A Human Gesture Recognition Method for Through-the-Wall MIMO Radar

The human body behind the wall has unique range image information, which can be used to identify and classify the human posture behind the wall. In this paper, a through-wall radar algorithm is proposed for recognizing the pose of human targets behind walls. Specifically, the radar echoes are first acquired using MIMO radar and converted into range images, then feed them into SVM nonlinear classifier and deep learning model composed of CNN+GRU, respectively, and finally the results identified by the two models are fused by D-S evidence theory. The final experiment shows that the accuracy of the algorithm reaches 96.99%.