Correlation Filter Tracking: Beyond an Open-loop System

Qingyong Hu, Yulan Guo, Yunjin Chen, Jingjing Xiao and Wei An

Abstract

Most existing Correlation Filter (CF) based trackers do not use any feedback from tracking output and can be considered as open-loop systems. They are prone to drifting when the object endures occlusion and large appearance changes. In this paper, we propose a generic self-correction mechanism for CF based trackers by introducing a closed-loop feedback technique. Our mechanism first detects the abnormality in tracking output using the Gaussian shape prior of a response map, and then estimates the tracking error by minimizing the discrepancy of tracking output and the expected response. An optimal offset is finally given to regulate the tracking process and prevent tracking drifting through a feedback loop. Extensive experiments have been conducted on four large-scale benchmarks, including OTB-2013, OTB-2015, TC-128, and UAV123@10fps. Experimental results show that our self-correction mechanism can be used to improve the overall performance of most CF based trackers by a large margin.

Session

Posters

Files

Paper (PDF)
Supplementary (PDF)

DOI

10.5244/C.31.152
https://dx.doi.org/10.5244/C.31.152

Citation

Bibtex

            @inproceedings{BMVC2017_152,
                title={Correlation Filter Tracking: Beyond an Open-loop System},
                author={Qingyong Hu, Yulan Guo, Yunjin Chen, Jingjing Xiao and Wei An},
                year={2017},
                month={September},
                pages={152.1-152.12},
                articleno={152},
                numpages={12},
                booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
                publisher={BMVA Press},
                editor={Tae-Kyun Kim, Stefanos Zafeiriou, Gabriel Brostow and Krystian Mikolajczyk},
                doi={10.5244/C.31.152},
                isbn={1-901725-60-X},
                url={https://dx.doi.org/10.5244/C.31.152}
            }