Distinction of Wet Road Surface Condition at Night-time using Texture Features

Abstract

The necessity of distinguishing of the road surface condition at night-time is increasing because most of the previously proposed method corresponds only to daytime. In this paper, we propose a distinction method of road surface condition by using only video information acquired from visible surveillance video camera. The feature of this method is simply to use the cars' headlights as the light source. As the result, it became possible to distinguish the road surface conditions such as dry and wet with high accuracy by using this method.