Acoustic 센서를 통한 노면의 종류와 상태 판단

Abstract

It is important to distinguish the type and condition of the road from the viewpoint of safe driving. Environmental sensors are needed to distinguish them. Acoustic sensor can distinguish the road surface using the sound of tire/road. In this paper, we analyze the sound of tire/road using Fast Fourier Transform(FFT). Based on the analyzed data, we distinguish the roads using multi-class Support Vector Machine(SVM). The proposed algorithm is verified through experiments using a test vehicle.