作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2020, Vol. 46 ›› Issue (12): 283-289,298. doi: 10.19678/j.issn.1000-3428.0056288

• 开发研究与工程应用 • 上一篇    下一篇

基于轨迹和形态识别的无人机检测方法

刘宜成1, 廖鹭川1, 张劲1, 吴浩2, 何凌1, 戴弘宁3, 张晗1, 杨刚1   

  1. 1. 四川大学 电气工程学院 自动化系, 成都 610065;
    2. 成都空御科技有限公司, 成都 610213;
    3. 澳门科技大学 咨讯科技学院, 澳门 999078
  • 收稿日期:2019-10-14 修回日期:2019-12-16 发布日期:2019-12-24
  • 作者简介:刘宜成(1975-),男,副教授、博士,主研方向为智能无人系统、非线性控制;廖鹭川,硕士研究生;张劲,副教授、博士;吴浩,硕士;何凌、戴弘宁、张晗、杨刚,副教授、博士。
  • 基金资助:
    国家自然科学基金(61571314);四川省智能制造与机器人重大专项课题"工业机器人成套装备研制与应用"(2019ZDZX0019)。

Unmanned Aerial Vehicle Detection Based on Trajectory and Pattern Recognition

LIU Yicheng1, LIAO Luchuan1, ZHANG Jing1, WU Hao2, HE Ling1, DAI Hongning3, ZHANG Han1, YANG Gang1   

  1. 1. Department of Automation, College of Electrical Engineering, Sichuan University, Chengdu 610065, China;
    2. Chengdu Sky Defence Technology Co., LTD., Chengdu 610213, China;
    3. Faculty of Information Technology, Macau University of Science and Technology, Macau 999078, China
  • Received:2019-10-14 Revised:2019-12-16 Published:2019-12-24

摘要: 无人机因具有体型小以及受环境干扰大等因素导致其在可见光图像序列下的检测准确率较低。为此,提出一种新的无人机检测方法。通过转台相机捕获飞行物形态变化,使用轨迹聚类算法获得运动小目标轨迹,提取并融合目标的轨迹特征和形态特征,进而通过人工神经网络识别目标,并采用小范围搜索算法进行追踪,同时运用干扰无线电定向压制无人机。实验结果表明,该方法对无人机和飞鸟的识别准确率达到99.53%,且能够实时检测、识别和追踪。

关键词: 无人机检测, 轨迹聚类, 特征提取, 轨迹识别, 人工神经网络, 目标追踪

Abstract: Many factors such as the interference and the small fuselage of Unmanned Aerial Vehicle(UAV) pose challenges to the high precision detection of the UAV in visible image sequences.Therefore,this paper proposes a new UAV detection method.The shape change of the flying object is captured by the turntable camera.Then the trajectory of the small moving target is obtained by using the trajectory clustering algorithm.The trajectory characteristics and morphological characteristics of the target are extracted and fused,and on this basis the target is identified through the Artificial Neural Network(ANN).At the same time,the small-range search algorithm is used to track the target and the jamming radio is used to suppress the UAV.Experimental results show that the method increases its UAV and bird detection accuracy to 99.53%,and can provide real-time detection,recognition and tracking of these targets.

Key words: Unmanned Aerial Vehicle(UAV) detection, trajectory clustering, feature extraction, trajectory recognition, Artificial Neural Network(ANN), object tracking

中图分类号: