Robust nonnegative matrix factorization for nonlinear unmixing of hyperspectral images - Archive ouverte HAL Access content directly
Conference Papers Year : 2013

Robust nonnegative matrix factorization for nonlinear unmixing of hyperspectral images

Abstract

This paper introduces a robust linear model to describe hyperspectral data arising from the mixture of several pure spectral signatures. This new model not only generalizes the commonly used linear mixing model but also allows for possible nonlinear effects to be handled, relying on mild assumptions regarding these nonlinearities. Based on this model, a nonlinear unmixing procedure is proposed. The standard nonnegativity and sum-to-one constraints inherent to spectral unmixing are coupled with a group-sparse constraint imposed on the nonlinearity component. The resulting objective function is minimized using a multiplicative algorithm. Simulation results obtained on synthetic and real data show that the proposed strategy competes with state-of-the-art linear and nonlinear unmixing methods.
Fichier principal
Vignette du fichier
Dobigeon_12438.pdf (515.32 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-01151017 , version 1 (12-05-2015)

Identifiers

  • HAL Id : hal-01151017 , version 1
  • OATAO : 12438

Cite

Nicolas Dobigeon, Cédric Févotte. Robust nonnegative matrix factorization for nonlinear unmixing of hyperspectral images. IEEE Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing - WHISPERS 2013, Jun 2013, Gainesville, United States. pp. 1-4. ⟨hal-01151017⟩
247 View
448 Download

Share

Gmail Mastodon Facebook X LinkedIn More