Saito, Hideo

写真a

Affiliation

Faculty of Science and Technology, Department of Information and Computer Science (Yagami)

Position

Professor

E-mail Address

E-mail address

Related Websites

External Links

Career 【 Display / hide

  • 1992.04
    -
    1995.03

    慶應義塾大学(理工学部) ,助手

  • 1994.04
    -
    1997.08

    日本体育大学 ,非常勤講師

  • 1995.04
    -
    2001.03

    Assistant Professor, Keio University

  • 1997.08
    -
    1999.08

    Visiting Scientist, Carnegie Mellon University

  • 2001.04
    -
    2006.03

    Associate Professor, Keio University

display all >>

Academic Background 【 Display / hide

  • 1987.03

    Keio University, Faculty of Science and Engineering, (電気工学科)

    University, Graduated

  • 1989.03

    Keio University, Graduate School, Division of Science and Engineeri, 電気工学専攻

    Graduate School, Completed, Master's course

  • 1992.03

    Keio University, Graduate School, Division of Science and Engineeri, 電気工学専攻

    Graduate School, Completed, Doctoral course

Academic Degrees 【 Display / hide

  • 工学, Keio University, 1992.03

 

Research Areas 【 Display / hide

  • Theory of informatics (Computer Science)

  • Communication/Network engineering (Information and Communication Engineering)

Research Keywords 【 Display / hide

  • Computer Vision

  • Pattern Recognition

  • Human Interface

  • Image Processing

 

Books 【 Display / hide

  • 人工生命「5.3 金融市場シミュレーションへの応用」分担

    尹 煕元,斎藤英雄,棚橋隆彦, 同文書院 編 井上春樹, 2002

     View Summary

    金融市場の株価の変動をGAを用いて解析する手法を提案し,実際の価格変動データを利用して解析結果の妥当性を検討した.

  • 'アドバンスド・センサ・ハンドブック, 「9-2-2 CT手法の産業応用」分担'

    '斎藤英雄, 中島真人', 培風館, 1994

     View Summary

    CT手法の産業応用例について解説した。

Papers 【 Display / hide

  • Resolving position ambiguity of imu-based human pose with a single RGB camera

    Kaichi T., Maruyama T., Tada M., Saito H.

    Sensors (Switzerland) (Sensors (Switzerland))  20 ( 19 ) 1 - 12 2020.10

    ISSN  14248220

     View Summary

    © 2020 by the authors. Licensee MDPI, Basel, Switzerland. Human motion capture (MoCap) plays a key role in healthcare and human–robot collaboration. Some researchers have combined orientation measurements from inertial measurement units (IMUs) and positional inference from cameras to reconstruct the 3D human motion. Their works utilize multiple cameras or depth sensors to localize the human in three dimensions. Such multiple cameras are not always available in our daily life, but just a single camera attached in a smart IP devices has recently been popular. Therefore, we present a 3D pose estimation approach from IMUs and a single camera. In order to resolve the depth ambiguity of the single camera configuration and localize the global position of the subject, we present a constraint which optimizes the foot-ground contact points. The timing and 3D positions of the ground contact are calculated from the acceleration of IMUs on foot and geometric transformation of foot position detected on image, respectively. Since the results of pose estimation is greatly affected by the failure of the detection, we design the image-based constraints to handle the outliers of positional estimates. We evaluated the performance of our approach on public 3D human pose dataset. The experiments demonstrated that the proposed constraints contributed to improve the accuracy of pose estimation in single and multiple camera setting.

  • InpaintFusion: Incremental RGB-D Inpainting for 3D Scenes

    Mori S., Erat O., Broll W., Saito H., Schmalstieg D., Kalkofen D.

    IEEE Transactions on Visualization and Computer Graphics (IEEE Transactions on Visualization and Computer Graphics)  26 ( 10 ) 2994 - 3007 2020.10

    ISSN  10772626

     View Summary

    © 1995-2012 IEEE. State-of-the-art methods for diminished reality propagate pixel information from a keyframe to subsequent frames for real-time inpainting. However, these approaches produce artifacts, if the scene geometry is not sufficiently planar. In this article, we present InpaintFusion, a new real-time method that extends inpainting to non-planar scenes by considering both color and depth information in the inpainting process. We use an RGB-D sensor for simultaneous localization and mapping, in order to both track the camera and obtain a surfel map in addition to RGB images. We use the RGB-D information in a cost function for both the color and the geometric appearance to derive a global optimization for simultaneous inpainting of color and depth. The inpainted depth is merged in a global map by depth fusion. For the final rendering, we project the map model into image space, where we can use it for effects such as relighting and stereo rendering of otherwise hidden structures. We demonstrate the capabilities of our method by comparing it to inpainting results with methods using planar geometric proxies.

