Adaptive estimation of the registration-noise distribution for accurate unsupervised change detection

Author

Bruzzone, Lorenzo ; Cossu, Roberto ; Gomarasca, Mario

Author_Institution

DICA, Trento Univ., Italy

Volume

6

fYear

2001

fDate

2001

Firstpage

2584

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

Keywords

adaptive signal processing; geophysical signal processing; geophysical techniques; image registration; image sequences; remote sensing; terrain mapping; vegetation mapping; adaptive estimation; change detection; geophysical measurement technique; image processing; image registration; land surface; land-cover; local adaptive decision strategy; misregistration; registration noise distribution; remote sensing; terrain mapping; unsupervised change detection; Adaptive estimation; Councils; Image analysis; Layout; Noise reduction; Pixel; Remote sensing; Satellites; Spatial resolution; Stability;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium, 2001. IGARSS '01. IEEE 2001 International

Conference_Location

Sydney, NSW

Print_ISBN

0-7803-7031-7

Type

conf

DOI

10.1109/IGARSS.2001.978096

Filename

978096