基于涡旋电磁波雷达的人体目标步态精细识别

doi:10.12382/bgxb.2021.0294

兵工学报 ›› 2022, Vol. 43 ›› Issue (5): 1167-1174.doi: 10.12382/bgxb.2021.0294

基于涡旋电磁波雷达的人体目标步态精细识别

袁航¹，罗迎^1，2，李开明¹，陈怡君^3，4，张群^1，2

(1.空军工程大学信息与导航学院，陕西西安 710077； 2.复旦大学电磁波信息科学教育部重点实验室，上海 200433；3.西安电子科技大学雷达信号处理国家重点实验室，陕西西安 710071； 4.武警工程大学信息工程学院，陕西西安 710086)

上线日期:2022-03-23
通讯作者: 罗迎（1984—），男，教授，博士生导师 E-mail:luoying2002521@163.com
作者简介:袁航（1997—），男，硕士研究生。E-mail:yuanhang517300@163.com
基金资助:
国家自然科学基金项目(61971434)；国家自然科学青年基金项目(61801516)

Fine Recognition of Human Gait with Vortex Electromagnetic Wave Radar

YUAN Hang¹， LUO Ying^1，2， LI Kaiming¹， CHEN Yijun^3，4， ZHANG Qun^1，2

(1.College of Information and Navigation，Air Force Engineering University，Xi'an 710077，Shaanxi，China；2.Key Laboratory of EMW Information，Fudan University，Shanghai 200433，China；3.National Key Laboratory of Radar Signal Processing，Xidian University，Xi'an 710071，Shaanxi，China；4.College of Information Engineering，Engineering University of PAP，Xi'an 710086，Shaanxi，China)

Online:2022-03-23

摘要/Abstract

摘要： 基于雷达的人体目标识别技术在诸多领域有着重要的应用。涡旋电磁波中携带有轨道角动量，在运动目标回波中会引起线多普勒和角多普勒效应，可为识别提供更丰富的信息。但与线多普勒相比，角多普勒较微弱，二者难以被分离。使用多发多收模型产生线性调频涡旋电磁波，通过双模态回波干涉抑制线多普勒。利用短时傅里叶变换，获得双模态回波的线多普勒和角多普勒时频图，将时频图的幅度值输入到双通道卷积神经网络模型中，获得分类结果。仿真实验结果表明，将线多普勒和角多普勒分离，同时输入到分类模型中可以提升人体步态精细识别能力。

关键词: 涡旋电磁波雷达, 人体目标, 步态识别, 卷积神经网络

Abstract: Radar-based human target recognition technology has important applications in many fields. The vortex electromagnetic (EM) wave carries orbital angular momentum，and the target motion may cause the linear and angular Doppler effects. Vortex EM wave contains more target information，which can provide more information for identification. But the angular Doppler effect is much smaller than the linear Doppler effect，so it is difficult to separate them.A multi-transmitter and multi-receiver model is used to generate linear frequency modulation vortex electromagnetic wave，and the linear Doppler is suppressed by dual-mode echo interference. Then，the linear and angular Doppler time-frequency images of the dual-mode echo are obtained by using the short-time Fourier transform. The amplitude values of the time-frequency images are input into the dual-channel convolutional neural network model to obtain the classification results.The simulated results show that the fine recognition ability of human gait is improved by separating the linear Doppler and angular Doppler.

Key words: vortexelectromagneticwaveradar, humantarget, gaitrecognition, convolutionalneuralnetwork

中图分类号:

TN957

袁航，罗迎，李开明，陈怡君，张群. 基于涡旋电磁波雷达的人体目标步态精细识别[J]. 兵工学报, 2022, 43(5): 1167-1174.

YUAN Hang， LUO Ying， LI Kaiming， CHEN Yijun， ZHANG Qun. Fine Recognition of Human Gait with Vortex Electromagnetic Wave Radar[J]. Acta Armamentarii, 2022, 43(5): 1167-1174.

