Detecção Remota e Sistemas de Informação Geográfica para produção de cartografia de uso e ocupação do solo

Resumen

The main purpose of this research is to develop and validate an efficient form of satellite image classification that integrates ancillary information (Census data; the Municipal Master Plan; the Road Network) and remote sensing data in a Geographic Information System. The developed procedure follows a layered classification approach, comprising three main stages: Pre-classification stratification; Application of Bayesian and Maximum-likelihood classifiers; Post-classification sorting. Common approaches incorporate the ancillary data before, during or after classification. In the proposed method, all the steps take the ancillary information into account. The proposed method achieves, much better classification results than the classical, one layer, Minimum Distance and Maximum-likelihood (ML) classifiers. Also, it greatly improves the accuracy of those classes where the classification process uses the ancillary data.