基于Wi-Fi信号的室内感知技术研究

      室内感知，作为未来智能家居和物联网场景下的核心技术具有重要的研究意义。Wi-Fi由于其低成本、易部署等特征逐渐成为室内感知的研究热点。于此同时，2020年9月工业界也设立了IEEE 802.11bf工作组，旨在提高Wi-Fi感知的可靠性和效率以推进全新应用落地。目前的研究现状表明，Wi-Fi感知仍然面临着以下几大挑战：CSI信号受到严重相位噪声的影响，包括频率偏移和时钟偏移；具体应用案例中算法鲁棒性和泛化性不高，本文中应用案例为跌倒检测。
      本文基于以上观察建立了Wi-Fi CSI信号的相位噪声模型，并采用双天线的方案来消除相位噪声以恢复真实相位。基于此，本文提出了鲁棒性和泛化性较优的跌倒检测方案。本文所提出的跌倒检测算法从CSI矩阵中提取多维度的综合特征以提高检测的稳定性，并在不同的多径场景下验证了算法的性能，结果显示系统的跌倒检测率高达90%以上。
      另外，本文验证了Wi-Fi同时动作识别和测距可能性，但由于现有Wi-Fi系统收发分置特性，难以获得准确的信号飞行时间，测距效果不理想。考虑到未来Wi-Fi感知有可能朝雷达感知的趋势发展，本文采用双频连续波雷达来模拟Wi-Fi的子载波信号，验证测距性能并给出性能参考。结果显示，基于双频雷达的动作识别率高达91%，测距精度可达厘米级。

[1] KIM E, HELAL S, COOK D. Human activity recognition and pattern discovery[J]. IEEE Pervasive Computing, 2010, 9(1): 48-53.
[2] LIN F, WANG Z, ZHAO H Y, et al. Adaptive multimodal fusion framework for activity monitoring of people with mobility disability[J]. IEEE Journal of Biomedical and Health Informatics, 2022: 1-1.
[3] M A S, THILLAIARASU N. A survey on different computer vision based human activityrecognition for surveillance applications[C]//2022 6th International Conference on Computing Methodologies and Communication (ICCMC). 2022: 1372-1376.
[4] HUANG X, DAI M. Indoor device-free activity recognition based on radio signal[J]. IEEE Transactions on Vehicular Technology, 2016, 66(6): 5316-5329.
[5] KUMAR K V, HARIKIRAN J, CHANDANA B S. Human activity recognition with privacy preserving using deep learning algorithms[C]//2022 2nd International Conference on Artificial Intelligence and Signal Processing (AISP). 2022: 1-8.
[6] FU B, DAMER N, KIRCHBUCHNER F, et al. Sensing technology for human activity recognition: A comprehensive survey[J]. IEEE Access, 2020, 8: 83791-83820.
[7] LUO C, YANG Z, FENG X, et al. Rfaceid: Towards rfid-based facial recognition[C]// Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies: volume5. New York, NY, USA: ACM, 2021: 1-21.
[8] WANG S, POHL A, JAESCHKE T, et al. A novel ultra-wideband 80 ghz fmcw radar system for contactless monitoring of vital signs[C]//2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). 2015: 4978-4981.
[9] LIU Z, LIU X, ZHANG J, et al. Opportunities and challenges of wireless human sensing for the smart iot world: A survey[J]. IEEE Network, 2019, 33(5): 104-110.
[10] HUAWEI. Definitions and scenarios of the wlan sensing[EB/OL]. (2021-11-21)
[2022-04-28]. https://mentor.ieee.org/802.11/dcn/21/11-21-0035-00-00bf-definitions-and-scenarios-of-the-wlan-sensing.pptx.
[11] PERAHIA E, STACEY R. Next generation wireless lans: 802.11 n and 802.11 ac[M]. Cambridge,UK: Cambridge university press, 2013.
