, Hirotake Yamazoe, Yasushi Yagi, IEEJ TRANSACTIONS ON ELECTRICAL AND ELECTRONIC ENGINEERING, IEEJ TRANSACTIONS ON ELECTRICAL AND ELECTRONIC ENGINEERING, 10, S108 - S115, Oct. 2015 , Refereed
    Summary:When using multiple Kinects, there must be enough distances among neighboring Kinects to avoid spoiled range data caused by the interference of their infrared speckle patterns. In the arrangement, their overlapped regions are too small to apply existing calibration methods using correspondences between their observations straightforwardly. Therefore, we propose a method to calibrate Kinects without large overlapped regions. In our method, first, we add extra RGB cameras in an environment to compensate overlapped regions. Thanks to them, we can estimate their camera parameters by obtaining correspondences between color images. Next, for accurate calibration, which considers range data as well as color images of Kinects, we optimize the estimated parameters by minimizing both the errors of correspondences between color images and those of range data of planar regions, which exist in a general environment such as walls and floors. Although our method consists of conventional techniques, its combination is optimized to achieve the calibration. (C) 2015 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.
  • Appearance-based Multiple Fish Tracking for Collective Motion Analysis, Kei Terayama, Koki Hongo, Hitoshi Habe, Masa-aki Sakagami, Proceedings 3rd IAPR Asian Conference on Pattern Recognition ACPR 2015, Proceedings 3rd IAPR Asian Conference on Pattern Recognition ACPR 2015, 361 - 365, 2015 , Refereed
    Summary:We propose a visual tracking method for dense fish schools in which occlusions occur frequently. Although much progress has been made for tracking multiple objects in video images, it is challenging to track individuals in highly dense groups. For occluded fishes, estimation of their positions and directions is difficult. However, if we know the number of fishes in a local area, we can accurately estimate their states by matching all of the combinations of possible parameters on the basis of our appearance model. We apply the idea to track multiple fishes in a school. Experimental results show that multiple fishes are practically tracked with our method compared to a well-known tracking method, and the average difference is less than 4% of the mean body length of the school.
  • Group Leadership Estimation Based on Influence of Pointing Actions, Hitoshi Habe, Kohei Kajiwara, Ikuhisa Mitsugami, Yasushi Yagi, 2013 SECOND IAPR ASIAN CONFERENCE ON PATTERN RECOGNITION (ACPR 2013), 2013 SECOND IAPR ASIAN CONFERENCE ON PATTERN RECOGNITION (ACPR 2013), 775 - 778, 2013 , Refereed
    Summary:When we act in a group with family members, friends, colleagues, each group member often play the respective role to achieve a goal that all group members have in common. This paper focuses on leadership among various kinds of roles observed in a social group and proposes a method to estimate a leader based on an interaction analysis. In order to estimate a leader in a group, we extract pointing actions of each person and measure how other people change their actions triggered by the pointing actions, i.e. how much influence the pointing actions have. When we can see the tendency that one specific person makes pointing actions and the actions have a high influence on another member, it is very likely that the person is a leader in a group. The proposed method is based on this intuition and measures the influence of pointing actions using their motion trajectories. We demonstrate that the proposed method has a potential for estimating the leadership through a comparison between the computed influence measures and subjective evaluations using some actual videos taken in a science museum.
  • Appearance-based parameter optimization for accurate stereo camera calibration, Hitoshi Habe, Yasutoshi Nakamura, MACHINE VISION AND APPLICATIONS, MACHINE VISION AND APPLICATIONS, 23(2), 313 - 325, Mar. 2012 , Refereed
    Summary:This paper proposes a method of camera calibration that compares the appearance of two images. Unlike conventional methods that evaluate point-to-point correspondences, ours makes a dense evaluation of the correspondence between two images. This enables us to robustly and efficiently calibrate range finders that are camera based. We explain the main principles and algorithm underlying our method, and we also present the results obtained from simulations and experimentally obtained data.
  • Dynamic Scene Reconstruction using Asynchronous Multiple Kinects, Mitsuru Nakazawa, Ikuhisa Mitsugami, Yasushi Makihara, Hozuma Nakajima, Hitoshi Habe, Hirotake Yamazoe, Yasushi Yagi, 2012 21ST INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR 2012), 2012 21ST INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR 2012), 469 - 472, 2012 , Refereed
    Summary:This paper proposes a novel method to reconstruct dynamic scenes by integrating depth data obtained by multiple Kinects, which cannot be synchronized to one another In this method, the multiple Kinects located so as to cover the whole surface are firstly calibrated so that their depth data are mapped into the world coordinate system. The synchronous depth data for each Kinect is then generated by interpolation of temporally neighboring captured data. Experimental results of marching person reconstruction show the effectiveness of our method.
