Visual tracking based on edge field with object proposal association
作者：
Highlights：
• We present a novel tracking system based on object proposal association.
• We apply our objectness algorithm to the visual tracking problem.
• We add the motion smoothness constraint and use edge features as well as color features.
• We extensively evaluate our tracker by using vast test sequences.
• We compare our tracker with recent deep learning based trackers.
摘要
•We present a novel tracking system based on object proposal association.•We apply our objectness algorithm to the visual tracking problem.•We add the motion smoothness constraint and use edge features as well as color features.•We extensively evaluate our tracker by using vast test sequences.•We compare our tracker with recent deep learning based trackers.
论文关键词：Visual tracking,Object proposal
论文评审过程：Received 22 November 2016, Revised 10 July 2017, Accepted 10 November 2017, Available online 21 November 2017, Version of Record 24 November 2017.
论文官网地址：https://doi.org/10.1016/j.imavis.2017.11.004
