An improved Kernelized Correlation Filter tracking algorithm based on multi-channel memory model

作者：

Highlights：

• A multi-channel memory based updating model is established.

• An improved KCF tracking algorithm based on multi-channel memory model is proposed.

• High accuracy and robustness with deformation, occlusion and background clutter.

摘要

•A multi-channel memory based updating model is established.•An improved KCF tracking algorithm based on multi-channel memory model is proposed.•High accuracy and robustness with deformation, occlusion and background clutter.

论文关键词：Multi-channel memory,Kernelized Correlation Filter,Target tracking

论文评审过程：Received 20 August 2018, Revised 28 May 2019, Accepted 29 May 2019, Available online 24 June 2019, Version of Record 16 July 2019.

论文官网地址：https://doi.org/10.1016/j.image.2019.05.019