FRONTIER TECHNOLOGY INC. — Department of Defense STTR Phase I: ABSTRACT: Frontier Technology, Inc. (FTI) and its research partners, University of Florid

Description

ABSTRACT: Frontier Technology, Inc. (FTI) and its research partners, University of Florida (UF) and Lockheed Corporation, propose to enhance fusion of multimodal (EO, IR, acoustic, radar, etc.) multisensor datastreams. Phase I will: (1) Determine physics models for apparent properties of targets and inherent properties of sensors; (2) Integrate target and sensor physics models to produce Multi-Physics Models (MPMs) for each application; (3) Enhance sensor fusion algorithms via semantic integration with MPMs, to increase probability of detection (Pd) and decrease false alarm rate (Rfa); (4) Test and validate MPM-enhanced sensor fusion algorithms including FTI/UF"s state-of-the-art Dynamically Adaptive Statistical Data Fusion (DASDAF) paradigm, to improve target classification; and (5) Analyze parallel processing architectures for real-time computation/application. Phase I will identify relevant technological applications, develop baseline MPMs encompassing selected measurement observables, derive multiphysics-based sensor fusion algorithms and demonstrate effectiveness using synthetic data. Phase II will further refine MPMs and companion MPM-based sensor fusion algorithms, and then conduct high fidelity performance demonstration/validation using finer grained simulations. Phase II will develop baseline embedded computing approaches for meeting tactical timeline requirements for chosen applications and quantify performance gains relative to conventional fusion algorithms. FTI will commercialize the resulting prototype software for Government and leading aerospace contractors. BENEFIT: If successful, the proposed research will constitute a breakthrough in the solution of problems related to sensor fusion and automated target recognition by using multi-physics models to optimize the fusion of datastreams from disparate modalities in multi-sensor networks. Our DASDAF data fusion methodology will be optimized by MPMs to combine results from multiple disparate sensors and modalities, with analysis (in Phase II) of numerical quality. This research and development applies to a wide variety of military applications, such as airborne, spaceborne and ground-based surveillance, remote sensing in support of battlefield surveillance, as well as domestic applications such as environmental assessment and monitoring applications for law enforcement. Frontier Technology will license or sell the Phase II product to one or more commercial aerospace corporations or defense contractors.