Fusion of Head and Full-Body Detectors for Multi-Object Tracking
This improves pedestrian tracking accuracy for surveillance and autonomous systems, though it is an incremental advance in detector fusion.
The paper tackles multi-object tracking by fusing head and full-body detectors into a tracking system, formulating it as a weighted graph labeling problem solved with a new Frank-Wolfe-based solver. It achieves state-of-the-art results, ranking 2nd on MOT16 and 1st on MOT17 benchmarks, outperforming over 90 trackers.
In order to track all persons in a scene, the tracking-by-detection paradigm has proven to be a very effective approach. Yet, relying solely on a single detector is also a major limitation, as useful image information might be ignored. Consequently, this work demonstrates how to fuse two detectors into a tracking system. To obtain the trajectories, we propose to formulate tracking as a weighted graph labeling problem, resulting in a binary quadratic program. As such problems are NP-hard, the solution can only be approximated. Based on the Frank-Wolfe algorithm, we present a new solver that is crucial to handle such difficult problems. Evaluation on pedestrian tracking is provided for multiple scenarios, showing superior results over single detector tracking and standard QP-solvers. Finally, our tracker ranks 2nd on the MOT16 benchmark and 1st on the new MOT17 benchmark, outperforming over 90 trackers.