Road extraction in SAR images based on fuzzy clustering

In this paper, a road extraction method in SAR images based on fuzzy clustering is proposed. First the fuzzy C means (FCM) algorithm is used to classify the image. And Hough transform is applied in windows to get segment candidates, which increases the robust of the method. Then a fitness function is used to group the segments. The membership values of the connection lines are used to connect the grouped segments. Finally the false road is removed and the main axes of roads are extracted. The results of experiments indicate the availability and the robust of the method.