Presentation	1999/3/19 Real-Time Human Pose Estimation from Stereoscopic Image Sequence Using a Human Stick Model Naonori KATO, Takeshi SHAKUNAGA,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	We propose a method for real-time human pose estimation from stereoscopic image sequence. A set of 2D sticks are extracted from each image, by using background suppression, skeletonization and line fitting. A 3D structure, named a 3D stick sketch, is reconstructed from a stereoscopic pair of the 2D stick set. Finally, the 3D stick sketch is matched with a human model named the 3D stick model. The matching problem is reduced to the labeling problem, and solved using the sketch-model correspondence tree. This method is implemented on PC with an image processing board and 2.8 images can be processed in a second.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	stereo motion / human pose estimation / stick model / labeling real-time
Paper #	PRMU98-265
Date of Issue

Conference Information
Committee	PRMU
Conference Date	1999/3/19(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 Human Pose Estimation from Stereoscopic Image Sequence Using a Human Stick Model
Sub Title (in English)
Keyword(1)	stereo motion
Keyword(2)	human pose estimation
Keyword(3)	stick model
Keyword(4)	labeling real-time
1st Author's Name	Naonori KATO
1st Author's Affiliation	Department of Information Technology, Okayama University()
2nd Author's Name	Takeshi SHAKUNAGA
2nd Author's Affiliation	Department of Information Technology, Okayama University
Date	1999/3/19
Paper #	PRMU98-265
Volume (vol)	vol.98
Number (no)	678
Page	pp.pp.-
#Pages	8
Date of Issue