VARIATIONAL SAR IMAGE SEGMENTATION BASED ON THE G 0 MODEL AND AN AUGMENTED LA

This paper present a fast algorithm for synthetic aperture radar (SAR) image segmentation based on the augmented Lagrangian method (ALM). The proposed approach considers the segmentation of SAR images as an energy minimization problem in a variational framework. The energy functional is formulated based on the statistical characteristic of SAR images. The total variation regularization is used to impose the smoothness constraint of the segmentation result. To solve the optimization problem e-ciently, the energy functional is flrstly modifled to be convex and difierentiable by using convex relaxing and variable splitting techniques, and then the constrained optimization problem is converted to an unconstrained one by using the ALM. Finally the energy is minimized with an iterative minimization algorithm. The efiectiveness of the proposed algorithm is validated by experiments on both synthetic and real SAR images.