系统工程与电子技术 ›› 2022, Vol. 44 ›› Issue (3): 746-754.doi: 10.12305/j.issn.1001-506X.2022.03.05

• 电子技术 • 上一篇    下一篇

基于决策融合的多无人机协同目标检测识别算法

李洪瑶1, 李小强1, 韩心中2, 谢学立1, 席建祥1,*   

  1. 1. 火箭军工程大学导弹工程学院, 西安 陕西 710025
    2. 火箭军研究院, 北京 100094
  • 收稿日期:2021-02-05 出版日期:2022-03-01 发布日期:2022-03-10
  • 通讯作者: 席建祥
  • 作者简介:李洪瑶(1998—), 女, 博士研究生, 主要研究方向为目标检测|李小强(1979—), 男, 工程师, 本科, 主要研究方向为人工智能|韩心中(1982—), 男, 助理研究员, 硕士, 主要研究方向为试验鉴定|谢学立(1995—), 男, 博士研究生, 主要研究方向为目标检测|席建祥(1981—), 男, 教授, 博士, 主要研究方向为多智能体协同控制、无人机编队
  • 基金资助:
    国家自然科学基金(61867005);国家自然科学基金(61703411)

Cooperative object detection and recognition algorithm for multiple UAVs based on decision fusion

Hongyao LI1, Xiaoqiang LI1, Xinzhong HAN2, Xueli XIE1, Jianxiang XI1,*   

  1. 1. School of Missile Engineering, Rocket Force University of Engineering, Xi'an 710025, China
    2. Academy of the Rocket Force, Beijing 100094, China
  • Received:2021-02-05 Online:2022-03-01 Published:2022-03-10
  • Contact: Jianxiang XI

摘要:

针对现阶段单无人机不能高效完成大区域巡视的问题, 提出一种多无人机决策融合的目标检测识别算法。首先改进Retinanet算法进行单无人机的目标检测, 根据航拍图像目标特性, 调整anchor参数和训练策略。同时利用特征提取算子配准多无人机航拍图像, 实现多机图像坐标一致, 并进行图像拼接。然后综合目标的位置信息和属性信息对多机图像进行目标关联。最后提出一种基于冲突度量的动态切换策略, 自适应选择DST(dempster-shafer theory)或DSmT(desert-smarandache theory)融合关联目标信息。在多无人机协同目标识别数据集上进行实验, 结果表明所提算法能在增大单次巡视范围的同时, 提高无人机巡视系统的检测精度。

关键词: 机器视觉, 多无人机协同, 目标检测, 多目标关联, 动态切换策略

Abstract:

Since a single unmanned aerial vehicle (UAV) cannot patrol a large area efficiently, an object detection and recognition algorithm based on multiple UAVs decision fusion is proposed. Firstly, Retinanet algorithm is improved for object detection of a single UAV. Anchor parameters and training strategies are adjusted according to object characteristics of aerial images. Meanwhile, the feature extraction operator is used to register the aerial images of multiple UAVs such that the coordinates of the images of multiple UAVs are consistent and the images are mosaic. Then, the multiple UAVs images are correlated by combining information of the object position and the attribute. Finally, a dynamic switching strategy based on collision measurement is proposed, which adaptively selects the Dempster-Shafer theory (DST) or desert-smarandache theory (DSmT) to fuse the associated object information. Experimental results on multiple UAVs cooperative object identification data set show that the proposed algorithm can not only increase the single patrol range, but also improve the detection accuracy of the UAV patrol system.

Key words: machine vision, multiple unmanned aerial vehicles (UAVs) cooperation, object detection, multi-objective association, dynamic switching strategy

中图分类号: