基于残差网络高分辨距离像的无人机识别  

UAV Recognition Based on High-resolution Range Profile Features Using Residual Network

作　　者：李佳霖 李卫东 王廉钧[1,2,3] 王锐 胡程 LI Jialin;LI Weidong;WANG Lianjun;WANG Rui;HU Cheng(School of Information and Electronics,Beijing Institute of Technology,Beijing 100081,China;Advanced Technology Research Institute,Beijing Institute of Technology,Jinan Shandong 250300,China;Beijing Key Laboratory of Embedded Real-time Information Processing Technology(Beijing Institute of Technology),Beijing 100081,China)

机构地区：[1]北京理工大学信息与电子学院,北京100081 [2]北京理工大学前沿技术研究院,山东济南250300 [3]嵌入式实时信息处理技术北京市重点实验室(北京理工大学),北京100081

出　　处：《现代雷达》2024年第7期30-36,共7页Modern Radar

基　　金：国家重点研发计划项目(2023YFC3341100)。

摘　　要：基于微波暗室测量的无人机宽带雷达回波数据,开展基于高分辨一维距离像的微小无人机型号识别方法探索研究,提出残差注意力金字塔池化网络(RAPPNet)模型,验证了利用高分辨一维距离像进行无人机识别的可行性。针对不同带宽的回波数据对比实验表明:更大的带宽可有效提高基于一维距离像的无人机识别正确率;在6 GHz带宽下,所提方法对无人机的识别准确率可达90.63%。Based on the wideband radar echo data measured in a microwave anechoic chamber.A study on the recognition method of micro drone models is conducted based on HRRP,and proposes the residual attention pyramid pooling net(RAPPNet)is proposed,which verifies the feasibility of using HRRP for drone recognition.Comparative experiments on echo data of different bandwidths show that larger bandwidths can effectively improve the accuracy of UAV recognition based on high resolution range profile.Under the 6 GHz bandwidth,the proposed method can identify drones with an accuracy of 90.63%.

关 键 词：无人机识别 一维距离像 卷积神经网络 宽带雷达 

分 类 号：TN957[电子电信—信号与信息处理] V279[电子电信—信息与通信工程]