Presentation 2012-03-30
Human Motion Tracking using 3D Sparse Template on Kinect Data
Yohei SHINOMIYA, Hideaki KATO, Takeshi SHAKUNAGA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A 3d sparse template tracker is proposed for human motion tracking when Kinect sensor is available. Motion of the upper half body is tracked in 14D pose space where a point represents a pose of torso and arms. Combining appearance data and depth data, the tracker can efficiently estimate a pose in each frame by a coarse-to-fine pose estimation algorithm. Experimental results show effectiveness of the proposed method on both simulation data and real image sequences.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Human motion tracking / 3d sparse template / Kinect data / articulated object / 14d pose space / coarse-to-fine tracker / cascade pose estimation
Paper # PRMU2011-264,HIP2011-92
Date of Issue

Conference Information
Committee HIP
Conference Date 2012/3/22(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 Human Information Processing (HIP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Human Motion Tracking using 3D Sparse Template on Kinect Data
Sub Title (in English)
Keyword(1) Human motion tracking
Keyword(2) 3d sparse template
Keyword(3) Kinect data
Keyword(4) articulated object
Keyword(5) 14d pose space
Keyword(6) coarse-to-fine tracker
Keyword(7) cascade pose estimation
1st Author's Name Yohei SHINOMIYA
1st Author's Affiliation Department of Computer Science, Okayama University()
2nd Author's Name Hideaki KATO
2nd Author's Affiliation Department of Computer Science, Okayama University
3rd Author's Name Takeshi SHAKUNAGA
3rd Author's Affiliation Department of Computer Science, Okayama University
Date 2012-03-30
Paper # PRMU2011-264,HIP2011-92
Volume (vol) vol.111
Number (no) 500
Page pp.pp.-
#Pages 6
Date of Issue