Classification of Ground Vehicles Based on Micro-Doppler Effect and Singular Value Decomposition

Abstract

Classification of ground vehicles before attacking from the unmanned aerial vehicles (UAVs) has always been the hotspot and difficulty of research. In this paper, a method based on micro-Doppler effect which provides unique information of targets is proposed for ground vehicles classification. Firstly, according to micro-Doppler theories, models illustrating the relationship between the UAV and ground vehicles are established to derive expressions of echo signals. Secondly, singular value decomposition (SVD) is utilized to analyze the distribution of echo signal components. Based on micro-Doppler differences of ground vehicles, four features are extracted. At last, these features are sent to support vector machine (SVM) for classification. Results show that method in this paper has better performance than traditional methods, and it is robust under different signal-to-noise ratios (SNRs).