Temporal Correlation Meets Embedding: Towards a 2nd Generation of JDE-based Real-Time Multi-Object Tracking
This work addresses the problem of limited utility of appearance features in real-time MOT for applications like video surveillance and autonomous driving, representing an incremental improvement over existing JDE methods.
The paper tackles the challenge of improving appearance feature discriminability in Joint Detection and Embedding (JDE) trackers for Multi-Object Tracking (MOT) by proposing a new learning approach that uses cross-correlation to capture temporal information from consecutive frames, resulting in state-of-the-art performance with 56.8 HOTA, 58.1 IDF1, and 92.5 MOTA on the DanceTrack dataset.
Joint Detection and Embedding (JDE) trackers have demonstrated excellent performance in Multi-Object Tracking (MOT) tasks by incorporating the extraction of appearance features as auxiliary tasks through embedding Re-Identification task (ReID) into the detector, achieving a balance between inference speed and tracking performance. However, solving the competition between the detector and the feature extractor has always been a challenge. Meanwhile, the issue of directly embedding the ReID task into MOT has remained unresolved. The lack of high discriminability in appearance features results in their limited utility. In this paper, a new learning approach using cross-correlation to capture temporal information of objects is proposed. The feature extraction network is no longer trained solely on appearance features from each frame but learns richer motion features by utilizing feature heatmaps from consecutive frames, which addresses the challenge of inter-class feature similarity. Furthermore, our learning approach is applied to a more lightweight feature extraction network, and treat the feature matching scores as strong cues rather than auxiliary cues, with an appropriate weight calculation to reflect the compatibility between our obtained features and the MOT task. Our tracker, named TCBTrack, achieves state-of-the-art performance on multiple public benchmarks, i.e., MOT17, MOT20, and DanceTrack datasets. Specifically, on the DanceTrack test set, we achieve 56.8 HOTA, 58.1 IDF1 and 92.5 MOTA, making it the best online tracker capable of achieving real-time performance. Comparative evaluations with other trackers prove that our tracker achieves the best balance between speed, robustness and accuracy. Code is available at https://github.com/yfzhang1214/TCBTrack.