Tatem, A.J., Lewis, H.G., Atkinson, P.M. and Nixon, M.S.
Land cover mapping at the sub-pixel scale using a Hopfield neural network
In Proceedings of the 28th International Symposium on Remote Sensing of the Environment.
International Symposium on Remote Sensing of the Environment., .
Full text not available from this repository.
Fuzzy classification techniques have been developed to estimate the class composition of image pixels, but their output provides no indication of how these classes are distributed spatially within the pixel. As such, it remains
for robust techniques that provide improved spatial representation of land cover to be developed. The use of a Hopfield neural network to map the spatial distribution of classes more reliably was investigated. An approach was
adopted which used the output from a fuzzy classification to constrain a Hopfield neural network formulated as an energy minimisation tool. The energy minimum represents a ‘best
guess’ map of the spatial distribution of class components in each pixel. The technique was applied to both synthetic and Landsat TM imagery. The resultant maps provided an accurate and improved representation of the land covers
studied. The Hopfield neural network used in this way represents a simple, robust and efficient tool for mapping land cover from remotely sensed imagery at the sub-pixel scale
Actions (login required)