Fast two-cycle curve evolution with narrow perception of background for object tracking and contour refinement
作者：
Highlights：
• A novel level set method without solving partial differential equations.
• Two tracking levels proposed: object tracking and contour refinement.
• The speed functions concerning the feature difference between foreground and close background.
• Fast two-cycle curve evolution process.
• Extensive evaluations and comparisons with the baseline methods.
摘要
Highlights•A novel level set method without solving partial differential equations.•Two tracking levels proposed: object tracking and contour refinement.•The speed functions concerning the feature difference between foreground and close background.•Fast two-cycle curve evolution process.•Extensive evaluations and comparisons with the baseline methods.
论文关键词：Object tracking,Contour refinement,Curve evolution,Region competition,Maximum likelihood
论文评审过程：Received 26 May 2015, Revised 16 January 2016, Accepted 1 March 2016, Available online 4 March 2016, Version of Record 24 March 2016.
论文官网地址：https://doi.org/10.1016/j.image.2016.03.001
