Urban monitoring using multi-temporal SAR and multi-spectral data

  • Authors:

  • Luis Gomez-Chova;Diego Fernández-Prieto;Javier Calpe;Emilio Soria;Joan Vila;Gustavo Camps-Valls

  • Affiliations:

  • Escuela Técnica Superior de Ingeniería, Dept. Ingenierıa Electrónica, Universidad de Valencia, C/Dr. Moliner, 50. 46100 Burjassot, Valencia, Spain;EO Science and Applications Department, European Space Agency, ESA-ESRIN, Via Galileo Galilei, 00044 Frascati, Rome, Italy;Escuela Técnica Superior de Ingeniería, Dept. Ingenierıa Electrónica, Universidad de Valencia, C/Dr. Moliner, 50. 46100 Burjassot, Valencia, Spain;Escuela Técnica Superior de Ingeniería, Dept. Ingenierıa Electrónica, Universidad de Valencia, C/Dr. Moliner, 50. 46100 Burjassot, Valencia, Spain;Escuela Técnica Superior de Ingeniería, Dept. Ingenierıa Electrónica, Universidad de Valencia, C/Dr. Moliner, 50. 46100 Burjassot, Valencia, Spain;Escuela Técnica Superior de Ingeniería, Dept. Ingenierıa Electrónica, Universidad de Valencia, C/Dr. Moliner, 50. 46100 Burjassot, Valencia, Spain

  • Venue:
  • Pattern Recognition Letters - Special issue: Pattern recognition in remote sensing (PRRS 2004)
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

In some key operational domains, the joint use of synthetic aperture radar (SAR) and multi-spectral sensors has shown to be a powerful tool for Earth observation. In this paper, we analyze the potentialities of combining interferometric SAR and multi-spectral data for urban area characterization and monitoring. This study is carried out following a standard multi-source processing chain. First, a pre-processing stage is performed taking into account the underlying physics, geometry, and statistical models for the data from each sensor. Second, two different methodologies, one for supervised and another for unsupervised approaches, are followed to obtain features that optimize the urban related information. Finally, classification of 'Urban/Non-Urban' areas is performed using standard algorithms. Multi-temporal data acquisition was carried out in the areas of Rome and Naples (Italy) in 1995 and 1999. The data set includes images from Landsat TM and 35-day interferometric pairs of ERS2 SAR images. We analyze the dependence of the classification accuracy on the selected input features. The good results obtained using selected features improve the overall classification accuracy, thus confirming the validity of our proposal. l.