Paper Info
Title
Multiple Target Tracking by Appearance-Based Condensation Tracker using Structure Information
Abstract
Multiple target tracking is a challenging problem, especially when targets are frequently crossing each other. It becomes very difficult and confusing when some targets are often occluded by other targets. This paper proposes a novel tracking method for the problem using an appearance-based condensation tracker. In order to overcome difficulties in the occlusion problem, a target object is regarded as a set of partsthat constrains each other in the target structure. While each part is tracked basically in the condensation method, all the parts cooperate in the drift step of the condensation. Experimental results show the effectiveness of the proposed method formultiple person tracking and human face tracking.
Year
DOI
Venue
2004
10.1109/ICPR.2004.604
ICPR (3)
Keywords
Field
DocType
novel tracking method,target structure,appearance-based condensation tracker,human face tracking,structure information,multiple target tracking,condensation method,target object,challenging problem,proposed method formultiple person,occlusion problem,face tracking,face recognition
Computer vision,Object detection,Facial recognition system,Pattern recognition,Computer science,Condensation,Appearance based,Tracking system,Video tracking,Artificial intelligence,Facial motion capture
Conference
ISSN
ISBN
Citations 
1051-4651
0-7695-2128-2
10
PageRank 
References 
Authors
0.75
1
2
Name
Order
Citations
PageRank
Junji Satake1468.40
Takeshi Shakunaga219243.46