Complementary Visual Tracking

In this paper, we propose a tracking algorithm which combines two complementary trackers together to supervise each other in dealing with different tracking problems. We design a region tracker based on high-level structure information (incremental PCA), and an object tracker based on mid-level visual cues, and adopt multi-state particle filter to integrate them into a robust tracking framework. While region tracker is more robust to scaling and in-plane rotation, object tracker is more competent in dealing with out-of-plane rotation and deformation. Experiment shows that these two tracker supervise each other against different challenges, and our Complementary Visual Tracking (CVT) framework can resist scaling, deformation, in-plane rotation and out-of-plane rotation simultaneously.