Journal
IEEE TRANSACTIONS ON CYBERNETICS
Volume 47, Issue 12, Pages 4182-4195Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCYB.2016.2626275
Keywords
Confidence-aware sampling; correspondence hypotheses; deformation; geometric hypergraph learning; mode-seeking; occlusion; visual tracking
Categories
Funding
- National Natural Science Foundation of China [61620106009, 61332016, 61472388, 61429201]
- Key Research Program of Frontier Sciences, CAS [QYZDJ-SSW-SYS013]
- ARO [W911NF-15-1-0290]
- Faculty Research Gift Awards by NEC Laboratories of America
- U.S. National Science Foundation Research Grant through Division of Computing and Communication Foundations [1319800]
- Blippar
- Direct For Computer & Info Scie & Enginr
- Division of Computing and Communication Foundations [1319800] Funding Source: National Science Foundation
- Div Of Information & Intelligent Systems
- Direct For Computer & Info Scie & Enginr [1537257] Funding Source: National Science Foundation
Ask authors/readers for more resources
Graph-based representation is widely used in visual tracking field by finding correct correspondences between target parts in different 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 or occlusion occurs. 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 different 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 among correspondences. 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 three challenging datasets (VOT2014, OTB100, and Deform-SOT) to demonstrate that our method performs favorably against other existing trackers.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available