Scholarlink

<p>Target tracking is one of the important tasks of UAV (Unmanned Aerial Vehicle). The indicators for completing the UAV tracking task are the system’s tracking speed, tracking error, and tracking of specific targets. This paper proposes a distributed system based on the YOLO (You Only Look Once) detection algorithm and the DIMP (Discriminative Model Prediction) tracking algorithm for real-time tracking of specific targets. The system separates algorithm initialization and online operation, coordinates detection and tracking, and gives full play to the accuracy and speed advantages of both. Then, on the basis of the YOLO detection algorithm, the CBAM (Convolutional Block Attention Module) module is integrated to improve the network structure, which improves the detection accuracy of the YOLO algorithm for specific targets. Then, on the basis of the DIMP tracking algorithm, the tracking speed and stability of the DIMP algorithm are improved by distributed design, replacing the backbone network, optimizing training and updating, and integrating the attention mechanism. Finally, simulation and experiments verified that the distributed system can achieve long-term and stable tracking of specific targets. The detection accuracy (mAP0.5:0.95) of the YOLO algorithm integrated with CBAM was improved by 5.2%, and the tracking speed of the improved DIMP algorithm was increased by 10FPS.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Research on a distributed strategy for UAV detection and tracking of specific targets

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年10月21日

查看全文
  • X. Liang,
  • Y. Qi,
  • G. Chen,
  • G. Meng

摘要

Target tracking is one of the important tasks of UAV (Unmanned Aerial Vehicle). The indicators for completing the UAV tracking task are the system’s tracking speed, tracking error, and tracking of specific targets. This paper proposes a distributed system based on the YOLO (You Only Look Once) detection algorithm and the DIMP (Discriminative Model Prediction) tracking algorithm for real-time tracking of specific targets. The system separates algorithm initialization and online operation, coordinates detection and tracking, and gives full play to the accuracy and speed advantages of both. Then, on the basis of the YOLO detection algorithm, the CBAM (Convolutional Block Attention Module) module is integrated to improve the network structure, which improves the detection accuracy of the YOLO algorithm for specific targets. Then, on the basis of the DIMP tracking algorithm, the tracking speed and stability of the DIMP algorithm are improved by distributed design, replacing the backbone network, optimizing training and updating, and integrating the attention mechanism. Finally, simulation and experiments verified that the distributed system can achieve long-term and stable tracking of specific targets. The detection accuracy (mAP0.5:0.95) of the YOLO algorithm integrated with CBAM was improved by 5.2%, and the tracking speed of the improved DIMP algorithm was increased by 10FPS.