Unsupervised segmentation of dual-polarization SAR images based on amplitude and texture characteristics
A new approach for the unsupervised segmentation of dual-polarization Synthetic Aperture Radar (SAR) images based on statistics of both the amplitude variations and the textural characteristics of the data is presented. A co-polarized amplitude image and a cross-polarized amplitude image are used in this study. It is a two-step process. In the first step, these images are filtered once to suppress the speckle noise while preserving the contrast associated with edges and subtle details. The feature vector composed of the two filtered image pixels is assumed to have a joint Gaussian distribution. A scanning window is used to discover clusters at each position. A merging procedure follows to combine these clusters based on the Mahalanobis distance measure, into a number appropriate for the image. A Bayes maximum likelihood classifier is then applied. In the second step, we adopt the second-order Gaussian Markov random field (GMRF) models for image textures in the original un-filtered images. Segments assigned to each class in the first step are examined for possible sub-division into groups, based on textural characteristics. Two segments are considered texturally similar if the ratio of the pseudo-likelihoods of the image before and after merging is close to one.