Supervised versus unsupervised methods for classification of coasts and river corridors from airborne remote sensing

Maximum likelihood classification (MLC) is compared with unsupervised class ification (USC) for operational cover mapping from airborne imagery. Data f rom the Compact Airborne Spectrographic Imager (CASI) were clustered into a large number of unsupervised subclasses then amalgamated into target class es. For extensive operational classification of coastal imagery, USC proved an acceptable alternative to MLC due to the wide spectral variation betwee n surface classes. However, for river corridors containing a variety of veg etated surfaces with similar reflectances, USC did not produce consistent r esults.