Evolving spectral transformations for multitemporal information extraction using evolutionary computation

Created by W.Langdon from gp-bibliography.bib Revision:1.4549

  author =       "Henrique G. Momm and Greg Easson",
  title =        "Evolving spectral transformations for multitemporal
                 information extraction using evolutionary computation",
  journal =      "Journal of Applied Remote Sensing",
  year =         "2011",
  volume =       "5",
  pages =        "053564--1 to 053564--18",
  email =        "henrique.momm@mtsu.edu",
  keywords =     "genetic algorithms, genetic programming,
                 multitemporal, evolutionary computation, remote
  ISSN =         "1931-3195",
  publisher =    "SPIE",
  URL =          "http://remotesensing.spiedigitallibrary.org/article.aspx?articleid=1182443",
  DOI =          "doi:10.1117/1.3662089",
  size =         "18 pages",
  abstract =     "Remote sensing plays an important role in assessing
                 temporal changes in land features. The challenge often
                 resides in the conversion of large quantities of raw
                 data into actionable information in a timely and
                 cost-effective fashion. To address this issue, research
                 was undertaken to develop an innovative methodology
                 integrating biologically-inspired algorithms with
                 standard image classification algorithms to improve
                 information extraction from multitemporal imagery.
                 Genetic programming was used as the optimisation engine
                 to evolve feature-specific candidate solutions in the
                 form of nonlinear mathematical expressions of the image
                 spectral channels (spectral indices). The temporal
                 generalisation capability of the proposed system was
                 evaluated by addressing the task of building rooftop
                 identification from a set of images acquired at
                 different dates in a cross-validation approach. The
                 proposed system generates robust solutions (kappa
                 values > 0.75 for stage 1 and > 0.4 for stage 2)
                 despite the statistical differences between the scenes
                 caused by land use and land cover changes coupled with
                 variable environmental conditions, and the lack of
                 radiometric calibration between images. Based on our
                 results, the use of nonlinear spectral indices enhanced
                 the spectral differences between features improving the
                 clustering capability of standard classifiers and
                 providing an alternative solution for multitemporal
                 information extraction.",

Genetic Programming entries for Henrique G Momm Greg Easson