Data fusion is a rapidly emerging technology. Numerous diverse definitions are being promoted and being adopted for various application techniques. The term 'data fusion' is being loosely used to signify combinations of often large amounts of diverse data into a consistent, accurate and intelligible whole. There are several distinct types of data fusion, for example, the data correspond to different attributes associated with the same geometry, within one architecture. In others, the data consist effectively of repeated measurements of different types of attributes that are assembled together using overlay techniques, which were formerly known as data compilation or data assimilation. In the former case, the data have to be fused in an intelligent manner, taking into account the different natures of the attributes, to gain as complete a picture as possible of the object from its component attributes. For the latter, the data are merely the overlaying of different types of attribution to produce a mosaic at the application level. The term data fusion can be broken into two components: true fusion, where one geometry is shared by multiple attributes within a single architecture or file; and data assimilation, where multiple redundant geometries with attributes are brought within the same context using overlay techniques.