Robust recognition of urban patterns using a two stage soft-hard neural classification

The aim of the work is To propose a methodology for spatial/spectral analysis of urban patterns using neural network. To address the problem of spectral ambiguity and spatial complexity related to built-up patterns a two-stage classification procedure based on Multi-Layer Perceptron, is proposed. The first stage is devoted to generate discriminating features for problematic patterns by a supervised soft classification It uses a moving window to evaluate the neighbouring influences during the classification. The spatial relationships among the window pixels to be classified are not explicitly formalised, but the corresponding window is directly presented as input to the neural network classifier. The generated features are used in the second stage for complete land cover mapping. For an experimental evaluation the strategy has been applied to the classification of natural colour aerial photographs acquired over heterogeneous landscape, including urban patterns, and characterised by high spatial resolution and low spectral information. The proposed methodology for the extraction of urban patterns proved to be accurate and robust besides transferable.