Geometric Hypergraph Learning for Visual Tracking
This addresses the challenge of robust visual tracking for applications like surveillance or robotics, though it is incremental as it builds on graph-based methods by extending to hypergraphs.
The paper tackles the problem of visual tracking under large deformation and occlusion by proposing a geometric hypergraph learning method that exploits high-order geometric relations among multiple correspondences, achieving favorable performance against existing trackers on VOT2014 and Deform-SOT datasets.
Graph based representation is widely used in visual tracking field by finding correct correspondences between target parts in consecutive frames. However, most graph based trackers consider pairwise geometric relations between local parts. They do not make full use of the target's intrinsic structure, thereby making the representation easily disturbed by errors in pairwise affinities when large deformation and occlusion occur. In this paper, we propose a geometric hypergraph learning based tracking method, which fully exploits high-order geometric relations among multiple correspondences of parts in consecutive frames. Then visual tracking is formulated as the mode-seeking problem on the hypergraph in which vertices represent correspondence hypotheses and hyperedges describe high-order geometric relations. Besides, a confidence-aware sampling method is developed to select representative vertices and hyperedges to construct the geometric hypergraph for more robustness and scalability. The experiments are carried out on two challenging datasets (VOT2014 and Deform-SOT) to demonstrate that the proposed method performs favorable against other existing trackers.