A Gauss-Markov model for hyperspectral texture analysis of urban areas

Abstract

In this paper we deal with the problem of texture segmentation using a joint spectral and spatial analysis of pixel distribution. Hyperspectral images are considered and, using a Markovian model, we develop a vectorial approach for this image type. A classification algorithm using this model was implemented for extracting and classifying urban areas. Results obtained from AVIRIS images are shown.