Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
10359993 | Information Fusion | 2005 | 20 Pages |
Abstract
From 1999 to 2002, CNES (Centre National d'Ãtudes Spatiales--French Space Agency) led a research program aiming at identifying and evaluating panchromatic/multispectral fusion method on infra-metric spatial resolution images. For this study, images have been acquired over nine sites covering various landscapes (rural, urban or coastal). Five methods, selected as the most efficient, are compared on this data set. The evaluation is both qualitative with visual experts opinions and quantitative with statistical criteria. Finally, the methods are ranked according to their efficiency as regards to the landscapes and the visual expertises.
Keywords
Related Topics
Physical Sciences and Engineering
Computer Science
Computer Vision and Pattern Recognition
Authors
Florence Laporterie-Déjean, Hélène de Boissezon, Guy Flouzat, Marie-José Lefèvre-Fonollosa,