Combined Approach of Geostatistical Analyses and Remote Sensing to Improve Classification

In the context of the use of remote sensed data for monitoring land cover it is very important to develop methodologies to obtain reliable maps. In order to achieve this objective a possible approach is to combine both "spectral" and "spatial" features to characterize each ground class. In this paper we propose the integration of a spectral classifier for remote sensed data at medium resolution, based on a traditional statistical supervised methodology as "Maximum Likelihood", with the spatial information provided by a geostatistical tool, as the "Indicator Kriging" algorithm. In the traditional "Maximum Likelihood" classifier, the a priori class probabilities of the Bayes' theorem are considered as independent of the spatial position (no neighbouring information is considered). The approach we adopt is based on the idea that a priori probability of occurrence of each class is not the same everywhere but depends on the pixel location so a priori probabilities are computed using geostatistical analyses based on the "Indicator Kriging" algorithm. Using this combined approach, better results in land cover class discrimination have been obtained and the resulting maps look more homogenous than in the case with the spectral information only. Images from Landsat TM5 with the spatial resolution of 30 meters and 6 bands in the visible and near/medium infrared spectrum have been used. The scene, from remote sensed data, is an area of south-eastern Sardinia (Italy) mostly cultivated to citrus groves, which is considered representative of many Mediterranean zones.