Understanding the physics behind remote sensing technologies such as optics, radar and telemetry, for integration into real time expert systems for decision support.
In our vision, the output of a data fusion system is aimed at supporting a human decision process. In fact, our experience is applied in our ABTS, AMAS and ASES projects. The peculiarity of the MMP software is the sensor data fusion and also the automatic decision features.
Sensor and Data Fusion Open Issues:
What algorithms or techniques are appropriate and optimal for a particular application?
What architecture should be used (i.e., where in the processing flow should data be fused (viz. at the data, feature, or decision levels)?
How should individual sensor data be processed to extract the maximum amount of information?
What accuracy can realistically be achieved by a data fusion process?
How can the fusion process be optimized in a dynamic sense?
How does the data collection environment (i.e., signal propagation, target characteristics, etc.) affect the processing?
Under what conditions does multi-sensor data fusion improve system operation (under what conditions does it impede or degrade performance)?