An EMD-Based Micro-Doppler Signature for Moving Vehicles Classification

Abstract

It is vital to discriminate wheeled vehicles and tracked vehicles because of their different role on modern battlefields. Micro-Doppler induced by mechanical vibration or rotation of structures in a radar target is potentially useful for target detection, classification and recognition. In this paper, a feature extraction of micro-Doppler information of vehicle is proposed. Then the signal is decomposed by empirical mode decomposition (EMD), and effective features would be extracted. At last, the SVM classifier is used to classify the moving vehicles.