Efficient Data Association and Uncertainty Quantification for Multi-Object Tracking
This addresses trajectory precision issues in complex scenes for applications like motion analysis, but it is incremental as it builds on Bayesian tracking methods.
The paper tackles the problem of robust data association and uncertainty quantification in multi-object tracking, proposing the Joint Posterior Tracker (JPT) which shows superior performance on standard metrics compared to existing baselines.
Robust data association is critical for analysis of long-term motion trajectories in complex scenes. In its absence, trajectory precision suffers due to periods of kinematic ambiguity degrading the quality of follow-on analysis. Common optimization-based approaches often neglect uncertainty quantification arising from these events. Consequently, we propose the Joint Posterior Tracker (JPT), a Bayesian multi-object tracking algorithm that robustly reasons over the posterior of associations and trajectories. Novel, permutation-based proposals are crafted for exploration of posterior modes that correspond to plausible association hypotheses. JPT exhibits more accurate uncertainty representation of data associations with superior performance on standard metrics when compared to existing baselines. We also show the utility of JPT applied to automatic scheduling of user-in-the-loop annotations for improved trajectory quality.