深度残差收缩网络下的定位与行为联合识别

doi:10.3778/j.issn.1002-8331.2105-0129

摘要/Abstract

摘要： 基于WiFi信道状态信息（channel state information，CSI）的人体感知方法在许多物联网场景得到了应用，但现有大部分基于CSI人体感知的系统仅进行定位或行为识别其中一项工作，而物联网的发展对两者能同时识别提出了新的要求。针对这一问题，提出一种基于深度残差收缩网络的定位与行为联合识别方法。通过普通商用WiFi设备获取两种场景（暗室、会议室和走廊）的CSI数据，将预处理后的数据输入结合了深度残差收缩网络的学习模型，进行12个位置与和6种日常行为（站起、坐下、跳跃、深蹲、跌倒、捡起）的联合任务识别。实验结果显示，针对在暗室、会议室和走廊三种场景下的室内定位的平均识别率达到97.29%，行为识别的平均识别率达到90.02%。能够实现定位与行为的高精度联合识别。

关键词: 信道状态信息, 行为识别, 室内定位, 联合识别, 深度残差收缩网络, 软阈值化

Abstract: Body sensing methods based on WiFi channel state information（CSI） have been applied in many Internet of things scenarios, but most existing CSI body sensing systems only perform one of the tasks of positioning or behavior recognition. The development of the Internet of things requires them to be able to identify simultaneously. To solve this problem, a joint localization and behavior recognition method based on deep residual shrinkage network is proposed. CSI data of two scenes（dark room and conference room） are obtained through common commercial WiFi devices. Combined with the pre-processed data input and the learning model of deep residual shrinkage network, joint task identification is performed for 12 positions and 6 daily behaviors（standing up, sitting down, jumping, squatting, falling down, and picking up）. The experimental results show that the average recognition rate for indoor positioning in dark room, meeting room and corridor is 97.29%, and the average recognition rate for behavior recognition is 90.02%. It can realize high precision joint identification of location and behavior.

Key words: channel state information, behavior recognition, indoor positioning, joint identification, deep residual shrinkage network, soft threshold

张力, 常俊, 武浩, 黄彬, 刘欢. 深度残差收缩网络下的定位与行为联合识别[J]. 计算机工程与应用, 2022, 58(21): 205-212.

ZHANG Li, CHANG Jun, WU Hao, HUANG Bin, LIU Huan. Joint Location and Behavior Recognition in Deep Residual Shrinkage Network[J]. Computer Engineering and Applications, 2022, 58(21): 205-212.

