A Research On CSI-based Human Motion Detection In Complex Scenarios

With the rapid development of wireless network technology,using wireless network for human motion detection has become a new technology,which holds a huge potential in security protection,and smart home applications.Since the multipath effect exists in indoor wireless signal propagation,human body motion can change the indoor wireless signal transmission paths,therefore,the wireless signals can be used to perceive the human motion characteristics in the current environment.Compared with the traditional human body motion detection technology based on sensors and vision,human body motion detection technology based on wireless network does not depend on the deployment of dense sensor nodes or surveillance cameras.Furthermore,it can work well in weak lights or in the case when there are obstacles between the transmitter and the receiver.A method for detecting human motion in complex scenarios is presented based on Channel State Information(CSI).First,the sensitivity of CSI amplitude and phase information to human motion is explored,especially to the strenuous motion.Through a large number of experiments,the influence of human motion on CSI amplitude and phase is found out,and the characteristics of signal changes are extracted.The One-class Support Vector Machine(OSVM)in machine learning is used to detect the multi-target strenuous human motion.LOS(Line-Of-Sight,LOS)and Non-Line-Of-Sight(NLOS)conditions are studied in the more complex scenarios in the case of obstacles appearing in the wireless link.LOS and NLOS are identified by the skewness of the channel impulse response(CIR)distribution.After recognizing the LOS condition and NLOS condition in the current environment,the human motion is analyzed and detected,which further improves the accuracy of human motion detection.This CSI-based human motion detection method combines human motion with the widely used wireless network technology,making full use of the wireless network resources,and reducing the cost of equipment deployment to a certain extent,providing a more powerful means for human motion detection.