Super-resolution mapping of urban scenes from IKONOS imagery using a Hopfield neural network

The availability of 4-metre spatial resolution satellite sensor imagery represents an important step in the automated mapping of urban scenes. However, a large amount of class mixing is still evident within such imagery, making traditional `hard' classification inappropriate for urban land cover mapping. Land cover class composition of image pixels can be estimated using soft classification techniques. However, their output provides no indication of how such classes are distributed spatially within the instantaneous field of view represented by the pixel. This paper examines the potential usage of a Hopfield neural network technique for super-resolution mapping of urban land cover from IKONOS imagery, using information of pixel composition determined from soft classification. The network converges to a minimum of an energy function defined as a goal and several constraints. The approach involved designing the energy function to produce a `best guess' prediction of the spatial distribution of class components in each pixel. The results show that the Hopfield neural network represents a simple efficient tool for mapping urban land cover from IKONOS imagery, and can deliver requisite results for the analysis of practical remotely sensed imagery at the sub pixel scale.