摘要
与传统惯性传感器和视觉传感器相比,利用毫米波雷达进行人体行为检测不仅对环境要求低、灵敏度高而且能很好地解决摄像头存在的泄露隐私等问题。针对目前毫米波雷达人体行为检测存在的杂波干扰和网络模型复杂度高的问题,本文对现有的残差网络进行改进和量化处理,并结合雷达时频变换和杂波抑制,提出了一套完整的雷达人体行为检测信号处理流程。时频变换部分采用距离维FFT、沿慢时间维进行高通滤波、短时傅里叶变换得到时间-多普勒谱;残差网络部分则是嵌入CBAM注意力机制并对其进行32~8位数据量化处理;最后将时间-多普勒谱输入网络模型进行特征提取和分类得到检测结果。实验结果表明,该方法能够消除静态杂波的干扰,检测准确率达97.33%,模型大小仅为20.2 MB。
Compared with traditional inertial sensors and visual sensors,using millimeter-wave radar for human activity detection not only requires low environmental demands and high sensitivity but also can effectively address privacy leakage issues associated with cameras.To tackle the problems of clutter interference and high complexity of network models in current millimeter-wave radar human activity detection,this paper proposes improvements and quantization processing of existing residual neural network.By integrating radar time-frequency transformation and clutter suppression,a complete signal processing flow for radar human activity detection is presented.The time-frequency transformation section adopts range dimension FFT,high-pass filtering in slow-time dimension,and short-time Fourier transformation to obtain Time-Doppler spectrum.The residual network section embeds the CBAM attention mechanism and quant it from 32 bits to 8 bits.Finally,the Time-Doppler spectrums are input into the network model for feature extraction and classification to obtain detection results.Experimental results demonstrate that this method can eliminate interference from static clutter,achieving a detection accuracy of 97.33%with a model size of 20.2 MB.
作者
孙梓誉
顾晶
Sun Ziyu;Gu Jing(College of Electronics&Information Engineering,Nanjing University of Information Science&Technology,Nanjing 210044,China;College of Electronic Information Engineering,Wuxi University,Wuxi 214105,China)
出处
《电子测量技术》
北大核心
2024年第10期27-33,共7页
Electronic Measurement Technology
基金
江苏省高等学校基础科学(自然科学)研究面上项目(23KJB510035,22KJB140015)资助。
关键词
毫米波雷达
时频变换
杂波抑制
时间-多普勒
残差网络
millimeter-wave radar
time-frequency transformation
clutter suppression
Time-Doppler
residual neural network
