Evaluations of classification and spectral unmixing algorithms using ground based satellite imaging

James F. Scholl, E. Keith Hege, Michael Lloyd-Hart, Daniel O'Connell, William R. Johnson, Eustace L. Dereniak

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

3 Citations (Scopus)

Abstract

Abundances of material components in objects are usually computed using techniques such as linear spectral unmixing on individual pixels captured on hyperspectral imaging devices. However, algorithms such as unmixing have many flaws, some due to implementation, and others due to improper choices of the spectral library used in the unmixing (as well as classification). There may exist other methods for extraction of this hyperspectral abundance information. We propose the development of spatial ground truth data from which various unmixing algorithm analyses can be evaluated. This may be done by implementing a three-dimensional hyperpspectral discrete wavelet transform (HSDWT) with a low-complexity lifting method using the Haar basis. Spectral unmixing, or similar algorithms can then be evaluated, and their effectiveness can be measured by how well or poorly the spatial and spectral characteristics of the target are reproduced at full resolution (which becomes single object classification by pixel).

Original languageEnglish (US)
Title of host publicationAlgorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XII
DOIs
StatePublished - Sep 20 2006
EventAlgorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XII - Kissimmee, FL, United States
Duration: Apr 17 2006Apr 20 2006

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume6233 II
ISSN (Print)0277-786X

Other

OtherAlgorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XII
CountryUnited States
CityKissimmee, FL
Period4/17/064/20/06

Fingerprint

Spectral Unmixing
Imaging
Satellites
Imaging techniques
evaluation
Evaluation
Pixel
Pixels
pixels
Object Classification
Hyperspectral Imaging
ground truth
Discrete wavelet transforms
wavelet analysis
Low Complexity
Wavelet Transform
Three-dimensional
Defects
Target
defects

Keywords

  • Hyperspectral signal processing
  • Remote sensing
  • Spectral unmixing
  • Wavelet transforms

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

Scholl, J. F., Hege, E. K., Lloyd-Hart, M., O'Connell, D., Johnson, W. R., & Dereniak, E. L. (2006). Evaluations of classification and spectral unmixing algorithms using ground based satellite imaging. In Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XII [623328] (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 6233 II). https://doi.org/10.1117/12.664954

Evaluations of classification and spectral unmixing algorithms using ground based satellite imaging. / Scholl, James F.; Hege, E. Keith; Lloyd-Hart, Michael; O'Connell, Daniel; Johnson, William R.; Dereniak, Eustace L.

Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XII. 2006. 623328 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 6233 II).

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

Scholl, JF, Hege, EK, Lloyd-Hart, M, O'Connell, D, Johnson, WR & Dereniak, EL 2006, Evaluations of classification and spectral unmixing algorithms using ground based satellite imaging. in Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XII., 623328, Proceedings of SPIE - The International Society for Optical Engineering, vol. 6233 II, Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XII, Kissimmee, FL, United States, 4/17/06. https://doi.org/10.1117/12.664954
Scholl JF, Hege EK, Lloyd-Hart M, O'Connell D, Johnson WR, Dereniak EL. Evaluations of classification and spectral unmixing algorithms using ground based satellite imaging. In Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XII. 2006. 623328. (Proceedings of SPIE - The International Society for Optical Engineering). https://doi.org/10.1117/12.664954
Scholl, James F. ; Hege, E. Keith ; Lloyd-Hart, Michael ; O'Connell, Daniel ; Johnson, William R. ; Dereniak, Eustace L. / Evaluations of classification and spectral unmixing algorithms using ground based satellite imaging. Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XII. 2006. (Proceedings of SPIE - The International Society for Optical Engineering).
@inproceedings{d679010987ce44f58c2dbb28ab305ec3,
title = "Evaluations of classification and spectral unmixing algorithms using ground based satellite imaging",
abstract = "Abundances of material components in objects are usually computed using techniques such as linear spectral unmixing on individual pixels captured on hyperspectral imaging devices. However, algorithms such as unmixing have many flaws, some due to implementation, and others due to improper choices of the spectral library used in the unmixing (as well as classification). There may exist other methods for extraction of this hyperspectral abundance information. We propose the development of spatial ground truth data from which various unmixing algorithm analyses can be evaluated. This may be done by implementing a three-dimensional hyperpspectral discrete wavelet transform (HSDWT) with a low-complexity lifting method using the Haar basis. Spectral unmixing, or similar algorithms can then be evaluated, and their effectiveness can be measured by how well or poorly the spatial and spectral characteristics of the target are reproduced at full resolution (which becomes single object classification by pixel).",
keywords = "Hyperspectral signal processing, Remote sensing, Spectral unmixing, Wavelet transforms",
author = "Scholl, {James F.} and Hege, {E. Keith} and Michael Lloyd-Hart and Daniel O'Connell and Johnson, {William R.} and Dereniak, {Eustace L.}",
year = "2006",
month = "9",
day = "20",
doi = "10.1117/12.664954",
language = "English (US)",
isbn = "0819462896",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
booktitle = "Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XII",

}

TY - GEN

T1 - Evaluations of classification and spectral unmixing algorithms using ground based satellite imaging

AU - Scholl, James F.

AU - Hege, E. Keith

AU - Lloyd-Hart, Michael

AU - O'Connell, Daniel

AU - Johnson, William R.

AU - Dereniak, Eustace L.

PY - 2006/9/20

Y1 - 2006/9/20

N2 - Abundances of material components in objects are usually computed using techniques such as linear spectral unmixing on individual pixels captured on hyperspectral imaging devices. However, algorithms such as unmixing have many flaws, some due to implementation, and others due to improper choices of the spectral library used in the unmixing (as well as classification). There may exist other methods for extraction of this hyperspectral abundance information. We propose the development of spatial ground truth data from which various unmixing algorithm analyses can be evaluated. This may be done by implementing a three-dimensional hyperpspectral discrete wavelet transform (HSDWT) with a low-complexity lifting method using the Haar basis. Spectral unmixing, or similar algorithms can then be evaluated, and their effectiveness can be measured by how well or poorly the spatial and spectral characteristics of the target are reproduced at full resolution (which becomes single object classification by pixel).

AB - Abundances of material components in objects are usually computed using techniques such as linear spectral unmixing on individual pixels captured on hyperspectral imaging devices. However, algorithms such as unmixing have many flaws, some due to implementation, and others due to improper choices of the spectral library used in the unmixing (as well as classification). There may exist other methods for extraction of this hyperspectral abundance information. We propose the development of spatial ground truth data from which various unmixing algorithm analyses can be evaluated. This may be done by implementing a three-dimensional hyperpspectral discrete wavelet transform (HSDWT) with a low-complexity lifting method using the Haar basis. Spectral unmixing, or similar algorithms can then be evaluated, and their effectiveness can be measured by how well or poorly the spatial and spectral characteristics of the target are reproduced at full resolution (which becomes single object classification by pixel).

KW - Hyperspectral signal processing

KW - Remote sensing

KW - Spectral unmixing

KW - Wavelet transforms

UR - http://www.scopus.com/inward/record.url?scp=33748667783&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33748667783&partnerID=8YFLogxK

U2 - 10.1117/12.664954

DO - 10.1117/12.664954

M3 - Conference contribution

AN - SCOPUS:33748667783

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

ER -