TL;DR
HOTA is a new unified metric for multi-object tracking evaluation that balances detection, association, and localization, providing clearer analysis and better alignment with human judgment than previous metrics.
Contribution
The paper introduces HOTA, a novel comprehensive metric for MOT that decomposes into sub-metrics for detailed error analysis and improves evaluation accuracy.
Findings
HOTA captures aspects of MOT performance overlooked by previous metrics.
HOTA scores correlate better with human visual assessment.
HOTA effectively evaluates detection, association, and localization errors.
Abstract
Multi-Object Tracking (MOT) has been notoriously difficult to evaluate. Previous metrics overemphasize the importance of either detection or association. To address this, we present a novel MOT evaluation metric, HOTA (Higher Order Tracking Accuracy), which explicitly balances the effect of performing accurate detection, association and localization into a single unified metric for comparing trackers. HOTA decomposes into a family of sub-metrics which are able to evaluate each of five basic error types separately, which enables clear analysis of tracking performance. We evaluate the effectiveness of HOTA on the MOTChallenge benchmark, and show that it is able to capture important aspects of MOT performance not previously taken into account by established metrics. Furthermore, we show HOTA scores better align with human visual evaluation of tracking performance.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
