计算机科学

计算机科学 ›› 2023, Vol. 50 ›› Issue (11A): 220800247-6.doi: 10.11896/jsjkx.220800247

• 图像处理&多媒体技术 • 上一篇    下一篇

基于残差网络的FMCW雷达人体行为识别

罗金燕1, 常俊1,2, 吴彭1, 许妍1, 卢中奎1   

  1. 1 云南大学信息学院 昆明 650500
    2 云南省高校物联网技术及应用重点实验室 昆明 650500
  • 发布日期:2023-11-09
  • 通讯作者: 常俊(changjun@yun.edu.cn)
  • 作者简介:(blxszaljy@163.com)

FMCW Radar Human Behavior Recognition Based on Residual Network

LUO Jinyan1, CHANG Jun1,2, WU Peng1, XU Yan1, LU Zhongkui1   

  1. 1 College of Information Science & Engineering,Yunnan University,Kunming 650500,China
    2 University Key Laboratory of Internet of Things Technology and Application,Kunming 650500,China
  • Published:2023-11-09
  • About author:LUO Jinyan,born in 1996.Her main research interests include radar human behavior recognition and so on.
    CHANG Jun,born in 1970,associate professor,postgraduate’s supervisor,is a member of China Computer Federation.His main research interests include intelligent wireless perception and wireless communication.

PDF (PC)

187

摘要： 现有的基于调频连续波(Frequency Modulated Continuous Wave,FMCW)雷达的人体行为识别方法大多采用深度卷积神经网络完成,但随着网络加深,会出现网络训练难度增大或特征提取不充分的问题。针对此问题,提出一种基于残差网络的FMCW雷达人体行为识别方法。通过对雷达回波数据分析处理得到每种行为的微多普勒时域谱图,将其作为识别模型的分类特征。将卷积块注意模块(Convolutional Block Attention Module,CBAM)引入残差网络的残差块中构建识别模型,CBAM关注谱图的颜色变化情况和谱图中每种颜色的位置信息,同时引入自适配归一化和改变网络输入部分的卷积结构提高模型的特征提取能力。实验验证,该模型的平均识别准确率可达98.17%,对于微多普勒特征相似的行为,识别准确率可达95%,证明了该模型具有较好的识别性能。

关键词: FMCW雷达, 微多普勒谱图, 行为识别, 残差网络, 卷积块注意模块

Abstract: For the existing FMCW radar human behavior recognition methods are mostly done by deep convolutional neural networks,however,with the deepening of the network,there will be problems such as the difficulty of network training will increase or the feature extraction will be insufficient.A method for FMCW radar human behavior recognition based on residual network is proposed.The micro-Doppler time-domain spectrogram of each behavior is obtained by analyzing and processing the radar echo data,which is used as the classification feature of the recognition model.The convolutional block attention module(CBAM) is introduced into the residual block of the residual network to build a recognition model.CBAM pays attention to the color change of the spectrogram and the position information of each color in the spectrogram,while introducing adaptive Matching normalization and changing the convolutional structure of the input part of the network improves the feature extraction ability of the model.Through experimental verification,the average recognition accuracy of the model can reach 98.17%,and for behaviors with similar micro-Doppler features,the recognition accuracy can reach 95%,which prove that the model has good recognition perfor-mance.

Key words: FMCW radar, Micro-Doppler spectrograms, Behavior recognition, Residual networks, Convolutional block attention module

中图分类号: 

