Analysis of Stochastic Distances and Wishart Mixture Models Applied on PolSAR Images

Naiallen Carolyne Rodrigues Lima Carvalho,Leonardo Sant’Anna Bins,Sidnei João Siqueira Sant’Anna

doi:10.3390/rs11242994

Naiallen Carolyne Rodrigues Lima Carvalho, Leonardo Sant’Anna Bins + Show 1 more

Open Access

https://doi.org/10.3390/rs11242994

Copy DOI

Journal: Remote sensing	Publication Date: Dec 12, 2019
Citations: 7	License type: CC BY 4.0

Affiliation: National Institute for Space Research

Abstract

This paper address unsupervised classification strategies applied to Polarimetric Synthetic Aperture Radar (PolSAR) images. We analyze the performance of complex Wishart distribution, which is a widely used model for multi-look PolSAR images, and the robustness of five stochastic distances (Bhattacharyya, Kullback-Leibler, Rényi, Hellinger and Chi-square) between Wishart distributions. Two unsupervised classification strategies were chosen: the Stochastic Clustering (SC) algorithm, which is based on the K-means algorithm but uses stochastic distance as the similarity metric, and the Expectation-Maximization (EM) algorithm for Wishart Mixture Model. With the aim of assessing the performance of all algorithms presented here, we performed a Monte Carlo simulation over a set of simulated PolSAR images. A second experiment was conducted using the study area of Tapajós National Forest and the surrounding area, in Brazilian Amazon Forest. The PolSAR images were obtained by the satellite PALSAR. The results, in both experiments, suggest that the EM algorithm and the SC with Hellinger and the SC with Bhattacharyya distance provide a better classification performance. We also analyze the initialization problem for SC and EM algorithms, and we demonstrate how the initial centroid choice influences the final classification result.

Highlights

Synthetic Aperture Radar (SAR) image classification has an important role in socioeconomic applications, and it has become fundamental in environmental monitoring
We propose the use of stochastic distances as a similarity measure of the K-means algorithm, named, hereafter, Stochastic Clustering (SC) algorithm
In this study we address the unsupervised Polarimetric Synthetic Aperture Radar (PolSAR) image classification topic and explore the potential of stochastic distances applied to clustering techniques by classifying PolSAR images with the following techniques: 1. Expectation-Maximization for Wishart mixture model distribution (EM-W); 2

Summary

Introduction

Synthetic Aperture Radar (SAR) image classification has an important role in socioeconomic applications, and it has become fundamental in environmental monitoring. The use of PolSAR (Polarimetric Synthetic Aperture Radar) images, which measures the target backscattering in different polarization, can provide further information such as soil moisture, surface roughness, target shape, and geometry. PolSAR system can provide high spatial resolution images, those are contaminated by an interference pattern called speckle, a common phenomenon on coherent systems, which cannot be avoided. The speckle causes a granular pattern in SAR images, making the analysis of objects contained within the image difficult, and it can lead to a reduction in classification accuracy and segmentation effectiveness [1]. Stochastic distances are any non-negative, symmetric function between two Probability Density Functions (PDF), which obeys the triangular inequality [5]

Objectives

Results

Discussion

Conclusion