Presentation 2013-02-21
Human Character Generation from Prerecorded Videos for Mixed Reality
Tomoya TAKEDA, Takeshi OISHI, Atsuhiko BANNO, Katsushi IKEUCHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In the research field of Mixed Reality, there have been many studies on displaying virtual human characters in real scenery "Human Billboards" are usually used when we want to show 2D human characters through an image-based method. However, a problem with conventional Human Billboards is that we cannot see the human characters from any arbitrary viewpoint In this paper, we propose a new Human Billboard system where the characters' appearance changes with respect to the user's viewpoint. We first prepare several databases that contain about 1000 of 3D human models, as well as some prerecorded movies as input. Then, we run Chamfer Matching and DP Matching on the databases. This allows us to obtain frames of the input movies that show the human characters from the different angles.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Mixed Reality / Chamfer Matching / DP Matching / 3D model
Paper # PRMU2012-135
Date of Issue

Conference Information
Committee PRMU
Conference Date 2013/2/14(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) Human Character Generation from Prerecorded Videos for Mixed Reality
Sub Title (in English)
Keyword(1) Mixed Reality
Keyword(2) Chamfer Matching
Keyword(3) DP Matching
Keyword(4) 3D model
1st Author's Name Tomoya TAKEDA
1st Author's Affiliation Institute of Industrial Science, the University of Tokyo()
2nd Author's Name Takeshi OISHI
2nd Author's Affiliation Institute of Industrial Science, the University of Tokyo
3rd Author's Name Atsuhiko BANNO
3rd Author's Affiliation National Institute of Advanced Industrial Science and Technology
4th Author's Name Katsushi IKEUCHI
4th Author's Affiliation Institute of Industrial Science, the University of Tokyo
Date 2013-02-21
Paper # PRMU2012-135
Volume (vol) vol.112
Number (no) 441
Page pp.pp.-
#Pages 6
Date of Issue