关键词: 无线保真, 信道状态信息, 非合作式, 运动检测, 异常检测, 相位矫正, 分类算法

Abstract: Concern the problem that using camera and sensor to detect human motion has the shortcomings of the difficult deployment, expensive and blind zone, a method of human motion detection using Wireless Fidelity (WiFi) signal was proposed. First, the wireless network card is used to receive the channel state information (CSI) of the WiFi in the detected environment. Secondly, the local outlier factor (LOF) algorithm and the Hampel filter are used to remove the abnormal CSI data. After that the frequency shift caused by the rough synchronization of the network card clock is removed by the regression algorithm, and then uses the Principal Component Analysis (PCA) to reduce dimension and Naive Bayes algorithm to classify the CSI data in different cases, generating a model for judging the movement state of the human. Finally, the model is used to judge the state of human motion. In the experiment, the method can quickly determine the state of human motion and reach the correct rate of 95.62%. The experimental results show that the method can detect and identify the movement of people well.

Key words: Wireless Fidelity(WiFi), Channel state information(CSI), non-cooperative, motion detection, outlier detection, phase rectification, classification