Assessing the quality of heathland vegetation by classification of hyperspectral data using spatial information

Publication Type:

Conference Paper


Geoscience and Remote Sensing Symposium,2009 IEEE International,IGARSS 2009, Volume 4, Cape Town, South Africa, p.IV-330 - IV-333 (2009)



Accession Number:



geophysical signal processing, heathland vegetation conservation, heathland vegetation quality, hyperspectral data classification, image segmentation, Markov processes, pixel based classification comparison, recursive supervised segmentation algorithm, smoothing post processing comparison, spatial information, tree structured Markov random field, trees (mathematics), TS-MRF, vegetation mapping, vegetation maps


This article deals with a method for acquiring vegetation maps, suitable for monitoring and evaluating the conservation status of heathland vegetation from hyperspectral data. The applied method is a recursive supervised segmentation algorithm based on a Tree-structured Markov Random Field (TS-MRF), capable of incorporating structural dependencies in the classification process. To this end, a tree structure is used that is built upon structural dependencies that are present in the field. The classification results from this TS-MRF with extended tree are compared to pixel-based classification results, results from a simple smoothing post-processing, and the result from the original binary TS-MRF technique.

Research area: