School of Computer and Communication, Hunan University of Technology, Zhuzhou, Hunan, 412008, China

---

Abstract—A robust visual kernel tracking approach is presented for solving the problem of existing background pixels in object model. At first, after definition of fuzzy set on image is given, a fuzzy factor is embedded into object model to form the fuzzy kernel representation. Secondly, a fuzzy membership functions are generated by centersurround approach and log likelihood ratio of feature distributions. Thirdly, details about fuzzy kernel tracking algorithm is provided. After that, methods of parameter selection and performance evaluation for tracking algorithm are proposed. At last, a mass of experimental results are done to show our method can reduce the influence of the incomplete representation of object model via integrating both color features and background features.

Index Terms—Fuzzy Kernel Histogram, Visual Tracking, Fuzzy Factor, Fuzzy Membership Function

[PDF]

Cite: Zhiqiang Wen, Yongxin Long, and Zhaoyi Peng, " Robust Visual Tracking via Fuzzy Kernel Representation," Journal of Computers vol. 8, no. 5, pp. 1292-1297, 2013.