Feature extraction from multiple data sources using genetic programming. Szymanski, J.&nbsp;J.; Brumby, S.&nbsp;P.; Pope, P.; Eads, D.; Esch-Mosher, D.; Galassi, M.; Harvey, N.&nbsp;R.; McCulloch, H.&nbsp;D.<nbsp>W.; Perkins, S.&nbsp;J.; Porter, R.; Theiler, J.; Young; Cody, A.; Bloch, J.&nbsp;J.; and David, N. In Shen, S.&nbsp;S. and Lewis, P.&nbsp;E., editors, Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery VIII, volume 4725, of SPIE, pages 338--345, August, 2002.
Feature extraction from multiple data sources using genetic programming [link]Paper  abstract   bibtex   
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.
@inproceedings{ szymanski02feature,
  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.},
  added-at = {2008-06-19T17:46:40.000+0200},
  author = {Szymanski, John J. and Brumby, Steven P. and Pope, Paul and Eads, Damian and Esch-Mosher, Diana and Galassi, Mark and Harvey, Neal R. and McCulloch, Hersey D. W. and Perkins, Simon J. and Porter, Reid and Theiler, James and Young, A. Cody and Bloch, Jeffrey J. and David, Nancy},
  biburl = {http://www.bibsonomy.org/bibtex/249e6ad1068af57c348cd910d1be5b974/brazovayeye},
  booktitle = {Algorithms and Technologies for Multispectral,
                 Hyperspectral, and Ultraspectral Imagery VIII},
  editor = {Shen, Sylvia S. and Lewis, Paul E.},
  interhash = {f888322694ade6877bd44bb6e6473aaa},
  intrahash = {49e6ad1068af57c348cd910d1be5b974},
  keywords = {algorithms, genetic programming},
  month = {August},
  notes = {also appears as oai:CiteSeerPSU:540967 but given
                 different authors!},
  organisation = {SPIE--The International Society for Optical
                 Engineering},
  pages = {338--345},
  series = {SPIE},
  size = {8 pages},
  title = {Feature extraction from multiple data sources using
                 genetic programming},
  url = {http://citeseer.ist.psu.edu/540967.html},
  volume = {4725},
  year = {2002}
}
Downloads: 0