Chapter 6. Multi-Temporal Image Classification with Kernels

  1. Dr Gustavo Camps-Valls B.Sc., Ph.D. professor member4 and
  2. Dr Lorenzo Bruzzone M.S., Ph.D. Postdoctoral Researcher Professor member Chair5
  1. Jordi Muñnoz-Marí1,
  2. Luis Gómez-Chova1,
  3. Manel Martínez-Ramón2,
  4. José Luis Rojo-Álvarez3,
  5. Javier Calpe-Maravilla1 and
  6. Dr Gustavo Camps-Valls B.Sc., Ph.D. professor member4

Published Online: 4 NOV 2009

DOI: 10.1002/9780470748992.ch6

Kernel Methods for Remote Sensing Data Analysis

Kernel Methods for Remote Sensing Data Analysis

How to Cite

Muñnoz-Marí, J., Gómez-Chova, L., Martínez-Ramón, M., Rojo-Álvarez, J. L., Calpe-Maravilla, J. and Camps-Valls, G. (2009) Multi-Temporal Image Classification with Kernels, in Kernel Methods for Remote Sensing Data Analysis (eds G. Camps-Valls and L. Bruzzone), John Wiley & Sons, Ltd, Chichester, UK. doi: 10.1002/9780470748992.ch6

Editor Information

  1. 4

    Image Processing Laboratory (IPL) & Dept. Enginyeria Electrónica, Universitat de Valéncia, Spain

  2. 5

    Dept. Information Engineering and Computer Science, University of Trento, Italy

Author Information

  1. 1

    Image Processing Laboratory (IPL) & Dept. Enginyeria Electrònica, Universitat de València, Spain

  2. 2

    Dept. Signal Theory and Communications, Univ. Carlos III de Madrid, Spain

  3. 3

    Dept. Signal Theory and Communications, Univ. Rey Juan Carlos, Madrid, Spain

  4. 4

    Image Processing Laboratory (IPL) & Dept. Enginyeria Electrónica, Universitat de Valéncia, Spain

Publication History

  1. Published Online: 4 NOV 2009
  2. Published Print: 23 OCT 2009

ISBN Information

Print ISBN: 9780470722114

Online ISBN: 9780470748992

SEARCH

Keywords:

  • multi-temporal image classification with kernels;
  • multi-temporal classification of remote sensing images;
  • binary Support Vector Machine classifier (SVM) and one-class Support Vector Domain Description (SVDD) classifier;
  • linking Gaussian Markov Random Fields (GMRF) at different dates;
  • family of powerful nonlinear classification methods for multi-temporal classification;
  • good classification performance using spectral signature;
  • multi-temporal classification and change detection with kernels;
  • two kernel-based formulations;
  • contextual and multi-source data fusion with kernels;
  • classifiers based on statistical learning theory, binary SVM and one-class SVDD classifier

Summary

This chapter contains sections titled:

  • Introduction

  • Multi-temporal classification and change detection with kernels

  • Contextual and multi-source data fusion with kernels

  • Multi-temporal/-source urban monitoring

  • Conclusions

  • Acknowledgments

  • References