Visual Tracking via Weighted Local Cosine Similarity

In this paper, we propose a novel weighted local cosine similarity (WLCS) and apply it to visual tracking. First, we present the local cosine similarity to measure the similarities between the target template and candidates, and provide some theoretical insights on it. Second, we develop an objective function to model the discriminative ability of local components, and use a quadratic programming method to solve the objective function and to obtain the discriminative weights. Finally, we design an effective and efficient tracker based on the WLCS method and a simple update manner within the particle filter framework. Experimental results on several challenging image sequences show that the proposed tracker achieves better performance than other competing methods.