Deep OC-SORT: Multi-Pedestrian Tracking by Adaptive Re-Identification
Authors:
Preprint
Abstract
Motion-based association for Multi-Object Tracking (MOT) has recently re-achieved prominence with the rise of powerful object detectors. Despite this, little work has been done to incorporate appearance cues beyond simple heuristic models that lack robustness to feature degradation. In this paper, we propose a novel way to leverage objects' appearances to adaptively integrate appearance matching into existing high-performance motion-based methods. Building upon the pure motion-based method OC-SORT, we achieve 1st place on MOT20 and 2nd place on MOT17 with 63.9 and 64.9 HOTA, respectively. We also achieve 61.3 HOTA on the challenging DanceTrack benchmark as a new state-of-the-art even compared to more heavily-designed methods. The code and models are available at \url{https://github.com/GerardMaggiolino/Deep-OC-SORT}.Keywords
All Related Versions
This publication has 18 references indexed in Scilit:
- Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking2023
- MOTR: End-to-End Multiple-Object Tracking with Transformer2022
- ByteTrack: Multi-object Tracking by Associating Every Detection Box2022
- TrackFormer: Multi-Object Tracking with Transformers2022
- DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion2022
- A General Recurrent Tracking Framework without Real Data2021
- FairMOT: On the Fairness of Detection and Re-identification in Multiple Object TrackingInternational Journal of Computer Vision, 2021
- Quasi-Dense Similarity Learning for Multiple Object Tracking2021
- Track to Detect and Segment: An Online Multi-Object Tracker2021
- HOTA: A Higher Order Metric for Evaluating Multi-object TrackingInternational Journal of Computer Vision, 2020