The Omnibus model: a new model of data fusion?

Abstract

Over the last two decades there have been several process models proposed (and used) for data and information fusion. A common theme of these models is the existence of multiple levels of processing within the data fusion process. In the 1980's three models were adopted: the intelligence cycle; the JDL model; and the Boyd control. The 1990's saw the introduction of the Dasarathy model and the Waterfall model. However, each of these models has particular advantages and disadvantages. A new model for data and information fusion is proposed. This is the Omnibus model, which draws together each of the previous models and their associated advantages whilst managing to overcome some of the disadvantages. Where possible, the terminology used within the Omnibus model is aimed at a general user of data fusion technology to allow use by a distributed audience.