Robust tracking with interest points: A sparse representation approach
作者：
Highlights：
• The proposed tracker combines the flexibility of interest points and robustness of sparse representation.
• Proposed a robust matching criteria for reliable tracking via L1 minimization
• The proposed tracker is computationally efficient and provides real-time performance.
• The tracker is benchmarked with many publicly available complex video sequences.
• Performance is compared with many recent state of the art trackers using 50 benchmark video dataset.
摘要
•The proposed tracker combines the flexibility of interest points and robustness of sparse representation.•Proposed a robust matching criteria for reliable tracking via L1 minimization•The proposed tracker is computationally efficient and provides real-time performance.•The tracker is benchmarked with many publicly available complex video sequences.•Performance is compared with many recent state of the art trackers using 50 benchmark video dataset.
论文关键词：Visual tracking,l1 minimization,Interest points,Harris corner,Sparse representation
论文评审过程：Received 6 December 2013, Revised 14 July 2014, Accepted 21 October 2014, Available online 7 November 2014.
论文官网地址：https://doi.org/10.1016/j.imavis.2014.10.006
