Tor Vergata Earth Observation Laboratory
 

Monitoring Urban Land Cover in Rome, Italy, and Its Changes by Single-Polarization
Multitemporal SAR Images

F. Del Frate, F. Pacifici, D. Solimini

 

 


Abstract

This study contributes an assessment of the potential of single-polarization decametric synthetic aperture radar (SAR) images in classifying land cover within and around large
urban areas and in monitoring their changes. The decision task is performed on a pixel basis and is carried out by supervised neural network algorithms fed by radar image features including backscattering intensity, coherence and textural parameters. Two configurations are considered: a short-term classification and change detection scheme intended for providing information in near-real time and a long-term scheme aimed at observing the urban changes at year time scales.We use a pair of interferometric images for the short-term case, while the long-term exercise utilizes two interferometric pairs and a fifth single acquisition. The
images are acquired by the ERS SAR in late winter, spring and early summer over 836 square kilometers including Rome, Italy, and its surroundings. The accuracy of the short-term algorithm in discriminating seven types of surface is higher than 86%, while the accuracy of the long-term algorithm is beyond 88%. The many changes undergone by Rome from 1994 to 1999 have been identified by the postclassification comparison change detection procedure. The pixel-by-pixel analysis of the results has been carried out for a 160 square kilometers test area, obtaining a correct detection above 82% (less than 18% missed alarms and 0.3% false alarms).

Index Terms—Change detection, coherence, feature contribution, land-cover classification, neural networks, synthetic aperture radar, texture, urban development.

© 2008 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

|| full paper || earth observation laboratory ||