CNN Based Classification of Rigid Targets in Space Using Radar Micro-Doppler Signatures

Micro-motion characteristics play an important role in some applications of radar target classification. In this paper, a classification method of rigid targets in space using radar micro-Doppler signatures is proposed. Based on the attitude kinematics of rigid targets, we analyze feasibility of classification using micro-Doppler signatures by the relationship among inertial properties of typical rigid targets, their micro-motion characteristics, and corresponding modulation to radar echoes. According to the micro-Doppler time-frequency distribution of echoes and the scale of training sample set, Convolutional neural network (CNN) based feature extraction method and softmax Classifier are designed. Simulations are carried out to validate its effectiveness and discuss the impact of observation duration, composition of training data and size of convolutional kernels on its classification robustness and computational cost.