Presentation 2001/1/24
Human motion estimation from monocular moving pictures
Takao Seki, Takayuki Ito,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) There are many visual approaches aiming at acquiring human body motion for generating CG animation and gesture recognition. Many methods using monocular moving pictures proposed in the past have problems to deal with 3D motion or error accumulation in estimating. In this paper we propose a method which allows tracking of 3D motion. The method is based on probabilistic estimation of stick model state from sequence of monocular images. We show effectiveness of proposed method, when applied to images of basic 2D and 3D motions, and show also that the proposed method can deal with quick human motion without errors.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) posture estimation / stick model / sequence
Paper # EID2000-311,IE2000-166
Date of Issue

Conference Information
Committee EID
Conference Date 2001/1/24(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 Electronic Information Displays (EID)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Human motion estimation from monocular moving pictures
Sub Title (in English)
Keyword(1) posture estimation
Keyword(2) stick model
Keyword(3) sequence
1st Author's Name Takao Seki
1st Author's Affiliation Graduate School of Engineering Shibaura Institute of Technology()
2nd Author's Name Takayuki Ito
2nd Author's Affiliation NHK Science and Technical Research Laboratories
Date 2001/1/24
Paper # EID2000-311,IE2000-166
Volume (vol) vol.100
Number (no) 605
Page pp.pp.-
#Pages 6
Date of Issue