Skip to Main content Skip to Navigation
Conference papers

Nonlinear hyperspectral unmixing using Gaussian processes

Abstract : This paper presents an unsupervised algorithm for nonlinear unmixing of hyperspectral images. The proposed model assumes that the pixel reflectances result from a nonlinear function of the abundancevectors associated with the pure spectral components. We assume that the spectral signatures of the pure components and the nonlinear function are unknown. The first step of the proposed method estimates the abundance vectors for all the image pixels using a Gaussian process latent variable model. The endmembers are subsequently estimated using Gaussian process regression. The performance of the unmixing strategy is compared with state-of-the-art unmixing strategies on synthetic data. One of the interesting propertiesof the proposed strategy is its robustness to the absence of pure pixels in the image.
Complete list of metadata

Cited literature [15 references]  Display  Hide  Download
Contributor : Open Archive Toulouse Archive Ouverte (OATAO) Connect in order to contact the contributor
Submitted on : Thursday, March 26, 2015 - 8:28:56 AM
Last modification on : Wednesday, June 1, 2022 - 4:39:36 AM
Long-term archiving on: : Thursday, July 2, 2015 - 7:41:39 AM


Files produced by the author(s)


  • HAL Id : hal-01135826, version 1
  • OATAO : 12437


yoann Altmann, Nicolas Dobigeon, Jean-yves Tourneret, Stephen Mclaughlin. Nonlinear hyperspectral unmixing using Gaussian processes. IEEE Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing - WHISPERS 2013, Jun 2013, Gainesville, United States. pp. 1-4. ⟨hal-01135826⟩



Record views


Files downloads