Fusion of Morphological and Spectral Information for Classification of Hyperspectal Urban Remote Sensing Data

Classification of hyperspectral data with high spatial resolution from urban areas is discussed. A previously proposed approach is based on using several principal components from the hyperspectral data to build morphological profiles. These profiles are used all together in one extended morphological profile, which is then classified by a neural network. A shortcoming of the approach is that it is primarily designed for classification of structures and it does not fully utilize the spectral information in the data. An extension is proposed in this paper in order to overcome the problems with the extended morphological profile approach. The proposed method is based on applying data fusion on the original data and the morphological information, after feature extraction. The proposed approach is tested in experiments on two different high resolution remote sensing data sets from urban areas.