Inverting hyperspectral images with Gaussian Regularized Sliced Inverse Regression

Caroline Bernard-Michel 1 Sylvain Douté 2 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 the context of hyperspectral image analysis in planetology, we show how to estimate the physical parameters that generate the spectral infrared signal reflected by Mars. The training approach we develop is based on the estimation of the functional relationship between parameters and spectra, using a database of synthetic spectra generated by a physical model. The high dimension of spectra is reduced by using Gaussian regularized inverse regression to overcome the curse of dimensionality. Compared with a basic k-nearest neighbors approach or a Partial Least Square (PLS) regression, estimates are more accurate and are thus promising.
Type de document :
Communication dans un congrès
ESANN'08 - 16h European Symposium on Artificial Neural Networks, Apr 2008, Bruges, Belgium. pp.463-468, 2008
Liste complète des métadonnées

Littérature citée [13 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-00778011
Contributeur : Stephane Girard <>
Soumis le : vendredi 18 janvier 2013 - 15:14:03
Dernière modification le : mardi 29 mai 2018 - 12:50:24
Document(s) archivé(s) le : vendredi 19 avril 2013 - 04:03:32

Fichier

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

Identifiants

  • HAL Id : hal-00778011, version 1

Collections

Citation

Caroline Bernard-Michel, Sylvain Douté, Laurent Gardes, Stephane Girard. Inverting hyperspectral images with Gaussian Regularized Sliced Inverse Regression. ESANN'08 - 16h European Symposium on Artificial Neural Networks, Apr 2008, Bruges, Belgium. pp.463-468, 2008. 〈hal-00778011〉

Partager

Métriques

Consultations de la notice

563

Téléchargements de fichiers

105