DMCA
Non-Gaussian Statistical Analysis of Polarimetric Synthetic Aperture Radar Images (2011)
BibTeX
@MISC{Doulgeris11non-gaussianstatistical,
author = {Anthony Paul Doulgeris},
title = {Non-Gaussian Statistical Analysis of Polarimetric Synthetic Aperture Radar Images},
year = {2011}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
This thesis describes general methods to analyse polarimetric synthetic aperture radar images. The primary application is for unsupervised image segmentation, and fast, practical methods are sought. The fundamental assumptions and statistical modelling are derived from the phys-ics of electromagnetic scattering from distributed targets. The physical basis directly leads to the image phenomenon called speckle, which is shown to be potentially non-Gaussian and several statistical distributions are investigated. Speckle non-Gaussianity and polarimetry both hold pertinent information about the target medium and methods that utilise both attributes are developed. Two distinct approaches are proposed: a local feature extraction method; and a model-based clustering algorithm. The local feature extraction approach creates a new six-dimensional description of the image that may be used for subsequent image analysis or for physical parameter extraction (inversion). It essentially extends standard polarimetric features with the addition of a non-Gaussianity measure for texture. Importantly, the non-Gaussianity
Keyphrases
polarimetric synthetic aperture radar image non-gaussian statistical analysis pertinent information model-based clustering algorithm local feature extraction approach physical basis unsupervised image segmentation practical method target medium local feature extraction method physical parameter extraction statistical modelling speckle non-gaussianity electromagnetic scattering primary application general method image phenomenon non-gaussianity measure standard polarimetric feature distinct approach fundamental assumption new six-dimensional description several statistical distribution subsequent image analysis
