Two edge-preserving segmentation algorithms for multiband images are proposed in this paper. In particular, when dealing with multi-polarization SAR data, adaptive neighborhood structures are selected for modeling polarimetric complex amplitudes and region labels, and for achieving detail-preservation. Experimental results show that the novel schemes produce significant visual improvements for detail preservation, and exhibit equivalent or higher classification performance with respect to the classical classification schemes. These results have been obtained from multi-band, polarimetric SAR SIR-C data, selected for archaeological application studies.
Andreadis, A., Benelli, G., Garzelli, A. (1996). Edge-preserving classification of multifrequency multipolarization SAR images. In Proceedings 1996 IEEE International Conference on Image Processing (pp.899-902). IEEE [10.1109/ICIP.1996.560936].
Edge-preserving classification of multifrequency multipolarization SAR images
Andreadis A.;Benelli G.;Garzelli A.
1996-01-01
Abstract
Two edge-preserving segmentation algorithms for multiband images are proposed in this paper. In particular, when dealing with multi-polarization SAR data, adaptive neighborhood structures are selected for modeling polarimetric complex amplitudes and region labels, and for achieving detail-preservation. Experimental results show that the novel schemes produce significant visual improvements for detail preservation, and exhibit equivalent or higher classification performance with respect to the classical classification schemes. These results have been obtained from multi-band, polarimetric SAR SIR-C data, selected for archaeological application studies.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11365/37003
Attenzione
Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo