Publicaties | Kaarten

nieuwe zoekopdracht

[ meld een fout in dit record ]mandje (0): toevoegen | toon Print deze pagina
Classifying hyperspectral airborne imagery for vegetation survey along coastlines
Kempeneers, P.; Deronde, B.; Bertels, L.; Debruyn, W.; De Backer, S.; Scheunders, P. (2004). Classifying hyperspectral airborne imagery for vegetation survey along coastlines, in: Proceedings of Geoscience and Remote Sensing Symposium, 20-24 september 2004. Anchorage, Alaska. Volume 2. pp. 1475-1478
In: (2004). Proceedings of Geoscience and Remote Sensing Symposium, 20-24 september 2004. Anchorage, Alaska. Volume 2. IEEE[s.l.]. ISBN 0-7803-8742-2
Beschikbaar in  Auteurs 
Documenttype: Congresbijdrage
Trefwoorden
    Hyperspectral imaging
    Remote sensing > Geosensing
    Remote sensing > Geosensing > Airborne sensing
    Remote sensors > Remote detectors > Remote sensing
    Belgische kust [Marine Regions]
    Marien/Kust
Auteurs  Top 
  • Kempeneers, P.
  • Deronde, B.
  • Bertels, L.
  • Debruyn, W.
  • De Backer, S.
  • Scheunders, P.
Abstract
    This paper studies the potential of airborne hyperspectral imagery for classifying vegetation along the Belgian coastlines. Here, the aim is to build vegetation maps using automatic classification. Besides a general linear multiclass classifier (Linear Discriminant Analysis), several strategies for combining binary classifiers are proposed: one based on a hierarchical decision tree, one based on the Hamming distance between the codewords obtained by binary classifiers and one based on the coupling of posterior probabilities. In addition, a new procedure is proposed for spatial classification smoothing. This procedure takes into account spatial information by letting the decision for classification of a pixel depend on the classification probabilities of neighboring pixels. This is shown to render smoother classification images.
Alle informatie in het Integrated Marine Information System (IMIS) valt onder het VLIZ Privacy beleid Top | Auteurs 
IMIS is ontwikkeld en wordt gehost door het VLIZ.