Share Email Print

Proceedings Paper

Automatic object extraction from VHR satellite SAR images using pulse coupled neural networks
Author(s): Fabio Del Frate; Daniele Latini; Chiara Pratola
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In this paper we investigate an unsupervised neural network approach for automatically extracting objects of interest from very high resolution (VHR) SAR images. The technique is based on the use of Pulse-Coupled Neural Networks (PCNN) which is a relatively novel technique based on models of the visual cortex of small mammals. The study discusses the use of PCNN technique in different applications. In a first case the extraction procedure is focused on the detection of buildings. In the second case the segmentation of a dark spot representing an oil spill in a SAR image is considered. The performance yielded by the PCNN is evaluated and critically discussed for a set of new generation of X-band SAR images taken by COSMO-Skymed and TerraSAR-X systems.

Paper Details

Date Published: 22 October 2010
PDF: 6 pages
Proc. SPIE 7829, SAR Image Analysis, Modeling, and Techniques X, 782905 (22 October 2010); doi: 10.1117/12.867918
Show Author Affiliations
Fabio Del Frate, Univ. degli Studi di Roma Tor Vergata (Italy)
Daniele Latini, Univ. degli Studi di Roma Tor Vergata (Italy)
Chiara Pratola, Univ. degli Studi di Roma Tor Vergata (Italy)

Published in SPIE Proceedings Vol. 7829:
SAR Image Analysis, Modeling, and Techniques X
Claudia Notarnicola, Editor(s)

© SPIE. Terms of Use
Back to Top