Classification of hyperspectral spatial/spectral patterns using Gauss-Markov random fields

Heidi A. Smartt; J. Scott Tyo

doi:10.1117/12.666041

Classification of hyperspectral spatial/spectral patterns using Gauss-Markov random fields

Heidi A. Smartt, J. Scott Tyo

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

3 Citations (Scopus)

Abstract

Hyperspectral imaging sensors capture digital images in hundreds of contiguous spectral bands, allowing remote material identification. Most algorithms for identifying materials characterize the materials according to spectral information only, ignoring potentially valuable spatial relationships. This paper investigates the use of integrated spatial and spectral information for characterizing materials. It examines the specific situation where a set of pixels has resolution such that it contains spatial patterns of mixed pixels. An autoregressive Gauss-Markov random field (GMRF) is used to model the predictability of a target pixel from neighboring pixels. At the resolution of interest, the GMRF model can successfully classify spatial patterns of aircraft and a residential area from the HYDICE airborne sensor Desert Radiance field collection at Davis Monthan Air Force Base, Arizona.

Original language	English
Title of host publication	Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XII
Publisher	SPIE - International Society for Optical Engineering
ISBN (Print)	0819462896, 9780819462893
DOIs	https://doi.org/10.1117/12.666041
Publication status	Published - 2006
Externally published	Yes
Event	Conference on Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XII 2006 - Kissimmee, United States of America Duration: 17 Apr 2006 → 20 Apr 2006 https://www.spiedigitallibrary.org/conference-proceedings-of-spie/6233.toc

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	6233 I
ISSN (Print)	0277-786X

Conference

Conference	Conference on Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XII 2006
Country/Territory	United States of America
City	Kissimmee
Period	17/04/06 → 20/04/06
Internet address	https://www.spiedigitallibrary.org/conference-proceedings-of-spie/6233.toc

Keywords

Gauss-Markov random fields
Hyperspectral classification
Hyperspectral texture

Access to Document

10.1117/12.666041

Cite this

Smartt, H. A., & Tyo, J. S. (2006). Classification of hyperspectral spatial/spectral patterns using Gauss-Markov random fields. In Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XII Article 62330I (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 6233 I). SPIE - International Society for Optical Engineering. https://doi.org/10.1117/12.666041

@inproceedings{95eecf3a8c624adb862fb46bc11baa77,

title = "Classification of hyperspectral spatial/spectral patterns using Gauss-Markov random fields",

abstract = "Hyperspectral imaging sensors capture digital images in hundreds of contiguous spectral bands, allowing remote material identification. Most algorithms for identifying materials characterize the materials according to spectral information only, ignoring potentially valuable spatial relationships. This paper investigates the use of integrated spatial and spectral information for characterizing materials. It examines the specific situation where a set of pixels has resolution such that it contains spatial patterns of mixed pixels. An autoregressive Gauss-Markov random field (GMRF) is used to model the predictability of a target pixel from neighboring pixels. At the resolution of interest, the GMRF model can successfully classify spatial patterns of aircraft and a residential area from the HYDICE airborne sensor Desert Radiance field collection at Davis Monthan Air Force Base, Arizona.",

keywords = "Gauss-Markov random fields, Hyperspectral classification, Hyperspectral texture",

author = "Smartt, {Heidi A.} and Tyo, {J. Scott}",

year = "2006",

doi = "10.1117/12.666041",

language = "English",

isbn = "0819462896",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

publisher = "SPIE - International Society for Optical Engineering",

booktitle = "Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XII",

address = "United States of America",

note = "Conference on Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XII 2006 ; Conference date: 17-04-2006 Through 20-04-2006",

url = "https://www.spiedigitallibrary.org/conference-proceedings-of-spie/6233.toc",

}

Smartt, HA & Tyo, JS 2006, Classification of hyperspectral spatial/spectral patterns using Gauss-Markov random fields. in Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XII., 62330I, Proceedings of SPIE - The International Society for Optical Engineering, vol. 6233 I, SPIE - International Society for Optical Engineering, Conference on Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XII 2006, Kissimmee, Florida, United States of America, 17/04/06. https://doi.org/10.1117/12.666041

Classification of hyperspectral spatial/spectral patterns using Gauss-Markov random fields. / Smartt, Heidi A.; Tyo, J. Scott.
Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XII. SPIE - International Society for Optical Engineering, 2006. 62330I (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 6233 I).

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Classification of hyperspectral spatial/spectral patterns using Gauss-Markov random fields

AU - Smartt, Heidi A.

AU - Tyo, J. Scott

PY - 2006

Y1 - 2006

N2 - Hyperspectral imaging sensors capture digital images in hundreds of contiguous spectral bands, allowing remote material identification. Most algorithms for identifying materials characterize the materials according to spectral information only, ignoring potentially valuable spatial relationships. This paper investigates the use of integrated spatial and spectral information for characterizing materials. It examines the specific situation where a set of pixels has resolution such that it contains spatial patterns of mixed pixels. An autoregressive Gauss-Markov random field (GMRF) is used to model the predictability of a target pixel from neighboring pixels. At the resolution of interest, the GMRF model can successfully classify spatial patterns of aircraft and a residential area from the HYDICE airborne sensor Desert Radiance field collection at Davis Monthan Air Force Base, Arizona.

AB - Hyperspectral imaging sensors capture digital images in hundreds of contiguous spectral bands, allowing remote material identification. Most algorithms for identifying materials characterize the materials according to spectral information only, ignoring potentially valuable spatial relationships. This paper investigates the use of integrated spatial and spectral information for characterizing materials. It examines the specific situation where a set of pixels has resolution such that it contains spatial patterns of mixed pixels. An autoregressive Gauss-Markov random field (GMRF) is used to model the predictability of a target pixel from neighboring pixels. At the resolution of interest, the GMRF model can successfully classify spatial patterns of aircraft and a residential area from the HYDICE airborne sensor Desert Radiance field collection at Davis Monthan Air Force Base, Arizona.

KW - Gauss-Markov random fields

KW - Hyperspectral classification

KW - Hyperspectral texture

UR - http://www.scopus.com/inward/record.url?scp=33748635216&partnerID=8YFLogxK

U2 - 10.1117/12.666041

DO - 10.1117/12.666041

M3 - Conference Paper

AN - SCOPUS:33748635216

SN - 0819462896

SN - 9780819462893

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XII

PB - SPIE - International Society for Optical Engineering

T2 - Conference on Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XII 2006

Y2 - 17 April 2006 through 20 April 2006

ER -

Smartt HA, Tyo JS. Classification of hyperspectral spatial/spectral patterns using Gauss-Markov random fields. In Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XII. SPIE - International Society for Optical Engineering. 2006. 62330I. (Proceedings of SPIE - The International Society for Optical Engineering). doi: 10.1117/12.666041

Classification of hyperspectral spatial/spectral patterns using Gauss-Markov random fields

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Cite this