Density-Based Unsupervised Classification for Remote Sensing *

  • Cees H. M. van Kemenade
  • Han La Poutre
  • Robert J. Mokken
Conference paper

Summary

Most image classification methods are supervised, and use a parametric model of the classes that have to be detected. The models of the different classes are trained by means of a set of training regions that usually have to be marked and classified by a human interpreter. Unsupervised classification methods are data-driven methods that do not use such a set of training samples. Instead these methods look for (repeated) structures in the data. In this chapter we describe a non-parametric unsupervised classification method, which uses biased sampling to obtain a learning sample with little noise. A density estimation based clustering is then used to find structures in the learning data. The method generated a non-parametric model for each of the classes and uses these models to classify the pixels in the image.

Keywords

Remote Sensing Landsat Rounded 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    J.H. Friedman, J.L. Bentley, and R.A. Finkel, “An algorithm for finding best matches in logarithmic expected time”, ACM Transactions on Mathematical Software, vol. 3, no. 3, pp. 209–226, 1977.CrossRefGoogle Scholar
  2. 2.
    C.H.M. van Kemenade, J.A. La Poutre, and R.J. Mokken, “Density-based unsupervised classification for remote sensing”, Technical Report SEN-R9810 (also available via http://www.cwi.nl/~hlp/PAPERS/RS/dense98.ps), CWI, Amsterdam, the Netherlands, 1998.Google Scholar
  3. 3.
    J.A. Richards, Remote sensing digital image analysis, Springer-Verlag, Berlin, 1993.Google Scholar
  4. 4.
    D.W. Scott, Multivariate Density Estimation, Wiley series in probability and Mathematical Statistics, John Wiley & Sons, INC., New York, 1993.Google Scholar
  5. 5.
    B.W. Silverman, Density estimation for statistics and data analysis, Monographs on Statistics and Applied Probability, Chapman and Hall, London, 1986.Google Scholar

Copyright information

© Springer-Verlag Berlin · Heidelberg 1999

Authors and Affiliations

  • Cees H. M. van Kemenade
    • 1
  • Han La Poutre
    • 1
  • Robert J. Mokken
    • 2
  1. 1.CWI, Centre for Mathematics and Computer ScienceAmsterdamthe Netherlands
  2. 2.Center for Computer Science in Organization and Management (CCSOM), Department of Statistics and Methodology, PSCWUniversity of AmsterdamAmsterdamthe Netherlands

Personalised recommendations