Fiddler

Background
DARPA is soliciting innovative research proposals to develop novel algorithms that can rapidly create synthetic imagery of targets for training Automatic Target Recognition (ATR) algorithms that operate on Synthetic Aperture Radar (SAR) imagery. The effort will develop software that can train on a sparse set of SAR imagery of an object, such as a commercial ship, and use the results of that training to create imagery of the same object under different viewing conditions.

Work Details
The effort will be executed in three phases: a 15-month base period for Phase 1 and separately priced options for the Phase 2 period and the Phase 3 period. The activities in each phase include developing software to train on SAR imagery of an object and create SAR imagery of the same object at any viewing angle, developing software to train on SAR imagery of an object for a limited set of RF characteristics and create SAR imagery of the same object at any viewing angle and at any RF characteristics, and maturing methods that add more combinational complexity and reduce execution times. The program will increase in diversity from Phase 1 to Phase 2, with target motion included throughout the program. Government Furnished Information (GFI) includes providing an evaluation kit, SAR imagery of maritime objects, and at least one government-provided ATR algorithm. DARPA anticipates multiple awards for the base period (Phase 1).

Period of Performance
The program will be performed over three phases: a 15-month base period for Phase 1, a 12-month option for Phase 2, and a 12-month option for Phase 3.