  • Point Cloud Transport, Hozuma Nakajima, Yasushi Makihara, Hsu Hsu, Ikuhisa Mitsugami, Mitsuru Nakazawa, Hirotake Yamazoe, Hitoshi Habe, Yasushi Yagi, 2012 21ST INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR 2012), 2012 21ST INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR 2012), 3803 - 3806, 2012 , Refereed
    Summary:In this paper we propose a method for temporal interpolation of a point cloud undergoing occlusions and topological changes. The point cloud is first merged into fine clusters, which are then further merged into coarse clusters for each source and target shape. In conjunction with trash box bins to cope with occlusions, a coarse correspondence between a source and a target shape is found that minimizes the transportation cost in the earth mover's distance framework. Subsequently, a fine correspondence is found in a similar way based on the coarse correspondence constraint to suppress locally isolated motion. Finally, the source and target point clouds are transported based on the fine correspondence. Experiments with point cloud sequences captured by a Kinect range finder show promising results.
  • Easy Depth Sensor Calibration, Hirotake Yamazoe, Hitoshi Habe, Ikuhisa Mitsugami, Yasushi Yagi, 2012 21ST INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR 2012), 2012 21ST INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR 2012), 465 - 468, 2012 , Refereed
    Summary:This paper proposes a depth measurement error model of consumer depth cameras such as Microsoft KINECT, and its calibration method. These devices are originally designed for video game interface, thus, the obtained depth map are not enough accurate for 3D measurement. To decrease these depth errors, several models have been proposed, however, these models consider only camera-related parameters. Since the depth sensors are based on projector-camera systems, we should consider projector-related parameters. Therefore, we propose the error model of the consumer depth cameras especially the KINECT, considering both intrinsic parameters of the camera and the projector To calibrate the error model, we also propose the parameter estimation method by only showing a planar board to the depth sensors. Our error model and its calibration are necessary step for using the KINECT as a 3D measuring device. Experimental results show the validity and effectiveness of the error model and its calibration.
  • Automatic composition of an informative wide-view image from video, Hitoshi Habe, Shota Makiyama, Masatsugu Kidode, Proceedings - International Conference on Pattern Recognition, Proceedings - International Conference on Pattern Recognition, 4117 - 4120, 2010 , Refereed
    Summary:We describe a method for generating an informative wide-view image using images captured by a moving camera. The generated image allows for events in the scene observed by the camera to be understood easily. Our method does not use 3D shape information explicitly. Instead, it employs the trajectory of feature points across multiple images and generates a composite image by taking into account the distribution of the trajectories of the feature points. © 2010 IEEE.
  • Efficient acquisition of human existence priors from motion trajectories, Hitoshi Habe, Hidehito Nakagawa, Masatsugu Kidode, IPSJ Transactions on Computer Vision and Applications, IPSJ Transactions on Computer Vision and Applications, 2, 145 - 155, 2010 , Refereed
    Summary:This paper proposes a method for acquiring the prior probability of human existence by using past human trajectories and the color of an image. The priors play an important role in human detection as well as in scene understanding. The proposed method is based on the assumption that a person can exist again in an area where he/she existed in the past. In order to acquire the priors efficiently, a high prior probability is assigned to an area having the same color as past human trajectories. We use a particle filter for representing and updating the prior probability. Therefore, we can represent a complex prior probability using only a few parameters. Through experiments, we confirmed that our proposed method can acquire the prior probability efficiently and use it to realize highly accurate human detection. © 2010 Information Processing Society of Japan.
  • Context-oriented layout optimization of large-print textbooks, Itaru Tatsumi, Hitoshi Habe, Masatsugu Kidode, Proceedings of the International Conference on Document Analysis and Recognition, ICDAR, Proceedings of the International Conference on Document Analysis and Recognition, ICDAR, 1016 - 1020, 2009 , Refereed
    Summary:Large-print textbooks are used by low vision students in school. Because these books are mainly prepared by volunteers and almost all steps in the preparation process are performed manually, they cannot be mass-produced. The chronic shortage of these books has been a social problem in Japan. The procedure for preparing a large-print textbook involves (1) converting the size of figures and characters in the original textbook to one suitable for low vision students and (2) positioning them appropriately on the pages. In this paper, we propose a novel method for automatically optimizing a layout by employing a context structure. We represent the context structure by using a graph called a context structure graph. The proposed method first allocates each material to an appropriate page, and then optimizes the layout of each page by using the sequence-pair method. Throughout these operations, we employ an objective function derived from the context structure graph to ensure that the context in the original textbook is preserved in the large-print textbook prepared. © 2009 IEEE.
