Method and device for realizing multi-user identity recognition based on WiFi signal detection gait

The invention relates to a method and a device for realizing multi-user identity recognition based on WiFi signal detection gait. The method comprises the following steps of: performing outlier removal, high-frequency denoising and principal component analysis on a wireless signal by using a WiFi signal, adaptively separating according to a training model to obtain different time domain signals for two users, further segmenting the two signals according to steps, extracting features, and training a classifier model capable of identifying multi-user identities in an intelligent space. The problem of multi-user identity recognition in an intelligent space is solved, gait information can be effectively extracted through mixed WiFi signals, preprocessing and wireless signal separation under walking of two persons, and therefore identity recognition of the two persons is achieved. 本发明涉及一种基于WiFi信号检测步态实现多用户身份识别的方法及装置，利用WiFi信号，在对无线信号进行离群点移除、高频去噪、主成分分析后，根据训练模型自适应分离得到针对两名用户的不同时域信号，进一步根据步伐分割两条信号，提取特征，训练出能够识别智能空间内多用户身份的分