[12] LIU J, LIU H, CHEN Y, et al. Wireless sensing for human activity: A survey[J]. IEEE CommunicationsSurveys & Tutorials, 2019, 22(3): 1629-1645.
[13] BAHL P, PADMANABHAN V N. Radar: An in-building rf-based user location and trackingsystem[C]//Proceedings IEEE INFOCOM 2000: volume 2. 2000: 775-784.
[14] PARAMESWARAN A T, HUSAIN M I, UPADHYAYA S, et al. Is rssi a reliable parameter insensor localization algorithms: An experimental study[C]//Field Failure Data Analysis Workshop(F2DA09): volume 5. 2009.
[15] ONG E H, KNECKT J, ALANEN O, et al. Ieee 802.11 ac: Enhancements for very high throughputwlans[C]//2011 IEEE 22nd International Symposium on Personal, Indoor and Mobile RadioCommunications. 2011: 849-853.
[16] HALPERIN D, HU W, SHETH A, et al. Tool release: Gathering 802.11 n traces with channelstate information[J]. ACM SIGCOMM Computer Communication Review, 2011, 41(1): 53-53.
[17] XIE Y, LI Z, LI M. Precise power delay profiling with commodity wi-fi[J]. IEEE Transactionson Mobile Computing, 2018, 18(6): 1342-1355.
[18] WU K, XIAO J, YI Y, et al. Fila: Fine-grained indoor localization[C]//2012 Proceedings IEEEINFOCOM. 2012: 2210-2218.
[19] HE W, WU K, ZOU Y, et al. Wig: Wifi-based gesture recognition system[C]//2015 24th InternationalConference on Computer Communication and Networks (ICCCN). 2015: 1-7.
[20] ABDELNASSER H, HARRAS K, YOUSSEF M. A ubiquitous wifi-based fine-grained gesturerecognition system[J]. IEEE Transactions on Mobile Computing, 2018, 18(11): 2474-2487.
[21] LI H, YANG W, WANG J, et al. Wifinger: Talk to your smart devices with finger-grained gesture[C]//Proceedings of the 2016 ACM International Joint Conference on Pervasive and UbiquitousComputing. New York, NY, USA: ACM, 2016: 250-261.
[22] VENKATNARAYAN R H, PAGE G, SHAHZAD M. Multi-user gesture recognition usingwifi[C]//Proceedings of the 16th Annual International Conference on Mobile Systems, Applications,and Services. 2018: 401-413.
[23] JIANG W, MIAO C, MA F, et al. Towards environment independent device free human activityrecognition[C]//Proceedings of the 24th Annual International Conference on Mobile Computingand Networking. 2018: 289-304.
[24] ZHANG J, TANG Z, LI M, et al. Crosssense: Towards cross-site and large-scale wifi sensing[C]//Proceedings of the 24th Annual International Conference on Mobile Computing andNetworking. 2018: 305-320.
[25] VIRMANI A, SHAHZAD M. Position and orientation agnostic gesture recognition usingwifi[C]//Proceedings of the 15th Annual International Conference on Mobile Systems, Applications,and Services. 2017: 252-264.
[26] ZHENG Y, ZHANG Y, QIAN K, et al. Zero-effort cross-domain gesture recognition withwi-fi[C]//Proceedings of the 17th Annual International Conference on Mobile Systems, Applications,and Services. 2019: 313-325.
[27] ABDELNASSER H, HARRAS K A, YOUSSEF M. Ubibreathe: A ubiquitous non-invasivewifi-based breathing estimator[C]//Proceedings of the 16th ACM International Symposium onMobile Ad Hoc Networking and Computing. New York, NY, USA: ACM, 2015: 277-286.
[28] CHEN C, HAN Y, CHEN Y, et al. Multi-person breathing rate estimation using time-reversal onwifi platforms[C]//2016 IEEE Global Conference on Signal and Information Processing (GlobalSIP).2016: 1059-1063.
