IMIS | Flanders Marine Institute
 

Flanders Marine Institute

Platform for marine research

IMIS

Publications | Institutes | Persons | Datasets | Projects | Maps
[ report an error in this record ]basket (0): add | show Printer-friendly version

Potentials of airborne hyperspectral remote sensing for vegetation mapping of spatially heterogeneous dynamic dunes, a case study along the Belgian coastline
Bertels, L.; Deronde, B.; Kempeneers, S.; Tortelboom, E. (2005). Potentials of airborne hyperspectral remote sensing for vegetation mapping of spatially heterogeneous dynamic dunes, a case study along the Belgian coastline, in: Herrier, J.-L. et al. (Ed.) Proceedings 'Dunes and Estuaries 2005': International Conference on nature restoration practices in European coastal habitats, Koksijde, Belgium 19-23 September 2005. VLIZ Special Publication, 19: pp. 153-163
In: Herrier, J.-L. et al. (Ed.) (2005). Proceedings 'Dunes and Estuaries 2005': International Conference on nature restoration practices in European coastal habitats, Koksijde, Belgium 19-23 September 2005. VLIZ Special Publication, 19. Vlaams Instituut voor de Zee (VLIZ): Oostende. XIV, 685 pp., more
In: VLIZ Special Publication. Vlaams Instituut voor de Zee (VLIZ): Oostende. ISSN 1377-0950, more

Available in  Authors | Dataset 
Document type: Conference paper

Keywords
    Classification; Vegetation mapping; Marine

Authors  Top | Dataset 
  • Bertels, L., more
  • Deronde, B., more
  • Kempeneers, S.
  • Tortelboom, E., more

Abstract
    The coastal defence and nature conservation authorities from the Ministry of the Flemish Community need detailed vegetation maps of the Belgian coast for policy planning and evaluation. From an Integrated Coastal Zone Management point of view, the development of efficient tools serving both authorities is desirable. Therefore new methods for objective, detailed and cost-efficient vegetation mapping are under investigation. This paper focuses on the application of airborne hyperspectral imagery. Two classification methods are used. The standard Spectral Angle Mapper, performed after a Minimum Noise Fraction transform, gives an overall accuracy of 59% with 15 vegetation classes. When using the Optimized Spectral Angle Mapper, the overall accuracy can be increased to 67% using the same 15 classes.

Dataset
  • Hyperspectrale vliegtuigopnamen duinvegetatie Vlaamse kust, more

All data in IMIS is subject to the VLIZ privacy policy Top | Authors | Dataset