Optimization Methods of Motion Recognition System Based on CSI

Motion recognition system based on WiFi overcomes the limitations of the system based on vision and wearable sensor in the past, it’s the most ideal design for the implementation of this technology. On the basis of realizing the motion recognition system based on CSI amplitude, a joint optimization algorithm based on CSI amplitude and phase difference is proposed in this paper. Through linear transformation and continuation compensation of CSI phase, the problem that phase distribution error can’t be used is overcome. The amplitude of CSI value of received motion signal is obtained. It is combined with the phase difference of multiple antennas at the receiving end as the basis signal. In order to solve the problem of high complexity of the system, an optimization algorithm based on amplitude distribution variance is proposed. The experimental results show that the system can recognize three different motions with high accuracy, and after using the optimization algorithm, the average recognition accuracy of the system is increased by 4.7%, and the distinguishing rate between static and motion behavior is greatly improved, which has a certain universality.