[29] WANG X, YANG C, MAO S. Phasebeat: Exploiting csi phase data for vital sign monitoringwith commodity wifi devices[C]//2017 IEEE 37th International Conference on DistributedComputing Systems (ICDCS). 2017: 1230-1239.
[30] UYSAL C, FILIK T. Rf-based noncontact respiratory rate monitoring with parametric spectralestimation[J]. IEEE Sensors Journal, 2019, 19(21): 9841-9849.
[31] WANG X, YANG C, MAO S. Tensorbeat: Tensor decomposition for monitoring multipersonbreathing beats with commodity wifi[J]. ACM Transactions on Intelligent Systems and Technology(TIST), 2017, 9(1): 1-27.
[32] ALWAN M, RAJENDRAN P J, KELL S, et al. A smart and passive floor-vibration based falldetector for elderly[C]//2006 2nd International Conference on Information & CommunicationTechnologies: volume 1. 2006: 1003-1007.
[33] WANG Y, WU K, NI L M. Wifall: Device-free fall detection by wireless networks[J]. IEEETransactions on Mobile Computing, 2016, 16(2): 581-594.
[34] ZHANG D, WANG H, WANG Y, et al. Anti-fall: A non-intrusive and real-time fall detectorleveraging csi from commodity wifi devices[C]//International Conference on Smart Homes andHealth Telematics. 2015: 181-193.
[35] WANG H, ZHANG D, WANG Y, et al. Rt-fall: A real-time and contactless fall detectionsystem with commodity wifi devices[J]. IEEE Transactions on Mobile Computing, 2016, 16(2): 511-526.
[36] PALIPANA S, ROJAS D, AGRAWAL P, et al. Falldefi: Ubiquitous fall detection using commoditywi-fi devices[J]. Proceedings of the ACM on Interactive, Mobile, Wearable and UbiquitousTechnologies, 2018, 1(4): 1-25.
[37] HU Y, ZHANG F, WU C, et al. A wifi-based passive fall detection system[C]//ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).2020: 1723-1727.
[38] YANG C, SHAO H R. Wifi-based indoor positioning[J]. IEEE Communications Magazine,2015, 53(3): 150-157.
[39] LI X, HE Y, JING X. A survey of deep learning-based human activity recognition in radar[J].Remote Sensing, 2019, 11(9): 1068.
[40] PENG Z, LI C. Portable microwave radar systems for short-range localization and life tracking:A review[J]. Sensors, 2019, 19(5): 1136.
[41] NANZER J A. A review of microwave wireless techniques for human presence detection andclassification[J]. IEEE Transactions on Microwave Theory and Techniques, 2017, 65(5): 1780-1794.
[42] LI C, PENG Z, HUANG T Y, et al. A review on recent progress of portable short-range noncontactmicrowave radar systems[J]. IEEE Transactions on Microwave Theory and Techniques,2017, 65(5): 1692-1706.
[43] LE H T, PHUNG S L, BOUZERDOUM A. Human gait recognition with micro-doppler radarand deep autoencoder[C]//2018 24th International Conference on Pattern Recognition (ICPR).2018: 3347-3352.
[44] KIM Y, MOON T. Human detection and activity classification based on micro-doppler signaturesusing deep convolutional neural networks[J]. IEEE Geoscience and Remote SensingLetters, 2015, 13(1): 8-12.
[45] TROMMEL R, HARMANNY R, CIFOLA L, et al. Multi-target human gait classification usingdeep convolutional neural networks on micro-doppler spectrograms[C]//2016 European RadarConference (EuRAD). 2016: 81-84.
[46] RAHMAN A, LUBECKE V M, BORIC-LUBECKE O, et al. Doppler radar techniques foraccurate respiration characterization and subject identification[J]. IEEE Journal on Emergingand Selected Topics in Circuits and Systems, 2018, 8(2): 350-359.
[47] ZHANG Z, TIAN Z, ZHOU M. Latern: Dynamic continuous hand gesture recognition usingfmcw radar sensor[J]. IEEE Sensors Journal, 2018, 18(8): 3278-3289.
