Building a Hyperspectral Library and its Incorporation into Sparse Unmixing for Mineral Identification - BRGM - Bureau de recherches géologiques et minières Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

Building a Hyperspectral Library and its Incorporation into Sparse Unmixing for Mineral Identification

Anne Salaün
  • Fonction : Auteur
Thomas Wallmach
  • Fonction : Auteur
Monique Le Guen
  • Fonction : Auteur

Résumé

The objective of the SOLSA project (EU-H2020) is to develop an analytical expert system for on-line-on-mine-real-time mineralogical and geochemical analyses on sonic drill cores. As one aspect of the system, this paper presents the building of the hyperspectral library and its incorporation into sparse unmixing techniques for mineral identification. Twenty seven spectra representing 14 minerals have been collected for the library. Three sparse unmixing techniques have been investigated and evaluated using simulated data generated from our hyperspectral library, and real hyperspectral data acquired from a serpentinized harzburgite sample. Among the three techniques, the collaborative sparse unmixing by variable splitting and augmented Lagrangian (CLSUnSAL) method provided the best accurate results on the simulated data. In addition, the results of the CLSUnSAL method show high correlation with that of the QEMSCAN® analysis on the harzburgite hyperspectral data.
Fichier non déposé

Dates et versions

hal-02734395 , version 1 (02-06-2020)

Identifiants

Citer

Thanh Bui, Beate Orberger, Simon Blancher, Ali Mohammad-Djafari, Henry Pilliere, et al.. Building a Hyperspectral Library and its Incorporation into Sparse Unmixing for Mineral Identification. IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium, Jul 2018, Valencia, France. pp.4261-4264, ⟨10.1109/IGARSS.2018.8519131⟩. ⟨hal-02734395⟩
110 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More