Passive Indoor Human Detection based on Channel State Information

Chong Han, Jian Guo, Wenjing Xun, Lijuan Sun

Abstract: Wireless intelligent sensing technology provides basic services for the Internet of Things and will play an important role in the era of Internet of Everything. In recent years, more and more wireless sensing researchers apply Wi-Fi to indoor human detection. We propose a passive indoor human detection method based on Wi-Fi Channel State Information (CSI). CSI feature fingerprints are generated after date preprocessing. The method uses BP neural network to determine whether the specific state of the indoor scenario is no target, a static target or a dynamic target. In order to improve the accuracy of human detection, this paper makes full use of multiple input multiple output (MIMO) information. A multi-antenna voting mechanism is adopted in the simulation experiment which comprehensively considers the detection results of different antenna pairs. The experimental results show that the proposed method has a high detection rate, which can reach more than 99% when there is a static target or no target indoor. The detection rate of scenario with a dynamic target indoor can reach more than 98%. The method also has a low false alarm rate.