We propose an approach aimed at reducing the effects of registration noise in unsupervised change detection. The proposed approach performs an adaptive estimation of the registration-noise distribution, given a specific scene of interest. The estimated distribution is used to define a local adaptive decision strategy for carrying out change detection by taking into account misregistration. Experimental results confirm the effectiveness of the proposed approach.
Adaptive estimation of the registration-noise distribution for accurate unsupervised change detection
Bruzzone, Lorenzo;
2001-01-01
Abstract
We propose an approach aimed at reducing the effects of registration noise in unsupervised change detection. The proposed approach performs an adaptive estimation of the registration-noise distribution, given a specific scene of interest. The estimated distribution is used to define a local adaptive decision strategy for carrying out change detection by taking into account misregistration. Experimental results confirm the effectiveness of the proposed approach.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione
