Chair for Computer Aided Medical Procedures & Augmented Reality
Lehrstuhl für Informatikanwendungen in der Medizin & Augmented Reality

THIS WEBPAGE IS DEPRECATED - please visit our new website

Invited Talk by Prof. Hideo Saito


Dr. Hideo Saito, Professor
Department of Information and Computer Science
Keio University, Japan

  • Date: Monday, 22 February 2016
  • Time: 10:00 - 12:00
  • Location: MI 03.13.010

Computer Vision-based technologies for augmenting visual information


In this presentation, I would like to introduce research topics that I have recently performed with students in Keio University. I have started such research since I had involved in the research project named as Virtualized Reality in Robotics Institute of Carnegie Mellon University during 1997-1999. The technical basement of Virtualized Reality was 3D modeling and rendering from multiple views, which includes a lot of essential issues in computer vision, such as camera pose estimation, finding pixel correspondences, 3D reconstruction, segmentation, etc. Those fundamental computer vision techniques can be used for various application technologies, such as free-viewpoint videos, augmented reality, mixed reality, etc. I think that the essential issue is visualization of reality that cannot simply be captured with generic cameras/videos, but needs to be somehow visually reconstructed for making human understand the reality. I will show some research topics for realizing such visualization of reality using computer vision technology.

My talk will be followed by short talks by master students visiting with me. The topics of the students will include the following topics.

  • Line segment feature based SLAM using RGB-D camera (by Naoto Ienaga)
  • Application of LSD-SLAM for visualization temperature in wide-area environments (by Masahiro Yamaguchi)
  • Camera pose estimation by example image database using deep learning (by Yoshikatsu Nakajima)
  • Visualization and obstacle detection around a truck using multiple cameras (by Kei Uehara)
  • Application of object pose estimation from depth images for spatial augmented reality and robot control (by Ryo Hachiuma)

Biography: Hideo Saito received his Ph.D. degree in Electrical Engineering from Keio University, Japan, in 1992. Since then, he has been on the Faculty of Science and Technology, Keio University. In 1997 to 1999, he had joined into Virtualized Reality Project in the Robotics Institute, Carnegie Mellon University as a visiting researcher. Since 2006, he has been a full Professor of Department of Information and Computer Science, Keio University. His recent activities for academic conferences includes a Program Chair of ACCV2014, a General Chair of ISMAR2015, and a Program Chair of ISMAR2016.

Title: Computer Vision-based technologies for augmenting visual information
Date: 22 February 2016
Location: MI 00.13.010
Abstract: Invited talk at 10:00am on Monday February 22
Imageurl: hideosaito.JPG
Type: News

Edit | Attach | Refresh | Diffs | More | Revision r1.4 - 18 Feb 2016 - 16:25 - PascalFallavollita

Lehrstuhl für Computer Aided Medical Procedures & Augmented Reality    rss.gif