HOTA: A Higher Order Metric for Evaluating Multi-object Tracking
RWTH Aachen University · University of Oxford · +2 more institutions
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, higher order tracking accuracy (HOTA), 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…
Citation impact
- FWCI
- 30.01
- Percentile
- 100%
- References
- 79
Authors
7- JLJonathon LuitenCorresponding
RWTH Aachen University
- AOAljos̆a Os̆ep
- PDPatrick Dendorfer
- PTPhilip Torr
University of Oxford
- AGAndreas Geiger
Max Planck Institute for Intelligent Systems, University of Tübingen
Topics & keywords
- Metric (unit)
- Tracking (education)
- Data association
- Pattern recognition (psychology)
- Tracking error
- Association (psychology)
- Video tracking