  • Efficient Acquisition of Human Existence Priors from Motion Trajectories, Hitoshi Habe, Hidehito Nakagawa, Masatsugu Kidode, 2009 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPR WORKSHOPS 2009), VOLS 1 AND 2, 2009 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPR WORKSHOPS 2009), VOLS 1 AND 2, 982 - 988, 2009 , Refereed
    Summary:This paper reports a method for acquiring the prior probability of human existence by using past human trajectories and the color of an image. The priors play important roles in human detection as well as in scene understanding. The proposed method is based on the assumption that a person can exist again in an area where he/she existed in the past. In order to acquire the priors efficiently, a high prior probability is assigned to an area having the same color as past human trajectories. We use a particle Iter for representing the prior probability. Therefore, we can represent a complex prior probability using only a few parameters. Through experiments, we confirmed that our proposed method can acquire the prior probability efficiently and it can realize highly accurate human detection using the obtained prior probability.
  • Compact Cataract Screening System : Design and Practical Data Acquisition, Retno Supriyanti, Hitoshi Habe, Masatsugu Kidode, Satoru Nagata, ICICI-BME: 2009 INTERNATIONAL CONFERENCE ON INSTRUMENTATION, COMMUNICATION, INFORMATION TECHNOLOGY, AND BIOMEDICAL ENGINEERING, ICICI-BME: 2009 INTERNATIONAL CONFERENCE ON INSTRUMENTATION, COMMUNICATION, INFORMATION TECHNOLOGY, AND BIOMEDICAL ENGINEERING, 96 - +, 2009 , Refereed
    Summary:The increasing number of cataract sufferers is a serious problem because cataracts are a leading cause of blindness in the world. To avoid blindness from cataracts, we need to detect them early. Today, ophthalmologists use a slit lamp to diagnose cataracts. This equipment is expensive and requires special training to use it. Unfortunately, a lot of developing countries have a limited number of ophthalmologists and health facilities, while a lot of cataract sufferers live in developing countries. Our algorithm is aimed at such developing countries and rural areas, and its main equipment is a compact digital camera. This equipment is inexpensive and easy for anyone to use without special training. Examination can be easily carried out in an outpatient department. We have already proposed a cataract screening method for the equipment that considers about specular reflection and statistical texture appearance inside the pupil. However, in order to accomplish our goal, not only the screening method itself, but also other aspects such as compactness and ease of use are crucial. In this paper, we will discuss system design for a compact cataract screening system. The final goal of our research is developing a simple and robust screening system for cataract with a compact digital camera. A user simply takes a patient's photograph and the system will automatically analyze the image by extracting information inside a pupil, including specular reflection analysis and texture appearance analysis, for distinguishing between serious and non-serious conditions. We emphasize how to implement our system in real conditions by giving a recommendation for acquiring appropriate image data while taking a photograph so that our system will work well. The results in a real implementation are similar to our recommendation.
  • Human Interaction Analysis Based on Walking Pattern Transitions, Hitoshi Habe, Kazuhisa Honda, Masatsugu Kidode, 2009 THIRD ACM/IEEE INTERNATIONAL CONFERENCE ON DISTRIBUTED SMART CAMERAS, 2009 THIRD ACM/IEEE INTERNATIONAL CONFERENCE ON DISTRIBUTED SMART CAMERAS, 425 - 432, 2009 , Refereed
    Summary:We propose a method that analyzes interaction between pedestrians based on their trajectories obtained using sensors such as cameras. Our objective is to understand the mutual relationship between pedestrians and to detect anomalous events in a video sequence. Under such situations, we can observe the interaction between a pair of pedestrians. This paper proposes a set of features that measures the interaction between pedestrians. We assume that a person is likely to change his/her walking patterns when he/she has been influenced by another person. Based on this assumption, the proposed method first extracts the transition points of a walking pattern from trajectories of two pedestrians and then measures the strength of the influence using the temporal and spatial closeness between them. Finally, experimental results obtained from actual videos demonstrate the method's effectiveness in understating mutual relationships and detecting anomalous events.