参考文献

［1］ NI Z F, HUANG B K.Open-set human identification based on gaitradar micro-Doppler signatures［J］.IEEE Sensors Journal，2021，21(6):8226-8233.
［2］ SEYFIOGLU M S，OZBAYOGLU A M，GURBUZ S Z，et al. Deep convolutional autoencoder for radar-based classification of similar aided and unaided human activities［J］.IEEE Transactions on Aerospace and Electronic Systems，2018，54(4): 1709-1723.
［3］ GURBUZ S Z，KAYNAK U，OZKAN B，et al.Design study of a short-range airborne UAV radar for human monitoring［C］∥Proceedings of the 48th Asilomar Conference on Signals，Systems and Computers.Pacific Grove，CA，US: IEEE，2014.
［4］李纪三，侯娇，刘溶，等.基于贝叶斯滤波算法的警戒相控阵雷达目标跟踪时间资源优化分配算法［J］.兵工学报，2021，42(9): 1902-1910.
LI J S，HOU J，LIU R，et ai.Optimal time resource allocation algorithm for surveillance phased array radar target tracking based on Bayesian filtering algorithm［J］. Acta Armamentarii，2021，42(9): 1902-1910. (in Chinese)
［5］ DING C W，HONG H，ZOU Y，et al. Continuous human motion recognition with a dynamic range-Doppler trajectory method based on FMCW radar［J］.IEEE Transactions on Geoscience and Remote Sensing，2019，57(9): 6821-6831.
［6］ BAI X，HUI Y，WANG L，et al.Radar-based human gait recognition using dual-channel deep convolutional neural network［J］.IEEE Transactions on Geoscience and Remote Sensing，2019，57(12): 9767-9778.
［7］ AMIN M G，EROL B.Understanding deep neural networks performance for radar-based human motion recognition［C］∥Proceedings of 2018 IEEE Radar Conference.Oklahoma City，OK，US:IEEE，2018.
［8］张群，胡健，罗迎，等.微动目标雷达特征提取、成像与识别研究进展［J］.雷达学报，2018，7(5):531-547.
ZHANG Q，HU J，LUO Y，et al. Research progresses in radar feature extraction，imaging，and recognition of target with micro-motions［J］.Journal of Radars，2018，7(5): 531-547. (in Chinese)
［9］刘康，黎湘，王宏强，等.涡旋电磁波及其在雷达中应用研究进展［J］.电子学报，2018，46(9): 2283-2290.
LIU K，LI X，WANG H Q，et al.The advances of vortex electromagnetic wave in radar applications［J］.Acta Electronica Sinica，2018，46(9):2283-2290. (in Chinese)
［10］ CHEN R，ZHOU H，MORETTI M，et al.Orbital angular momentum waves: generation，detection，and emerging applications［J］.IEEE Communications Surveys & Tutorials，2019，22(2): 840-868.
［11］ LUO Y，CHEN Y J，ZHU Y Z，et al. Doppler effect and micro-Doppler effect of vortex-electromagnetic-wave-based radar［J］. IET Radar Sonar and Navigation，2020，14(1): 2-9.
［12］ THIDE B，THEN H，SJOHOLM J，et al. Utilization of photon orbital angular momentum in the low frequency radio domain［J］.Physical Review Letters，2007，99(8):087701.
［13］ LIU K，LIU H Y，QIN Y L，et al. Generation of OAM beams using phased array in the microwave band［J］.IEEE Transactions on Antennas and Propagation，2016，64(9): 3850-3857.
［14］ TAMBURINI F，MARI E，SPONSELLI A，et al. Encoding many channels on the same frequency through radio vorticity: first experimental test［J］.New Journal of Physics，2012，14(3): 03001.
［15］ BU X X，ZHANG Z，CHEN L Y，et al. Implementation of vortex electromagnetic waves high-resolution synthetic aperture radar imaging［J］.IEEE Antennas and Wireless Propagation Letters，2018，17(5): 764-767.
［16］ LI R，LUO Y，ZHANG Q，et al. lectromagnetic vortex imaging based on multiple measurement vectors in low SNR condition［C］∥Proceedings of 2019 IEEE International Conference on Computational Electromagnetics. Shanghai，China: IEEE，2019.
［17］ BU X X，ZHANG Z， HEN L Y，et al. Synthetic aperture radar interferometry based on vortex electromagnetic waves［J］.IEEE Access，2019，7:82693-82700.
［18］袁航，倪嘉成，荣楠，等.基于单频涡旋电磁波雷达的人体目标步态精细识别［J］.空军工程大学学报(自然科学版)，2020，21(6):39-45.
YUAN H，NI J C，RONG N，et al.Fine Gait Recognition of Human Target with Single-Frequency Vortex Electromagnetic Wave Radar［J］.Journal of Air Force Engineering University (Natural Science Edition)，2020，21(6):39-45.(in Chinee)
［19］ KIM Y，MOON T.Human detection and activity classification based on micro-Doppler signatures using deep convolutional neural networks［J］.IEEE Geoscience and Remote Sensing Letters，2016，13(1): 8-12.
［20］ TROTT K D.Stationary phase derivation for RCS of an ellipsoid［J］.IEEE Antennas and Wireless Propagation Letters，2007，6(6): 240-243.
［21］侯斐斐，施荣华，雷文太，等.面向探地雷达 B-scan图像的目标检测算法综述［J］.电子与信息学报，2020，42(1):191-200.
HOU F F，SHI R H，LEI W T，et al. A review of target detection algorithm for GPR B-scan processing［J］.Journal of Electronics and Information Technology，2020，42(1): 191-200. (in Chinese)
［22］苏宁远，陈小龙，关键，等.基于卷积神经网络的海上微动目标检测与分类方法［J］.雷达学报，2018，7(5): 565-574.
SU N Y，CHEN X L，GUAN J，et al. Detection and classification of maritime target with micro-motion based on CNNs［J］.Journal of Radars，2018，7(5): 565-574. (in Chinese)

