Feature extraction from multiple data sources using genetic programming

John J. Szymanski; Steven P. Brumby; Paul Pope; Damian Eads; Diana Esch-Mosher; Mark Galassi; Neal R. Harvey; Hersey D W McCulloch; Simon J. Perkins; Reid Porter; James Theiler; A. Cody Young; Jeffrey J. Bloch; Nancy David

doi:10.1117/12.478765

Feature extraction from multiple data sources using genetic programming

John J. Szymanski, Steven P. Brumby, Paul Pope, Damian Eads, Diana Esch-Mosher, Mark Galassi, Neal R. Harvey, Hersey D W McCulloch, Simon J. Perkins, Reid Porter, James Theiler, A. Cody Young, Jeffrey J. Bloch, Nancy David

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

10 Scopus citations

Abstract

Feature extraction from imagery is an important and long-standing problem in remote sensing. In this paper, we report on work using genetic programming to perform feature extraction simultaneously from multispectral and digital elevation model (DEM) data. We use the GENetic Imagery Exploitation (Genie) software for this purpose, which produces image-processing software that inherently combines spatial and spectral processing. Genie is particularly useful in exploratory studies of imagery, such as one often does in combining data from multiple sources. The user trains the software by painting the feature of interest with a simple graphical user interface. Genie then uses genetic programming techniques to produce an image-processing pipeline. Here, we demonstrate evolution of image processing algorithms that extract a range of land cover features including towns, wildfire burnscars, and forest. We use imagery from the DOE/NNSA Multispectral Thermal Imager (MTI) spacecraft, fused with USGS 1:24000 scale DEM data.

Original language	English (US)
Title of host publication	Proceedings of SPIE - The International Society for Optical Engineering
Editors	S.S. Shen, P.E. Lewis
Pages	338-345
Number of pages	8
Volume	4725
DOIs	https://doi.org/10.1117/12.478765
State	Published - 2002
Externally published	Yes
Event	Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery VIII - Orlando, FL, United States Duration: Apr 1 2002 → Apr 4 2002

Other

Other	Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery VIII
Country/Territory	United States
City	Orlando, FL
Period	4/1/02 → 4/4/02

Keywords

Evolutionary computation
Feature extraction
Image processing
Multispectral analysis

ASJC Scopus subject areas

Electrical and Electronic Engineering
Condensed Matter Physics

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1117/12.478765

Cite this

Szymanski, J. J., Brumby, S. P., Pope, P., Eads, D., Esch-Mosher, D., Galassi, M., Harvey, N. R., McCulloch, H. D. W., Perkins, S. J., Porter, R., Theiler, J., Young, A. C., Bloch, J. J., & David, N. (2002). Feature extraction from multiple data sources using genetic programming. In S. S. Shen, & P. E. Lewis (Eds.), Proceedings of SPIE - The International Society for Optical Engineering (Vol. 4725, pp. 338-345) https://doi.org/10.1117/12.478765

Feature extraction from multiple data sources using genetic programming. / Szymanski, John J.; Brumby, Steven P.; Pope, Paul; Eads, Damian; Esch-Mosher, Diana; Galassi, Mark; Harvey, Neal R.; McCulloch, Hersey D W; Perkins, Simon J.; Porter, Reid; Theiler, James; Young, A. Cody; Bloch, Jeffrey J.; David, Nancy.

Proceedings of SPIE - The International Society for Optical Engineering. ed. / S.S. Shen; P.E. Lewis. Vol. 4725 2002. p. 338-345.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Szymanski, JJ, Brumby, SP, Pope, P, Eads, D, Esch-Mosher, D, Galassi, M, Harvey, NR, McCulloch, HDW, Perkins, SJ, Porter, R, Theiler, J, Young, AC, Bloch, JJ & David, N 2002, Feature extraction from multiple data sources using genetic programming. in SS Shen & PE Lewis (eds), Proceedings of SPIE - The International Society for Optical Engineering. vol. 4725, pp. 338-345, Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery VIII, Orlando, FL, United States, 4/1/02. https://doi.org/10.1117/12.478765

Szymanski, John J. ; Brumby, Steven P. ; Pope, Paul ; Eads, Damian ; Esch-Mosher, Diana ; Galassi, Mark ; Harvey, Neal R. ; McCulloch, Hersey D W ; Perkins, Simon J. ; Porter, Reid ; Theiler, James ; Young, A. Cody ; Bloch, Jeffrey J. ; David, Nancy. / Feature extraction from multiple data sources using genetic programming. Proceedings of SPIE - The International Society for Optical Engineering. editor / S.S. Shen ; P.E. Lewis. Vol. 4725 2002. pp. 338-345

