Geometric structure-constraint tracking with confident parts
作者：
Highlights：
• We construct an adaptive structure representation model of object.
• We infer state of object with confident parts of object.
• Confident parts are obtained by measuring appearance variance and deformation.
• Robust for tracking with multiple challenges especially deformation and occlusion.
摘要
Highlights•We construct an adaptive structure representation model of object.•We infer state of object with confident parts of object.•Confident parts are obtained by measuring appearance variance and deformation.•Robust for tracking with multiple challenges especially deformation and occlusion.
论文关键词：Visual tracking,Structure representation,Dynamic programming,State estimation
论文评审过程：Received 12 December 2014, Revised 3 June 2015, Accepted 3 June 2015, Available online 11 June 2015, Version of Record 23 June 2015.
论文官网地址：https://doi.org/10.1016/j.image.2015.06.001
