Classification of urban high-resolution satellite imagery using morphological and neural approaches

Abstract

Classification of panchromatic high resolution data from urban areas using morphological and neural approaches is investigated. The proposed approach is in three steps. First, the composition of geodesic opening and closing operations of different sizes is used in order to build a morphological profile. Although, the original panchromatic data only has one feature, the use of the composition operations will give many additional features which may contain redundancies. Therefore, feature extraction based on discriminant analysis is applied in the second step. Thirdly, a neural network is used to classify the features. The proposed method is particularly well suited for complex image scenes such as aerial or fine-resolution satellite images, where very thin, enveloped and/or nested regions have to be retained. It performs well in the presence of both low radiometric contrast and relative low spatial resolution, which are factors that may produce a textural effect, a border effect, and ambiguity in the object/background distinction.