GATrack: Group-Aware features for multiple object tracking

Xiaolong Wang, Ping Hu, Rongyao Hu, Xiaofeng ZhuICME 2024 · OpenReview

Abstract

Current multiple object tracking methods typically associate two detected objects from consecutive frames via discriminative appearance features or motion modeling at the object level. However, in scenarios of dense crowds and prolonged occlusions, the extracted object-level features lack reliability, resulting in less effective target association. To tackle this challenge, we introduce GAT, a novel Group-Aware Transformer that learns to automatically group objects and complement targets’ appearance features with multi-level contextual information. In response to the prolonged occlusions issue, we further introduce an effective Trajectory Merging Mechanism (TMM), which relink the failed trajectories in prolonged occlusion based on motion patterns inferred from historical information. We demonstrate the effectiveness of our method with ablative experiments and exhibit outstanding tracking performance on the three popular multiple object tracking benchmarks MOT17, MOT20, and DanceTrack.
BibTeX
@inproceedings{wang2024gatrack,
  author = {Xiaolong Wang and Ping Hu and Rongyao Hu and Xiaofeng Zhu},
  title = {{GATrack: Group-Aware features for multiple object tracking}},
  booktitle = {ICME},
  year = {2024},
  url = {https://openreview.net/forum?id=JASzPzYDkB},
}

Loading related content...

Figure