计算机工程 ›› 2020, Vol. 46 ›› Issue (1): 286-293.doi: 10.19678/j.issn.1000-3428.0053821

• 开发研究与工程应用 • 上一篇    下一篇

基于信道状态信息的人体复杂动作识别方法

郝占军1,2, 段渝1, 党小超1,2, 曹渊1   

  1. 1. 西北师范大学 计算机科学与工程学院, 兰州 730070;
    2. 甘肃省物联网工程研究中心, 兰州 730070
  • 收稿日期:2019-01-26 修回日期:2019-02-27 出版日期:2020-01-15 发布日期:2019-03-14
  • 作者简介:郝占军(1979-),男,副教授,主研方向为位置服务、无线定位技术;段渝,硕士研究生;党小超,教授;曹渊,硕士研究生。
  • 基金项目:
    国家自然科学基金(61662070,61762079);甘肃省科技重点研发项目(1604FKCA097,17YF1GA015)。

Human Complex Motion Recognition Method Based on Channel State Information

HAO Zhanjun1,2, DUAN Yu1, DANG Xiaochao1,2, CAO Yuan1   

  1. 1. College of Computer Science and Engineering, Northwest Normal University, Lanzhou 730070, China;
    2. Gansu Province Internet of Things Engineering Research Center, Lanzhou 730070, China
  • Received:2019-01-26 Revised:2019-02-27 Online:2020-01-15 Published:2019-03-14

摘要: 现有人类行为识别方法识别精度低、成本高,所能识别的动作也相对简单。为此,通过引入信道状态信息(CSI)提出一种人体复杂动作识别方法,并以传统武术形意拳招式动作为背景进行验证。利用Wi-Fi网卡采集形意拳招式的CSI数据,以数据中的振幅为特征值,使用巴特沃斯低通滤波器和离散小波变换分别过滤数据中的高频和低频异常值。离线阶段采用受限波尔兹曼机对预处理数据进行训练和分类,并构建形意拳招式指纹库。在线阶段使用深度置信网络对采集数据进行分类,将分类结果与指纹库数据进行匹配,实现对形意拳招式的准确识别。实验结果表明,与CSI-SRC方法和基于传统RSSI模型的方法相比,该方法具有较高的识别精度,并且鲁棒性较好。

关键词: 信道状态信息, 巴特沃斯低通滤波器, 离散小波变换, 受限玻尔兹曼机, 人体复杂动作识别

Abstract: Most of the existing human motion recognition methods have drawbacks such as low recognition accuracy,high cost,and limited identification ability,in that only simple motions can be identified.Therefore,this paper proposes a human complex motion recognition method based on Channel State Information(CSI),which is verified by the actions of traditional martial arts Xing Yi Quan.First,the Wi-Fi network adapter is used to collect the CSI data of Xing Yi Quan.Then,the amplitude of the collected data is used as the characteristic value,and the high frequency and low frequency abnormal values are respectively filtered by the Butterworth low pass filter and the Discrete Wavelet Transform(DWT).In the offline phase,the Restricted Boltzmann Machine(RBM) is adopted for the training and classification of pre-processing data,thus building the fingerprint database of Xing Yi Quan.In the online phase,the Deep Belief Network(DBN) is applied for the classification of collected data,and the classification results are matched with the fingerprints database,so the accurate recognition of Xing Yi Quan actions is realized.Experimental results show that compared with CSI-SRC method and the traditional RSSI model method,the proposed method has better recognition accuracy and robustness.

Key words: Channel State Information(CSI), Butterworth low pass filter, Discrete Wavelet Transform(DWT), Restricted Boltzmann Machine(RBM), human complex motion recognition

中图分类号: