李刚1,,,
霍超颖2,,
殷红成2,
①.清华大学电子系 ??北京 ??100084
②.北京环境特性研究所 ??北京 ??100854
基金项目:装备预研教育部联合基金、装备预研基金重点实验室基金
详细信息
作者简介:章鹏飞(1989–)，男，江苏人，工程师，清华大学在读硕士研究生。主要研究方向为雷达信号处理与目标识别技术。E-mail: zhang-pf16@mails.tsinghua.edu.cn
李刚：李 ? 刚(1979–)，男，2002年和2007年于清华大学电子系分别获得学士、博士学位，现为清华大学电子系研究员、博士生导师，研宄方向为雷达成像、时频分析、稀疏信号处理、分布式信号处理等。E-mail: gangli@tsinghua.edu
霍超颖(1982–)，女，河北人，博士生，高级工程师，电磁散射重点实验室，主要研究方向为雷达特征提取与应用技术。E-mail: 34604336@qq.com
殷红成(1967–)，男，江西人，博士后，研究员，电磁散射重点实验室，主要研究方向为电磁场与微波技术。E-mail: yinhc207@126.com
通讯作者:李刚? gangli@tsinghua.edu.cn
计量
文章访问数:1800
HTML全文浏览量:711
PDF下载量:440
被引次数:0
出版历程
收稿日期:2018-08-23
修回日期:2018-10-22
Classification of Drones Based on Micro-Doppler Radar Signatures Using Dual Radar Sensors
Zhang Pengfei1,,Li Gang1,,,
Huo Chaoying2,,
Yin Hongcheng2,
①. Department of Electronic Engineering, Tsinghua University, Beijing 100084, China
②. Beijing Institute of Environmental Features, Beijing 100854, China
Funds:Ministry Research Foundation, Ministry Key Laboratory Research Foundation
摘要
摘要:无人机的日益流行在带来便利的同时也造成了潜在的威胁，对无人机进行分类识别具有重要意义。雷达微多普勒信号能够区分不同类型的无人机。为了提高基于微多普勒的无人机分类的鲁棒性，该文提出了一种多角度雷达观测微动特征融合的无人机识别方法。首先利用多部雷达同时从不同角度观测目标；然后对采集的雷达数据分别进行短时傅里叶变换(Short-Time Fourier Transform, STFT)，得到时频谱图；接着利用主成分分析(Principal Component Analysis, PCA)从时频谱图中提取特征，将两个不同角度雷达传感器得到的特征融合在一起；最后利用支持向量机(Support Vector Machine, SVM)进行训练与分类识别。基于实际雷达数据的实验结果表明：两个雷达传感器观测融合得到的分类精度优于单个雷达传感器的分类精度，最终识别准确率较仅利用X波段雷达传感器方法提升了5%以上。
关键词:微多普勒/
无人机/
目标识别/
多角度多波段观测
Abstract:Classification of drones is important due to their increasing popularity and potential threats. The micro-Doppler signatures that depend on the rotation of rotor blades facilitate the classification of drones. To enhance the robustness of micro-Doppler based classification of drones, dual radar sensing classification scheme is proposed in this paper. First, time-frequency spectrograms are obtained by performing a short-time Fourier transform on the radar data collected by two radar sensors that have similar angular diversity. Then, principal components analysis is utilized to extract the features from the time-frequency spectrograms and the features obtained by the two radar sensors are fused together. Finally, the classification results are obtained by using the support vector machine. The experimental results show that the classification accuracy obtained by the fusion of dual radar sensors is 5% higher than that obtained by only using a single radar sensor.
Key words:Micro-Doppler/
Drones/
Target classification/
Multi-angle and multi-band observation
PDF全文下载地址:
https://plugin.sowise.cn/viewpdf/198_524_R18061
