Ensemble methods for spectral-spatial classification of urban hyperspectral data

Classification of hyperspectral data with high spatial resolution from urban areas is investigated. The approach is an extension of existing approaches, using both spectral and spatial information for classification. The spatial information is derived by mathematical morphology and principal components of the hyperspectral data set, generating a set of different morphological profiles. The whole data set is classified by the Random Forest algorithm. However, the computational complexity as well as the increased dimensionality and redundancy of data sets based on morphological profiles are potential drawbacks. Thus, in the presented study, feature selection is applied, using nonparametric weighted feature extraction and the variable importance of the random forests. The proposed approach is applied to ROSIS data from an urban area. The experimental results demonstrate that a feature reduction is useful in terms of accuracy. Moreover, the proposed approach also shows excellent results with a limited training set.