Testbed for Fusion of Imaging and Non-Imaging Sensor Attributes in Airborne Surveillance Missions

An Adaptable Data Fusion Testbed (ADFT) has been constructed that can analyze simulated and/or real data with the help of modular algorithms for each of the main fusion functions and image interpretation algorithms. The results obtained from data fusion of information coming from an imaging Synthetic Aperture Radar (SAR) and non-imaging sensors (ESM, IFF, 2-D radar) on-board an airborne maritime surveillance platform are presented for two typical scenarios of Maritime Air Area Operations and Direct Fleet Support. An Image Support Module (ISM) has been designed and implemented that consists of a four-step hierarchical SAR classifier that can extract attributes such as ship length, ship category, ship type and (in the future) ship class. The SAR classifier can distinguish between merchant and combatant categories and can select amongst 5 combatant types and it estimates confidence levels for each sensor declaration that it produces, for example through the use of properly trained neural nets. A truncated Dempster-Shafer evidential reasoning scheme is used that proves robust under countermeasures and deals efficiently with uncertain, incomplete or poor quality information. Since the Dempster-Shafer method reasons over an exhaustive list of all possible platforms, an extensive set of realistic databases has been created that contains over 140 platforms, carrying over 170 emitters and representing targets from 24 countries.