Learn-select-track: An approach to multi-object tracking

作者：

Highlights：

• Density based clustering for learning object features to track.

• Density based clustering for tracking objects in videos.

• Training and tracking without knowing the number of objects.

• Performance of the tracking and training algorithms.

摘要

•Density based clustering for learning object features to track.•Density based clustering for tracking objects in videos.•Training and tracking without knowing the number of objects.•Performance of the tracking and training algorithms.

论文关键词：Multi-object tracking,Object colours,Density-based clustering,Low level local features

论文评审过程：Received 15 October 2018, Revised 20 February 2019, Accepted 20 February 2019, Available online 26 February 2019, Version of Record 2 March 2019.

论文官网地址：https://doi.org/10.1016/j.image.2019.02.009