UTrack: Multi-Object Tracking with Uncertain Detections
This work addresses safety-critical applications such as autonomous driving and surveillance by enhancing tracking reliability through uncertainty handling, though it is incremental as it builds on existing trackers.
The paper tackles the problem of multi-object tracking by incorporating empirical predictive uncertainty from object detectors into the tracking process, resulting in improved performance on benchmarks like MOT17, MOT20, DanceTrack, and KITTI.
The tracking-by-detection paradigm is the mainstream in multi-object tracking, associating tracks to the predictions of an object detector. Although exhibiting uncertainty through a confidence score, these predictions do not capture the entire variability of the inference process. For safety and security critical applications like autonomous driving, surveillance, etc., knowing this predictive uncertainty is essential though. Therefore, we introduce, for the first time, a fast way to obtain the empirical predictive distribution during object detection and incorporate that knowledge in multi-object tracking. Our mechanism can easily be integrated into state-of-the-art trackers, enabling them to fully exploit the uncertainty in the detections. Additionally, novel association methods are introduced that leverage the proposed mechanism. We demonstrate the effectiveness of our contribution on a variety of benchmarks, such as MOT17, MOT20, DanceTrack, and KITTI.