Multi-level temporal feature fusion with feature exchange strategy for multiple object tracking
CSTR:
Author:
Affiliation:

1.College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou 325035, China;2.School of Computer Science and Technology, Zhejiang Normal University, Jinhua 321019, China;3.Department of Digital Media Technology, Hangzhou Dianzi University, Hangzhou 310023, China;4. College of Intelligent Manufacturing, Wenzhou Polytechnic, Wenzhou 325035, China

  • Article
  • | |
  • Metrics
  • |
  • Reference
  • |
  • Related
  • |
  • Cited by
  • | |
  • Comments
    Abstract:

    With the deepening of neural network research, object detection has been developed rapidly in recent years, and video object detection methods have gradually attracted the attention of scholars, especially frameworks including multiple object tracking and detection. Most current works prefer to build the paradigm for multiple object tracking and detection by multi-task learning. Different with others, a multi-level temporal feature fusion structure is proposed in this paper to improve the performance of framework by utilizing the constraint of video temporal consistency. For training the temporal network end-to-end, a feature exchange training strategy is put forward for training the temporal feature fusion structure efficiently. The proposed method is tested on several acknowledged benchmarks, and encouraging results are obtained compared with the famous joint detection and tracking framework. The ablation experiment answers the problem of a good position for temporal feature fusion.

    Reference
    Related
    Cited by
Get Citation

GE Yisu, YE Wenjie, ZHANG Guodao, LIN Mengying. Multi-level temporal feature fusion with feature exchange strategy for multiple object tracking[J]. Optoelectronics Letters,2024,20(8):505-511

Copy
Share
Article Metrics
  • Abstract:
  • PDF:
  • HTML:
  • Cited by:
History
  • Received:January 12,2024
  • Revised:April 08,2024
  • Online: July 24,2024
Article QR Code