Multi-Object Tracking: Decoupling Features to Solve the Contradictory Dilemma of Feature Requirements
- 27 February 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 33 (9) , 5117-5132
Abstract
Multi-object tracking achieves the acquisition of target location information and identity information through two subtasks, detection and re-identification (ReID). The existing commonly used one-shot framework has speed advantages, but the two subtasks have different feature requirements, which leads to competitive learning in the training and thus weakens the feature quality. We propose a feature decoupling based multi-object tracking framework FDTrack for contradictory feature requirements. Through the mutual inhibition of the two subtasks, the features of the backbone network are decoupled. Then the decoupled features are self-constrained to enhance effective features. Considering the instability of the target state and the different confidence of the detections, a more reasonable association strategy is employed to maximize the matchings between detections, thus recovering low-confidence targets. FDTrack is extensively tested on the MOT17 and MOT20 benchmarks. The experimental results show that FDTrack surpasses the previous state-of-the-art (SOTA) methods and has good anti-interference and real-time performance. Moreover, our proposed modules have good portability and can be applied in other one-shot trackers to achieve performance improvement.Keywords
Funding Information
- Guangxi Science and Technology Base and Talent Project (2020AC19253)
- Natural Science Foundation of China (62276242)
- Chinese Association for Artificial Intelligence (CAAI)-Huawei MindSpore Open Fund (CAAIXSJLJJ-2021-016B, CAAIXSJLJJ-2022-001A)
- Anhui Province Key Research and Development Program (202104a05020007)
- University of Science and Technology of China, Institute of Advantage Technology (USTC-IAT) Application Science and Technology Achievement Cultivation Program (JL06521001Y)
- Bagui Scholar Program of Guangxi
- Science and Technology Innovation Special Zone (20-163-14-LZ-001-004-01)
This publication has 78 references indexed in Scilit:
- High-Speed tracking-by-detection without using image information2017
- Joint Detection and Identification Feature Learning for Person Search2017
- CityPersons: A Diverse Dataset for Pedestrian Detection2017
- Safe driving envelopes for path tracking in autonomous vehiclesControl Engineering Practice, 2017
- Online multi-object tracking via robust collaborative model and sample selectionComputer Vision and Image Understanding, 2017
- Crowd Tracking by Group Structure EvolutionIEEE Transactions on Circuits and Systems for Video Technology, 2016
- Simple online and realtime tracking2016
- Evaluating Multiple Object Tracking Performance: The CLEAR MOT MetricsEURASIP Journal on Image and Video Processing, 2008
- A New Approach to Linear Filtering and Prediction ProblemsJournal of Basic Engineering, 1960
- The Hungarian method for the assignment problemNaval Research Logistics Quarterly, 1955