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.
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: