A conceptual approach to the fusion of earth observation data
Résumé
Data fusion is a subject becoming increasingly relevant as scientists try to extract more and more information from remotely sensed data using their synergy. A definition of data fusion is proposed, which allows to set up a conceptual approach to the fusion of Earth observation data by putting an emphasis on the framework and on the fundamentals in remote sensing underlying data fusion instead of on the tools and means themselves, as is done usually. Further definitions are given, which describe the objects intervening in any problem of data fusion. Fusion may be performed at different levels, simultaneously: measurement level (also improperly called pixel level), at attribute level, and at rule, or decision, level. It is shown that any process of fusion should deal with the selection of the representation space, the level of fusion and the processing to be applied onto the sources of information. The various architectures of fusion systems are presented. Their properties are discussed, including aspects in accuracy, time-consuming, operational constraints. From these basic architectures, more complex systems can be built, which are suitable to a given application.
Origine : Fichiers produits par l'(les) auteur(s)