Micro-doppler radar signature classification by time-frequency and time-scale analysis

Abstract

This paper deals with the micro-Doppler (m-D) phenomenon which is a frequency modulation induced on the returned radar signal due to micro-motion. Indeed, the micro-Doppler provides an additional information for target recognition that is complementary to existing recognition methods. In this paper we present a comparative study between feature extraction based on 2 types of analysis: time frequency (Instantaneous Frequency IF) analysis and time scale analysis (Wavelet Transform WT and Multiplicative Multiresolution Decomposition MMD), associated to SVM classifier to perform target identification. These approaches are tested on RadEch Database, containing radar echoes from various targets. The data has been collected in controlled test environments at the premises of Military Academy - Republic of Serbia. Thus, the results show that good performances are provided by the association of the instantaneous frequency with the MMD descriptor.