Chaotic target representation for robust object tracking

作者：

Highlights：

• In this paper, a chaotic sparse representation is introduced to balance the local and global features for object tracking.

• The fractal dimension and the position distance are used to provide an efficient online learning procedure.

• This method improves the effectiveness and efficiency of the online classifier in the online MIL tracker.

摘要

•In this paper, a chaotic sparse representation is introduced to balance the local and global features for object tracking.•The fractal dimension and the position distance are used to provide an efficient online learning procedure.•This method improves the effectiveness and efficiency of the online classifier in the online MIL tracker.

论文关键词：Chaos theory,Fractal theory,Online multiple-instance learning,Object tracking

论文评审过程：Received 10 August 2016, Revised 11 February 2017, Accepted 12 February 2017, Available online 24 February 2017, Version of Record 6 March 2017.

论文官网地址：https://doi.org/10.1016/j.image.2017.02.004