WiFi环境下基于CGRU-ELM混合模型的手势识别

计算机工程与科学 ›› 2022, Vol. 44 ›› Issue (02): 298-305.

WiFi环境下基于CGRU-ELM混合模型的手势识别

张鑫，冯秀芳

（太原理工大学信息与计算机学院，山西晋中 030600）

收稿日期:2020-07-17 修回日期:2020-10-25 接受日期:2022-02-25 出版日期:2022-02-25 发布日期:2022-02-18
基金资助:
山西省重点研发计划(201903D121121);虚拟现实技术与系统国家重点实验室（北京航空航天大学）开放基金(VRLAB2019A05)

Gesture recognition based on CGRU-ELM hybrid model in WiFi environment

ZHANG Xin，FENG Xiu-fang

（School of Information and Computer,Taiyuan University of Technology,Shanxi 030600,China）

Received:2020-07-17 Revised:2020-10-25 Accepted:2022-02-25 Online:2022-02-25 Published:2022-02-18

摘要/Abstract

摘要： 针对传统手势识别方法存在的耗能大、部署困难等问题，提出了一种基于WiFi的手势识别方法。通过从WiFi信号中收集到的信道状态信息中抽取多普勒频移组件，解决无线手势识别方法中提取的统计特征与具体手势动作映射关系不明确的问题。同时，提出了一种CGRU-ELM的深度混合模型，对提取到的多普勒频移组件进行特征提取和分类，并对常用的6种人机交互手势进行了识别。实验结果表明，该方法对于以WiFi信号为输入参数的手势识别平均准确度达到了93.4%。

关键词: 信道状态信息, 多普勒频移, 手势识别, 深度学习

Abstract: Aiming at the problems of high energy consumption and difficult deployment in traditional gesture recognition methods , a WiFi-based gesture recognition method is proposed. By extracting the Doppler frequency shift components from the fine-grained channel state information collected from WiFi signal, the problem of unclear mapping relationship between the statistical features extracted by wireless gesture recognition method and specific gestures is solved. Meanwhile, a deep hybrid model of CGRu-ELM is proposed to extract and classify the extracted Doppler frequency shift components, and to recognize six commonly used human-computer interaction gestures. The experimental results show that the average
accuracy of this method for gesture recognition with WiFi signal as input parameter is 93.4%.

Key words: channel state information, Doppler frequency shift, gesture recognition, deep learning

张鑫, 冯秀芳. WiFi环境下基于CGRU-ELM混合模型的手势识别[J]. 计算机工程与科学, 2022, 44(02): 298-305.

ZHANG Xin, FENG Xiu-fang. Gesture recognition based on CGRU-ELM hybrid model in WiFi environment[J]. Computer Engineering & Science, 2022, 44(02): 298-305.

