Millimeter-wave radar body interference recognition based on spatial attribute features
In gesture recognition,the movement of the body is easily misjudged as a gesture action,which interferes the gesture recognition.Therefore,in view of the existing body interference problem,a body interference recognition algorithm based on spatial attribute features is proposed.After preprocessing the received signal of millimeter-wave radar,firstly,the one-dimensional potential targets and the two-dimensional potential targets are extracted from the one-dimensional range image and the two-dimensional range angle spectrum,and the connected domains are labeled for the two-dimensional potential targets.Then,based on the potential targets and the connected domains,the spatial attribute features used to distinguish between body interference and gesture targets are extracted.Finally,the support vector machine(SVM)classifier is used for body interference recognition.Experimental results show that the proposed method can effectively distinguish body interference from gesture targets,and the accuracy rate reaches 97.3％under single-frame prediction and 98.94％under multi-frame prediction.
NETL
NSTL
万方数据
