SciELO - Scientific Electronic Library Online

 
vol.19 issue2EXPERIMENTAL ANALYSIS FOR A PROPAGATION MODEL OF THE MOBILE TELEPHONY MILITAR UNIVERSITY3D TOOLS FOR MODELING VIRTUAL SCENARIOS BASED ON LOGO. STATE OF THE ART author indexsubject indexarticles search
Home Pagealphabetic serial listing  

Services on Demand

Article

Indicators

Related links

  • On index processCited by Google
  • Have no similar articlesSimilars in SciELO
  • On index processSimilars in Google

Share


Ciencia e Ingeniería Neogranadina

Print version ISSN 0124-8170

Abstract

AMEZQUITA BECERRA, Germán  and  PEREZ CASTILLO, José Nelson. GRID SERVICE FOR UNSUPERVISED CLASSIFICATION OF SATELLITE IMAGES USING CELLULAR AUTOMATA. Cienc. Ing. Neogranad. [online]. 2009, vol.19, n.2, pp.59-76. ISSN 0124-8170.

This paper describes the research process to explore and implement a Grid technology as a promoter of unsupervised, LANDSAT satellite image classification process. In fact, a Grid service has been implemented using cellular automata as an artificial intelligence technique. Those tasks have been achieved by establishing a Grid infrastructure and an implementation model supporting the Grid service. The service model displays the service container and the portlet container, which are integrated to form both client and server. The cellular automaton used is defined by two-dimension neighborhoods, and also a digital level projection of each three bands of the image and location on a defined neighborhood is established. The algorithm is based on transition rules generating changes to neighborhoods to get the desired categories. As a result of the classification process a new image is generated in which categories are expressed in values from 0 to 255 but providing false color to display the results.

Keywords : Grid Services; cellular automata; classification of satellite images..

        · abstract in Spanish     · text in Spanish     · Spanish ( pdf )

 

Creative Commons License All the contents of this journal, except where otherwise noted, is licensed under a Creative Commons Attribution License