DocumentCode :
104150
Title :
Locally discriminative stable model for visual tracking with clustering and principle component analysis
Author :
Canlong Zhang ; Zhongliang Jing ; Yanping Tang ; Bo Jin ; Gang Xiao
Author_Institution :
Sch. of Aeronaut. & Astronaut., Shanghai Jiao Tong Univ., Shanghai, China
Volume :
7
Issue :
3
fYear :
2013
fDate :
Jun-13
Firstpage :
151
Lastpage :
162
Abstract :
The challenge of visual tracking mainly comes from intrinsic appearance variations of the target and extrinsic environment changes around the target in a long duration, so the tracker that can simultaneously tolerate these variabilities is largely expected. In this study, the authors propose a new tracking approach based on discriminative stable regions (DSRs). The DSRs are obtained based on the criterion of maximal local entropy and spatial discrimination, which enables the tracker to handle well distractors and appearance variations. The collaborative tracking incorporated hierarchical clustering can tolerate motion noise and occlusions. In addition, as an efficient tool, the principle component analysis is used to discover the potential affine relation between DSR and the target, which timely adapts to the shape deformation of the target. Extensive experiments show that the proposed method achieves superior performance in many challenging target tracking tasks.
Keywords :
image motion analysis; object tracking; pattern clustering; principal component analysis; target tracking; DSR; discriminative stable regions; hierarchical clustering; intrinsic appearance variations; locally discriminative stable model; maximal local entropy criterion; motion noise; occlusions; principle component analysis; spatial discrimination; target tracking; visual tracking approach;
fLanguage :
English
Journal_Title :
Computer Vision, IET
Publisher :
iet
ISSN :
1751-9632
Type :
jour
DOI :
10.1049/iet-cvi.2012.0180
Filename :
6531138
Link To Document :
بازگشت