FusionSORT: Fusion Methods for Online Multi-object Visual Tracking
This work addresses data association in multi-object visual tracking for computer vision applications, but it is incremental as it focuses on comparing existing fusion techniques rather than introducing new ones.
The paper investigated four fusion methods for associating detections to tracklets in multi-object visual tracking, incorporating both strong and weak cues, and found that the choice of fusion method is crucial for performance across MOT17, MOT20, and DanceTrack datasets.
In this work, we investigate four different fusion methods for associating detections to tracklets in multi-object visual tracking. In addition to considering strong cues such as motion and appearance information, we also consider weak cues such as height intersection-over-union (height-IoU) and tracklet confidence information in the data association using different fusion methods. These fusion methods include minimum, weighted sum based on IoU, Kalman filter (KF) gating, and hadamard product of costs due to the different cues. We conduct extensive evaluations on validation sets of MOT17, MOT20 and DanceTrack datasets, and find out that the choice of a fusion method is key for data association in multi-object visual tracking. We hope that this investigative work helps the computer vision research community to use the right fusion method for data association in multi-object visual tracking.