Abstract
AbstractMulti-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 previously taken into account by established metrics. Furthermore, we show HOTA scores better align with human visual evaluation of tracking performance.
Funder
European Research Council
Google
Alexander von Humboldt-Stiftung
CCAV
Engineering and Physical Sciences Research Council
Publisher
Springer Science and Business Media LLC
Subject
Artificial Intelligence,Computer Vision and Pattern Recognition,Software
Reference90 articles.
1. Andriluka, M., Iqbal, U., Insafutdinov, E., Pishchulin, L., Milan, A., Gall, J., & Schiele, B. (2018). Posetrack: A benchmark for human pose estimation and tracking. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5167–5176).
2. Babaee, M., Li, Z., & Rigoll, G. (2019). A dual cnn-rnn for multiple people tracking. Neurocomputing, 368, 69–83.
3. Baisa, N.L. (2018). Online multi-target visual tracking using a hisp filter. In Proceedings of the 13th international joint conference on computer vision, imaging and computer graphics theory and applications (Vol. 5: VISAPP, pp. 429–438).
4. Baisa, N.L. (2019). Online multi-object visual tracking using a gm-phd filter with deep appearance learning. In 2019 22th international conference on information fusion (FUSION) (pp. 1–8).
5. Baisa, N. L., & Wallace, A. (2019). Development of a n-type gm-phd filter for multiple target, multiple type visual tracking. Journal of Visual Communication and Image Representation, 59, 257–271.
Cited by
470 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献