Knowledge-based semi-supervised satellite image classification

Spectral information on its own has proven to be insufficient for classification of remotely sensed images. In general, it is difficult to distinguish between types of land-cover classes that have similar or identical spectral signatures from remotely sensed data. Contextual data can be dasiafusedpsila with spectral data to improve the accuracy of classification algorithms. In this paper we use Dempster-Shafer theory of evidence to fuse the output of a semi-supervised classification (SSC) technique with contextual data in the form of a digital elevation model. The final classification accuracy is shown to improve when using this approach.