一种基于CSI的人体动作计数与识别方法

doi:10.13190/j.jbupt.2020-040

北京邮电大学学报 ›› 2020, Vol. 43 ›› Issue (5): 105-111.doi: 10.13190/j.jbupt.2020-040

一种基于CSI的人体动作计数与识别方法

刘希文, 陈海明

宁波大学信息科学与工程学院, 宁波 315000

收稿日期:2020-03-31 发布日期:2021-03-11
通讯作者: 陈海明(1981-),男,副教授,硕士生导师,E-mail:chenhaiming@nbu.edu.cn. E-mail:chenhaiming@nbu.edu.cn
作者简介:刘希文(1994-),女,硕士生.
基金资助:
浙江省自然科学基金项目（LY18F020011）；宁波市自然科学基金项目（2018A610154）

A Human Action Counting and Recognition Method Based on CSI

LIU Xi-wen, CHEN Hai-ming

School of Electrical Engineering and Computer Science, Ningbo University, Ningbo 315000, China

Received:2020-03-31 Published:2021-03-11

摘要/Abstract

摘要： WiFi信道状态信息（CSI）被广泛应用于被动式（非侵入式）人体行为判断，为使用现有商用设备实现人体连续动作计数与识别，提出了一种Wi-ACR方法.先利用阈值和活动指标检测出一组连续动作发生的区间和时间，再通过peak-find算法统计出动作的数量，并确定每个动作的开始和结束时间；再分别采用基于波形特征的动作识别模型和基于统计特征的动作识别模型，得到动作识别结果.实验评估结果表明，Wi-ACR对动作计数的准确率可达95%，两类识别模型对于2个动作（深蹲和走）的平均识别精准率为90%.

关键词: 动作计数, 动作识别, 信道状态信息

Abstract: Nowadays WiFi channel state information is widely applied in passive(unobtrusive)human continuous activity recognition. The article uses commercial off-the-shelf devices and proposes a human action counting and recognition (Wi-ACR) method, based on channel state information(CSI). Wi-ACR takes advantage of the threshold algorithm and action indicator to detect the start and end time of a set of continuous actions,and then counts the number of actions through the peak-find algorithm and determines the start and end time of each action. After that,Wi-ACR takes the waveform-feature-based action recognition model and the statistical-feature-based action recognition model to obtain action recognition results respectively. Experiments show that Wi-ACR can achieve action counting accuracy of 95% and recognition accuracy of 90% with these two recognition models,in the scenarios with two types of actions(i.e. squat and walk)occurring simultaneously.

Key words: action counting, action recognition, channel state information

中图分类号:

TP391.4

刘希文, 陈海明. 一种基于CSI的人体动作计数与识别方法[J]. 北京邮电大学学报, 2020, 43(5): 105-111.

LIU Xi-wen, CHEN Hai-ming. A Human Action Counting and Recognition Method Based on CSI[J]. Journal of Beijing University of Posts and Telecommunications, 2020, 43(5): 105-111.

参考文献

[1] Yatani K, Truong K N. BodyScope:a wearable acoustic sensor for activity recognition[C]//UbiComp 2012:Proceedings of the 2012 ACM Conference on Ubiquitous Computing. New York:ACM, 2012:341-350.
[2] Kim D, Hilliges O, Izadi S, et al. Digits:freehand 3D interactions anywhere using a wrist-worn gloveless sensor[C]//UIST 2012:Proceedings of the 25th annual ACM Symposium on User Interface Software and Technology. Massachusetts:ACM, 2012:167-176.
[3] Herath S, Harandi M, Porikli F. Going deeper into action recognition:a survey[J]. Image and Vision Computing, 2017, 60:4-21.
[4] Kerola T, Inoue N, Shinoda K. Spectral graph skeletons for 3D action recognition[C]//ACCV 2014:Proceedings of the Asian Conference on Computer Vision. Singapore:Springer, 2014:417-432.
[5] El-Kafrawy K, Youssef M, El-Keyi A, et al. Propagation modeling for accurate indoor WLAN RSS-based localization[C]//VTC-Fall 2010:Proceedings of the 2010 IEEE 72nd Vehicular Technology Conference-Fall. Cairo:IEEE, 2010:1-5.
[6] Kosba A E, Abdelkader A, Youssef M. Analysis of a device-free passive tracking system in typical wireless environments[C]//NTMS 2009:Proceedings of the 3rd International Conference on New Technologies, Mobility and Security. Ottawa:IEEE, 2009:1-5.
[7] PuQifan, Gupta S, Gollakota S, et al. Whole-home gesture recognition using wireless signals[C]//MobiCom 2013:Proceedings of the 19th Annual International Conference on Mobile Computing & Networking. Florida:ACM, 2013:27-38.
[8] Kellogg B, Talla V, Gollakota S. Bringing gesture recognition to all devices[C]//NSDI 2014:Proceedings of the 11th USENIX Symposium on Networked Systems Design and Implementation. Seattle:ACM, 2014:303-316.
[9] Wang Yuxi, Wu Kaishun, Ni L M. Wifall:device-free fall detection by wireless networks[J]. IEEE Transactions on Mobile Computing, 2016, 16(2):581-594.
[10] Wang Wei, Liu A X, Shahzad M, et al. Understanding and modeling of wifi signal based human activity recognition[C]//MobiCom 2015:Proceedings of the 21st Annual International Conference on Mobile Computing and Networking. Paris:ACM, 2015:65-76.
[11] Wang Yan, Liu Jian, Chen Yingying, et al. E-eyes:device-free location-oriented activity identification using fine-grained wifi signatures[C]//MobiCom 2014:Proceedings of the 20th Annual International Conference on Mobile Computing and Networking. Hawaii:ACM, 2014:617-628.
[12] Xi Wei, Zhao Jizhong, Li Xiangyang, et al. Electronic frog eye:counting crowd using wifi[C]//INFOCOM 2014:Proceedings of the IEEE Conference on Computer Communications. Toronto:IEEE, 2014:361-369.
[13] Li Hong, Yang Wei, Wang Jianxin, et al. WiFinger:talk to your smart devices with finger-grained gesture[C]//UbiComp 2016:Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing. Heidelberg:ACM, 2016:250-261.
[14] Zeng Yunze, Pathak P H, Mohapatra P. WiWho:wifi-based person identification in smart spaces[C]//IPSN 2016:Proceedings of the 15th International Conference on Information Processing in Sensor Networks. Vienna:IEEE, 2016:4.
[15] Halperin D, Hu Wenjun, 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.
[16] Qian Kun, Wu Chenshu, Zhou Zimu, et al. Inferring motion direction using commodity Wi-Fi for interactive exergames[C]//CHI 2017:Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems. Denver:ACM, 2017:1961-1972.
[17] Palipana S, Rojas D, Agrawal P, et al. FallDeFi:ubiquitous fall detection using commodity Wi-Fi devices[J]. ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 2018, 1(4):1-25.

