Share Email Print

Journal of Electronic Imaging

One-class support vector machine-assisted robust tracking
Author(s): Keren Fu; Chen Gong; Yu Qiao; Jie Yang; Irene Yu-Hua Gu
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

Recently, tracking is regarded as a binary classification problem by discriminative tracking methods. However, such binary classification may not fully handle the outliers, which may cause drifting. We argue that tracking may be regarded as one-class problem, which avoids gathering limited negative samples for background description. Inspired by the fact the positive feature space generated by one-class support vector machine (SVM) is bounded by a closed hyper sphere, we propose a tracking method utilizing one-class SVMs that adopt histograms of oriented gradient and 2bit binary patterns as features. Thus, it is called the one-class SVM tracker (OCST). Simultaneously, an efficient initialization and online updating scheme is proposed. Extensive experimental results prove that OCST outperforms some state-of-the-art discriminative tracking methods that tackle the problem using binary classifiers on providing accurate tracking and alleviating serious drifting.

Paper Details

Date Published: 8 April 2013
PDF: 12 pages
J. Electron. Imag. 22(2) 023002 doi: 10.1117/1.JEI.22.2.023002
Published in: Journal of Electronic Imaging Volume 22, Issue 2
Show Author Affiliations
Keren Fu, Shanghai Jiao Tong Univ. (China)
Chen Gong, Shanghai Jiao Tong Univ. (China)
Yu Qiao, Shanghai Jiao Tong Univ. (China)
Jie Yang, Shanghai Jiao Tong Univ. (China)
Irene Yu-Hua Gu, Chalmers Univ. of Technology (Sweden)

© SPIE. Terms of Use
Back to Top