Unmixing hyperspectral data

Lucas Parra, Clay Spence, Paul Sajda, Andreas Ziehe, Klaus Muller

Research output: Chapter in Book/Report/Conference proceedingConference contribution

102 Citations (Scopus)

Abstract

In hyperspectral imagery one pixel typically consists of a mixture of the reflectance spectra of several materials' where the mixture coefficients correspond to the abundances of the constituting materials. We assume linear combinations of reflectance spectra with some additive normal sensor noise and derive a probabilistic MAP framework for analyzing hyperspectral data. As the material reflectance characteristics are not know a priori' we face the problem of unsupervised linear unmixing. The incorporation of different prior information (e.g. positivity and normalization of the abundances) naturally leads to a family of interesting algorithms' for case yielding an algorithm that can be understood as constrained independent component analysis (ICA). Simulations underline the usefulness of our theory.

Original languageEnglish
Title of host publicationAdvances in Neural Information Processing Systems
PublisherNeural information processing systems foundation
Pages942-948
Number of pages7
ISBN (Print)0262194503, 9780262194501
Publication statusPublished - 2000 Jan 1
Externally publishedYes
Event13th Annual Neural Information Processing Systems Conference, NIPS 1999 - Denver, CO, United States
Duration: 1999 Nov 291999 Dec 4

Other

Other13th Annual Neural Information Processing Systems Conference, NIPS 1999
CountryUnited States
CityDenver, CO
Period99/11/2999/12/4

Fingerprint

Independent component analysis
Pixels
Sensors

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Cite this

Parra, L., Spence, C., Sajda, P., Ziehe, A., & Muller, K. (2000). Unmixing hyperspectral data. In Advances in Neural Information Processing Systems (pp. 942-948). Neural information processing systems foundation.

Unmixing hyperspectral data. / Parra, Lucas; Spence, Clay; Sajda, Paul; Ziehe, Andreas; Muller, Klaus.

Advances in Neural Information Processing Systems. Neural information processing systems foundation, 2000. p. 942-948.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Parra, L, Spence, C, Sajda, P, Ziehe, A & Muller, K 2000, Unmixing hyperspectral data. in Advances in Neural Information Processing Systems. Neural information processing systems foundation, pp. 942-948, 13th Annual Neural Information Processing Systems Conference, NIPS 1999, Denver, CO, United States, 99/11/29.
Parra L, Spence C, Sajda P, Ziehe A, Muller K. Unmixing hyperspectral data. In Advances in Neural Information Processing Systems. Neural information processing systems foundation. 2000. p. 942-948
Parra, Lucas ; Spence, Clay ; Sajda, Paul ; Ziehe, Andreas ; Muller, Klaus. / Unmixing hyperspectral data. Advances in Neural Information Processing Systems. Neural information processing systems foundation, 2000. pp. 942-948
@inproceedings{b5a8172ea6be4ce9920fefc3c19026d3,
title = "Unmixing hyperspectral data",
abstract = "In hyperspectral imagery one pixel typically consists of a mixture of the reflectance spectra of several materials' where the mixture coefficients correspond to the abundances of the constituting materials. We assume linear combinations of reflectance spectra with some additive normal sensor noise and derive a probabilistic MAP framework for analyzing hyperspectral data. As the material reflectance characteristics are not know a priori' we face the problem of unsupervised linear unmixing. The incorporation of different prior information (e.g. positivity and normalization of the abundances) naturally leads to a family of interesting algorithms' for case yielding an algorithm that can be understood as constrained independent component analysis (ICA). Simulations underline the usefulness of our theory.",
author = "Lucas Parra and Clay Spence and Paul Sajda and Andreas Ziehe and Klaus Muller",
year = "2000",
month = "1",
day = "1",
language = "English",
isbn = "0262194503",
pages = "942--948",
booktitle = "Advances in Neural Information Processing Systems",
publisher = "Neural information processing systems foundation",

}

TY - GEN

T1 - Unmixing hyperspectral data

AU - Parra, Lucas

AU - Spence, Clay

AU - Sajda, Paul

AU - Ziehe, Andreas

AU - Muller, Klaus

PY - 2000/1/1

Y1 - 2000/1/1

N2 - In hyperspectral imagery one pixel typically consists of a mixture of the reflectance spectra of several materials' where the mixture coefficients correspond to the abundances of the constituting materials. We assume linear combinations of reflectance spectra with some additive normal sensor noise and derive a probabilistic MAP framework for analyzing hyperspectral data. As the material reflectance characteristics are not know a priori' we face the problem of unsupervised linear unmixing. The incorporation of different prior information (e.g. positivity and normalization of the abundances) naturally leads to a family of interesting algorithms' for case yielding an algorithm that can be understood as constrained independent component analysis (ICA). Simulations underline the usefulness of our theory.

AB - In hyperspectral imagery one pixel typically consists of a mixture of the reflectance spectra of several materials' where the mixture coefficients correspond to the abundances of the constituting materials. We assume linear combinations of reflectance spectra with some additive normal sensor noise and derive a probabilistic MAP framework for analyzing hyperspectral data. As the material reflectance characteristics are not know a priori' we face the problem of unsupervised linear unmixing. The incorporation of different prior information (e.g. positivity and normalization of the abundances) naturally leads to a family of interesting algorithms' for case yielding an algorithm that can be understood as constrained independent component analysis (ICA). Simulations underline the usefulness of our theory.

UR - http://www.scopus.com/inward/record.url?scp=84898930340&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84898930340&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84898930340

SN - 0262194503

SN - 9780262194501

SP - 942

EP - 948

BT - Advances in Neural Information Processing Systems

PB - Neural information processing systems foundation

ER -