Abstract

The mean-shift algorithm has achieved considerable success in object tracking due to its simplicity and efficiency. Color histogram is a common feature in the description of an object. However, the kernel-based color histogram may not have the ability to discriminate the object from clutter background. To boost the discriminating ability of the feature, based on background contrasting, this letter presents an improved Bhattacharyya similarity metric for mean-shift tracking. Experiments show that the proposed tracker is more robust in relation to background clutter.

© 2012 Chinese Optics Letters

Infrared target tracking with kernel-based performance metric and eigenvalue-based similarity measure

Jianguo Ling, Erqi Liu, Haiyan Liang, and Jie Yang
Appl. Opt. 46(16) 3239-3252 (2007)

Robust object tracking based on local discriminative sparse representation

Xin Wang, Siqiu Shen, Chen Ning, Yuzhen Zhang, and Guofang Lv
J. Opt. Soc. Am. A 34(4) 533-544 (2017)

Improved infrared target-tracking algorithm based on mean shift

Zhile Wang, Qingyu Hou, and Ling Hao
Appl. Opt. 51(21) 5051-5059 (2012)

Infrared human tracking with improved mean shift algorithm based on multicue fusion

Xin Wang, Lei Liu, and Zhenmin Tang
Appl. Opt. 48(21) 4201-4212 (2009)

Spatiotemporal difference-of-Gaussians filters for robust infrared small target tracking in various complex scenes

Xin Wang, Chen Ning, and Lizhong Xu
Appl. Opt. 54(7) 1573-1586 (2015)