Occlusion detection and drift-avoidance framework for 2D visual object tracking

作者：

Highlights：

• A 2D tracking framework is proposed, that avoids drifts by detecting and handling occlusions.

• Occlusions/drifts are detected from the whole tracker response maps.

• The solution targets on potential UAV implementation.

• Object re-detection is performed by the tracker model.

摘要

•A 2D tracking framework is proposed, that avoids drifts by detecting and handling occlusions.•Occlusions/drifts are detected from the whole tracker response maps.•The solution targets on potential UAV implementation.•Object re-detection is performed by the tracker model.

论文关键词：2D visual object tracking,Occlusion-detection,Fast motion change,ODDA framework

论文评审过程：Received 11 October 2019, Revised 25 September 2020, Accepted 27 September 2020, Available online 3 October 2020, Version of Record 12 October 2020.

论文官网地址：https://doi.org/10.1016/j.image.2020.116011