Learning reliable-spatial and spatial-variation regularization correlation filters for visual tracking

作者：

Highlights：

• A novel spatial regularization strategy for solving the boundary effects in the correlation filters is proposed.

• A spatial variation regularization term is introduced into the standard SRDCF to avoid overfitting.

• The proposed algorithm is efficiently solved by the alternating direction method of multipliers in very few iterations.

摘要

•A novel spatial regularization strategy for solving the boundary effects in the correlation filters is proposed.•A spatial variation regularization term is introduced into the standard SRDCF to avoid overfitting.•The proposed algorithm is efficiently solved by the alternating direction method of multipliers in very few iterations.

论文关键词：Correlation filters,Visual tracking,Spatial regularization

论文评审过程：Received 2 November 2019, Revised 19 December 2019, Accepted 29 December 2019, Available online 10 January 2020, Version of Record 21 January 2020.

论文官网地址：https://doi.org/10.1016/j.imavis.2020.103869