计算机科学 ›› 2025, Vol. 52 ›› Issue (10): 317-327.doi: 10.11896/jsjkx.240800060
段鹏松, 张伊航, 方焘, 曹仰杰, 王超
DUAN Pengsong, ZHANG Yihang, FANG Tao, CAO Yangjie, WANG Chao
摘要： 针对CSI中空间特征缺失导致人数识别模型精度有限且计算复杂度较高的问题,提出了一种基于幅相融合的轻量级人数识别模型WiLCount。首先,针对原始相位信息中存在载波频率偏移和采样频率偏移而无法直接使用的问题,使用线性变换方法对相位信息进行校准;其次,将幅相数据重构为二维图像,以充分利用CSI信息中蕴含的人数空间映射特征;最后,融合深度可分离卷积与多分支结构技术,设计了一种轻量级的人数识别模型WiLCount。目前,在Wi-Fi感知人数领域暂无公开数据集,为此精心构建了一个在人数规模、行为种类均处于业界领先水平的自采数据集,并已公开。实验结果表明,WiLCount在自采数据集上的识别准确率高达99.58%,参数规模仅为同类模型的4%,相比现有方法有显著提升,且具有较好的鲁棒性。
中图分类号:
| [1]CHOI J W,QUAN X,CHO S H.Bi-Directional Passing People Counting System based on IR-UWB Radar Sensors[J].IEEE Internet of Things Journal,2017,5(2):512-522. [2]LIU P C,NGUANG S K,PARTRIDGE A.Occupancy Inference Using Pyroelectric Infrared Sensors Through Hidden Markov Models[J].IEEE Sensors Journal,2016,16(4):1062-1068. [3]ZHANG Y Y,ZHOU D S,CHEN S Q,et al.Single-ImageCrowd Counting via Multi-Column Convolutional Neural Network[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2016:589-597. [4]LIN H,MA Z H,JI R,et al.Boosting Crowd Counting via Multifaceted Attention[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition.IEEE,2022:19596-19605. [5]LU Y,LYU S H,WANG X D,et al.A survey onWiFi based human behavior analysis technology[J].Chinese Journal of Computers,2019,42(2):231-251. [6]HAN Z J,LU Z M,WEN X M,et al.CentiTrack:Toward Centimeter-Level Passive Gesture Tracking With Commodity WiFi[J].IEEE Internet of Things Journal,2023,10(14):13012-13027. [7]ZHANG C S,JIAO W G.ImgFi:A High Accuracy and Lightweight Human Activity Recognition Framework Using CSI Image[J].IEEE Sensors Journal,2023,23(18):21966-21977. [8]LIU K Z,PEI D S,ZHANG S K,et al.WiCrew:Gait-Based Crew Identification for Cruise Ships Using Commodity WiFi[J].IEEE Internet of Things Journal,2023,10(8):6960-6972. [9]TEWES S,HEINRICHS M,KRONBERGER R,et al.IRS-Enabled Breath Tracking With Colocated Commodity WiFi Transceivers[J].IEEE Internet of Things Journal,2023,10(8):6870-6886. [10]JIN R N,ZHOU J Y,HU J H,et al.Toward Practical Lightweight Passive Human Tracking Using WiFi Sensing[J].IEEE Internet of Things Journal,2023,10(15):13769-13783. [11]BAHL P,PADMANABHAN V N.RADAR:an in-building RF-based user location and tracking system[C]//Proceedings IEEE INFOCOM 2000.Conference on Computer Communications.Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies.IEEE,2000:775-784. [12]NAKATSUKA M,IWATANI H,KATTO J.A study on pas-sive crowd density estimation using wireless sensors[C]//In The 4th Intl.Conf.on Mobile Computing and Ubiquitous Networking.2008. [13]YOSHIDA T,TANIGUCHI Y.Estimating the number of people using existing WiFi access point in indoor environment[C]//International Conference on Evolutionary Computing;European Conference of Computer Science.IEEE,2015. [14]DEPATLA S,MURALIDHARAN A,MOSTOFI Y.Occupancy Estimation Using Only WiFi Power Measurements[J].IEEE Journal on Selected Areas in Communications,2015,33(7):1381-1393. [15]LI H C,CHAN E,GUO X N,et al.Wi-Counter:Smartphone-Based People Counter Using Crowdsourced Wi-Fi Signal Data[J].IEEE Transactions on Human-Machine Systems,2015,45(4):442-452. [16]KURA S,YAMAGUCHI H,SHIRAISHI Y.Low-cost Pedestrian Counter Using Wi-Fi APs for Smart Building Applications[C]//2018 IEEE 42nd Annual Computer Software and Applications Conference.IEEE,2018:640-645. [17]HALPERIRR D,HU W,SHETH A,et al.Tool release:gathering 802.11n traces with channel state information[J].ACM Sigcomm Computer Communication Review,2011,41(1):53-53. [18]YANG Z,ZHOU Z M,LIU Y H.From RSSI to CSI:Indoor Localization via Channel Response[J].ACM Computing Surveys,2013,46(2):1-32. [19]XI W,ZHAO J Z,LI X Y,et al.Electronic frog eye:Counting crowd using WiFi[C]//IEEE INFOCOM 2014－IEEE Confe-rence