  • Pose estimation of primitive-shaped objects from a depth image using superquadric representation

    Hachiuma R., Saito H.

    Applied Sciences (Switzerland) (Applied Sciences (Switzerland))  10 ( 16 )  2020.08

     View Summary

    © 2020 by the authors. This paper presents a method for estimating the six Degrees of Freedom (6DoF) pose of texture-less primitive-shaped objects from depth images. As the conventional methods for object pose estimation require rich texture or geometric features to the target objects, these methods are not suitable for texture-less and geometrically simple shaped objects. In order to estimate the pose of the primitive-shaped object, the parameters that represent primitive shapes are estimated. However, these methods explicitly limit the number of types of primitive shapes that can be estimated. We employ superquadrics as a primitive shape representation that can represent various types of primitive shapes with only a few parameters. In order to estimate the superquadric parameters of primitive-shaped objects, the point cloud of the object must be segmented from a depth image. It is known that the parameter estimation is sensitive to outliers, which are caused by the miss-segmentation of the depth image. Therefore, we propose a novel estimation method for superquadric parameters that are robust to outliers. In the experiment, we constructed a dataset in which the person grasps and moves the primitive-shaped objects. The experimental results show that our estimation method outperformed three conventional methods and the baseline method.

  • CorsNet: 3D Point Cloud Registration by Deep Neural Network

    Kurobe A., Sekikawa Y., Ishikawa K., Saito H.

    IEEE Robotics and Automation Letters (IEEE Robotics and Automation Letters)  5 ( 3 ) 3960 - 3966 2020.07

     View Summary

    © 2016 IEEE. Point cloud registration is a key problem for robotics and computer vision communities. This represents estimating a rigid transform which aligns one point cloud to another. Iterative closest point (ICP) is a well-known classical method for this problem, yet it generally achieves high alignment only when the source and template point cloud are mostly pre-aligned. If each point cloud is far away or contains a repeating structure, the registration often fails because of being fallen into a local minimum. Recently, inspired by PointNet, several deep learning-based methods have been developed. PointNetLK is a representative approach, which directly optimizes the distance of aggregated features using gradient method by Jacobian. In this paper, we propose a point cloud registration system based on deep learning: CorsNet. Since CorsNet concatenates the local features with the global features and regresses correspondences between point clouds, not directly pose or aggregated features, more useful information is integrated than the conventional approaches. For comparison, we also developed a novel deep learning approach (DirectNet) that directly regresses the pose between point clouds. Through our experiments, we show that CorsNet achieves higher accuracy than not only the classic ICP method, but also the recently proposed learning-based proposal PointNetLK and DirectNet, including on seen and unseen categories.

  • Pose Estimation of Stacked Rectangular Objects from Depth Images

    Matsuno D., Hachiuma R., Saito H., Sugano J., Adachi H.

    IEEE International Symposium on Industrial Electronics (IEEE International Symposium on Industrial Electronics)  2020-June   1409 - 1414 2020.06

    ISSN  9781728156354

     View Summary

    © 2020 IEEE. This paper addresses the task of six degrees of freedom (6-DoF) pose estimation of stacked rectangular objects from depth images. Object pose estimation is one of the key challenges for visual processing systems since it plays a vital role in many situations such as warehouse/factory automation, robotic manipulation, and augmented reality. Many recent approaches to object pose estimation use RGB information for detecting and estimating the pose of objects. However, in warehouse/factory automation, objects are often small, occluded, cluttered, and texture-less which makes it difficult to utilize RGB features for detection and pose estimation. In order to overcome this restriction, we use only the depth information (without RGB information) and its geometric features to segment each object and to estimate the 6-DoF (position and orientation) in a stacked scene. We segment the rectangular objects in each scene from the depth and surface normal discontinuities (geometric segmentation). From the geometrically segmented image, four object corner points can be estimated using the convex hull detection and the eight corner points, which are required for the 6-DoF pose estimation, can be calculated. To improve the accuracy of orientation estimation, we estimate four orientation candidates and select the best among them. Experimental results using two evaluation methods show that our method outperformed the baseline method.

display all >>

Papers, etc., Registered in KOARA 【 Display / hide

Reviews, Commentaries, etc. 【 Display / hide

Presentations 【 Display / hide

  • デジタルヒューマンモデルを用いた深層学習による物体組込型カメラ画像からの把持姿勢推 定

    稲生健太郎,家永直人,杉浦裕太,斎藤英雄,宮田なつき,多田充徳

    2018年電子情報通信学会総合大会, 2018.03, Poster (general), 電子情報通信学会

  • 3D スキャン点群の建物のセグメンテーション

    王 麒雁,楊 亮,斎藤英雄,木下久史

    2018年電子情報通信学会総合大会, 2018.03, Poster (general), 電子情報通信学会

  • 3次元点群を用いた単一視点画像による絶対スケール測定

    安藤隆平、斎藤英雄

    Dynamic Image processing for real Application workshop 2018 (中京大学 名古屋キャンパス) , 2018.03, Oral Presentation(general), 精密工学会 画像応用技術専門委員会

