Title :
An automated approach for registration of multisensor/multi-resolution imagery
Author :
Deniz Gerçek;Davut Çeşmeci;M. Kemal Güllü;Alp Ertürk;Sarp Ertürk
Author_Institution :
Isaret ve Gö
fDate :
4/1/2012 12:00:00 AM
Abstract :
In this study, an automated method that is based on image intensities for geometric registration of multi-sensor/multi-resolution imagery acquired from EO-1 Hyperion and IKONOS satellite platforms is proposed. Method performs an area-based transformation to register images of different spectral and spatial resolution with high geometric accuracy. Method basically compares similarity of intensities of two images. Position where there is highest similarity score in translated blocks gives the best match. Chrominance Transform Operation (CTO) that we tested in this study as a similarity measure depicted higher accuracy and performance compared to methods commonly used in the field i.e. Normalized Cross-Correlation (NCC) and Mutual Information (MI).
Keywords :
"Image registration","Mutual information","Remote sensing","Spatial resolution","Accuracy","Transforms","Image restoration"
Conference_Titel :
Signal Processing and Communications Applications Conference (SIU), 2012 20th
Print_ISBN :
978-1-4673-0055-1
DOI :
10.1109/SIU.2012.6204776