Application of Multisource Data for Urban Land Cover Mapping

The aim of this study is to discriminate urban land cover types using the features derived from optical and spaceborne interferometric synthetic aperture radar (InSAR) data sets. For the efficient discrimination of the selected classes, a rule-based algorithm that uses the initial image segmentation procedure based on a Mahalanobis distance rule and the constraints on spectral parameters and spatial thresholds is constructed. The result of the rule-based method is compared with the results of a standard supervised classification and it demonstrates a higher accuracy. Overall, the research indicates that the integrated features of the optical and InSAR images can significantly improve the classification of land cover types and the rule-based classification is a powerful tool in the production of a reliable land cover map.