Existing visual tracking methods usually localize a target object with a bounding box, in which the performance of the foreground object trackers or detectors is often affected by the inclusion of background clutter. To handle this problem, we learn a patch-based graph representation for visual tracking. The tracked object is modeled by with a graph by taking a set of non-overlapping image patches as nodes, in which the weight of each node indicates how likely it belongs to the foreground and edges are weighted for indicating the appearance compatibility of two neighboring nodes. This graph is dynamically learned and applied in object tracking and model updating. During the tracking process, the proposed algorithm performs three main steps in each frame. First, the graph is initialized by assigning binary weights of some image patches to indicate the object and background patches according to the predicted bounding box. Second, the graph is optimized to refine the patch weights by using a novel alternating direction method of multipliers. Third, the object feature representation is updated by imposing the weights of patches on the extracted image features. The object location is predicted by maximizing the classification score in the structured support vector machine. Extensive experiments show that the proposed tracking algorithm performs well against the state-of-the-art methods on large-scale benchmark datasets.
|Number of pages||13|
|Journal||IEEE transactions on pattern analysis and machine intelligence|
|Publication status||Published - 2019 Nov 1|
Bibliographical noteFunding Information:
This work is jointly supported by State Key Development Program under Grant 2018YFC0830103, National Natural Science Foundation of China (61702002, 61472002), Natural Science Foundation of Anhui Province (1808085QF187), China Postdoctoral Science Foundation, the Guangdong Natural Science Foundation Project for Research Teams under Grant 2017A030312006, and Open fund for Discipline Construction, Institute of Physical Science and Information Technology, Anhui University.
© 1979-2012 IEEE.
All Science Journal Classification (ASJC) codes
- Computer Vision and Pattern Recognition
- Computational Theory and Mathematics
- Artificial Intelligence
- Applied Mathematics