SAR Image Segmentation using a Fast Level Set Technique

Inhalt:
In this work we propose a level set method in order to automatically outline the boundaries between regions, characterized by SAR data with different statistical parameters. Level set methods are a powerful image segmentation technique and have advantages over parametric models. In order to reduce the computational cost involved in this technique a fast level set algorithm is used. It consists of evolving a curve or a set of curves simultaneously by computing operations, such as switching elements between two linked lists, that are simpler than solving partial differential equations. We propose a filtering procedure based on the G0 statistical model, as a criterion for multiple region segmentation. This techniques are applied on real SAR images.