Semantic Decomposition of LandSat TM Image

  • Miguel Torres
  • Giovanni Guzmán
  • Rolando Quintero
  • Marco Moreno
  • Serguei Levachkine
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4251)

Abstract

In this paper, we propose a semantic supervised clustering approach to classify multispectral information in geo-images. We use the Maximum Likelihood Method to generate the clustering. In addition, we complement the analysis applying spatial semantics to determine the training sites and to improve the classification. The approach considers the a priori knowledge of the multispectral geo-image to define the classes related to the geographic environment. In this case the spatial semantics is defined by the spatial properties, functions and relations that involve the geo-image. By using these characteristics, it is possible to determine the training data sites with a priori knowledge. This method attempts to improve the supervised clustering, adding the intrinsic semantics of the geo-images to determine the classes that involve the analysis with more precision.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Unsalan, C., Boyer, K.L.: Classifying land development in high-resolution Satellite imagery using hybrid structural-multispectral features. IEEE Transactions on GeoScience and Remote Sensing 42(12), 2840–2850 (2004)CrossRefGoogle Scholar
  2. 2.
    Torres, M., Levachkine, S.: Generating spatial ontologies based on spatial semantics. In: Levachkine, S., Serra, J., Egenhofer, M. (eds.) Research on Computing Science, Semantic Processing of Spatial Data, vol. 4, pp. 169–178 (2003)Google Scholar
  3. 3.
    Nishii, R., Eguchi, S.: Supervised image classification by contextual AdaBoost based on posteriors in neighborhoods. IEEE Transactions on GeoScience and Remote Sensing 43(11), 2547–2554 (2005)CrossRefGoogle Scholar
  4. 4.
    Bandyopadhyay, S.: Satellite image classification using genetically guided fuzzy clustering with spatial information. International Journal of Remote Sensing 26(3), 579–593 (2005)CrossRefGoogle Scholar
  5. 5.
    Jianwen, M., Bagan, H.: Land-use classification using ASTER data and self-organized neutral networks. International Journal of Applied Earth Observation and Geoinformation 7(3), 183–188 (2005)CrossRefGoogle Scholar
  6. 6.
    Morgan, J.T., Ham, J., Crawford, M.M., Henneguelle, A., Ghosh, J.: Adaptative feature spaces for land cover classification with limited ground truth data. International Journal of Pattern Recognition and Artificial Intelligence 18(5), 777–799 (2004)CrossRefGoogle Scholar
  7. 7.
    Torres, M., Moreno, M., Quintero, R., Guzmán, G.: Applying Supervised Clustering to Land-sat MSS Images into GIS-Application. In: Advances in: Artificial Intelligence, Computing Science and Computer Engineering, Research on Computing Science, vol. 10, pp. 167–176 (2004)Google Scholar
  8. 8.
    Chung, K.F., Wang, S.T.: Note on the relationship between probabilistic and fuzzy clustering. In: GI-NTG Fachtagung Struktur und Betrieb von Rechensystemen. LNCS, vol. 8(7), pp. 523–526. Springer, Berlin (2003)Google Scholar
  9. 9.
    Bandyopadhyay, S., Maulik, U., Pakhira, M.K.: Clustering using simulated annealing with probabilistic redistribution. International Journal of Pattern Recognition and Artificial Intelligence 15(2), 269–285 (2001)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Miguel Torres
    • 1
  • Giovanni Guzmán
    • 1
  • Rolando Quintero
    • 1
  • Marco Moreno
    • 1
  • Serguei Levachkine
    • 1
  1. 1.Geoprocessing LaboratoryCentre for Computing Research – National Polytechnic, InstituteMexico CityMexico

Personalised recommendations