BAYESIAN ADAPTIVE OIL SPILL SEGMENTATION OF SAR IMAGES VIA GRAPH CUTS
Pelizzari, S.
;
Bioucas-Dias, J.
BAYESIAN ADAPTIVE OIL SPILL SEGMENTATION OF SAR IMAGES VIA GRAPH CUTS, Proc Advances in SAR Oceanography from Envisat and ERS Missions, Frascati, Italy, Vol. 1, pp. 1 - 1, January, 2006.
Digital Object Identifier:
Abstract
This paper presents a Bayesian supervised segmentation algorithm aimed at oil spill detection in SAR images, a crucial step in any SAR based automatic oil spill surveillance system. The data term, i.e., the density of the observed backscattered signal given the region, is modeled as a finite mixture of Gamma distributions. The mixture renders robustness to backscattering fluctuations inside each region.
The prior is an M-level Markov Random Field defined on a 2D grid, enforcing local continuity in a statistical sense. The maximum a posteriori (MAP) segmentation is computed efficiently by means of recent graph-cut techniques. The effectiveness of the proposed method is illustrated with real ERS and ENVISAT data.