The study of ERS-1 SAR and Landsat TM synergism for land use classification

This work presents a comparative analysis of ERS-1 Synthetic Aperture Radar (SAR) and Landsat-5 Thematic Mapper (TM) images used for land use classifi cation. The study area of 361 km(2) is located in the City of Campinas, Sao Paulo State, Brazil, and contains several classes of land use, including u rban, agricultural and forests. The TM and SAR images were registered and t ransformed using the principal components transformation. SAR images were a lso filtered using an average filter. The principal components derived from SAR filtered, SAR, TM and coregistered TM/SAR and TM/SAR filtered images w ere classified using the maximum likelihood approach. Tests of 'goodness of fit' were also made to assess the statistical properties of the images. Th e results, confirmed by Kappa statistics, show a significant improvement wh en classifying the principal components of filtered SAR and TM images for u rban, pasture and forest classes.