Automatic Pavement Crack Detection Based on Aerial Imagery

Road health information is an important indicator for assessing the status of the road in management systems. Identifying the abandonment of surfaces is an important process in maintaining roads and traffic safety, which is traditionally conducted on the basis of field surveys. Today, remote sensing methods, especially photogrammetric imaging, are presented. In this article, based on by UAVs images, the road surface cracks are extracted. The proposed method consists of six stages of acquisition of images, separating the road from the background, identifying and eliminating disturbing objects, preprocessing, combining morphological filters with complication features, applying SVM classifications, generation of crack map .The results of the proposed method show the success rate of 98% in the extraction of the cracks.