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
李佳霖 1李卫东 1王廉钧 1王锐 1胡程1
作者信息
- 1. 北京理工大学信息与电子学院,北京 100081;北京理工大学前沿技术研究院,山东济南 250300;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
- 折叠
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％.
Abstract
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 pro-posed,which verifies the feasibility of using HRRP for drone recognition.Comparative experiments on echo data of different band-widths 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Key words
UAV recognition/HRRP/convolutional neural network/wideband radar引用本文复制引用
基金项目
国家重点研发计划项目(2023YFC3341100)
出版年
2024
国家科技期刊平台
NSTL
万方数据