Automatic PolSAR segmentation with the u-distribution and Markov Random Fields

Citation

Doulgeris AP, Akbari V & Eltoft T (2012) Automatic PolSAR segmentation with the u-distribution and Markov Random Fields. In: EUSAR 2012; 9th European Conference on Synthetic Aperture Radar, Nuremberg, 23.04.2012-26.04.2012. VDE, pp. 183-186. https://ieeexplore.ieee.org/abstract/document/6217009

Abstract
A novel unsupervised, non-Gaussian and contextual clustering algorithm is demonstrated for segmentation of Polarimetric SAR images. Previous works have shown the added value of both non-Gaussian modelling and contextual smoothing individually, and goodness-of-fit techniques were introduced to determine the appropriate number of statistically distinct classes. This paper extends our previous work by using the more flexible, two parameter, U-distribution model and includes a Markov Random Field approach for contextual smoothing, without losing the benefits of the goodness-of-fit testing. The proposed, fully automatic, algorithm is demonstrated with both simulated and real data-sets.

Keywords
Data models;Clustering algorithms;Context modeling;Image segmentation;Smoothing methods;Testing;Markov random fields