Multi-task Correlation Particle Filter for Robust Object Tracking

Tianzhu Zhang      Changsheng Xu      Ming-Hsuan Yang

Figure 1. Comparisons of the proposed MCPF tracker with the state-of-the-art correlation filter trackers (DSST, KCF, CF2, and HDT) on the motorRolling, KiteSurf, and car4 sequences. These trackers perform differently as various features and scale handling strategies are used. The proposed algorithm performs favorably against these trackers.

Abstract

In this paper, we propose a multi-task correlation particle filter (MCPF) for robust visual tracking. We first present the multi-task correlation filter (MCF) that takes the interdependencies among different features into account to learn correlation filters jointly. The proposed MCPF is designed to exploit and complement the strength of a MCF and a particle filter. Compared with existing tracking methods based on correlation filters and particle filters, 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 filters, 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.

Related Publications

Experimental Results

Figure 2. Precision and success plots over all the 50 sequences using one-pass evaluation on the OTB-2013 Dataset. The legend contains the area-under-the-curve score and the average distance precision score at 20 pixels for each tracker. Our MCPF method performs favorably against the state-of-the-art trackers.

Figure 3. Precision and success plots over all 100 sequences using one-pass evaluation on the OTB-2015 dataset. The legend contains the area-under-the-curve score and the average distance precision score at 20 pixels for each tracker. Our MCPF method performs favorably against the state-of-the-art trackers.

Figure 4. Precision and success plots over the 128 sequences using one-pass evaluation on the Temple Color dataset. The legend contains the area-under-the-curve score and the average distance precision score at 20 pixels for each tracker. Our MCPF method performs favorably against the state-of-the-art trackers.

Video Tracking Results

We show tracking results on the OTB2013 dataset.