Advanced Sensor Data Fusion

Frontier Technology, Inc. (FTI) and its research partner, University of Florida (UF), propose to update and implement theory, algorithms, and software for fusion of multi-sensor (e.g., RADAR and EO) datastreams, to provide enhanced acquisition, tracking, and discrimination of threat objects in a cluttered multi-target environment. We propose to enhance/extend our successful Phase-I technology to support: (a) Parallel application of multiple classifiers to RADAR and/or EO/IR sensor data to identify probable target type/ track/location; (b) Processing of partial classification results in pattern space, for efficiency and visibility to developers, to produce refined classifier results that fuse multiple sensor datastreams; (c) Adaptation of classifiers and pattern-space processing to track targets given nonergodic (statistically changing) inputs; (d) Analysis of complexity and performance on several processor system architectures, with best-performance implementation on a hardware system. Phase II will utilize adaptive pattern selection and pattern-space processing to develop, test, and verify prototype data fusion / target classification algorithms that incorporate partially-corrupted signatures and will also produce a prototype hardware implementation. FTI has provided additional details of the technology to Mr. David Hangsleben, MDA/CCBMC, and Mr. Donald Drouin, Technology Integration Manager for the Boeing Company. Both gentlemen expressed interest and a desire for continued updates.