Integration of Optical and Microwave Remote Sensing Data for Agricultural Land Use Classification

Abstract

An agricultural land use classification of Oltrepo' Pavese region (in Northern Italy) is performed through integration of remote sensing data from optical and radar sensors. The source of optical data was a Landsat-TM image acquired on April 1994, while the source of microwave data was a contemporaneous image of the new radar sensor SIR-C/X-SAR which was flown on-board the Space Shuttle during an experimental mission over the chosen test site. Then, they were combined through calculation of the principal components of the multidimensional data sets and a final classification was carried out and compared with the classifications obtained from optical and radar recordings separately. Results showed remarkable improvement in the classification accuracy of seedbeds and uncultivated fields with radar recordings and of herbaceous crop type with integrated data. Potential ability of a multi-sensor classification and limits of a single-temporal approach are discussed.