ICIP 2006, Atlanta, GA
 

Slide Show

Atlanta Conv. & Vis. Bureau

 

Technical Program

Paper Detail

Paper:WP-L1.6
Session:Video Object Tracking
Time:Wednesday, October 11, 16:20 - 16:40
Presentation: Lecture
Title: PROBABILISTIC PEDESTRIAN TRACKING BASED ON A SKELETON MODEL
Authors: Jumpei Ashida; Kyoto University 
 Ryusuke Miyamoto; Kyoto University 
 Hiroshi Tsutsui; Kyoto University 
 Takao Onoye; Osaka University 
 Yukihiro Nakamura; Kyoto University 
Abstract: A novel pedestrian tracking scheme based on a particle filter is proposed, which adopts a skeleton model of a pedestrian as a state space model and uses 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 highly accurate pedestrian tracking without any of prior learning.