Bayesian Segmentation of Oceanic SAR Images: Application to Oil Spill Detection

TL;DR

This paper presents Bayesian segmentation algorithms for oceanic SAR images, utilizing mixture models, Markov random fields, and graph-cut techniques, demonstrated on oil spill detection in simulated and real satellite data.

Contribution

It introduces new Bayesian supervised and unsupervised segmentation methods with automatic parameter estimation for oceanic SAR images, specifically tailored for oil spill detection.

Findings

Effective segmentation of oil spills in SAR images.

Automatic estimation of scene homogeneity parameters.

Successful application to real ERS and Envisat satellite scenes.

Abstract

This paper introduces Bayesian supervised and unsupervised segmentation algorithms aimed at oceanic segmentation of SAR images. The data term, \emph{i.e}., the density of the observed backscattered signal given the region, is modeled by a finite mixture of Gamma densities with a given predefined number of components. To estimate the parameters of the class conditional densities, a new expectation maximization algorithm was developed. The prior is a multi-level logistic Markov random field enforcing local continuity in a statistical sense. The smoothness parameter controlling the degree of homogeneity imposed on the scene is automatically estimated, by computing the evidence with loopy belief propagation; the classical coding and least squares fit methods are also considered. The maximum a posteriori segmentation is computed efficiently by means of recent graph-cut techniques, namely the $\alpha$-Expansion algorithm that extends the methodology to an optional number of classes. The effectiveness of the proposed approaches is illustrated with simulated images and real ERS and Envisat scenes containing oil spills.