A Novel SAR Image Change Detection Based on Graph-Cut and Generalized Gaussian Model

In this letter, a robust and fast unsupervised change-detection framework is proposed for synthetic aperture radar (SAR) images. It contains three aspects. First, a robust difference image is constructed with the idea of probability patch-based, and it can suppress the speckle effects on the changed regions and enhance the change information synchronously. Then, each class of the difference image is modeled by generalized Gaussian distribution (GGD), and its parameters are learned by the expectation-maximization algorithm. Moreover, the graph-cut algorithm is employed on the difference image to extract the spatial prior information, based on which the parameters of GGD are initialized well via the fuzzy c-means algorithm. Finally, the Bayesian inference for maximum a posteriori performs the final detection. Experimental results on simulated and real SAR data sets confirm the robustness and accuracy of the proposed algorithm in which graph-cut and GGD make great contribution on improving the accuracy of detection and speed of algorithm.