@inproceedings{878b04a962d84221b3ac14e8683473f1,

title = "Feature extraction from multiple data sources using genetic programming",

abstract = "Feature extraction from imagery is an important and long-standing problem in remote sensing. In this paper, we report on work using genetic programming to perform feature extraction simultaneously from multispectral and digital elevation model (DEM) data. We use the GENetic Imagery Exploitation (Genie) software for this purpose, which produces image-processing software that inherently combines spatial and spectral processing. Genie is particularly useful in exploratory studies of imagery, such as one often does in combining data from multiple sources. The user trains the software by painting the feature of interest with a simple graphical user interface. Genie then uses genetic programming techniques to produce an image-processing pipeline. Here, we demonstrate evolution of image processing algorithms that extract a range of land cover features including towns, wildfire burnscars, and forest. We use imagery from the DOE/NNSA Multispectral Thermal Imager (MTI) spacecraft, fused with USGS 1:24000 scale DEM data.",

keywords = "Evolutionary computation, Feature extraction, Image processing, Multispectral analysis",

author = "Szymanski, {John J.} and Brumby, {Steven P.} and Paul Pope and Damian Eads and Diana Esch-Mosher and Mark Galassi and Harvey, {Neal R.} and McCulloch, {Hersey D W} and Perkins, {Simon J.} and Reid Porter and James Theiler and Young, {A. Cody} and Bloch, {Jeffrey J.} and Nancy David",

year = "2002",

doi = "10.1117/12.478765",

language = "English (US)",

volume = "4725",

pages = "338--345",

editor = "S.S. Shen and P.E. Lewis",

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

note = "Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery VIII ; Conference date: 01-04-2002 Through 04-04-2002",

}

TY - GEN

T1 - Feature extraction from multiple data sources using genetic programming

AU - Szymanski, John J.

AU - Brumby, Steven P.

AU - Pope, Paul

AU - Eads, Damian

AU - Esch-Mosher, Diana

AU - Galassi, Mark

AU - Harvey, Neal R.

AU - McCulloch, Hersey D W

AU - Perkins, Simon J.

AU - Porter, Reid

AU - Theiler, James

AU - Young, A. Cody

AU - Bloch, Jeffrey J.

AU - David, Nancy

PY - 2002

Y1 - 2002

N2 - Feature extraction from imagery is an important and long-standing problem in remote sensing. In this paper, we report on work using genetic programming to perform feature extraction simultaneously from multispectral and digital elevation model (DEM) data. We use the GENetic Imagery Exploitation (Genie) software for this purpose, which produces image-processing software that inherently combines spatial and spectral processing. Genie is particularly useful in exploratory studies of imagery, such as one often does in combining data from multiple sources. The user trains the software by painting the feature of interest with a simple graphical user interface. Genie then uses genetic programming techniques to produce an image-processing pipeline. Here, we demonstrate evolution of image processing algorithms that extract a range of land cover features including towns, wildfire burnscars, and forest. We use imagery from the DOE/NNSA Multispectral Thermal Imager (MTI) spacecraft, fused with USGS 1:24000 scale DEM data.

AB - Feature extraction from imagery is an important and long-standing problem in remote sensing. In this paper, we report on work using genetic programming to perform feature extraction simultaneously from multispectral and digital elevation model (DEM) data. We use the GENetic Imagery Exploitation (Genie) software for this purpose, which produces image-processing software that inherently combines spatial and spectral processing. Genie is particularly useful in exploratory studies of imagery, such as one often does in combining data from multiple sources. The user trains the software by painting the feature of interest with a simple graphical user interface. Genie then uses genetic programming techniques to produce an image-processing pipeline. Here, we demonstrate evolution of image processing algorithms that extract a range of land cover features including towns, wildfire burnscars, and forest. We use imagery from the DOE/NNSA Multispectral Thermal Imager (MTI) spacecraft, fused with USGS 1:24000 scale DEM data.

KW - Evolutionary computation

KW - Feature extraction

KW - Image processing

KW - Multispectral analysis

UR - http://www.scopus.com/inward/record.url?scp=0036911786&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036911786&partnerID=8YFLogxK

U2 - 10.1117/12.478765

DO - 10.1117/12.478765

M3 - Conference contribution

AN - SCOPUS:0036911786

VL - 4725

SP - 338

EP - 345

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

A2 - Shen, S.S.

A2 - Lewis, P.E.

T2 - Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery VIII

Y2 - 1 April 2002 through 4 April 2002

ER -

Feature extraction from multiple data sources using genetic programming

Abstract

Other

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this