In this paper we test an unsupervised neural network approach for extracting features from very high resolution X-band SAR images. The purpose of this study is buildings recognition in images of low density urban areas, acquired by COSMO-Skymed and TerraSAR-X satellites, by means of Pulse Coupled Neural Network (PCNN), a relatively novel unsupervised algorithm based on models of the visual cortex of small mammals. The features retrieved from geo-referenced SAR images are compared against the ground truth provided by corresponding optical images. The accuracy yielded by PCNN is quantitatively evaluated and critically discussed, also in comparison with commonly used feature extraction techniques
DEL FRATE, F., Pacifici, F., Licciardi, G., Pratola, C., Solimini, D. (2009). Pulse coupled neural networks for automatic features extraction from cosmo-skymed and terrasar-x imagery. In Geoscience and Remote Sensing Symposium,2009 IEEE International,IGARSS 2009 (pp.384-387). IEEE [10.1109/IGARSS.2009.5417783].
Pulse coupled neural networks for automatic features extraction from cosmo-skymed and terrasar-x imagery
DEL FRATE, FABIO;
2009-01-01
Abstract
In this paper we test an unsupervised neural network approach for extracting features from very high resolution X-band SAR images. The purpose of this study is buildings recognition in images of low density urban areas, acquired by COSMO-Skymed and TerraSAR-X satellites, by means of Pulse Coupled Neural Network (PCNN), a relatively novel unsupervised algorithm based on models of the visual cortex of small mammals. The features retrieved from geo-referenced SAR images are compared against the ground truth provided by corresponding optical images. The accuracy yielded by PCNN is quantitatively evaluated and critically discussed, also in comparison with commonly used feature extraction techniquesI documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
