ANALYSIS OF SEGMENTATION ALGORITHMS FOR PAVEMENT DISTRESS IMAGES

Collection and analysis of pavement distress data is an important comp onent of any pavement-management system. Various systems are currently under development that automate this process. They consist of appropr iate hardware for the acquisition of pavement distress images and, in some cases, software for the analysis of the collected data. An import ant step in the automatic interpretation of images is segmentation, th e process of extracting the objects of interest (distresses) from the background. We examine algorithms for segmenting pavement images and e valuate their effectiveness in separating the distresses from the back ground. The methods examined include the Otsu method, Kittler's method , a modified relaxation method, and a method based on a threshold esti mated by regression analysis. Comparison of the algorithms on a data s et of asphalt pavement images indicates that the relaxation and regres sion thresholding methods consistently outperform the other methods. T he regression thresholding method has the potential to become the meth od of choice due to its computational advantage over the relaxation me thod.