  • A simple and robust method to screen cataracts using specular reflection appearance, Retno Supriyanti, Hitoshi Habe, Masatsugu Kidode, Satoru Nagata, MEDICAL IMAGING 2008: COMPUTER-AIDED DIAGNOSIS, PTS 1 AND 2, MEDICAL IMAGING 2008: COMPUTER-AIDED DIAGNOSIS, PTS 1 AND 2, 6915, 2008 , Refereed
    Summary:The high prevalence of cataracts is still a serious public health problem as a leading cause of blindness, especially in developing countries with limited health facilities. In this paper we propose a new screening method for cataract diagnosis by easy-to-use and low cost imaging equipment such as commercially available digital cameras. The difficulties in using this sort of digital camera equipment are seen in the observed images, the quality of which is not sufficiently controlled; there is no control of illumination, for example. A sign of cataracts is a whitish color in the pupil which usually is black, but it is difficult to automatically analyze color information under uncontrolled illumination conditions. To cope with this problem, we analyze specular reflection in the pupil region. When an illumination light hits the pupil, it makes a specular reflection on the frontal surface of the lens of the pupil area. Also the light goes through the rear side of the lens and might be reflected again. Specular reflection always appears brighter than the surrounding area and is also independent of the illumination condition, so this characteristic enables us to screen out serious cataract robustly by analyzing reflections observed in the eye image. In this paper, we demonstrate the validity of our method through theoretical discussion and experimental results. By following the simple guidelines shown in this paper, anyone would be able to screen for cataracts.
  • Background subtraction under varying illumination, Takashi Matsuyama, Toshikazu Wada, Hitoshi Habe, Kazuya Tanahashi, Systems and Computers in Japan, Systems and Computers in Japan, 37(4), 77 - 88, Apr. 2006 , Refereed
    Summary:Background subtraction is widely used as an effective method for detecting moving objects in a video image. However, background subtraction requires a prerequisite in that image variation cannot be observed, and the range of application is limited. Proposed in this research paper is a method for detecting moving objects by using background subtraction that can be applied to cases in which the image has varied due to varying illumination. This method is based on two object detection methods that are based on different lines of thinking. One method compares the background image and the observed image using invariant features of illumination. The other method estimates the illumination conditions of the observed image and normalizes the brightness before carrying out background subtraction. These two methods are complementary, and highly precise detection results can be obtained by ultimately integrating the detection results of both methods. © 2006 Wiley Periodicals, Inc.

Books etc

  • Human-Harmonized Information Technology, Volume 2, Toyoaki Nishida, Contributor, Behavior Understanding Based on Intention-Gait Model, Springer,   2017 , 9784431565352
  • The Elements of Statistical Learning --- Japanese Edition, Joint translator, Chapter 15 Random Forests, Kyoritsu Shuppan,   2014 06 , 432012362X
  • Utilization of Portable Digital Camera for Detecting Cataract, Rerno Supriyanti, Hitoshi Habe, Masatsugu Kidode, Joint author, Ocular Diseases, INTECH,   2012 09

Conference Activities & Talks

  • Relevant Feature Extraction for Social Group Segmentation in the Real World", Hitoshi Habe, International Workshop on Human Behavior Analysis in the Real World,   2015 11 03
  • Appearance-based Multiple Fish Tracking for Collective Motion Analysis, Kei Terayama, Koki Hongo, Hitoshi Habe, Masa-aki Sakagami, ACPR 2015,   2015 11
  • Group Leadership Estimation Based on Influence of Pointing Actions., Hitoshi Habe, Kohei Kajiwara, Ikuhisa Mitsugami, Yasushi Yagi, Proc. of the International Joint Workshop on Advanced Sensing/Visual Attention and Interaction (ASVAI2013),   2013 11
  • Easy depth sensor calibration., Hirotake Yamazoe, Hitoshi Habe, Ikuhisa Mitsugami, Yasushi Yagi, Proceedings of the 21st International Conference on Pattern Recognition, ICPR 2012, Tsukuba, Japan, November 11-15, 2012,   2012 11
  • Dynamic scene reconstruction using asynchronous multiple Kinects., Mitsuru Nakazawa, Ikuhisa Mitsugami, Yasushi Makihara, Hozuma Nakajima, Hitoshi Habe, Hirotake Yamazoe, Yasushi Yagi, Proceedings of the 21st International Conference on Pattern Recognition, ICPR 2012, Tsukuba, Japan, November 11-15, 2012,   2012 11
  • Point cloud transport., Hozuma Nakajima, Yasushi Makihara, Hsu Hsu, Ikuhisa Mitsugami, Mitsuru Nakazawa, Hirotake Yamazoe, Hitoshi Habe, Yasushi Yagi, Proceedings of the 21st International Conference on Pattern Recognition, ICPR 2012, Tsukuba, Japan, November 11-15, 2012,   2012 11
  • Random Forests, 波部 斉, 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,   2012 05 , 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
    Summary:ランダムフォレストはアンサンブル学習による機械学習アルゴリズムの一つであ る.複数の決定木(tree)を弱識別器として用い,その結果を統合(forest)し て正しい結果を得る.Leo Breiman による2001年の論文以降様々な分野に適用さ れてきたが,近年コンピュータビジョン分野でも盛んに用いられている.本稿で は,その概要,最近の適用例,また,利用時の留意点などについて概観する.
