A Doppler-based Human Activity Recognition System using WiFi Signals

WiFi-based human activity recognition has drawn a lot of attention in recent years due to the low cost and high popularity of WiFi devices. The wireless monitoring system is able to efficiently detect abnormal activities like falling and body shaking, without privacy invasion. In this paper, we propose a framework using Doppler Frequency Shift-based methodology to extract the features and classify different activities with channel state information collected from WiFi devices. The experimental results demonstrate the reliability of our method for the application of activity recognition.

近年来，基于WiFi的人类活动识别由于WiFi设备成本低且普及度高而备受关注。该无线监测系统能够有效检测跌倒和身体晃动等异常活动，且不会侵犯隐私。在本文中，我们提出了一个基于多普勒频移方法的框架，利用从WiFi设备收集的信道状态信息来提取特征并对不同活动进行分类。实验结果证明了我们的方法在活动识别应用中的可靠性。