Image texture processing and data integration for surface pattern discrimination

摘要: This study evaluates the increases in classification accuracy possible from satellite and airbone image texture processing integration with ancillary topographic data for a moderate relief, boreal environment Gros Morne National Park, eastern Canada. The measures angular second moment, entropy, inverse difference moment were computed spatial co-occurrence matrices different orientations SPOT multispectral linear array (MLA) synthetic aperture radar (SAR) imagery. general system of geomorphometry (elevation, slope, aspect, curvature, relief) was extracted co-registered digital elevation model (DEM). Stepwise discriminant analyses used to rank relative information content all variables ascertain accuracies combinations