Abstract

It is difficult for a single-feature tracking algorithm to achieve strong robustness under a complex environment. To solve this problem, we proposed a multifeature fusion tracking algorithm that is based on game theory. By focusing on color and texture features as two gamers, this algorithm accomplishes tracking by using a mean shift iterative formula to search for the Nash equilibrium of the game. The contribution of different features is always keeping the state of optical balance, so that the algorithm can fully take advantage of feature fusion. According to the experiment results, this algorithm proves to possess good performance, especially under the condition of scene variation, target occlusion, and similar interference.

© 2017 Optical Society of America

Color spatial feature-based approach for multiple-vehicle tracking

Qi Wei, Zhang Xiong, and Chao Li
Appl. Opt. 49(31) 6043-6056 (2010)

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)

Real-time infrared target tracking based on ℓ₁ minimization and compressive features

Ying Li, Pengcheng Li, and Qiang Shen
Appl. Opt. 53(28) 6518-6526 (2014)

Oversaturated part-based visual tracking via spatio-temporal context learning

Wei Liu, Jicheng Li, Zhiguang Shi, Xiaotian Chen, and Xiao Chen
Appl. Opt. 55(25) 6960-6968 (2016)