Detection of Road Surface Conditions using Automobile Tire Sounds

摘要

Information about road surface conditions is important and helpful for road users such as automobile drivers, especially in snowy seasons. Actually, the surface conditions depend greatly on changeable weather, road users, locations, and other relevant parties. This report is concerned with the reliable detection of the surface conditions using automobile tire sounds. The pass-by tire sounds of vehicles vary to follow the road surface properties. It seems then feasible to detect passively and readily the state of the surface: as a rule of thumb, dry, wet, and snowy state. To pick up tire sounds, we used a microphone as an acoustic sensor, which can make it easy to reduce the price and size of the road surface condition system for practical applications. We propose three new detection methods for classifying successfully the surface conditions into several categories of state and for improving the monitoring accuracy.