Algorithms of Expert Classification Applied in Quickbird Satellite Images for Land Use Mapping

Alberto Jesús Perea1*, José Emilio Meroño1, and María Jesús Aguilera1

The objective of this paper was the development of a methodology for the classification of digital aerial images, which, with the aid of object-based classification and the Normalized Difference Vegetation Index (NDVI), can quantify agricultural areas, by using algorithms of expert classification, with the aim of improving the final results of thematic classifications. QuickBird satellite images and data of 2532 plots in Hinojosa del Duque, Spain, were used to validate the different classifications, obtaining an overall classification accuracy of 91.9% and an excellent Kappa statistic (87.6%) for the algorithm of expert classification.

Keywords: expert classification, vegetation index, land cover, object-based classification
1 Universidad de Córdoba, Escuela Técnica Superior de Ingenieros Agrónomos y de Montes, Edificio Paraninfo-Campus de Rabanales, Córdoba, España. *Corresponding author (g12pemoa@uco.es).