Presentation 2006/6/9
Stochastic Pedestrian Tracking based on Skeleton Model with Likelihood Estimation using Distance Transformed Images
Ryusuke MIYAMOTO, Jumpei ASHIDA, Hiroshi TSUTSUI, Yukihiro NAKAMURA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A novel pedestrian tracking scheme based on a particle filter is proposed, which uses a skeleton model of a pedestrian and distance transformed images for likelihood estimation. The six-stick skeleton model used in the proposed approach is very distinctive in representing a pedestrian simply but effectively, with which the efficient state space for the pedestrian tracking can be derived. Experimental results by using PETS sample sequences demonstrate that the proposed approach achieves high-accurate pedestrian tracking without any of prior learning.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Pedestrian Tracking / Particle Filter / Skeleton / Distance Transformation
Paper # SIS2006-17
Date of Issue

Conference Information
Committee SIS
Conference Date 2006/6/9(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 Smart Info-Media Systems (SIS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Stochastic Pedestrian Tracking based on Skeleton Model with Likelihood Estimation using Distance Transformed Images
Sub Title (in English)
Keyword(1) Pedestrian Tracking
Keyword(2) Particle Filter
Keyword(3) Skeleton
Keyword(4) Distance Transformation
1st Author's Name Ryusuke MIYAMOTO
1st Author's Affiliation Department of Communications and Computer Engineering, Graduate School of Informatics, Kyoto University()
2nd Author's Name Jumpei ASHIDA
2nd Author's Affiliation Department of Communications and Computer Engineering, Graduate School of Informatics, Kyoto University
3rd Author's Name Hiroshi TSUTSUI
3rd Author's Affiliation Department of Communications and Computer Engineering, Graduate School of Informatics, Kyoto University
4th Author's Name Yukihiro NAKAMURA
4th Author's Affiliation Department of Communications and Computer Engineering, Graduate School of Informatics, Kyoto University
Date 2006/6/9
Paper # SIS2006-17
Volume (vol) vol.106
Number (no) 96
Page pp.pp.-
#Pages 6
Date of Issue