  • TN959
[1]LI C,LUBECKE V M,BORIC-LUBECKE O,et al.A review on recent advances in Doppler radar sensors for noncontact healthcare monitoring [J].IEEE Transactions on Microwave Theory and Techniques,2013,61(5):2046-2060.
[2]LI H,SHRESTHA A,HEIDARI H,et al.Magnetic and radar sensing for multimodal remote health monitoring [J].IEEE Sensors Journal,2018,19(20):8979-8989.
[3]WANG P,LIU H,WANG L,et al.Deep learning-based human motion recognition for predictive context-aware human-robot collaboration [J].CIRP annals,2018,67(1):17-20.
[4]LI X,HE Y,JING X.A survey of deep learning-based human activity recognition in radar [J].Remote Sensing,2019,11(9):1068.
[5]CHEN Z,LI G,FIORANELLI F,et al.Personnel recognitionand gait classification based on multistatic micro-Doppler signatures using deep convolutional neural networks [J].IEEE Geoscience and Remote Sensing Letters,2018,15(5):669-673.
[6]NKWARI P,SINHA S,FERREIRA H.Through-the-wall radar imaging:A review [J].IETE Technical Review,2018,35(6):631-639.
[7]TAN Z G,LU M,HU Y P,et al.LIDAR target recognitionbased on point cloud-model matching [J].Computer Engineering &Science,2012,34(4):32-36.
[8]LAI J L,YANG Z C,BAO R H,et al.Daily motion classification based on ultra-wideband radar [J].Radar Science and Technology,2021,19(3):265-270.
[9]JANKIRAMAN M.FMCW Radar Design [M].Artech House,2018.
[10]KIM Y,LING H.Human activity classification based on micro-Doppler signatures using a support vector machine [J].IEEE Transactions on Geoscience and Remote Sensing,2009,47(5):1328-37.
[11]SEYFIOĞLU M S,ÖZBAYOĞLU A M,GÜRBÜZ S Z.Deep Convolutional Autoencoder for Radar-Based Classification of Similar Aided and Unaided Human Activities [J].IEEE Transactions on Aerospace and Electronic Systems,2018,PP(4):1709-1723.
[12]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,2015,13(1):8-12.
[13]JIN F,ZHANG R,SENGUPTA A,et al.Multiple patients behavior detection in real-time using mmWave radar and deep CNNs[C]//Proceedings of the 2019 IEEE Radar Conference(RadarConf).IEEE,2019.
[14]WANG B,GUO L,ZHANG H,et al.A millimetre-wave radar-based fall detection method using line kernel convolutional neural network [J].IEEE Sensors Journal,2020,20(22):13364-13370.
[15]DING W,GUO X,WANG G.Radar-Based Human ActivityRecognition Using Hybrid Neural Network Model With Multidomain Fusion [J].IEEE Transactions on Aerospace and Electronic Systems,2021,57(5):2889-98.
[16]TAYLOR W,DASHTIPOUR K,SHAH S A,et al.Radar sensing for activity classification in elderly people exploiting micro-doppler signatures using machine learning [J].Sensors,2021,21(11):3881.
[17]HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016
[18]AHMAD A,ROH J C,WANG D,et al.Vital signs monitoring of multiple people using a FMCW millimeter-wave sensor[C]//Proceedings of the 2018 IEEE Radar Conference(RadarConf18).IEEE,2018.
[19]ZHOU Z,CAO Z,PI Y.Dynamic gesture recognition with a terahertz radar based on range profile sequences and Doppler signatures [J].Sensors,2017,18(1):10.
[20]WANG J,CHEN Y,HAO S,et al.Deep learning for sensor-based activity recognition:A survey [J].Pattern Recognition Letters,2019,119:3-11.
[21]HELEN VICTORIA A,MARAGATHAM G.Activity recognition of FMCW radar human signatures using tower convolutionalneural networks [J].Wireless Networks,2021:1-17.
[22]JOKANOVIĆ B,AMIN M.Fall detection using deep learning in range-Doppler radars [J].IEEE Transactions on Aerospace and Electronic Systems,2017,54(1):180-189.
[23]SEYFIOĞLU M S,ÖZBAYOĞLU A M,GÜRBÜZ S Z.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.
[24]BHAVANASI G,WERTHEN-BRABANTS L,DHAENE T,et al.Patient activity recognition using radar sensors and machine learning [J].Neural Computing and Applications,2022,34:16033-16048.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发