Support vectors machines regression for estimation of Mars surface physical properties

Caroline Bernard-Michel 1 Sylvain Douté 2 Mathieu Fauvel 1 Laurent Gardes 1 Stephane Girard 1
1 MISTIS - Modelling and Inference of Complex and Structured Stochastic Systems
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : In this paper, the estimation of physical properties from hyperspectral data with support vector machine is addressed. Several kernel functions were used, from classical to advanced ones. The results are compared with Gaussian Regularized Sliced Inversion Regression and Partial Least Squares, both in terms of accuracy and complexity. Experiments on simulated data show that SVM produce highly accurate results, for some kernels, but with an increased of the processing time. Inversion of real images shows that SVM are robust and generalize well. In addition, the analysis of the support vectors allows to detect saturation of the physical model used to generate the simulated data.
Type de document :
Communication dans un congrès
ESANN 2009 - 17th European Symposium on Artificial Neural Networks, Apr 2009, Bruges, Belgium. d-side publications, pp.195-200, 2009
Liste complète des métadonnées

Littérature citée [9 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-00761724
Contributeur : Stephane Girard <>
Soumis le : mardi 6 mai 2014 - 14:29:19
Dernière modification le : mardi 29 mai 2018 - 12:50:24
Document(s) archivé(s) le : mercredi 6 août 2014 - 13:00:15

Fichier

esann09.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00761724, version 2

Collections

Citation

Caroline Bernard-Michel, Sylvain Douté, Mathieu Fauvel, Laurent Gardes, Stephane Girard. Support vectors machines regression for estimation of Mars surface physical properties. ESANN 2009 - 17th European Symposium on Artificial Neural Networks, Apr 2009, Bruges, Belgium. d-side publications, pp.195-200, 2009. 〈hal-00761724v2〉

Partager

Métriques

Consultations de la notice

831

Téléchargements de fichiers

142