Near-Real-Time Data Fusion, Phase II

摘要

Report developed under SBIR contract for topic N93-084. In Phase I of this project, we explored several different approaches to Near-Real-Time Data Fusion (NRTDF), and in Phase II we developed the most promising architecture into a prototype NRTDF system. The system automatically extracts the maximum amount of information and produces the best possible tactical picture from the available data by accurately processing all relevant target data in near-real-time. In addition, we demonstrated that this system was capable of fusing large amounts of data in near-real-time using multiple-hypothesis and non-Gaussian data fusion techniques. As part of the project, with additional support from NAVAIR (PMA-299), we also developed a SH-60R Decision Support System Testbed (DSST) based on NRTDF. The DSST allows the operator to: (1) set up a scenario, with the desired friendly, neutral, and hostile platforms, (2) feed the contacts produced by the friendly sensors into NRTDF, (3) produce a common tactical/ operational picture using NRTDF, and (4) utilize an operationally oriented, 'unbiased', and 'honesty inducing' metric to measure the difference between the ground truth data and the common tactical/operational picture. We also developed a commercial version of the NRTDF system for use in transportation, manufacturing, retail, and security applications.