Morphological transformations and feature extraction of urban data with high spectral and spatial resolution

摘要

The classification of urban data with high spectral and spatial resolution is considered. For processing, a morphological profile is constructed. The morphological profile is based on the repeated use of opening and closings with a differently sized structuring element. Morphological profiles have been shown to contain redundancies. Therefore, feature extraction is applied on the profile. The morphological approach is applied in experiments on high resolution DAIS remote sensing data from an urban area. To apply the morphological approach on the DAIS data, the first principal component is used as a basis for the morphological transformations. In experiments, the use of the morphological method performs well in terms of classification accuracies. With feature extraction, it is observed that classification on reduced features gives higher accuracies than in the original feature space.