参考文献［11］

［1］	He Wen-feng.Research on gesture recognition based on WIFI ［D］.Shenzhen:Shenzhen University,2015.(in Chinese)
［2］	Marin G,Dominio F,Zanuttigh P.Hand gesture recognition with leap motion and kinect devices［C］∥Proc of IEEE International Conference on Image Processing,2015:1565-1569.
［3］	Haseeb M A,Parasuraman R.Wisture:Touch-less hand gesture classification in unmodified smartphones using Wi-Fi signals［J］.IEEE Sensors Journal,2019,19(1):257-267.
［4］	Mohammed A Q, Fangmin L.WiGeR:WiFi-based gesture recognition system［J］.
	ISPRS International Journal of Geo-Information,2016,5(6):92-108.
［5］	He W,Wu K,Zou Y,et al.WiG:WiFi-based gesture recognition system［C］∥Proc of 2015 24th International Conference on Computer Communication and Networks,2015:1-7.
［6］	Wang Y,Liu J,Chen Y Y,et al.E-eyes:Device-free location-oriented activity identification using fine-grained WiFi signatures［C］∥Proc of the 20th Annual International Conference on Mobile Computing and Networking,2014:617-628.
［7］	Niu K, Zhang F S,Xiong J,et al.Boosting fine-grained activity sensing by embracing wireless multipath effects［C］∥Proc of the 14th International Conference on Emerging
	Network- ing Experiments and Technologies,2018:139-151.
［8］	Wang W,Liu A X,Shahzad M,et al.Device-free human acti- vity recognition using commercial WiFi devices［J］.IEEE Journal on Selected Areas in Communications,2017,35(1):1118-1131.
［9］	Venkatnarayan R H,Page G,Shahzad M.Multi-user gesture recognition using WiFi［C］∥Proc of the 16th Annual International Conference on Mobile Systems,Applications,and Services,2018:401-413.
［10］	Qian K, Wu C S,Zhou Z M,et al.Inferring motion direction using commodity Wi-Fi for interactive exergames［C］∥Proc of the 2017 CHI Conference on Human Factors in Comput- ing Systems,2017:1961-1972.
［11］	Yang Zheng, Liu Yun-hao.Wi-fi radar:From RSSI to CSI［J］.Communications of the CCF,2014,10 (11):55-59.(in Chinese)
［12］	Zheng Y, Zhang Y,Qian K,et al.Zero-effort cross-domain gesture recognition with Wi-Fi［C］∥Proc of the 17th Annual International Conference on Neural Networks,2019:313-325.
［13］	Huang G B,Zhu Q Y,Siew C K.Extreme learning machine:A new learning scheme of feedforward neural networks［C］∥Proc of 2004 IEEE International Joint Conference onMobile Systems, Applications, and Services,2004：985-990.
［14］	Zou H,Zhou Y,Yang J,et al.WiFi-enabled device-free gesture recognition for smart home automation［C］∥Proc of 2018 IEEE 14th International Conference on Control and Automation,2018:476-481.
	附中文参考文献：
［1］	何文锋.基于WIFI的手势识别研究［D］.深圳:深圳大学,2015.
［11］	杨峥，刘云浩.Wi-Fi 雷达：从 RSSI 到 CSI［J］.中国计算机学会通讯，2014，10（11）：55-59.

[1]	胡宗承, 段晓威, 周亚同, 何昊. 基于多模态融合的动态手势识别研究[J]. 计算机工程与科学, 2023, 45(04): 665-673.
[2]	赵艺. 基于路径签名的改进时空图卷积网络[J]. 计算机工程与科学, 2022, 44(12): 2213-2219.
[3]	王伟喆, 郭威彤, 杨鸿武, . 手语到情感语音的转换[J]. 计算机工程与科学, 2022, 44(10): 1869-1876.
[4]	郝占军, 乔志强, 党小超, 段渝. 一种基于CSI的高鲁棒性步态识别方法[J]. 计算机工程与科学, 2022, 44(07): 1302-1312.
[5]	曹玉东, 蔡希彪. 基于并行小规模卷积神经网络的图像质量评价[J]. 计算机工程与科学, 2021, 43(10): 1810-1816.
[6]	刘颜星, 郝占军, 田冉. 基于CSI信号的被动式室内指纹定位算法研究[J]. 计算机工程与科学, 2021, 43(08): 1398-1404.
[7]	党小超, 汝春瑞, 郝占军, . 基于CSI与SVM回归的室内定位方法[J]. 计算机工程与科学, 2021, 43(05): 853-861.
[8]	仇增辉, 赫明杰, 林正奎. 基于深度学习的网购评论命名实体识别方法[J]. 计算机工程与科学, 2020, 42(12): 2287-2294.
[9]	严淑萍，段桂华，张士庚. 一种基于视距路径识别的设备无关室内定位算法[J]. 计算机工程与科学, 2018, 40(08): 1412-1419.
[10]	刘辉，代照坤，王龙. 基于Hu-GLCM的手势识别方法研究[J]. 计算机工程与科学, 2018, 40(03): 525-532.
[11]	屈燕琴，李昕，卢夏衍. 基于表观特征分析的手势识别及其应用[J]. J4, 2015, 37(01): 139-145.
[12]	许凯，王敏. 基于手轮廓的深度图像手势识别方法[J]. J4, 2014, 36(05): 941-946.
[13]	刘云志1，赵森严2，谢世珺1. 基于自适应滤波器PN码同步和多普勒频移联合捕获方法[J]. J4, 2012, 34(5): 141-145.
[14]	李文生1，解梅1,2，邓春健1，姚琼1. 基于Hermite神经网络的动态手势学习和识别[J]. J4, 2012, 34(2): 116-122.
[15]	翁汉良，战荫伟. 基于视觉的多特征手势识别[J]. J4, 2012, 34(2): 123-127.