Spatial Classification of Hyperspectral Data of Dune Vegetation along the Belgian Coast

Publication Type:

Conference Paper


Geoscience and Remote Sensing Symposium, 2008. IGARSS 2008. IEEE International, Volume 3, Boston, MA, USA, p.III-483 - III-486 (2008)



Accession Number:



airborne data, airborne radar, Belgian Coast, binary Markov Random Field, dune environment, dune vegetation mapping, Europe, hyperspectral data, image classification, image segmentation, Markov processes, spatial classification, spatial smoothing, supervised segmentation algorithm, tree-structured Markov Random Field, trees (mathematics), TS-MRF model, vegetation mapping


This work evaluates a classification method, including spatial information, for dune vegetation along the Belgian coastline. The used method is a recursive supervised segmentation algorithm based on a tree-structured Markov Random Field. This technique describes a K-ary field as a sequence of binary Markov Random Fields, each of which is represented by a node in the tree. The obtained classification results were compared to results with the same data set, for a purely spectral classification and a spectral classification, followed by spatial smoothing.

Research area: