SVMMAP Modeling of SAR Imagery for Unsupervised Segmentation with Bootstrap Sampling

Abstract

A spatially variant mixture multiscale autoregressive prediction (SVMMAP) model is present, which was applied to segmentation of SAR imagery. General process is as follow: at first, by Bootstrap sampling technique a small representative set of pixels is selected; then, expectation maximization (EM) algorithm and least square (LS) estimation were used to estimate the model, and minimum description length (MDL) rule was employed to choose classification number; at last, Bayes classifier was used to segment image. For a simulated image of size 256×256, a segmentation accuracy of 99.76% was achieved. Besides, quantitative assessment was also presented about segmentation quality of images.