Indoor Through-The-Wall Passive Target Detection Algorithm Based on Graph Convolutional Neural Network

YANG Xiao-long; TANG Ting; LI Zhao-yu; TANG Xin-xing

doi:10.12263/DZXB.20220561

您当前的位置：

首页 >

文章列表页 >

Indoor Through-The-Wall Passive Target Detection Algorithm Based on Graph Convolutional Neural Network

PAPERS | 更新时间：2025-12-11

- Indoor Through-The-Wall Passive Target Detection Algorithm Based on Graph Convolutional Neural Network
- ACTA ELECTRONICA SINICA Vol. 52, Issue 2, Pages: 614-625(2024)
- 作者机构：
  
  重庆邮电大学通信与信息工程学院，重庆 400065
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China(62101085);Science and Technology Research Project of Chongqing Jiulongpo District(2022-02-005-Z)
- DOI：10.12263/DZXB.20220561
  CLC： TN929.5;
- Received：16 May 2022，
  
  Revised：2023-01-29，
  
  Published：25 February 2024
- 稿件说明：
移动端阅览
杨小龙,唐婷,李兆玉,等.基于图卷积神经网络的室内穿墙无源目标检测算法[J].电子学报,2024,52(02):614-625.

YANG Xiao-long, TANG Ting, LI Zhao-yu, et al.Indoor Through-The-Wall Passive Target Detection Algorithm Based on Graph Convolutional Neural Network[J].Acta Electronica Sinica, 2024, 52(02): 614-625.
杨小龙,唐婷,李兆玉,等.基于图卷积神经网络的室内穿墙无源目标检测算法[J].电子学报,2024,52(02):614-625. DOI：10.12263/DZXB.20220561

YANG Xiao-long, TANG Ting, LI Zhao-yu, et al.Indoor Through-The-Wall Passive Target Detection Algorithm Based on Graph Convolutional Neural Network[J].Acta Electronica Sinica, 2024, 52(02): 614-625. DOI：10.12263/DZXB.20220561

摘要

针对室内穿墙场景下目标状态差异而导致的信道状态信息（Channel State Information，CSI）功率谱密度在时序发生相应变化规律的不同，本文提出了一种基于图卷积神经网络（Graph Convolutional Neural，GCN）的室内穿墙无源目标检测算法．不同于传统的基于CSI的统计特征实现目标检测的相关系统，该算法从CSI的图域出发，基于CSI时频图特征构建得到GCN图结构后，使用可实现对复杂图中各节点进行分类的GCN作为分类器，提高了室内复杂环境下目标检测的性能．该方法在对原始CSI进行异常值去除和小波阈值去噪的基础上，利用短时傅里叶变换得到每个子载波上CSI幅值的时频图；然后根据各子载波CSI时频图特点，将存在能量的频率平均分为5个频段，再计算每个频段的平均功率谱密度，并在每个时序对其进行排序；最后基于对平均功率谱密度排序后各频段索引的变化规律构造GCN图，并将其邻接矩阵和特征矩阵输入GCN网络中进行训练，最终实现图节点特征与目标状态的一一映射．实验结果表明，在玻璃墙和砖墙场景下，本文提出的算法能够很好地刻画目标状态不同而导致的CSI功率谱密度变化规律的差异，且其平均检测准确率均高于现有的R-TTWD（Robust device-free Through-The-Wall Detection）和TWMD（The-Wall Moving Detection）目标检测算法．

Abstract

According to variation laws of channel state information (CSI) power spectral density (PSD) in the timing series caused by different target states in indoor through-the-wall scenarios

this paper proposes a passive target detection algorithm based on graph convolutional neural (GCN). Different from the traditional correlation system for target detection based on CSI statistical features

this algorithm starts from the graph domain of CSI

constructs the GCN graph structure based on CSI time-frequency diagram

and uses the GCN that can classify the nodes in the complex graph as the classifier

which improves the performance of target detection in the indoor complex environment. Based on outlier removal and wavelet threshold denoising for original CSI information

it uses the short-time Fourier transform to obtain the time-frequency diagram of the CSI amplitude on each subcarrier. Then

according to the characteristics of each subcarrier’s CSI time-frequency diagram

the total spectrum is divided into five frequency bands on average

and the average PSD of each frequency band is calculated and sorted at every sample time. Finally

a GCN graph is constructed based on the variation law of the index of each frequency band after sorting the average PSD

and then its adjacency matrix and feature matrix are input into the GCN network for training

which can finally realize the one-to-one mapping between graph node features and target states. Experimental results show that under the scenarios of glass wall and brick wall

the proposed algorithm can essentially characterize the difference of CSI PSD change regularity caused by different target states; and its average detection accuracy is higher than that of the existing R-TTWD (Robust device-free Through-The-Wall Detection) and TWMD (The-Wall Moving Detection) target detection algorithms.

关键词

Keywords

references

高洁 , 朱元 , 陆科 . 基于雷达和相机融合的目标检测方法 [J]. 计算机应用 , 2021 , 41 ( 11 ): 3242 - 3250 .

GAO J , ZHU Y , LU K . Object detection method based on radar and camera fusion [J]. Journal of Computer Applications , 2021 , 41 ( 11 ): 3242 - 3250 . (in Chinese)

苗壮 , 张湧 , 李伟华 . 基于中心点的实时红外目标检测方法 [J]. 红外与毫米波学报 , 2021 , 40 ( 6 ): 858 - 864 .

