Online maximum a posteriori tracking of multiple objects using sequential trajectory prior
作者：
Highlights：
• Sequential trajectory prior can assist the object detection and data association.
• The detections and trajectories can be jointly optimized to improve performance.
• The proposed method outperforms the state-of-art multi-object tracking methods.
摘要
•Sequential trajectory prior can assist the object detection and data association.•The detections and trajectories can be jointly optimized to improve performance.•The proposed method outperforms the state-of-art multi-object tracking methods.
论文关键词：Online multi-object tracking,Sequential trajectory prior,Maximum a posteriori,Data association
论文评审过程：Received 1 November 2017, Revised 10 September 2019, Accepted 8 December 2019, Available online 13 December 2019, Version of Record 7 January 2020.
论文官网地址：https://doi.org/10.1016/j.imavis.2019.103867
