Application of Image Analysis to the Identification and Rating of Road Surface Distress

Abstract

Numerical image analysis is used to detect narrow cracks on bituminous pavement. This problem is complicated because of the variable road aspect, which depends on coarseness textures, changing ambient lighting, presence of humidity and because of the poor contrast of the cracks with regard to the road texture. The paper presents algorithms suited to detect random cracks edges in a noisy environment in three stages. The pre-treatment consisted mainly in applying a background correction to eliminate the heterogeneity due to humidity, shade, ... In the treatment, a threshold value was applied to segment the "objects" from the rest of the image. As these objects may be cracks, parts of cracks, or some noise erroneously segmented as defect, a post-treatment was applied to appreciate more accurately if a pixel belonged to an object or to the background. It aimed also to assemble parts of cracks in continuous structure. When compared to visual detection, efficient detection of cracks is obtained. Further work needs to be done to get an automatic detection of the cracks whatever the road texture. For the covering abstract see ITRD E118503.