航空学报 > 2024, Vol. 45 Issue (14): 629379-629379   doi: 10.7527/S1000-6893.2023.29379

基于视觉图像的空对空多无人机目标跟踪

褚昭晨, 宋韬, 金忍(), 林德福   

  1. 北京理工大学 宇航学院,北京 100081
  • 收稿日期:2023-07-28 修回日期:2023-08-22 接受日期:2023-11-08 出版日期:2024-07-25 发布日期:2023-12-07
  • 通讯作者: 金忍 E-mail:renjin@bit.edu.cn
  • 基金资助:
    国家自然科学基金(62206020);山东省重大科技创新工程项目(2019SDZY05)

Vision-based air-to-air multi-UAVs tracking

Zhaochen CHU, Tao SONG, Ren JIN(), Defu LIN   

  1. School of Aerospace Engineering,Beijing Institute of Technology,Beijing 100081,China
  • Received:2023-07-28 Revised:2023-08-22 Accepted:2023-11-08 Online:2024-07-25 Published:2023-12-07
  • Contact: Ren JIN E-mail:renjin@bit.edu.cn
  • Supported by:
    National Natural Science Foundation of China(62206020);Major Science and Technology Innovation Project of Shandong Province(2019SDZY05)

摘要:

基于视觉的空对空多目标跟踪技术是对无人机目标态势感知的关键技术,目前的研究局限于单目标无人机跟踪和通用多目标跟踪算法的迁移运用。针对空对空条件下现有算法对多无人机目标跟踪不准确的问题,提出一种基于分块增强特征提取与局部几何信息关联的级联多目标跟踪算法,将无人机图像按照机身和机臂特点分块处理,提取目标细粒度形态特征,利用连续时间内目标间相对几何关系变化微小的特性,构建局部区域目标相对几何关系向量,综合上述技术组件设计级联关联算法,提高所提出的算法对无人机目标的检索能力和关联成功率,从而提高算法的跟踪性能。实验表明,在测试集中,所提出的算法相比于目前最先进的多目标跟踪算法OC-SORT算法,身份编号F1值(ID F1 Score, IDF1)提升了5.6%,相比于在通用多目标跟踪领域较优的ByteTrack算法,多目标跟踪准确率(Multiple Object Tracking Accuracy, MOTA)提升了2.7%,实现了对多无人机目标跟踪的最优性能。同时,所提出的算法中用到的技术可应用于SORT、BYTE等数据关联算法中,从而可提高这些关联算法的性能。

关键词: 无人机, 多目标跟踪, 深度学习, 特征提取, 数据关联

Abstract:

Vision-based air-to-air multi-object tracking is a key technology for UAV situational awareness. Recent research is limited to single-UAV tracking and migration of general multi-object tracking algorithms. To address the problem of inaccurate air-to-air multi-UAVs tracking, a cascade multi-UAVs tracking algorithm based on block feature enhancement extraction and local geometric association is designed. The UAV image is processed in blocks according to the characteristics of the fuselage and the arm, and the UAV’s fine-grained morphological features are extracted. The property that the relative geometric relationship between the UAVs is virtually invariant in the continuous frames is also utilized to extract the local geometric vectors of the UAVs. Then, the cascade association algorithm is designed by synthesizing the above technical components to improve the multi-object tracking algorithm’s ability to retrieve UAV objects and the association success rate, so as to improve the tracking performance of the proposed algorithm. Experiments show that in the test set, the proposed algorithm improves ID F1 Score (IDF1) by 5.6% compared to the state-of-the-art multi-object tracking algorithms OC-SORT, and improves Multiple Object Tracking Accuracy (MOTA) by 2.7% compared to the ByteTrack, which also performs well in the general multi-object tracking. The optimal performance for air-to-air multi-UAVs tracking can be realized, and the components used by the proposed algorithm can also be applied to SORT, BYTE and other data association algorithms to jointly improve their performance.

Key words: Unmanned Aerial Vehicle (UAV), multi-object tracking, deep learning, feature extraction, data association

中图分类号: