Road pavement crack automatic detection by MMS images

The research topic was to test different feature extraction methods to localize road pavement cracks useful to construct a spatial database for the pavement distress monitoring. Several images were acquired by means of a line scan camera that assembled in a Mobile Mapping System (MMS) allows tracking directly the position of the images by a GPS-INS system. Following an automatic digital image processing was performed by means of several algorithms based on different approaches (edge detection and fuzzy set theory). The detected cracks were described with some parameters in relation to some shape characteristics (dimension, typology, direction), which are necessary to recognize the gravity of the road pavement conditions. The edge detection techniques tested in this research allowed identifying fatigue cracking or alligator cracking and also thin linear cracks in images with strong radiometric jumps by applying filters, gradient functions and morphological operators. The snake approach was one of them, in particular the type called Gradient Vector Flow (GVF). Another approach was based on the fuzzy theory. The advantage of this method is that the pixels, necessary to identify the cracks in road pavement, are darker than their surroundings in an image. The last stage was the pavement distress spatial database collection. The Mobile Mapping System (MMS) has allowed localizing the raster data and consequently the vector features of the detected cracks, associating into the table their attributes too. The proposed approaches allow to automatically localize and classify the kind of road pavement crack.