on Computer Communications.IEEE,2014:361-369. [20]DING Y S,GUO B,XIN T,et al.WiCount:A Crowd Counting Method Based on WiFi Channel State Information[J].Computer Science,2019,46(11):297-303. [21]WANG S N,XUN Y J,ZHAO J,et al.A Novel PersonnelCounting Method Based on WiFi Perception[C]//2022 IEEE 23rd International Conference on High Performance Switching and Routing.IEEE,2022:206-211. [22]CHOI H,FUJIMOTO M,MATSUI T,et al.Wi-CaL:WiFi Sensing and Machine Learning based Device-Free Crowd Coun-ting and Localization[J].IEEE Access,2022,10:24395-24410. [23]GUO Z X,FU X,SHENG B Y,et al.TWCC:A RobustThrough-the-Wall Crowd Counting System Using Ambient WiFi Signals[J].IEEE Transactions on Vehicular Technology,2022,71(4):4198-4211. [24]HOU H W,BI S Z,ZHENG L L,et al.DASECount:Domain-Agnostic Sample-Efficient Wireless Indoor Crowd Counting via Few-Shot Learning[J].IEEE Internet of Things Journal,2022,10(8):7038-7050. [25]KHAN D,HO I.CrossCount:Efficient Device-Free CrowdCounting by Leveraging Transfer Learning[J].IEEE Internet of Things Journal,2023,10(5):4049-4058. [26]YOUSSEF M,MAH M,AGRAWALA A.Challenges:Device-free passive localization for wireless environments[C]//ACM/IEEE International Conference on Mobile Computing and Networking.ACM,2007:9-14. [27]BAO N,DU J J,WU C Y,et al.Wi-Breath:A WiFi-Based Contactless and Real-Time Respiration Monitoring Scheme for Remote Healthcare[J].IEEE Journal of Biomedical and Health Informatics,2022,27(5):2276-2285. [28]SEN S,RADUNOVIC B,CHOUDHURY R R,et al.You are facing the Mona Lisa:spot localization using PHY layer information[C]//ACM SIGMOBILE International Conference on Mobile Systems,Applications,and Services.ACM,2012:183-196. [29]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.IEEE,2014:1-8. [30]LIU Z J,WANG L,LIU W Y,et al.Human Movement Detection and Gait Periodicity Analysis Using Channel State Information[C]//International Conference on Mobile Ad-hoc & Sensor Networks.IEEE,2016:167-174. [31]HOWARD A G,ZHU M L,CHEN B,et al.MobileNets:Effi-cient Convolutional Neural Networks for Mobile Vision Applications[J].arXiv:1704.04861,2017. [32]XIE Y X,LI Z J,LI M.Precise Power Delay Profiling with Commodity Wi-Fi[J].IEEE Transactions on Mobile Computing,2015,18:1342-1355. [33]GRINGOLI F,SCHULZ M,LINK J,et al.Free Your CSI:A Channel State Information Extraction Platform For Modern Wi-Fi Chipsets[C]//13th ACM International Workshop on Wireless Network Testbeds,Experimental Evaluation and Characterization.ACM,2019:21-28. [34]HUSSEIN K,CLAUDIO P,FEDERICO P,et al.Impact of Wi-Fi traffic on the IEEE 802.15.4 channels occupation in indoor environments[C]//2009 International Conference on Electromagnetics in Advanced Applications.IEEE,2009:1042-1045. [35]SZEGEDY C,VANHOUCKE V,IOFFE S,et al.Rethinking the Inception Architecture for Computer Vision[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2016:2818-2826. [36]HE K M,ZHANG X,REN S Q,et al.Deep Residual Learning for Image Recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2015:770-778. [37]DOSOVITSKIY A,BEYER L,KOLESNIKOV A,et al.AnImage is Worth 16×16 Words:Transformers for Image Recognition at Scale [J].arXiv:2010.11929,2020. [38]CHEN H T,WANG Y H,GUO J Y,et al.VanillaNet:thePower of Minimalism in Deep Learning[J].arXiv:2305.12972,2023. [39]SANDLER M,HOWARD A,ZHU M L,et al.MobileNetV2:Inverted Residuals and Linear Bottlenecks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.IEEE,2018:4510-4520. [40]IANDOLA F N,MOSKEWICZ M W,ASHRAF K,et al.SqueezeNet:AlexNet-level accuracy with 50x fewer parameters and <1 MB model size[J].arXiv:1602.07360,2016. [41]CAO C Y,YANG X D,DUAN P S.WiDoor:Close-range Contactless Human Identification Approach[J].Cpmputer Science,2023,50(4):388-396. |
|
||
首页