  • D-12-40 Efficient Face Recognition Using Multiresolution Discrimination, Iwasaki Tsuyoshi, Habe Hitoshi, Kidode Mastsugu, Proceedings of the IEICE General Conference,   2011 02 28
  • D-12-91 Cross-viewpoint Video Retrieval Using Using Relations of Feature Space, Matsuda Takashi, Habe Hitoshi, Kidode Masatsugu, Proceedings of the IEICE General Conference,   2011 02 28
  • Automatic Composition of an Informative Wide-View Image from Video., Hitoshi Habe, Shota Makiyama, Masatsugu Kidode, 20th International Conference on Pattern Recognition, ICPR 2010, Istanbul, Turkey, 23-26 August 2010,   2010 08
  • Integration of Local and Global Features for Pruning Human Motion Trajectories, NISHIYUKI Kenta, HABE Hitoshi, KIDODE Masatsugu, Technical report of IEICE. PRMU,   2010 03 08
    Summary:We propose a method to analyze much information stored by cameras off-line, and acquire human motion trajectories. Human detections and tracking in a real environment is essential for human motion analysis, but acquiring human motion trajectories in various environments is difficult. We use not only local features such as results of human detection and similarities of appearance but also global features such as disappearance point and consistency of motion trajectories to acquire correct human motion trajectories in outdoor environment. We ascertained the validity of this method in experime...
  • Generation of Informative Wide Range Composite Image from Multi-Viewpoint Images, MAKIYAMA Shota, HABE Hitoshi, KIDODE Masatsugu, 電気学会研究会資料. GID, 一般産業研究会,   2009 12 11
  • Compact Cataract Screening System: Design and Practical Data Acquisition, Retno Supriyanti, Hitoshi Habe, Masatsugu Kidode, Satoru Nagata, Int. Conf. on Instrumentation, Comm., Information Tech. and Biomedical Engineering (ICICI-BME,   2009 11
  • Human interaction analysis based on walking pattern transitions., Hitoshi Habe, Kazuhisa Honda, Masatsugu Kidode, Third ACM/IEEE International Conference on Distributed Smart Cameras, ICDSC 2009, Como, Italy, August 30 - September 2, 2009,   2009 09
  • Context-oriented Layout Optimization of Large-Print Textbooks., Itaru Tatsumi, Hitoshi Habe, Masatsugu Kidode, 10th International Conference on Document Analysis and Recognition, ICDAR 2009, Barcelona, Spain, 26-29 July 2009,   2009 07
  • Efficient Acquisition of Human Existence Priors from Motion Trajectories, Hitoshi Habe, Hidehito Nakagawa, Masatsugu Kidode, Workshop on Visual and Contextual Learning from Annotated Images and Videos,   2009 06
  • Extracting Appearance Information inside the Pupil for Cataract Screening., Retno Supriyanti, Hitoshi Habe, Masatsugu Kidode, Satoru Nagata, Proceedings of the IAPR Conference on Machine Vision Applications (IAPR MVA 2009), Keio University, Yokohama, Japan, May 20-22, 2009,   2009 05
  • Efficient prior acquisition of human existence by using past human trajectories and color of image, NAKAGAWA HIDEHITO, HABE HITOSHI, KIDODE MASATSUGU, IPSJ SIG Notes. CVIM,   2009 03 06
    Summary:Research about human detection has been done continuously, although it is difficult to detect a human accurately. An effective way to get a high performance for human detection is acquiring the area where a human can exist beforehand. In this paper, we propose a method for acquiring prior probability of human existence by using past human trajectories and color of image. High prior probability is given to the same color area with past human trajectories. It is based on the intuition that human can exist again in the area where a human existed in the past. Also, we use the particle filter fo...
