Human-vehicle classification using feature-based SVM in 77-GHz automotive FMCW radar

Abstract

In this study, a human-vehicle classification using a feature-based support vector machine (SVM) in a 77-GHz automotive frequency modulated continuous wave (FMCW) radar system is proposed. As a classification criterion, the authors use a newly defined parameter called root radar cross section which reflects the reflection characteristics of targets. Based on this parameter, three distinctive signal features are extracted from frequency-domain received FMCW radar signals, and they become classification standards used for the SVM. Finally, through measurement results on the test field, the classification performance of the authors' proposed method is verified, and the average classification accuracy from a four-fold cross data validation is found to be higher than 90%. In addition, the authors' proposed classification method is applied to distinguish a pedestrian, a vehicle, and a cyclist in a more practical situation, and it also shows good classification performance.