Occlusion Aware Online Deformable Object Tracking Based on Structure-Aware Hyper-Graph

Recent advances in online visual tracking focus on designing part-based model to handle the deformation and occlusion challenges. This paper describes a new and efficient method for online deformable object tracking. Different from most existing methods, this paper exploits higher order structural dependences of different parts of the tracking target in multiple consecutive frames. In this project, we present a robust tracking method by exploiting a fragment-based appearance model with consideration of both temporal continuity and discontinuity information. In the first stage, by adopting the estimated occlusion state as a prior, the optimal state of the tracked object can be obtained by solving an optimization problem, where the objective function is designed based on the classification score, occlusion prior, and temporal continuity information. In the second stage, we propose a discriminative occlusion model, which exploits both foreground and background information to detect the possible occlusion, and also models the consistency of occlusion labels among different frames. The experimental result of the proposed method shows considerable improvement in performance over the state-of-the-art tracking