Supervised learning and automatic recognition of asphalt pavement deteriorations

Automatic recognition of pavement deteriorations from a digital image is a difficult problem; the images classification problem has been widely studied, particularly in the medical imaging field. Compared to this, our problem adds two main difficulties. The first one is the characterization of different types of deteriorations, and the second is the removal of noise (trace of tire, oil stains,). To do this, we are interested in a first time to the issue of classification of deterioration images, and this in the hope of being able to generalize the process to video flow. In this article we give a characterization of some types of deteriorations, then we propose an algorithm based on learning techniques to classify deterioration images. Finally, we describe and comment some experiments. The evaluation is done on 80 real photos of pavement. The results demonstrate the suitability of the approach for recognition of asphalt pavement deteriorations.