MIAO Z , ZHANG Y , LI W H . Real-time infrared target detection based on center points [J]. Journal of Infrared and Millimeter Waves , 2021 , 40 ( 6 ): 858 - 864 . (in Chinese)

蒋留兵 , 周小龙 , 车俐 . 基于无载波超宽带雷达的小样本人体动作识别 [J]. 电子学报 , 2020 , 48 ( 3 ): 602 - 615 .

JIANG L B , ZHOU X L , CHE L . Few-shot learning for human motion recognition based on carrier-free UWB radar [J]. Acta Electronica Sinica , 2020 , 48 ( 3 ): 602 - 615 . (in Chinese)

FENG C , XIONG J , CHANG L Q , et al . RF-identity: Non-intrusive person identification based on commodity RFID devices [J]. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies , 2021 , 5 ( 1 ): 1 - 23 .

LIN Y X , GAO Y , LI B J , et al . Revisiting indoor intrusion detection with WiFi signals: Do not panic over a pet! [J]. IEEE Internet of Things Journal , 2020 , 7 ( 10 ): 10437 - 10449 .

WU C S , YANG Z , ZHOU Z M , et al . Non-invasive detection of moving and stationary human with WiFi [J]. IEEE Journal on Selected Areas in Communications , 2015 , 33 ( 11 ): 2329 - 2342 .

XIAO J , WU K S , YI Y W , et al . FIMD: fine-grained device-free motion detection [C]// 2012 IEEE 18th International Conference on Parallel and Distributed Systems . Piscataway : IEEE , 2012 : 229 - 235 .

QIAN K , WU C S , YANG Z , et al . PADS: Passive detection of moving targets with dynamic speed using PHY layer information [C]// 2014 20th IEEE International Conference on Parallel and Distributed Systems (ICPADS) . Piscataway : IEEE , 2014 : 1 - 8 .

ADIB F , KATABI D . See through walls with WiFi! [J]. ACM SIGCOMM Computer Communication Review , 2013 , 43 ( 4 ): 75 - 86 .

ZHU H , XIAO F , SUN L J , et al . R-TTWD: Robust device-free through-the-wall detection of moving human with WiFi [J]. IEEE Journal on Selected Areas in Communications , 2017 , 35 ( 5 ): 1090 - 1103 .

ZHANG F , WU C S , WANG B B , et al . WiDetect: Robust motion detection with a statistical electromagnetic model [J]. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies , 2019 , 3 ( 3 ): 1 - 24 .

何艾琳 . 基于WiFi穿墙雷达的移动目标检测算法研究 [D]. 重庆 : 重庆邮电大学 , 2019 .

HE A L . Research on Moving Target Detection Algorithm Based on WiFi Through-The-Wall Radar [D]. Chongqing : Chongqing University of Posts and Telecommunications , 2019 . (in Chinese)

杨小龙 , 吴世明 , 周牧 , 等 . 室内穿墙场景下的无源人体目标检测算法 [J]. 电子与信息学报 , 2020 , 42 ( 3 ): 603 - 612 .

YANG X L , WU S M , ZHOU M , et al . Indoor through-the-wall passive human target detection algorithm [J]. Journal of Electronics & Information Technology , 2020 , 42 ( 3 ): 603 - 612 . (in Chinese)

戴欢 , 蒋敬敬 , 束沁冬 , 等 . 基于信道状态相位信息的生命体征监测算法 [J]. 计算机科学 , 2020 , 47 ( 10 ): 48 - 54 .

DAI H , JIANG J J , SHU Q D , et al . Vital signs monitoring method based on channel state phase information [J]. Computer Science , 2020 , 47 ( 10 ): 48 - 54 . (in Chinese)

赵明富 , 唐平 , 汤斌 , 等 . 基于小波变换的压缩感知理论对水质检测紫外-可见光谱数据的去噪研究 [J]. 光谱学与光谱分析 , 2018 , 38 ( 3 ): 844 - 850 .

ZHAO M F , TANG P , TANG B , et al . Research on denoising of UV-vis spectral data for water quality detection with compressed sensing theory based on wavelet transform [J]. Spectroscopy and Spectral Analysis , 2018 , 38 ( 3 ): 844 - 850 . (in Chinese)

李淑雅 , 施明 , 张建秋 . 时频分析的卡尔曼滤波匹配解调变换法 [J]. 电子学报 , 2018 , 46 ( 4 ): 769 - 774 .

LI S Y , SHI M , ZHANG J Q . Matching demodulation transform with a Kalman filter for time-frequency analyses [J]. Acta Electronica Sinica , 2018 , 46 ( 4 ): 769 - 774 . (in Chinese)

GRINGOLI F , SCHULZ M , LINK J , et al . Free your CSI: A channel state information extraction platform for modern Wi-Fi chipsets [C]// Proceedings of the 13th International Workshop on Wireless Network Testbeds , Experimental Evaluation & Characterization . New York : ACM , 2019 : 21 - 28 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research on Bidirectional Mobile Cross-Technology Communication Method Between WiFi and ZigBee

Graph-Based Representation Knowledge Distillation for Image Classification

A Deep Semantic Mining Model Based on Aspect-Level Sentiment Analysis

Related Author

LI Zi-long

NIU Qiang

YANG Xu

YIN Yu-qing

XU Shan-zhi

LI Ming

ZHAO Er-hu

YANG Chuan-guang

Related Institution

School of Computer Information Engineering， Qingdao City University

School of Computer Science and Technology， China University of Mining and Technology

Unit of PLA

Institute of Computing Technology， Chinese Academy of Sciences

School of Innovation and Entrepreneurship Education， Inner Mongolia University of Science and Technology

⁰