A real-time behavior detection system using millimeter wave radar is presented in this article. Radar is used to sense the micro-Doppler information of targets. A convolution neural network (CNN) is further implemented in the detection and classification of the human motion behaviors using this information. Both the convolution layers and architecture of CNNs are presented. The analysis on loss and accuracy of training results is also shown. The experimental result indicates a precise determination of human motion behavior detection using the proposed system.
- Microwave/millimeter wave sensors
- behavior detection
- convolution neural network (CNN)
- micro-Doppler effect
- micro-Doppler signature
ASJC Scopus subject areas
- Electrical and Electronic Engineering