计算机科学 ›› 2019, Vol. 46 ›› Issue (12): 266-271.doi: 10.11896/jsjkx.190200349

• 图形图像与模式识别 • 上一篇    下一篇

一种基于CSI的非合作式人体行为识别方法

李晓薇, 余江, 常俊, 杨锦朋, 冉亚鑫   

  1. (云南大学信息学院 昆明650500)
  • 收稿日期:2019-02-23 出版日期:2019-12-15 发布日期:2019-12-17
  • 通讯作者: 余江(1961-),男,教授,硕士生导师,主要研究领域为无线通信技术、网络通信理论等,E-mail:yujiang@ynu.edu.cn。
  • 作者简介:李晓薇(1994-),女,硕士生,CCF会员,主要研究领域为无线感知技术应用;常俊(1970-),男,副教授,硕士生导师,主要研究领域为网络通信理论、无线通信与网络等;杨锦朋(1992-),男,硕士生,主要研究领域为室内定位技术理论及应用等;冉亚鑫(1996-),女,硕士生,主要研究领域为人体行为检测技术应用。
  • 基金资助:
    本文受国家自然科学基金(61162406),云南省高校频谱传感与边疆无线电安全重点实验室开放课题(C6165903),云南省教育厅科学研究基金项目(2019J0007),云南大学2018年研究生科研创新项目(Y2000211)资助。

Non-cooperative Human Behavior Recognition Method Based on CSI

LI Xiao-wei, YU Jiang, CHANG Jun, YANG Jin-peng, RAN Ya-xin   

  1. (School of Information Science and Engineering,Yunnan University,Kunming 650500,China)
  • Received:2019-02-23 Online:2019-12-15 Published:2019-12-17

摘要: 目前,基于Wi-Fi的无线人员感知技术被广泛应用于防入侵安全监测、人类健康护理、步态识别等领域,对此提出了一种基于无设备的非合作式人体行为识别方法,利用Wi-Fi信号的信道状态信息CSI来识别5个动态活动:行走、坐-站、深蹲、跳跃和跌倒。该方法利用SIMO系统采集CSI数据,在对CSI幅度和相位分别进行预处理之后,实施3个步骤来降低计算开销机制:子载波融合、基于移动方差阈值的不良数据链路剔除以及基于小波变换的动态时间窗口的数据分割。在经过前期的各项预处理后提取动作特征,从时域扩展到频率域,通过分析多普勒功率谱的特性来提高CSI信号的利用率。实验结果表明,总体识别率随着使用特征维度的增加而上升;组合分类器加权投票方法经过两轮投票优化,把对5个动作的总体识别率提高到90.3%,且相较于RSSI,CSI在人体行为识别领域的优势更加明显。

关键词: 多普勒功率谱, 非合作式, 小波分析, 信道状态信息

Abstract: Currently,Wi-Fi-based wireless personnel perception technology is widely used in anti-intrusion security monitoring,human health care,gait recognition and other fields,regarding this,this paper proposed a non-cooperative human behavior recognition method.The channel state information (CSI) of Wi-Fi signals can be used to recognize five dynamic activities:walking,sitting-standing up,squatting,jumping and falling.The method uses a SIMO system to collect CSI data,and after performing pre-processing on the CSI amplitude and phase respectively,implements a three-step computational cost reduction mechanism:subcarrier fusion,rejection of bad data link based on mobile variance threshold,and data segmentation of dynamic time window based on wavelet transform.Then activity features are extracted and extended from the time domain to the frequency domain.By analyzing the characteristics of the Doppler power spectrum,the utilization of the CSI signal is improved.Experiment results show that the overall recognition rate increases with the use of feature dimensions.Optimized by two rounds of voting,the combined classifier weighted voting method is increasing the overall recognition rate of five dynamic activities to 90.3%.And compared to RSSI,the advantages of CSI in the field of human behavior recognition are more prominent.

