UNSUPERVISED ONE-CLASS SVM USING A WATERSHED ALGORITHM AND HYSTERESIS THRESHOLDING TO DETECT BURNT AREAS - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2008

UNSUPERVISED ONE-CLASS SVM USING A WATERSHED ALGORITHM AND HYSTERESIS THRESHOLDING TO DETECT BURNT AREAS

Olivier Zammit
  • Fonction : Auteur
  • PersonId : 844039
Xavier Descombes
Josiane Zerubia
  • Fonction : Auteur
  • PersonId : 833424

Résumé

This paper addresses the issue of color image classification. Support Vector Machines (SVM) have shown great performances concerning classification problems but require positive and negative training sets. One-Class SVM allow to avoid the negative training set choice. We also propose to automatically select the positive training set by using the watershed algorithm on the 3-D histogram. Finally a hysteresis thresholding allow to improve the cluster edges. Our method is applied to multispectral satellite images in order to assess burnt areas after a forest fire. The results are compared to official ground truths to validate the approach.
Fichier principal
Vignette du fichier
PRIA-08-zammit.pdf (6.24 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

inria-00316297 , version 1 (03-09-2008)

Identifiants

  • HAL Id : inria-00316297 , version 1

Citer

Olivier Zammit, Xavier Descombes, Josiane Zerubia. UNSUPERVISED ONE-CLASS SVM USING A WATERSHED ALGORITHM AND HYSTERESIS THRESHOLDING TO DETECT BURNT AREAS. Pattern Recognition and Image Analysis (PRIA), Sep 2008, Nijni Novgorod, Russia. ⟨inria-00316297⟩
421 Consultations
118 Téléchargements

Partager

Gmail Facebook X LinkedIn More