Robust visual tracking via co-trained Kernelized correlation filters

作者：

Highlights：

• We train a pool of discriminative classifiers jointly in a closed-form fashion for visual tracking.

• We propose analytic model for datasets of thousands of translated patches.

• It is able to outperform the baseline by a larger margin.

摘要

•We train a pool of discriminative classifiers jointly in a closed-form fashion for visual tracking.•We propose analytic model for datasets of thousands of translated patches.•It is able to outperform the baseline by a larger margin.

论文关键词：Visual tracking,High speed,Kernelized correlation filter,Ensemble tracking,KCF tracker,COKCF tracker,Correlation filter

论文评审过程：Received 12 October 2016, Revised 14 March 2017, Accepted 4 April 2017, Available online 14 April 2017, Version of Record 19 April 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.04.004