Key words: CSI, Dopplerpower spectrum, Non-cooperative, Wavelet analysis

中图分类号: 

  • TP391.4
[1]WANG L.Research on human behavior recognition technology based on wearable sensor network[D].Nanjing:Nanjing University,2014.
[2]WU C S,YANG Z,ZHOU Z M,et al.Non-invasive detection of moving and stationary human with Wi-Fi[J].IEEE Journal on Selected Areas in Communications,2015,33(11):2329-2342.
[3]QIAN K,WU C,YANG Z,et al.Enabling Contactless Detection of Moving Humans with Dynamic Speeds Using CSI[J].ACM Transactions on Embedded Computing Systems,2018,17(2):1-18.
[4]ZEHUA D,FANGMIN L,JULANG Y,et al.Indoor Motion Detection Using Wi-Fi Channel State Information in Flat Floor Environments Versus in Staircase Environments[J].Sensors,2018,18(7):2177.
[5]LIU M G,ZHANG L,YANG P L,et al.Wi-Run:Device-free step estimation system with commodity Wi-Fi[J].Journal of Network and Computer Applications,2019,143(1):77-88.
[6]YOUSSEF M,MAH M.Challenges:Device-free Passive Localization for Wireless[C]//Acm International Conference on Mobile Computing & Networking.Montréal,Québec,Canada:ACM,2007.
[7]SIGG S,SCHOLZ M,SHI S,et al.RF-Sensing of Activities from Non-Cooperative Subjects in Device-Free Recognition Systems Using Ambient and Local Signals[J].IEEE Transactions on Mobile Computing,2014,13(4):907-920.
[8]YANG Z,ZHOU Z,LIU Y.From RSSI to CSI:Indoor Localization via Channel Response[J].ACM Computing Surveys,2013,46(2):1-32.
[9]YANG Z,LIU Y H.Wi-Fi Radar:From RSSI to CSI[J].Chinese Computer Society,2014,10(11):55-60.
[10]TIAN X H,ZHU S J,XIONG S J,et al.Performance Analysis of Wi-Fi Indoor Localization with Channel State Information [J].IEEE Transactions on Mobile Computing,2019,18(8):1870-1884.
[11]ZHANG Y,LI D P,WANG Y J.An Indoor Passive Positioning Method Using CSI Fingerprint Based on Adaboost [J].IEEE Sensors Journal,2019,19(14):5792-5800.
[12]XIN T,GUO B,WANG Z,et al.FreeSense:human-behavior understanding using Wi-Fi signals [J].Journal of Ambient Intelligence and Humanized Computing,2018,9(5):1611-1622.
[13]LI W D,TAN B,PIECHOCKI R J.Wi-Fi based passive sensing system for human presence and activity event classification [J].IET Wireless Sensor Systems,2018,8(6):276-283.
[14]LI L X.Research and Design of Personnel Perception and Intrusion Detection Technology Based on WLAN[D].Beijing:Beijing University of Posts and Telecommunications,2018.
[15]XIAO L,PAN H.Human motion recognition system based on Wi-Fi signal[J].Journal of Beijing University of Posts and Telecommunications,2018,41(3):119-124.
[16]WANG T,YANG D D,ZHANG S Q,et al.Wi-Alarm:Low-Cost Passive Intrusion DetectionUsing Wi-Fi[J].Sensors,2019,19(10):2335.
[17]WU K,XIAO J,YI Y,et al.FILA:Fine-grained indoor localization[C]//Proceedings of IEEE INFOCOM.2012:2210-2218.
[18]WANG W,LIU A X,SHAHZAD M,et al.Device-Free Human Activity Recognition Using Commercial Wi-Fi Devices[J].IEEE Journal on Selected Areas in Communications,2017,35(5):1118-1131.
[19]LI Y H,CHEN B.A Parameter-Independent Access Point Location Method Based on CSI[J].Computer Science,2017,44(12):74-77.
