Principal component analysis (PCA) is applied to investigate on changes occurring in multitemporal polarimetric SAR imagery. Correlation instead of covariance matrix is used in the transformation, thus reducing gain variations introduced by the imaging system and giving equal weight to each polarization. The approach is effective when PCA is computed on images recorded simultaneously, as well as when it is applied to the whole set of multitemporal images.
Principal component analysis for change detection on polarimetric multitemporal SAR data / Baronti, S; Carlà, R.; Sigismondi, S.; Alparone, L.. - STAMPA. - 4:(1994), pp. 2152-2154. (Intervento presentato al convegno 1994 International Geoscience and Remote Sensing Symposium tenutosi a Pasadena, CA, USA nel 8 - 12 August 1994) [10.1109/IGARSS.1994.399678].
Principal component analysis for change detection on polarimetric multitemporal SAR data
ALPARONE, LUCIANO
1994
Abstract
Principal component analysis (PCA) is applied to investigate on changes occurring in multitemporal polarimetric SAR imagery. Correlation instead of covariance matrix is used in the transformation, thus reducing gain variations introduced by the imaging system and giving equal weight to each polarization. The approach is effective when PCA is computed on images recorded simultaneously, as well as when it is applied to the whole set of multitemporal images.
I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
