Information Theory and Image Understanding: An Application to Polarimetric SAR Imagery

TL;DR

This paper explores the application of information theory to analyze Polarimetric SAR images, introducing contrast tests based on various statistical distances, with the Kullback-Leibler distance showing superior performance in experiments and real data analysis.

Contribution

It introduces new statistical contrast tests for PolSAR images using information-theoretic distances, especially highlighting the effectiveness of the Kullback-Leibler distance.

Findings

Kullback-Leibler distance outperforms others in empirical tests.

Monte Carlo experiments validate the proposed contrast measures.

Application to real data demonstrates practical utility.

Abstract

This work presents a comprehensive examination of the use of information theory for understanding Polarimetric Synthetic Aperture Radar (PolSAR) images by means of contrast measures that can be used as test statistics. Due to the phenomenon called `speckle', common to all images obtained with coherent illumination such as PolSAR imagery, accurate modelling is required in their processing and analysis. The scaled multilook complex Wishart distribution has proven to be a successful approach for modelling radar backscatter from forest and pasture areas. Classification, segmentation, and image analysis techniques which depend on this model have been devised, and many of them employ some kind of dissimilarity measure. Specifically, we introduce statistical tests for analyzing contrast in such images. These tests are based on the chi-square, Kullback-Leibler, R\'enyi, Bhattacharyya, and Hellinger distances. Results obtained by Monte Carlo experiments reveal the Kullback-Leibler distance as the best one with respect to the empirical test sizes under several situations which include pure and contaminated data. The proposed methodology was applied to actual data, obtained by an E-SAR sensor over surroundings of We$\beta$ssling, Bavaria, Germany.