INTERPRETATION OF REMOTELY-SENSED IMAGES IN A CONTEXT OF MULTISENSOR FUSION USING A MULTISPECIALIST ARCHITECTURE

This paper presents a scene interpretation system in multisensor fusio n context whose application involves the interpretation of remote sens ed images. First we discuss how multisensor fusion is achieved, and we derive the modeling problems for objects, scene, and strategy. The pr oposed multispecialist architecture generalizes the ideas of our previ ous works by taking into account the knowledge about sensors, the mult iple viewing notion (shot), and the uncertainty and imprecision of mod els and data modeled with the possibility theory. Especially, generic models of objects are represented by concepts independent of sensors ( geometry, material, and spatial context). Three kinds of specialists a re present in the architecture: generic specialists (scene and conflic t), semantic object specialists, and low level specialists. A blackboa rd structure with a centralized control is used. The interpreted scene is implemented as a matrix of pointers allowing easy conflict detecti on and easy spatial context verification. Under the control of the sce ne specialist, the conflict specialist solves conflicts using the spat ial context knowledge of objects. Finally, an interpretation system wi th SAR/SPOT sensor images is described, and an example of a scene inte rpretation involving rivers, bridges, urban areas, and roads detection is shown.