Nonlinear estimation of material abundances in hyperspectral images with ell1-Norm Spatial Regularization

Jie Chen, Cedric Richard, Paul Honeine

Research output: Contribution to journalArticlepeer-review

71 Scopus citations

Abstract

Integrating spatial information into hyperspectral unmixing procedures has been shown to have a positive effect on the estimation of fractional abundances due to the inherent spatial-spectral duality in hyperspectral scenes. However, current research works that take spatial information into account are mainly focused on the linear mixing model. In this paper, we investigate how to incorporate spatial correlation into a nonlinear abundance estimation process. A nonlinear unmixing algorithm operating in reproducing kernel Hilbert spaces, coupled with a ell1-Type spatial regularization, is derived. Experiment results, with both synthetic and real hyperspectral images, illustrate the effectiveness of the proposed scheme.

Original languageEnglish
Article number6531654
Pages (from-to)2654-2665
Number of pages12
JournalIEEE Transactions on Geoscience and Remote Sensing
Volume52
Issue number5
DOIs
StatePublished - May 2014
Externally publishedYes

Keywords

  • Hyperspectral imaging
  • nonlinear spectral unmixing
  • spatial regularization

Fingerprint

Dive into the research topics of 'Nonlinear estimation of material abundances in hyperspectral images with ell1-Norm Spatial Regularization'. Together they form a unique fingerprint.

Cite this