Efficient distinction of road surface conditions using surveillance camera images in night time

Knowing the road surface condition is one of the most important topics at contributes to the safety of pedestrians and car drivers. It is increasingly becoming necessary to distinguish road surface condition at night-time, as most of the previously methods only focus on daytime conditions. In this paper, we propose a distinction method of road surface conditions by using only video information acquired from a visible surveillance video camera. The main feature of this method is to simply use passing car´s headlights as the lighting source. As a result, we were able to distinguish road surface conditions such as dry or wet with high accuracy.