Cost-sensitive and modular land-cover classification based on posterior probability estimates

Abstract

Many types of nonlinear classifiers have been proposed to automatically generate land-cover maps from satellite images. Some are based on the estimation of posterior class probabilities, whereas others estimate the decision boundary directly. In this paper, we propose a modular design able to focus the learning process on the decision boundary by using posterior probability estimates. To do so, we use a self-configuring architecture that incorporates specialized modules to deal with conflicting classes, and we apply a learning algorithm that focuses learning on the posterior probability regions that are critical for the performance of the decision problem stated by the user-defined misclassification costs. Moreover, we show that by filtering the posterior probability map, the impulsive noise, which is a common effect in automatic land-cover classification, can be significantly reduced. Experimental results show the effectiveness of the proposed solutions on real multi- and hyperspectral images, versus other typical approaches, that are not based on probability estimates, such as Support Vector Machines.

Acknowledgements

The authors wish to thank Dr. José Luis Rojo-Álvarez for his valuable comments. Thanks are also due to the Group of Óptica Atmosférica (Universidad de Valladolid), and Grafos, S.A. company for providing the Img-V image. This paper was partially supported by Spanish MEC projects TEC2005-06766-C03-01/TCM and -2/TCM, and CAM project P-TIC-000223-0505.