  • A-19-15 Primitive Motion Spotting in Long-time Image Sequences for Daily Life Analysis, Kimura Yusaku, Habe Hitoshi, Kidode Masatsugu, Proceedings of the IEICE General Conference,   2009 03 04
  • Extracting Mutual Relationship between Pedestrians from their Motion Trajectories, Hitoshi Habe, Kazuhisa Honda, Masatsugu Kidode, International Workshop on "Sensing Web",   2008 12
  • Context-oriented Layout Optimization for Large Print Textbooks, TATSUMI Itaru, HABE Hitoshi, KIDODE Masatsugu, IEICE technical report. Welfare Information technology,   2008 03 15
    Summary:Large print textbooks are used by low vision students in schools. Because it is mainly made by volunteers and almost all steps to make them are conducted manually, they cannot be mass-produced. Their chronic shortage has been a social problem in Japan. The procedure of making a large print textbook consists of (1) convert figures and characters in an original textbook to suitable ones for low vision students and (2) put them at appropriate positions in the pages. Among them, we propose a novel method which automatically optimizes the layout exploiting context structure. The context structur...
  • A Simple and Robust Method to Screen Cataracts using Specular Reflection Appearance, Retno Supriyanti, Hitoshi Habe, Masatsugu Kidode, Satoru Nagata, SPIE Medical Imaging,   2008 02
  • Inter-Reflection Compensation for Immersive Projection Display., Hitoshi Habe, Nobuo Saeki, Takashi Matsuyama, 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2007), 18-23 June 2007, Minneapolis, Minnesota, USA,   2007 06
  • An Efficient 3D Video Compression Method Based on Global Geometric Structures, LU Yang, HABE Hitoshi, MATSUYAMA Takashi, IEICE technical report. Image engineering,   2007 03 12
    Summary:3D video is a new image media which records whole information of a target object; that is, its shape, motion, color, and texture. Although it has potential applicability which innovates our everyday life, there are many open issues to obatain, handle and utilize 3D video. We, in this report, focus on the compression of 3D video. Among various proposed methods, a compression technique called skin-off first cuts 3D shape and map all 3D video data onto a 2D planar screen. This operation enables us to apply conventional 2D video codec for 3D video compression, and raise practical usability. How...
  • Report on 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR2006), Ijiri Yoshinisa, Habe Hitoshi, Banno Atsuhiko, Fujiyoshi Hironobu, Makihara Yasushi, Masuda Takeshi, Saito Hideo, Sato Yoichi, IPSJ SIG Notes. CVIM,   2006 09 08
    Summary:This report gives an overview of 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR2006), which was held in New York City, NY, USA, from June 19th to 21st, 2006.
  • Dynamic Background Modeling using Linear Dynamical System, MITSUI KEN, HABE HITOSHI, MATSUYAMA TAKASHI, IPSJ SIG Notes. CVIM,   2006 05 18
    Summary:In order to detect target objects in dynamic scenes, we need to model a nonstationary backgrounds. In this paper, we introduce the linear dynamical system (LDS) as a model to express the non-stationary background. LDS consists of a linear equation of a state vector, which represents a continuous state transition. It is quite important how to obtain the state vector from observed images, because the inference accuracy of the background variations depends on the state vector. To obtain the suitable state vector, we have to reduce the inference error. Therefore, we smooth observed images and g...
  • Enhancing Education Systems using High Definition Image Media, Hitoshi Habe, 3rd AEARU Workshop on Network Education,   2005 12
  • Object Detection : Model of Foreground and Background, Sumi K, Seki M, Habe H, IPSJ SIG Notes. CVIM,   2005 09 05
    Summary:Object detection is a basic problem of image understanding in a real environment. It can be defined as means to segment an image into foreground regions and background regions. There can be two approaches in object detection. One is to use characteristics of appearance of target objects. The other is to user characteristics of background. Those characteristics are referred as to foreground model and background model respectively. Those models are obtained not only by prior knowledge but also by examples gathered on line under operation. In this survey, we focus on background model and foreg...
  • Skin-off:Representation and Compression Scheme for 3D Video, Hitoshi Habe, Yosuke Katsura, Takashi Matsuyama, Picture Coding Symposium (PCS) 2004,   2004 12
  • LJ-002 Skin-off: Representation and Compression for 3D Video by Unfolding onto 2D Planes, Katsura Yosuke, Habe Hitoshi, Boehme Martin, Matsuyama Takashi, 情報科学技術レターズ,   2004 08 20
  • Compression of Omnidirectional Video with Polyhedral Mapping, KATSURA Yosuke, HABE Hitoshi, YAMAZAWA Kazumasa, MATSUYAMA Takashi, IPSJ SIG Notes. CVIM,   2003 05 08
    Summary:When we transmit or store omnidirectional video, because of its wide field of view, the amount of data becomes very large. Therefore, it is necessary to compress omnidirectional video to achieve practical usability. However, when we apply conventional compression methods to omnidirectional video, their efficiency is limited. This is because the geometry of omnidirectional video is not taken into account in conventional compression methods. In this paper, we propose a novel method for compressing omnidirectional video. In our method, omnidirectional video is mapped onto a polyhedral screen, ...
