Visual Tracking Via Kernel Sparse Representation With Multikernel Fusion

It remains a challenging task to track an object robustly due to factors such as pose variation, illumination change, occlusion, and background clutter. In the past decades, a number of researchers have been attracted to tackling these difficulties, and they proposed many effective methods. Among them, sparse representation-based tracking method is a promising. While much success has been demonstrated, there are several issues that still need to be addressed. First, the introduction to trivial occlusion templates brings a high computational cost of this method. Second, the utilization of raw template object representation makes this method difficult to adopt sophisticated object features. To solve these problems, we consider the sparse representation problem in a kernel space and propose a kernel sparse representation (KSR)-based tracking algorithm. Under the kernel representation, it is not necessary to introduce trivial occlusion templates in order to reduce the computational cost. Furthermore, multikernel fusion allows our method to use multiple sophisticated object features, such as spatial color histogram and spatial gradient-orientation histogram, and let these features complement each other during the tracking process. Comparative experiments on challenging scenes demonstrate that our KSR-based tracking algorithm outperforms the state-of-the-art approaches in tracking accuracy.