Efficiency Evaluation of SAR-derived Indices in Urban Impervious Surfaces Extraction using Full Polarimetric Image

Detection of urban impervious surfaces is of great importance. Synthetic Aperture Radar (SAR) images are getting more and more attention in urban areas mapping. SAR indices are computed based on data of two or more polarimetric bands. Therefore, they contain more information of land cover classes. Since the efficiency of full polarimetric SAR has not been evaluated for urban impervious surfaces, this study focused on the extraction of these surfaces in the complex urban area by the L-band full polarimetric SAR image. Tehran has been chosen as the study area since it has a complex structure. One ALOS/PALSAR scene encompassed Tehran has been selected. Ratio index, average index, difference index, normalized difference index and NLI index have been computed by the different combination of two polarimetric bands. For classification purpose, support vector machine algorithm has been applied. The overall classification accuracy of four polarimetric bands was 92.67%. The combination of HV-VV and driven indices reached to 90.30% for classification accuracy. The highest classification accuracy from two polarimetric bands achieved by this two bands. This results could be justified by the presence of vertical polarization in both bands. Diverse vertical structures in the urban texture could be better distinguished by vertical polarization. Three main conclusions can be driven from the findings of this study. First, full polarimetric bands are capable of urban impervious surface extraction. Second, dual polarimetric SAR images and their driven indices can extract impervious surface efficiently. And the last conclusion implies the importance of vertical polarization.