第43卷第5期2022 年5月
兵工学报ACTA ARMAMENTARII
Vol.43No.5May2022

[1]	普运伟，刘涛涛，郭江，吴海潇. 基于卷积神经网络和模糊函数主脊坐标变换的雷达辐射源信号识别[J]. 兵工学报, 2021, 42(8): 1680-1689.
[2]	马月红，孔梦瑶. 基于改进快速区域卷积网络的目标检测轻量化算法[J]. 兵工学报, 2021, 42(12): 2664-2674.
[3]	张宏鹏，黄长强，唐上钦，轩永波. 基于卷积神经网络的无人作战飞机飞行轨迹实时预测[J]. 兵工学报, 2020, 41(9): 1894-1903.
[4]	刘秋，孙晋伟，张华, 胡煦，顾亮. 基于卷积神经网络的路面识别及半主动悬架控制[J]. 兵工学报, 2020, 41(8): 1483-1493.
[5]	呙鹏程，吴礼洋. 融合卷积特征与判别字典学习的低截获概率雷达信号识别[J]. 兵工学报, 2019, 40(9): 1881-1889.
[6]	吴春志，冯辅周，吴守军，陈汤，江鹏程. 一种有效的不均衡样本生成方法及其在行星变速箱故障诊断中的应用[J]. 兵工学报, 2019, 40(7): 1349-1357.
[7]	梁杰，李磊，任君，齐航，周红丽. 基于深度学习的红外图像遮挡干扰检测方法[J]. 兵工学报, 2019, 40(7): 1401-1410.
[8]	张玉燕，李永保，温银堂，张芝威. 基于Faster R-卷积神经网络的金属点阵结构缺陷识别方法[J]. 兵工学报, 2019, 40(11): 2329-2335.
[9]	孙皓泽，常天庆，王全东，孔德鹏，戴文君. 一种基于分层多尺度卷积特征提取的坦克装甲目标图像检测方法[J]. 兵工学报, 2017, 38(9): 1681-1691.

基于涡旋电磁波雷达的人体目标步态精细识别

Fine Recognition of Human Gait with Vortex Electromagnetic Wave Radar

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 9

编辑推荐

Metrics

本文评价