Distinction of road surface conditions based on RGB color space at night-time using a car-mounted camera

In this paper, we propose a distinction method for road surface conditions at night-time. This method uses only video information acquired by an inexpensive car-mounted video camera and uses image features by the difference in road surface features for each condition. The image features of the road surface vary depending on the illumination by street lamps, signal lights, reflections and other light sources. Therefore, we analyze image features based on RGB color information and take into consideration the presence of other light sources. As a result, the distinction of road conditions was achieved with high accuracy, including the portions illuminated by street lamps and other light sources.