SAR Image Segmentation using a Fast Level Set Technique

Conference: EUSAR 2008 - 7th European Conference on Synthetic Aperture Radar
06/02/2008 - 06/05/2008 at Friedrichshafen, Germany

Proceedings: EUSAR 2008

Pages: 4Language: englishTyp: PDF

Personal VDE Members are entitled to a 10% discount on this title

Mejail, Marta; Gambini, Juliana; Goussies, Norberto; Buemi, María E.; Jacobo, Julio C. (Universidad de Buenos Aires, Departamento de Computación, Ciudad Universitaria, Pab. I, 1428 Buenos Aires, República Argentina)

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.