Abstract
In this paper, we propose a multi-task correlation particle fifilter (MCPF) for robust visual tracking. We fifirst present the multi-task correlation fifilter (MCF) that takes the interdependencies among different features into account to learn correlation fifilters jointly. The proposed MCPF is designed to exploit and complement the strength of a MCF and a particle fifilter. Compared with existing tracking methods based on correlation fifilters and particle fifilters, the proposed tracker has several advantages. First, it can shepherd the sampled particles toward the modes of the target state distribution via the MCF, thereby resulting in robust tracking performance. Second, it can effectively handle large-scale variation via a particle sampling strategy. Third, it can effectively maintain multiple modes in the posterior density using fewer particles than conventional particle fifilters, thereby lowering the computational cost. Extensive experimental results on three benchmark datasets demonstrate that the proposed MCPF performs favorably against the state-of-the-art methods