Generation of Synthetic SAR Imagery for ATR Development

Due to increased use of imaging sensors in military aircraft, future combat airplane pilots will need onboard artificial intelligence for aiding them in image interpretation and target designation. This document presents a system which is able to create high-resolution artificial SAR imagery. The resulting images can be used to facilitate automatic target recognition (ATR) algorithm development. The system provides an interface that allows dynamically requesting imagery depending on the location and heading of a simulated carrier platform. Landscapes, structures and target signatures are generated based on digital terrain elevation and cultural data and 3d models. Post-processing algorithms for overcoming weaknesses of digital terrain databases and improving image realism are presented. Simulated sensor imagery is useful in a wide range of applications, two of which are training of ATR algorithms and sensor simulation in flight simulation environments. Using an existing ATR method as an example, the applicability and the influences of synthetic imagery on ATR training are shown and first approaches how to validate the correctness of the imagery are outlined. The integration of the system into a flight simulator in the context of interfacing and control topics is presented as another example for its applicability. As an outlook, an example of using external databases for creating imagery of crisis areas is outlined.