Presentation	2008-09-05 3D Body-part Tracking of a Human in Clothing using Probabilistic Non-linear Time-series Volume Learning MICHIRO HIRAI, NORIMICHI UKITA, MASATSUGU KIDODE,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	We propose a method for tracking 3D human body parts and clothing from synchronized video sequences. Our objective is (1) to identify each body region with its corresponsing clothing in the entire body volume and (2) to refine the volume. Time-series sample volumes are acquired by a sophisticated 3D reconstruction algorithm off-line. The history of these samples are stored as low dimensional trajectories with probabilistic nonlinear representation. With this representation, body-part tracking becomes robust to various noises and delicate, complicated, and quick shape variations. Experimental results using loose-fitting clothing demonstrated the effectiveness of our method.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)
Paper #	PRMU2008-64,HIP2008-64
Date of Issue

Conference Information
Committee	PRMU
Conference Date	2008/8/29(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)	3D Body-part Tracking of a Human in Clothing using Probabilistic Non-linear Time-series Volume Learning
Sub Title (in English)
Keyword(1)
1st Author's Name	MICHIRO HIRAI
1st Author's Affiliation	()
2nd Author's Name	NORIMICHI UKITA
2nd Author's Affiliation	/ Graduate School of Information Science, Nara Institute of Science and Technology
3rd Author's Name	MASATSUGU KIDODE
3rd Author's Affiliation
Date	2008-09-05
Paper #	PRMU2008-64,HIP2008-64
Volume (vol)	vol.108
Number (no)	198
Page	pp.pp.-
#Pages	8
Date of Issue