  • Interactive Visualization of Omnidirectional Video with Dome Display, Yamaguchi Takeshi, Habe Hitoshi, Matsuyama Takashi, IPSJ SIG Notes. CVIM,   2003 05 08
    Summary:We can obtain immersive experiences by displaying omnidirectional video on a dome display. In the case of ordinary display systems, a viewer operates the display system with some mechanical interfaces such as a keyboard. However, in the case of an immersive display system, the operation of such tools is inconsistent with the immersive experience. In this paper, we propose an interactive visualization system of omnidirectional video on a dome display. Our system can perceive viewer's intentions via gesture recognition and generate effective and attractive video images based on the viewer's i...
  • Background Subtraction for Non-Stationary Scenes, Takashi Matsuyama, Takashi Ohya, Hitoshi Habe, Proc. Asian Conference on Computer Vision, pp. 622-667,   2000 01
  • A Robust Background Subtraction Method under Varying Illumination, Habe H, Wada T, Matsuyama T, IPSJ SIG Notes. CVIM,   1999 03 18
    Summary:The background subtraction is a simple but effective methed to detect moving objects in video images. However, since it assumes that image variations are caused only by moving objects, its applicability is limited. In this paper, we propose a robust background subtraction method under varying illumination. To augment the background subtraction under varying illumination, we focus on illumination-invariant features called as texture and normalized intensity. These illumination-invariant features are independent of each other. We integrate detection results using the features, and realize the...

Misc

  • Development of a system for converting BLE communication and acoustic communication to use BLE devices in underwater environments, Hiroto Masuda, Yoshiaki Taniguchi, Hitoshi Habe, Koji Abe, Nobukazu Iguchi, Proceedings of 2019 IPSJ Kansai Conference, 1, 4,   2019 09
  • 魚群を構成する個体の計数技術の開発―個体画像抽出手法の検討―, 阿部悟, 高木力, 米山和良, 鳥澤眞介, 波部斉, 阿部孝司, 井口信和, 竹原幸生, 升間主計, 八木洋樹, 中井彰治, 山口武治, 浅海茂, 日本水産学会大会講演要旨集, 2019, 11,   2019 03 26 , https://jglobal.jst.go.jp/detail?JGLOBAL_ID=201902240730515462
  • Features for Video Scenes of Burst Swimming by Fly of Bluefin Tuna, Masaru Tanaka, Koji Abe, Hitoshi Habe, Yoshiaki Taniguchi, Nobukazu Iguchi, Proceedings of annual conference of Electronics, Information and Systems Society, IEE of Japan, 1340, 1341,   2018 09
  • Features for extracting video scenes of the instantaneous swimming by fish using an infrared camera, Daisuke Kishida, Koji Abe, Hitoshi Habe, Yoshiaki Taniguchi, Nobukazu Iguchi, Proceedings of FAN 2016, 108, 111,   2016 10
  • A study on estimation of turbidity using visible light communication in underwater sensor networks, Tomohiko Yatsuzuka, Yoshiaki Taniguchi, Hitoshi Habe, Koji Abe, Nobukazu Iguchi, Proceedings of 2016 IPSJ Kansai Conference, 1, 5,   2016 09
  • Features for extracting video scenes of the instantaneous swimming by farm-raised fry, Daisuke Kishida, Koji Abe, Hitoshi Habe, Yoshiaki Taniguchi, Nobukazu Iguchi, Proceedings of annual conference of Electronics, Information and Systems Society, IEE of Japan, 1293, 1296,   2015 08
  • Development of a Parking Lot Surveillance System with an Outdoor Camera Using Machine Learning, MAE Yuki, HABE Hitoshi, SHIBATA Tomohiro, IEICE technical report. Image engineering, 111, 441, 165, 169,   2012 02 20 , http://id.ndl.go.jp/bib/023496725
    Summary:Currently used parking systems involve sensors, such as ultrasonic waves, infrared rays, and cameras. These systems check whether a parking space has a car, however parking time measurements are, to the best of our knowledge, not performed. Currently known methods for measuring parking time can be difficult to introduce and might consume space and/or have installation costs. If parking time can be measured by using surveillance cameras installed in the parking lot, this can be advantageous with respect to installation spaces and/or cost. In this research, a parking lot surveillance system which guesses parking time without using correlations of time series data for a large parking lot, using a network camera at an outdoor parking lot, has been created. Discrimination between occupied or vacant parking spaces is done using a support vector machine, and features are extracted by Bag-of-features used in the field of generic object recognition. Furthermore, similarities are calculated from SIFT features, and when a threshold similarity value which is previously determined by Bayes decision rule from estimated densities is exceeded, the parking time of each car is guessed by discriminating from the same car.
