Pavement condition rating method

Abstract

An object is to provide a pavement condition rating system which utilizes a road surface image based on perspective and which is extracted from a moving image obtained by traveling while photographing a road surface of a road, makes it possible to use the whole of an image area of a road surface included in a road surface image for detection of damage, and is less susceptible to damage erroneous detection. By using a plurality of images obtained by combining image of damage included in a road surface still image based on perspective and definitions of the damage as damage learning data, an object detection model is built. By using a plurality of data wherein the number of rectangles in an analysis result image displaying the rectangles surrounding the damage output as an analysis result and a pavement condition rating result obtained by visual inspection of the analysis result image are combined as condition rate learning data, a rating estimation model is built, and the pavement condition is rated using the rating estimation model.

Dependencies are inferred from the claim text.