Visual tracking using Locality-constrained Linear Coding and saliency map for visible light and infrared image sequences
作者：
Highlights：
•
• This paper proposes a tracking algorithm combining LLC and spectral residual. Because of the low computation cost of spectral residual-based saliency analysis, the proposed algorithm reduces the computational complexity.
• Under the framework of particle filter, the new update mechanism of particle weight are designed according to the saliency score.
• The proposed algorithm can be used for target tracking in both visible light and infrared images.
摘要
•This paper proposes a tracking algorithm combining LLC and spectral residual. Because of the low computation cost of spectral residual-based saliency analysis, the proposed algorithm reduces the computational complexity.•Under the framework of particle filter, the new update mechanism of particle weight are designed according to the saliency score.•The proposed algorithm can be used for target tracking in both visible light and infrared images.
论文关键词：Visual tracking,Visible light image,Infrared image,Locality-constrained Linear Coding,Spectral residual saliency,Particle filtering
论文评审过程：Received 19 March 2018, Revised 25 June 2018, Accepted 28 June 2018, Available online 5 July 2018, Version of Record 6 July 2018.
论文官网地址：https://doi.org/10.1016/j.image.2018.06.019
