Support Vector Machines for burnt area discrimination - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Reports (Research Report) Year : 2007

Support Vector Machines for burnt area discrimination

Olivier Zammit
  • Function : Author
  • PersonId : 844039
Xavier Descombes
Josiane Zerubia
  • Function : Author
  • PersonId : 833424


This report addresses the problem of burnt area discrimination using remote sensing images. The detection is based on a single post-fire image acquired by SPOT 5 satellite. To delineate the burnt areas, we use a recent classification method called Support Vectors Machines (SVM). This approach is compared to more conventional classifiers such as K-means or K-nearest neighbours which are widely used in image processing. We also proposed a new automatic classification approach combining K-means and SVM. The results given by the different methods are finally compared to ground truths on various burnt areas.
Fichier principal
Vignette du fichier
RR-6343.pdf (5.83 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

inria-00185101 , version 1 (07-11-2007)
inria-00185101 , version 2 (08-11-2007)


  • HAL Id : inria-00185101 , version 2


Olivier Zammit, Xavier Descombes, Josiane Zerubia. Support Vector Machines for burnt area discrimination. [Research Report] RR-6343, INRIA. 2007, pp.37. ⟨inria-00185101v2⟩
186 View
188 Download


Gmail Facebook Twitter LinkedIn More