In this paper, we present Gibbs random field models in the form of a powerf
ul toolbox for spatial information extraction from remote sensing images. T
hese models are defined via parametrised energy functions that characterise
local interactions between neighbouring pixels. After shortly revisiting t
he information theoretical concept and defining a family of Gibbs models, w
e give a tour through examples of different kinds of spatial information ex
traction. These examples range from parameter estimation and analysis, via
selection of the model that best describes the image data, up to the segmen
tation of the whole image into regions with uniform properties of the model
. Finally, the concept of across-image segmentation of spatial information
leads to an application for content-based queries from remote sensing image
archives. (C) 2000 Elsevier Science Ltd. All rights reserved.