Human identification based on radar micro-doppler signatures separation

Abstract

In this Letter, the authors propose a method for personnel recognition using deep convolutional neural networks (DCNNs) based on human micro-Doppler (m-D) signal separation. In which, the m-D separation algorithm is firstly performed to separate m-D signal induced by limbs movement and Doppler signal caused by torso motion, which can highlight the difference contained limbs' m-D signatures between the same activity of different people. Afterwards, a five-layer DCNN is used to learn the necessary features directly from the separated m-D spectrogram of walking human and then implement human identification task. The method is validated on real data measured with a 5.8 GHz radar system. Experimental results show that an average recognition accuracy of about 90% can be achieved for different human group sizes.