Application of Multifractal Analysis to Segmentation of Water Bodies in Optical and Synthetic Aperture Radar Satellite Images

TL;DR

This paper introduces a multifractal analysis-based method for segmenting water bodies in optical and SAR satellite images, leveraging textural features and multiscale regularity analysis for improved classification accuracy.

Contribution

It presents a novel multiscale multifractal analysis approach for water body segmentation, comparing its effectiveness with neural networks and NDWI methods.

Findings

Multifractal spectra effectively distinguish water from other land types.

The method outperforms neural networks in classification accuracy.

Water bodies exhibit higher local regularity than other soil types.

Abstract

A method for segmenting water bodies in optical and synthetic aperture radar (SAR) satellite images is proposed. It makes use of the textural features of the different regions in the image for segmentation. The method consists in a multiscale analysis of the images, which allows us to study the images regularity both, locally and globally. As results of the analysis, coarse multifractal spectra of studied images and a group of images that associates each position (pixel) with its corresponding value of local regularity (or singularity) spectrum are obtained. Thresholds are then applied to the multifractal spectra of the images for the classification. These thresholds are selected after studying the characteristics of the spectra under the assumption that water bodies have larger local regularity than other soil types. Classifications obtained by the multifractal method are compared quantitatively with those obtained by neural networks trained to classify the pixels of the images in covered against uncovered by water. In optical images, the classifications are also compared with those derived using the so-called Normalized Differential Water Index (NDWI).