LCO: Lightweight Convolution Operators for fast tracking

作者：

Highlights：

• This is the first work that conceptually combines the ideas in BACF and ECO.

• We propose an optimization strategy for efficient online filter learning.

• LCO scarcely suffers from residual boundary effects in circular correlation.

摘要

•This is the first work that conceptually combines the ideas in BACF and ECO.•We propose an optimization strategy for efficient online filter learning.•LCO scarcely suffers from residual boundary effects in circular correlation.

论文关键词：Correlation filter,Feature compression,Spatial constraints

论文评审过程：Received 7 November 2017, Revised 29 March 2018, Accepted 9 October 2018, Available online 17 October 2018, Version of Record 3 November 2018.

论文官网地址：https://doi.org/10.1016/j.imavis.2018.10.001