Collaborative Correlation Tracking

Guibo Zhu, Jinqiao Wang, Yi Wu and Hanqing Lu

Abstract

Correlation filter based tracking has attracted many researchers' attention in recent years for high efficiency and robustness. Most existing works focus on exploiting different characteristics with correlation filters for visual tracking, e.g. circulant structure, kernel trick, effective feature representation and context information. However, how to handle the scale variation and the model drift is still an open problem. In this paper, we propose a unified collaborative correlation tracking framework that can handle both problems. Firstly, we extend correlation tracking filter by embedding the scale factor into the kernelized matrix to handle the scale variation. Then a novel long-term CUR filter for detection is learnt efficiently by random sampling to alleviate the model drift problem by detecting effective object candidates in the collaborative framework. In this way, the proposed approach could estimate the object state accurately and handle the model drift problem effectively. Extensive experiments show the superiority of the proposed method.

Session

Tracking and Pose Estimation

Files

Extended Abstract (PDF, 45K)
Paper (PDF, 151K)

DOI

10.5244/C.29.184
https://dx.doi.org/10.5244/C.29.184

Citation

Bibtex

@inproceedings{BMVC2015_184,
	title={Collaborative Correlation Tracking},
	author={Guibo Zhu and Jinqiao Wang and Yi Wu and Hanqing Lu},
	year={2015},
	month={September},
	pages={184.1-184.12},
	articleno={184},
	numpages={12},
	booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
	publisher={BMVA Press},
	editor={Xianghua Xie, Mark W. Jones, and Gary K. L. Tam},
	doi={10.5244/C.29.184},
	isbn={1-901725-53-7},
	url={https://dx.doi.org/10.5244/C.29.184}
}