Correlation Filter Selection for Visual Tracking Using Reinforcement Learning

Xie, Yanchun, Xiao, Jimin, Huang, Kaizhu, Thiyagalingam, Jeyarajan ORCID: 0000-0002-2167-1343 and Zhao, Yao
(2018) Correlation Filter Selection for Visual Tracking Using Reinforcement Learning. IEEE Transactions on Circuits and Systems for Video Technology, 30 (1). pp. 192-204.

[thumbnail of 1811.03196.pdf] Text
1811.03196.pdf - Submitted version

Download (4MB) | Preview


Correlation filter has been proven to be an effective tool for a number of approaches in visual tracking, particularly for seeking a good balance between tracking accuracy and speed. However, correlation filter-based models are susceptible to wrong updates stemming from inaccurate tracking results. To date, very little effort has been devoted towards handling the correlation filter update problem. In this paper, we propose a novel approach to address the correlation filter update problem. In our approach, we update and maintain multiple correlation filter models in parallel, and we use deep reinforcement learning for the selection of an optimal correlation filter model among them. To facilitate the decision process in an efficient manner, we propose a decision-net to deal with target appearance modeling, which is trained through hundreds of challenging videos using proximal policy optimization and a lightweight learning network. An exhaustive evaluation of the proposed approach on the OTB100 and OTB2013 benchmarks shows that the approach is effective enough to achieve the average success rate of 62.3% and the average precision score of 81.2%, both exceeding the performance of traditional correlation filter-based trackers.

Item Type: Article
Uncontrolled Keywords: Correlation filter, visual tracking, reinforcement learning, model selection, deep learning
Depositing User: Symplectic Admin
Date Deposited: 28 Feb 2020 10:22
Last Modified: 14 Mar 2024 17:26
DOI: 10.1109/tcsvt.2018.2889488
Related URLs: