Dirty Secrets in Multisensor Data Fusion

Multisensor data fusion systems seek to combine information from multiple sources and sensors in order to achieve inferences that cannot be achieved with a single sensor or source. Applications of data fusion for Department of Defense (DoD) applications include automatic target recognition (ATR), identification-friend-foe-neutral (IFFN), and battlefield surveillance and situation assessment. The use of data fusion for these applications is appealing. Conceptually, the use of a broad spectrum of sensors should improve system accuracy, decrease uncertainty, and make these systems more robust to changes in the targets and environmental conditions. Techniques for data fusion are drawn from a diverse set of disciplines including signal and image processing, pattern recognition, statistical estimation, and artificial intelligence. Many of these techniques have an extensive history, ranging from Bayesian inference (first published in 1793) to fuzzy logic (originating in the 1920s) to neural nets (developed in the 1940s). In the past two decades an enormous amount of DoD funds have been expended to develop data fusion systems. While there are many successes, there are still a number of challenges and limitations. Indeed, critics of data fusion argue that data fusion technology is disappointing and ask, “why is it that when all is said and done (in data fusion), there is so much more said than done?” This paper presents a summary of the current state and limitations of data fusion. Key issues are identified that limit the ability to implement a successful data fusion system. AApproved for public release, distribution is unlimited.