  • 距離カメラ付きスマートフォンを用いた人体の足の3次元形状計測

    小林巧、家永直人、杉浦裕太、斎藤英雄、宮田なつき、多田充徳

    Dynamic Image processing for real Application workshop 2018 (中京大学 名古屋キャンパス) , 2018.03, Oral Presentation(general), 精密工学会 画像応用技術専門委員会

  • 球面ドロネー三角形分割法を用いた3D-LiDAR点群の領域分割処理法

    田中季晃、大石圭、中島由勝、斎藤英雄

    Dynamic Image processing for real Application workshop 2018 (中京大学 名古屋キャンパス) , 2018.03, Oral Presentation(general), 精密工学会 画像応用技術専門委員会

display all >>

Awards 【 Display / hide

  • Fellow

    2017.03, the Institute of Electronics, Information and Communication Engineers

    Country: Japan

  • Best Paper

    Yusuke Nakayama, Hideo Saito, Masayoshi Shimizu, and Nobuyasu Yamaguchi, 2016.02, IS & T, Marker-less AR framework using on-site 3D line segment based model generation

    Type of Award: International Academic Awards.  Country: USA

  • 査読功労賞

    2015.08, 映像情報メディが学会

    Type of Award: Awards of National Conference, Council and Symposium.  Country: 日本

  • Jon Campbell Best Paper Prize

    Y. Shinozuka, F. de Sorbier and H. Saito, 2014.08, Organising Committee of the Irish Machine Vision and Image Processing Conference 2014, Specular 3D Object Tracking by View Generative Learning

    Type of Award: International Academic Awards.  Country: United Kingdom

  • 活動功労賞

    斎藤英雄, 2014.06, 電子情報通信学会 情報・システムソサイエティ, パターン認識・メディア理解研究専門委員会活動への貢献

    Type of Award: Awards of National Conference, Council and Symposium.  Country: 日本

display all >>

 

Courses Taught 【 Display / hide

  • LABORATORIES IN INFORMATION AND COMPUTER SCIENCE 1B

    2020

  • LABORATORIES IN INFORMATION AND COMPUTER SCIENCE 1A

    2020

  • INDEPENDENT STUDY ON SCIENCE FOR OPEN AND ENVIRONMENTAL SYSTEMS

    2020

  • GRADUATE RESEARCH ON SCIENCE FOR OPEN AND ENVIRONMENTAL SYSTEMS 2

    2020

  • GRADUATE RESEARCH ON SCIENCE FOR OPEN AND ENVIRONMENTAL SYSTEMS 1

    2020

display all >>

 

Social Activities 【 Display / hide

  • 「IAPR Workshop on Machine Vision Applications」

    1997.08
    -
    1998.11
  • 「第3回画像センシングシンポジウム」 (1996年6月)

    1996.10
    -
    1997.06
  • 「第2回画像センシングシンポジウム」 (1996年6月 13日、14日)

    1995.11
    -
    1996.06
  • 「IAPR Workshop on Machine Vision Applications 」

    1995.09
    -
    1996.11
  • 電子情報通信学会学生会連絡会

    1995.05
    -
    1997.05

display all >>

Memberships in Academic Societies 【 Display / hide

  • 日本バーチャルリアリティ学会 複合現実感研究会, 

    2013.01
    -
    Present
  • the 23rd International Conference on Artificial Reality and Telexistence (ICAT 2013), 

    2012.12
    -
    2013.12
  • IPSJ Transactions on Computer Vision and Applications, MIRU Conference Editorial Board, 

    2012.10
    -
    Present
  • 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, 

    2012.04
    -
    Present
  • 日本バーチャルリアリティ学会, 

    2012.04
    -
    Present

display all >>

Committee Experiences 【 Display / hide

  • 2017.04
    -
    Present

    Editor in Chief, IPSJ Transactions on Computer Vision and Applications, Editorial Board

  • 2016.06
    -
    2018.05

    副会長(技術会議担当), 電子情報通信学会 情報システムソサイエティ

  • 2016.04
    -
    2018.03

    評議員, 日本バーチャルリアリティ学会

  • 2016.04
    -
    2018.03

    運営委員, 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

  • 2016.04
    -
    2017.03

    専門委員長, 電子情報通信学会 汎光線時空間映像学研究専門委員会

display all >>