Road Pattern Classification Using Deep Learning for Noise Data for Autonomous Driving Vehicle

Abstract

Tire-pavement Interaction Noise (TPIN) is noise caused by interactions between rolling tires and road surfaces. After measuring the TPIN using a microphone, transform TPIN to images using continuous wavelet transform (CWT). The transformed images are used to classify the driving road and tire using convolutional neural network (CNN). The road and tire classification network using CNN is required for braking systems in autonomous vehicle. The CNN in this paper can classify snow road, asphalt road, and two types of tires with over 97% accuracy.