一种基于CSI的人体动作计数与识别方法

A Human Action Counting and Recognition Method Based on CSI

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	张浩冯春燕杨佳汇郭彩丽周博文. 面向语义通信的3D骨骼点数据编码与压缩方法[J]. 北京邮电大学学报, 2022, 45(6): 62-69.
[2]	汪萧萧, 淡振雷, 顾晨伟, 朱卫平, 林敏. 多天线无人机通信系统中的安全波束成形方案[J]. 北京邮电大学学报, 2020, 43(6): 103-109.
[3]	常紫英, 王文涵, 李涛, 刘芬, 陈朋朋. 一种基于Shapelet算法的指纹定位方法[J]. 北京邮电大学学报, 2020, 43(4): 95-100.
[4]	蒋芳, 张南飞, 胡艳军, 王翊. 基于BP神经网络的CSI无源目标分类方法[J]. 北京邮电大学学报, 2020, 43(1): 40-45.
[5]	孙朝宇, 高守婉, 杨旭, 陈朋朋, 牛强. 基于信道状态信息的矿难人员检测研究[J]. 北京邮电大学学报, 2019, 42(4): 96-101.
[6]	卢润华, 李为. 两小区多用户蜂窝干扰网络的回溯干扰中和方案[J]. 北京邮电大学学报, 2018, 41(3): 87-91.
[7]	周墨淼, 李红艳, 王侃, 索龙, 马建鹏. 卡尔曼预测在干扰对齐中的应用[J]. 北京邮电大学学报, 2017, 40(1): 89-93.
[8]	李一兵, 张新忠, 黄诚, 王英赫. 结合功率分配的干扰对齐预编码优化算法[J]. 北京邮电大学学报, 2016, 39(2): 93-97.
[9]	蔡振浩, 赵昆, 陈文. TD-LTE-A系统下行多用户CoMP联合预编码算法[J]. 北京邮电大学学报, 2015, 38(1): 67-70.
[10]	欧静兰, 吴皓威, 邹玉涛, 胡亚文. 过时信道状态下机会双向中继选择算法[J]. 北京邮电大学学报, 2014, 37(6): 44-48.
[11]	张彬贺志强牛凯. MIMO中继系统中的线性鲁棒收发机联合设计[J]. 北京邮电大学学报, 2010, 33(2): 29-33.
[12]	孙锴1，2；王莹2；张平2. 非完美信道下SDMA系统动态自适应调度方案[J]. 北京邮电大学学报, 2010, 33(1): 106-110.
[13]	王绪振贺志强牛凯于光玮吴伟陵. 鲁棒线性预测编码器设计[J]. 北京邮电大学学报, 2009, 32(4): 117-121.
[14]	张然然, 杨爱敏, 刘思杨, 刘元安. 低复杂度的MIMO比特和功率分配方案[J]. 北京邮电大学学报, 2008, 31(5): 53-56.
[15]	刘晓峰，杨鸿文，古建. 量化信道边信息下的对称容量研究[J]. 北京邮电大学学报, 2008, 31(4): 86-89.