Comparison and integration of optical and quadpolarization radar imagery for land cover/use delineation

With the recent increase in the availability of multiple polarization radar data, the need to assess the relative usefulness of these data for land cover/use classification and other applications is important and is the premise of this study. The primary methodology employed is spectral signature extraction and use of Transformed Divergence (TD) separability measures to evaluate the relative utility of multiple radar bands and polarizations (Shuttle Imaging Radar-C), optical imagery (Landsat Thematic Mapper) and texture derived information for a study site in Bangladesh. Variance texture measures at a 7x7 window size are used in an evaluation of improving the overall separability among classes. SIR-C L-band provided slightly better results than C-band but no single polarization provided consistently higher TD values. Texture greatly improved separability for all SIR-C bands but did not assist TM separability. This study also indicated the value of combining TM and SIR-C and particularly the TM original data and SIR-C texture.