A multi-view model for visual tracking via correlation filters

作者：

Highlights：

• The first contribution is proposing to combine features from distinct views to do tracking via correlation filters. The fusion method is induced by minimizing the Kullback–Leibler (KL) divergence under a probabilistic framework.

• The second contribution is proposing a simple and effective scale evaluation model.

摘要

•The first contribution is proposing to combine features from distinct views to do tracking via correlation filters. The fusion method is induced by minimizing the Kullback–Leibler (KL) divergence under a probabilistic framework.•The second contribution is proposing a simple and effective scale evaluation model.

论文关键词：Visual object tracking,Multi-view,Correlation filters,Robust tracking

论文评审过程：Received 17 March 2016, Revised 10 September 2016, Accepted 18 September 2016, Available online 19 September 2016, Version of Record 20 October 2016.

论文官网地址：https://doi.org/10.1016/j.knosys.2016.09.014