Conference Papers Year : 2007

Morphological segmentation of hyperspectral images - ICSXII

Abstract

The present paper develops a general methodology for the morphological segmentation of hyperspectral images, i.e. with an important number of channels. This approach, based on watershed, is composed of a spectral classification to obtain the markers and a vectorial gradient which gives the spatial information. Several alternative gradients are adapted to the different hyperspectral functions. Data reduction is performed either by Factor Analysis or by model fitting. Image segmentation is done on different spaces: factor space, parameters space, etc. On all these spaces the spatial/spectral segmentation approach is applied, leading to relevant results on the image.

Fichier principal
Vignette du fichier
Morphological_seg_hyperspectral_ICSXII.pdf (749.68 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Licence
Loading...

Dates and versions

hal-02958884 , version 1 (06-10-2020)

Licence

Identifiers

  • HAL Id : hal-02958884 , version 1

Cite

Guillaume Noyel, Jesus Angulo, Dominique Jeulin. Morphological segmentation of hyperspectral images - ICSXII. 12th International Congress for Stereology (ICS XII), Université Jean Monnet, Aug 2007, Saint-Etienne, France. ⟨hal-02958884⟩
4736 View
145 Download

Share

  • More