  • Development of a Parking Lot Surveillance System with an Outdoor Camera Using Machine Learning, 36, 9, 165, 169,   2012 02 , http://id.ndl.go.jp/bib/023536399
  • Skin-off:Representation and Compression Scheme for 3D Video, Hitoshi Habe, Yosuke Katsura, Takashi Matsuyama, Picture Coding Symposium (PCS) 2004,   2004 , Refereed
  • Inter-reflection compensation for immersive projection display, Hitoshi Habe, Nobuo Sam, Takashi Matsuyama, 2007 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOLS 1-8, 3584, +,   2007 , Refereed, 10.1109/CVPR.2007.383473
    Summary:This paper proposes an effective method for compensating inter-reflection in immersive projection displays (IPDs). Because IPDs project images onto a screen, which surrounds a viewer, we have perform out both geometric and photometric corrections. Our method compensates interreflection on the screen. It requires no special device, and approximates both diffuse and specular reflections on the screen using block-based photometric calibration.

Awards & Honors

  •   2012 05 , IEICE, ISS Reviewer Award
  •   2008 02 , SPIE, SPIE Medical Imaging 2008 Honorable Mention Poster Award

Research Grants & Projects

  • Ministry of Education, Culture, Sports, Science and Technology, Grants-in-Aid for Scientific Research(若手研究(B)), Flexible Scene Understanding Based on Geometric Structure Estimation from Appearance of Video Sequence, In order to detect and track pedestrians in an outdoor scene, we proposed the methods that exploit its geometric structure. For example, if we know where a road and a building are in the scene, it is possible to improve the performance of pedestrian detection drastically. Specifically speaking, we proposed the methods for (1) estimating prior probability of human existence and (2) obtaining accurate human motion trajectories. Additionally, in order develop the new application area of pedestrian detection and tracking, we proposed a method that analyzes interaction between pedestrians and es...
  • Ministry of Education, Culture, Sports, Science and Technology, Grants-in-Aid for Scientific Research(基盤研究(B)), Realization of highly available distance learning environment with fusion of network technologies and media cognition technologies, Development of stable and dependable streaming method: To satisfy high-availability and low-cost at the same time, it is effective to connect multiple different cheap and best-effort networks and realize a feature to select a network among them or use them at the same time. UDP which is used for streaming does not have mechanisms to control bandwidth or recognize situation of network. We use TFRC (TCP Friendly Rate Control), which has mechanism for congestion control, for streaming using multiple networks at the same time. We also use SCTP (Stream Control Transmission Protocol) not to inter...
  • Ministry of Education, Culture, Sports, Science and Technology, Grants-in-Aid for Scientific Research(特定領域研究(C), 特定領域研究), Understanding human intention and activities for versatile real-time human-machine-interactions, In the 21st century, our personal and social activities are conducted in two different domains: physical real world and cyber network society. For realizing smooth and casual integration of these domains, we need a novel interaction model that goes a step further beyond the existing "command-and-response model."In this research, we proposed a concept of "man-machine symbiotic systems" as the next generation interaction model. Man-machine symbiotic systems are characterized by such a feature that the systems work for humans even if they are not explicitly ordered. For rea...
  • Ministry of Education, Culture, Sports, Science and Technology, Grants-in-Aid for Scientific Research(基盤研究(A)), Real-Tune 3D Shape Reconstruction, Visualization, Editing, and Coding for 3D Video, We have obtained the following technical attainments to realize 3D video generation, visualization, editing, and coding.1. PC cluster system (PC : 30, active camera : 25) to capture synchronized multi-view video of human action2. Precise calibration method for quasi fixed-viewpoint pan-tilt-zoom camera3. 3 base plane visual cone intersection algorithm and its parallel pipeline processing method for real-time dynamic 3D shape reconstruction using PC cluster ; with this system, we can reconstruct over 10 volumes per second of human action at 2cm X 2cm X 2cm spatial resolution.4. cooperative c...