参考文献

[1] BAYAT A，POMPLUN M，TRAN D A.A study on human activity recognition using accelerometer data from smartphones[J].Procedia Computer Science，2014，34：450-457.
[2] GKIOXARI G，GIRSHICK R，DOLLáR P，et al.Detecting and recognizing human-object interactions[C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition，2018：8359-8367.
[3] DANG X，TANG X，HAO Z，et al.Discrete hopfield neural network based indoor Wi-Fi localization using CSI[J].EURASIP Journal on Wireless Communications and Networking，2020（1）.
[4] 张峻豪，吴飞，朱海.基于GD-Kmeans和菲涅尔理论的WiFi手势识别方法[J].计算机工程与应用，2020，56（19）：126-131.
ZHANG J H，WU F，ZHU H.WiFi gesture recognition method based on GD-Kmeans and fresnel theory[J].Computer Engineering and Applications，2020，56（19）：126-131.
[5] YAN H，ZHANG Y，WANG Y，et al.WiAct：a passive WiFi-based human activity recognition system[J].IEEE Sensors Journal，2020，20（1）：296-305.
[6] WANG Y，LIU J，CHEN Y Y，et al.E-eyes：device-free location-oriented activity identification using fine-grained WiFi signatures[C]//MobiCom’14：Proceedings of the 20th Annual International Conference on Mobile Computing and Networking，2014.
[7] DANG X C，ZHANG T，HAO Z J，et al.Wi-SD：a human motion recognition method based on CSI amplitude and phase information[C]//Communications in Computer and Information Science，Wireless Sensor，2019：332-347.
[8] JIE Z，TANG Z，MENG L，et al.CrossSense：towards cross-site and large-scale WiFi sensing[C]//24th Annual International Conference，2018.
[9] QIAN K，WU C，ZHANG Y，et al.Widar2.0：passive human tracking with a single Wi-Fi link[C]//16th Annual International Conference，2018.
[10] 左泽谦，潘军，蒋立军，等.基于WIFI的位置指纹参考节点密度与定位精度关系研究[J].世界地质，2019，38（2）：532-538.
ZUO Z Q，PAN J，JIANG L J，et al.Research on the relation between density of reference nodes of location fingerprint and positioning accuracy based on WIFI[J].Global Geology，2019，38（2）：532-538.
[11] 侯春萍，蒋天丽，郎玥，等.基于卷积神经网络的雷达人体动作与身份多任务识别[J].激光与光电子学进展，2020（2）：113-121.
HOU C P，JIANG T L，LANG Y，et al.Human activity and identity multi-task recognition based on convolutional neural network using Doppler radar[J].Laser & Optoelectronics Progress，2020（2）：113-121.
[12] KOIKE-AKINO T，WANG P，PAJOVIC M，et al.Fingerprinting-based indoor localization with commercial MMWave WiFi：a deep learning approach[J].IEEE Access，2020，8.
[13] TAN S，ZHANG L，WANG Z，et al.MultiTrack：multi-user tracking and activity recognition using commodity WiFi[C]//CHI’19：Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems，2019.
[14] WANG F，J FENG，ZHAO Y，et al.Joint activity recognition and indoor localization with WiFi fingerprints[J].IEEE Access，2019，7.
[15] MüLLER R，KORNBLITH S，HINTON G E.When does label smoothing help?[J].IEICE Transactions on Fundamentals of Electronics，Communications and Computer Sciences，2019.
[16] 周宪英，高成文，曹建华.主成分分析法及其在数据降噪中的应用[J].兵工自动化，2014，33（9）：55-58.
ZHOU X Y，GAO C W，CAO J H.Principal component analysis method and its application in data noise reducing[J].Ordnance Industry Automation，2014，33（9）：55-58.
[17] WEI W，LIU A X，SHAHZAD M，et al.Understanding and modeling of WiFi signal based human activity recognition[C]//MobiCom’15：Proceedings of the 21st Annual International Conference on Mobile Computing and Networking，2015.
[18] VIRMANI A，SHAHZAD M.Position and orientation agnostic gesture recognition using WiFi[C]//MobiSys’17：Proceedings of the 15th Annual International Conference on Mobile Systems，Applications，and Services，2017.
[19] ZHAO M，ZHONG S，FU X，et al.Deep residual shrinkage networks for fault diagnosis[J].IEEE Transactions on Industrial Informatics，2020，16（7）：4681-4690.
[20] ISOGAWA K，IDA T，SHIODERA T，et al.Deep shrinkage convolutional neural network for adaptive noise reduction[J].IEEE Signal Processing Letters，2018，25（2）：224-228.
[21] HE K M，ZHANG X Y，REN S Q，et al.Identity mappings in deep residual networks[C]//European Conference on Computer Vision，2016.
[22] HUANG G，LIU Z，LAURENS V，et al.Densely connected convolutional networks[C]//IEEE Conference on Computer Vision and Pattern Recognition，2017.
[23] SANDLER M，HOWARD A，ZHU M，et al.MobileNetV2： inverted residuals and linear bottlenecks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR），2018.
[24] MA N，ZHANG X，ZHENG H T，et al.ShuffleNet V2： practical guidelines for efficient CNN architecture design[C]//European Conference on Computer Vision.Cham：Springer，2018.