MOTR: End-to-End Multiple-Object Tracking with Transformer
Authors:
- Bin DongBDBin Dong
- Tiancai WangTWTiancai Wang
Preprint
Abstract
Temporal modeling of objects is a key challenge in multiple object tracking (MOT). Existing methods track by associating detections through motion-based and appearance-based similarity heuristics. The post-processing nature of association prevents end-to-end exploitation of temporal variations in video sequence. In this paper, we propose MOTR, which extends DETR and introduces track query to model the tracked instances in the entire video. Track query is transferred and updated frame-by-frame to perform iterative prediction over time. We propose tracklet-aware label assignment to train track queries and newborn object queries. We further propose temporal aggregation network and collective average loss to enhance temporal relation modeling. Experimental results on DanceTrack show that MOTR significantly outperforms state-of-the-art method, ByteTrack by 6.5% on HOTA metric. On MOT17, MOTR outperforms our concurrent works, TrackFormer and TransTrack, on association performance. MOTR can serve as a stronger baseline for future research on temporal modeling and Transformer-based trackers. Code is available at https://github.com/megvii-research/MOTR.Keywords
All Related Versions
This publication has 29 references indexed in Scilit:
- ByteTrack: Multi-object Tracking by Associating Every Detection Box2022
- FairMOT: On the Fairness of Detection and Re-identification in Multiple Object TrackingInternational Journal of Computer Vision, 2021
- Tracking Objects as Points2020
- HOTA: A Higher Order Metric for Evaluating Multi-object TrackingInternational Journal of Computer Vision, 2020
- Non-local Neural Networks2018
- High-Speed tracking-by-detection without using image information2017
- Deep Network Flow for Multi-object Tracking2017
- Deep Residual Learning for Image Recognition2016
- Microsoft COCO: Common Objects in Context2014
- The Hungarian method for the assignment problemNaval Research Logistics Quarterly, 1955