Presentation 2004-12-17
Real-Time Generation of Novel View of a Dynamic Scene Using Morphing and Visual Hull
Tomoya ISHIKAWA, Kazumasa YAMAZAWA, Naokazu YOKOYA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Recently, generation of novel view images from images which were acquired by multiple cameras has been investigated. It can be applied to telepresence effectively. The conventional methods need assumptions such as the static scene and the limited position of the object within the positions of cameras. In this paper, we propose the method of generation of novel view images of a dynamic scene. The acquired images from omni-directional cameras are divided into static regions and dynamic regions. The novel view images are generated by morphing of static regions and by visual hull of dynamic regions in real-time. In the experiment, we show that the implemented system can generate novel view images in real-time from live video streams.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Novel View / Morphing / Visual Hull / Real-Time / Dynamic Scene / Omni-directional Camera
Paper # PRMU2004-136
Date of Issue

Conference Information
Committee PRMU
Conference Date 2004/12/10(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Real-Time Generation of Novel View of a Dynamic Scene Using Morphing and Visual Hull
Sub Title (in English)
Keyword(1) Novel View
Keyword(2) Morphing
Keyword(3) Visual Hull
Keyword(4) Real-Time
Keyword(5) Dynamic Scene
Keyword(6) Omni-directional Camera
1st Author's Name Tomoya ISHIKAWA
1st Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology()
2nd Author's Name Kazumasa YAMAZAWA
2nd Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology
3rd Author's Name Naokazu YOKOYA
3rd Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology
Date 2004-12-17
Paper # PRMU2004-136
Volume (vol) vol.104
Number (no) 524
Page pp.pp.-
#Pages 6
Date of Issue