V. Krylov, J. Zerubia.
"Generalized gamma mixtures for supervised SAR image classification".
International Conference on Computer Graphics and Vision "Graphicon’2010",
Proc. of Graphicon, pp. 107-110, Saint Petersburg (Russia), September 22-24, 2010.
[link] [pdf]
Abstract
In this paper we develop a new statistical model for supervised classification of high resolution synthetic aperture radar (SAR) mplitude images. This model is based on the recently proposed generalized gamma distribution (GGD) for statistics of amplitude SAR images. In order to improve the fit of GGD when dealing with inherently heterogenous high resolution SAR imagery, we model the statistics of thematic classes as mixtures of GGD. This enables to consider not homogeneous thematic classes, which is an often requirement in practice. We complete the developed method by proving the identifiability of the developed GGD finite mixture model and the consistency of the involved parameter estimation scheme (method of log-cumulants) for GGD, which renders the developed approach mathematically correct. In order to improve the computational performance of the GGD mixture estimation we suggest the use of an approximative solution of the equations involved, thus, avoiding time-consuming iterative processes. The accuracy of the developed approach is validated on a high resolution TerraSAR-X image and compared to related finite mixture-based SAR classification techniques.
Bibtex
@INPROCEEDINGS{KrylovGc10,
author = {Krylov, V. and Zerubia, J.},
title = {Generalized gamma mixtures for supervised {SAR} image classification},
year = {2010},
booktitle = {Proceedings of ``Graphicon'2010''},
address = {Saint Petersburg, Russia},
pages = {107--110}
}