[48] WANG S, SONG J, LIEN J, et al. Interacting with soli: Exploring fine-grained dynamic gesturerecognition in the radio-frequency spectrum[C]//Proceedings of the 29th Annual Symposium onUser Interface Software and Technology. 2016: 851-860.
[49] PENG Z, LI C, MUÑOZ-FERRERAS J M, et al. An fmcw radar sensor for human gesturerecognition in the presence of multiple targets[C]//2017 First IEEE MTT-S International MicrowaveBio Conference (IMBIOC). 2017: 1-3.
[50] ZHOU H, CAO P, CHEN S. A novel waveform design for multi-target detection in automotivefmcw radar[C]//2016 IEEE Radar Conference (RadarConf). 2016: 1-5.
[51] KIM B S, JIN Y, KIM S, et al. A low-complexity fmcw surveillance radar algorithm using tworandom beat signals[J]. Sensors, 2019, 19(3): 608.
[52] MOLCHANOV P, GUPTA S, KIM K, et al. Short-range fmcw monopulse radar for handgesturesensing[C]//2015 IEEE Radar Conference (RadarCon). 2015: 1491-1496.
[53] NANZER J A. Millimeter-wave interferometric angular velocity detection[J]. IEEE Transactionson Microwave Theory and Techniques, 2010, 58(12): 4128-4136.
[54] HARIHARAN P. Basics of interferometry[M]. Amsterdam, The Netherlands: Elsevier, 2010.
[55] PENG Z, MUÑOZ-FERRERAS J M, TANG Y, et al. A portable fmcw interferometry radarwith programmable low-if architecture for localization, isar imaging, and vital sign tracking[J].IEEE Transactions on Microwave Theory and Techniques, 2016, 65(4): 1334-1344.
[56] WANG G, GU C, INOUE T, et al. A hybrid fmcw-interferometry radar for indoor precisepositioning and versatile life activity monitoring[J]. IEEE Transactions on Microwave Theoryand Techniques, 2014, 62(11): 2812-2822.
[57] SHAO Y, GUO S, SUN L, et al. Human motion classification based on range informationwith deep convolutional neural network[C]//2017 4th International Conference on InformationScience and Control Engineering (ICISCE). 2017: 1519-1523.
[58] LANG Y, HOU C, YANG Y, et al. Convolutional neural network for human micro-dopplerclassification[C]//Proc. Eur. Microw. Conf. 2017: 1-4.
[59] YANG Y, HOU C, LANG Y, et al. Open-set human activity recognition based on micro-dopplersignatures[J]. Pattern Recognition, 2019, 85: 60-69.
[60] BRYAN J, KIM Y. Classification of human activities on uwb radar using a support vectormachine[C]//2010 IEEE Antennas and Propagation Society International Symposium. 2010:1-4.
[61] BRYAN J, KWON J, LEE N, et al. Application of ultra-wide band radar for classification ofhuman activities[J]. IET Radar, Sonar & Navigation, 2012, 6(3): 172-179.
[62] XIE Y, LI Z, LI M. Precise power delay profiling with commodity wi-fi[J]. IEEE Transactionson Mobile Computing, 2019, 18(6): 1342-1355.
[63] Ieee standard for information technology– local and metropolitan area networks– specificrequirements– part 11: Wireless lan medium access control (mac)and physical layer (phy)specifications amendment 5: Enhancements for higher throughput[J]. IEEE Std 802.11n-2009 (Amendment to IEEE Std 802.11-2007 as amended by IEEE Std 802.11k-2008, IEEEStd 802.11r-2008, IEEE Std 802.11y-2008, and IEEE Std 802.11w-2009), 2009: 1-565.
[64] TZUR A, AMRANI O, WOOL A. Direction finding of rogue wi-fi access points using anoff-the-shelf mimo-ofdm receiver[J]. 2015, 17(C): 149-164.
