An Estimation Method of Road Surface Condition on Winter Expressway via Mobile Nets using In-vehicle Camera Images

This paper proposes a novel method of road surface condition on winter expressway via Mobile Nets using invehicle camera images. In the proposed method, by utilizing obtained data from actual vehicles on the winter expressway, the classification model for estimating road surface conditions from in-vehicle camera images is constructed. The classifying road surface conditions are Dry, Semi-wet, Wet, Slush, and Snow. By utilizing the classification results, the effort of the road surface management work will be reduced. The effectiveness of our method is verified by utilizing the actual data.