Human behavior classification method based on multi-station radar micro Doppler motion direction finding

Abstract

The invention discloses a human behavior classification method based on multi-station radar micro Doppler motion direction finding, and belongs to the field of radar target detection signal processing. According to the implementation method, azimuth angles of human motion relative to different radar receivers are measured in real time by using a human motion direction estimation method based on multi-station radar Doppler frequency. The method comprises the following steps: performing interval division on multi-station data according to different influences of measured angle values and different azimuth angles on classification performance, performing data-level fusion according to divided intervals, and performing feature extraction and classification on the data of different intervals by using a dual-channel convolutional principal component analysis network (CPCAN), and carrying out adaptive weighted decision level fusion on classification results of the two channels to obtain a final behavior category result. According to the method, the influence of the micro Doppler data caused by the movement azimuth change is fully considered, so that a multi-station classification network structure can be simplified, and better classification performance and a more stable classification effect are achieved.

Description

technical field [0001] The invention relates to a human behavior classification method based on multi-station radar micro-Doppler motion direction finding, and belongs to the field of radar target detection signal processing. Background technique [0002] Human behavior monitoring and gait recognition are of great value in modern life. After decades of research, human behavior recognition technology has made great progress, and various methods have been proposed. Currently, commonly used human behavior and health monitoring methods include: wearable devices (accelerometers, three-axis gyroscopes), video, infrared , radar, etc. Compared with other methods, radar monitoring has the following advantages: First, radar detects by actively emitting electromagnetic waves with low power consumption and harmless to the human body. Discomfort caused by users and easy to be lost; Second, the electromagnetic wave signal emitted by the radar has a strong propagation ability, a long det...

AI Technical Summary

Problems solved by technology

However, since the azimuth and angle of the human body are constantly changing during the actual movement, there are certain differences in the micro-Doppler information of the human body obtained by the same radar at different times or at different positions. Leading to a decline in the accuracy of human behavior classification

Images