PROJECT TITLE :

A modified level set approach for segmentation of multiband polarimetric sar images - 2014

ABSTRACT:

This paper investigates the appliance of a level set methodology for the automated multiphase segmentation of multiband and polarimetric artificial aperture radar (SAR) images. The amount set formulation is employed to make an energy practical that features the image statistical information defined on active contours. Besides the classical Wishart/Gaussian distribution for locating region boundaries, edge data is incorporated into the energy functional to boost the performance of polarimetric knowledge segmentation. An active contour model with a footing indicator is proposed by assuming that the image boundary term follows a Gibbs prior. An empirical parameter setting criterion is developed to ensure that the elements of the energy purposeful are in correct proportion. We then investigate the multiphase extension for energy minimization, and we use a piecewise constant model to embed the proposed active contour model. Synthetic and real multiband polarimetric SAR data are used for verification. The experiments show that our methodology is superior to a different level set method based mostly on the Wishart/Gaussian distribution, in that SAR edge info is not included, significantly for discriminating among low-distinction regions. Furthermore, results additionally show that segmentation is improved when multiband data are employed in the amount set framework.