Proceedings PaperSensor fusion for target recognition: a review of fundamentals and a potential approach to multisensor requirements allocation
|Format||Member Price||Non-Member Price|
In the first part of this paper, a brief tutorial review of sensor fusion for target recognition applications is presented. In this context, relevant aspects of system architecture, sensor integration, and data fusion are discussed. Several unresolved issues in the practical implementation of sensor fusion are identified; significant among these are the rationale for selection of a sensor suite and a means for optimal allocation of requirements between sensors. In the second part, a novel methodology offering the potential for resolving these two issues is presented. An approach to defining sensor data information content is described. Coupling this approach with accepted rules of thumb describing target recognition capabilities results in a quantitative method for comparing the target recognition ability of diverse sensors (imagers, non-imagers, active, passive, electromagnetic, acoustic, etc.). Extension to describing the performance of multiple sensors is straightforward. Application of the technique to sensor selection and requirements allocation is discussed.