[20]GENG Y,CHEN J,FU R,et al.Enlighten Wearable Physiological Monitoring Systems:On-body RF Characteristics Based Human Motion Classification Using a Support Vector Machine[J].IEEE Transactions on Mobile Computing,2016,15(3):656-671.
[1] 卿朝进, 杜艳红, 叶青, 杨娜, 张岷涛.
存在CSI估计错误的增强型ELM叠加CSI反馈方法
Enhanced ELM-based Superimposed CSI Feedback Method with CSI Estimation Errors
计算机科学, 2022, 49(6A): 632-638. https://doi.org/10.11896/jsjkx.210800036
[2] 王炽, 常俊.
基于3D卷积神经网络的CSI跨场景手势识别方法
CSI Cross-domain Gesture Recognition Method Based on 3D Convolutional Neural Network
计算机科学, 2021, 48(8): 322-327. https://doi.org/10.11896/jsjkx.200600122
[3] 罗靖杰, 王永利.
ADCSM:一种细粒度汽车行驶工况模型构建方法
ADCSM:A Fine-grained Driving Cycle Model Construction Method
计算机科学, 2021, 48(6A): 289-294. https://doi.org/10.11896/jsjkx.200600019
[4] 尤凌, 管张均.
一种低复杂度的水声OFDM通信系统子载波分配算法
Low-complexity Subcarrier Allocation Algorithm for Underwater OFDM Acoustic CommunicationSystems
计算机科学, 2021, 48(6A): 387-391. https://doi.org/10.11896/jsjkx.201100064
[5] 王颖颖, 常俊, 武浩, 周详, 彭予.
基于WiFi-CSI的入侵检测方法
Intrusion Detection Method Based on WiFi-CSI
计算机科学, 2021, 48(6): 343-348. https://doi.org/10.11896/jsjkx.200700006
[6] 向昌盛, 陈志刚.
面向海量数据的网络流量混沌预测模型
Chaotic Prediction Model of Network Traffic for Massive Data
计算机科学, 2021, 48(5): 289-293. https://doi.org/10.11896/jsjkx.200400056
[7] 李向利, 贾梦雪.
基于预处理的超图非负矩阵分解算法
Nonnegative Matrix Factorization Algorithm with Hypergraph Based on Per-treatments
计算机科学, 2020, 47(7): 71-77. https://doi.org/10.11896/jsjkx.200200106
[8] 田春元, 余江, 常俊, 王彦舜.
NWI:基于CSI的非视距信号识别方法
NWI:CSI Based Non-line-of-sight Signal Recognition Method
计算机科学, 2020, 47(11): 327-332. https://doi.org/10.11896/jsjkx.190900019
[9] 何明星, 周杰, 吴鹏, 刘杨.
山洞环境中声信号的传播模型及其性能研究
Acoustic Signal Propagation Model and Its Performance in Cave Environment
计算机科学, 2019, 46(9): 113-119. https://doi.org/10.11896/j.issn.1002-137X.2019.09.015
[10] 杜臻, 马立鹏, 孙国梓.
一种基于小波分析的网络流量异常检测方法
Network Traffic Anomaly Detection Based on Wavelet Analysis
计算机科学, 2019, 46(8): 178-182. https://doi.org/10.11896/j.issn.1002-137X.2019.08.029
[11] 刘佳慧, 王昱洁, 雷艺.
基于LSTM的CSI手势识别方法
CSI Gesture Recognition Method Based on LSTM
计算机科学, 2019, 46(11A): 283-288.
[12] 丁亚三, 郭斌, 辛通, 王沛, 王柱, 於志文.
WiCount:一种基于WiFi-CSI的人数识别方法
WiCount:A Crowd Counting Method Based on WiFi Channel State Information
计算机科学, 2019, 46(11): 297-303. https://doi.org/10.11896/jsjkx.191100506C
[13] 陈雯雯,王亚林,周杰.
三维统计信道中的多普勒效应及其信号分析
Doppler Effect and Analysis of Signals in Three-dimensional Channel Model
计算机科学, 2017, 44(3): 84-88. https://doi.org/10.11896/j.issn.1002-137X.2017.03.020
[14] 李耀辉,陈兵.
一种基于CSI的参数无关接入点定位方法
Parameter Independent Access Point Positioning Method Based on CSI
计算机科学, 2017, 44(12): 68-71. https://doi.org/10.11896/j.issn.1002-137X.2017.12.013
[15] 贺清碧,黄大荣,杨永琴.
基于小波分析和多项式细分定位的超分辨率图像重建算法
Super-resolution Reconstruction Method Based on Wavelet Analysis and Polynomial Subdivision Location
计算机科学, 2016, 43(3): 313-316. https://doi.org/10.11896/j.issn.1002-137X.2016.03.059
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!