The problem of Multiple Object Tracking (MOT) consists in following the trajectory of different objects in a sequence, usually a video. In recent years, with the rise of Deep Learning, the algorithms that provide a solution to this problem have benefited from the representational power of deep models. This paper provides a comprehensive survey on works that employ Deep Learning models to solve the task of MOT on single-camera videos. Four main steps in MOT algorithms are identified, and an in-depth review of how Deep Learning was employed in each one of these stages is presented. A complete experimental comparison of the presented works on the three MOTChallenge datasets is also provided, identifying a number of similarities among the top-performing methods and presenting some possible future research directions.
- Pub Date:
- July 2019
- Computer Science - Computer Vision and Pattern Recognition;
- Computer Science - Machine Learning;
- Statistics - Machine Learning
- Accepted in Neurocomputing, 2019. New in v4: updated license in compliance with Elsevier policy. Main text: 29 pages, 10 figures, 7 tables. Summary table in appendix at the end of the paper