UncertaintyTrack: Exploiting Detection and Localization Uncertainty in Multi-Object Tracking
This work addresses safety-critical issues in autonomous driving by reducing tracking errors, though it is incremental as it builds on existing tracking-by-detection and probabilistic detection methods.
The paper tackles the problem of multi-object tracking in autonomous driving by incorporating localization uncertainty from probabilistic object detectors into tracking-by-detection methods, resulting in a 19% reduction in ID switches and a 2-3% improvement in mMOTA on the Berkeley Deep Drive MOT dataset.
Multi-object tracking (MOT) methods have seen a significant boost in performance recently, due to strong interest from the research community and steadily improving object detection methods. The majority of tracking methods follow the tracking-by-detection (TBD) paradigm, blindly trust the incoming detections with no sense of their associated localization uncertainty. This lack of uncertainty awareness poses a problem in safety-critical tasks such as autonomous driving where passengers could be put at risk due to erroneous detections that have propagated to downstream tasks, including MOT. While there are existing works in probabilistic object detection that predict the localization uncertainty around the boxes, no work in 2D MOT for autonomous driving has studied whether these estimates are meaningful enough to be leveraged effectively in object tracking. We introduce UncertaintyTrack, a collection of extensions that can be applied to multiple TBD trackers to account for localization uncertainty estimates from probabilistic object detectors. Experiments on the Berkeley Deep Drive MOT dataset show that the combination of our method and informative uncertainty estimates reduces the number of ID switches by around 19\% and improves mMOTA by 2-3%. The source code is available at https://github.com/TRAILab/UncertaintyTrack