ESA-EUSC-JRC3-5November,200911Buildings.PDFVIP

Buildings extraction from very high resolution SAR images using Pulse Coupled Neural Network Fabio Del Frate(1) and Chiara Pratola(1) (1): Tor Vergata Earth Observation Lab – Dipartimento di Informatica, Sistemi e Produzione Tor Vergata University ESA – EUSC - JRC 3-5 November, 2009: Image Information Mining: automation of geospatial intelligence from Earth Observation Purpose of the study Buildings detection in images of low density urban areas, acquired by COSMO-Skymed and TerraSAR-X satellites. COSMO-Skymed - COstellation of Small Satellites for the Mediterranean basin Observation • Italian Space Agency (ASI) mission • Constellation of four satellites COSMO (1-4) equipped with X-band SAR sensors with global coverage of the planet • Observations of an area of interest can be repeated several times a day in all-weather conditions (revisit time of about 140 min) TerraSAR-X • German Aerospace Centre (DLR) mission • The spacecraft acquires X-band radar images of the entire planet whilst circling Earth in a polar orbit at 514 km altitude • Designed to carry out its task for five years • Spatial resolution up to 1 m ESA - EUSC- JRC 3-5 November, 2009 2 DATA SET COSMO-Skymed - COstellation of Small Satellites for the Mediterranean basin Observation Fucino region (Italy), 22-11-2008 Spotlight mode Ground truth from spatial resolution: 1 m