Supervised Baysian SAR image Classification Using The Full Polarimetric Data

Supervised classification procedures are developed and applied to synthetic aperture radar (SAR) in order to identify their various earth terrain components. An implementation of the maximum a posteriori (MAP) and the maximum likelihood (ML) algorithms are presented. These two techniques need a statistic model for the conditional distribution of the polarimetric complex data. Many previous studies used the classical Rayleigh distribution to characterize the earth terrain, but this model doesn’t yield a good result for heterogeneous backscattering media. This study applies a new model based on the K-distribution. This distribution, based on the physical definition of the texture and its mathematical representation, will be shown as rigorous model to describe amplitudes and intensities of the backscattering signal. We also use Markov fields to enhance the results of the classifications. These classification procedures have been applied to the Flevoland site (Holland) and Landes forest (France) SAR images, supplied by the Jet Propulsion Laboratory. Key-Words : SAR Images, Supervised Classification, K-distribution, Markov Random Field