[65] JANA S, KASERA S K. On fast and accurate detection of unauthorized wireless access pointsusing clock skews[J]. IEEE Transactions on Mobile Computing, 2010, 9(3): 449-462.
[66] KOTARU M, JOSHI K, BHARADIA D, et al. Spotfi: Decimeter level localization using wifi[J].SIGCOMM Comput. Commun. Rev., 2015, 45(4): 269-282.
[67] SEN S, RADUNOVIC B, CHOUDHURY R R, et al. You are facing the mona lisa: Spot localizationusing phy layer information[C]//Proceedings of the 10th International Conference onMobile Systems, Applications, and Services. New York, NY, USA: Association for ComputingMachinery, 2012: 183–196.
[68] WANG Y, LIU J, CHEN Y, et al. E-eyes: Device-free location-oriented activity identificationusing fine-grained wifi signatures[C]//MobiCom ’14: Proceedings of the 20th Annual InternationalConference on Mobile Computing and Networking. New York, NY, USA: Associationfor Computing Machinery, 2014: 617–628.
[69] ZHUO Y, ZHU H, XUE H, et al. Perceiving accurate csi phases with commodity wifi devices[C]//IEEE INFOCOM 2017 - IEEE Conference on Computer Communications. 2017:1-9.
[70] JIMENEZ V, GARCIA M G, SERRANO F, et al. Design and implementation of synchronizationand agc for ofdm-based wlan receivers[J]. IEEE Transactions on Consumer Electronics, 2004,50(4): 1016-1025.
[71] LI X, ZHANG D, LV Q, et al. Indotrack: Device-free indoor human tracking with commoditywi-fi[J]. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., 2017, 1(3).
[72] ZENG Y, WU D, XIONG J, et al. Farsense: Pushing the range limit of wifi-based respirationsensing with csi ratio of two antennas[C]//Proc. ACM Interact. Mob. Wearable UbiquitousTechnol.: volume 3. New York, NY, USA: Association for Computing Machinery, 2019.
[73] SCHWERDTFEGER H. Geometry of complex numbers: circle geometry, moebius transformation,non-euclidean geometry[M]. Mineola, New York, USA: Courier Corporation., 1979:342.
[74] SMITH L N. Cyclical learning rates for training neural networks[C]//2017 IEEE Winter Conferenceon Applications of Computer Vision (WACV). 2017: 464-472.
[75] BREIMAN L. Bagging predictors[J]. Machine Learning, 1996, 24(2): 123-140.
[76] MARPLE L. Computing the discrete-time ”analytic” signal via fft[J]. IEEE Transactions onSignal Processing, 1999, 47(9): 2600-2603.
[77] ALLEN J. Applications of the short time fourier transform to speech processing and spectralanalysis[C]//ICASSP ’82. IEEE International Conference on Acoustics, Speech, and SignalProcessing: volume 7. 1982: 1012-1015.
[78] MALYSA G, WANG D, NETSCH L, et al. Hidden markov model-based gesture recognitionwith fmcw radar[C]//2016 IEEE Global Conference on Signal and Information Processing(GlobalSIP). 2016: 1017-1021.
[79] HOWARD A, ZHU M, CHEN B, et al. Efficient convolutional neural networks for mobilevision applications (2017)[J]. arXiv preprint arXiv:1704.04861.
[80] DENG J, DONG W, SOCHER R, et al. ImageNet: A Large-Scale Hierarchical ImageDatabase[C]//CVPR09. 2009.
[81] TAN D K P, LESTURGIE M, SUN H, et al. Moving target localization using dual-frequencycontinuous wave radar for urban sensing applications[C]//2009 International Radar Conference”Surveillance for a Safer World” (RADAR 2009). 2009: 1-6.
[82] ZHAO R, MA X, LIU X, et al. Continuous human motion recognition using micro-dopplersignatures in the scenario with micro motion interference[J]. IEEE Sensors Journal, 2021, 21(4): 5022-5034.