Maritime/Systems & Technology Research

Airborne radars operating over open water must classify maritime vessels by measuring and exploiting highly-variable radar signatures. Sources of signature variability include within-class ship construction and equipment differences, complex in-situ 6-DoF ship motion caused by ocean waves across a range of sea state conditions, acquisition geometry including grazing angle and maritime-specific RF propagation effects that may include varying degrees of multi-path fading and ducting. Furthermore, there is limited availability of measured signature data for adversary ships of interest that can be used for classifier training. This Phase I program designs a ship classification algorithm that exploits ISAR imagery using modern machine learning techniques to address the challenges of highly-variable signatures and limited measured training data. It surveys and selects promising discriminative and generative transfer learning techniques to achieve performance against adversary ship classes. Furthermore, it accomplishes design trades that include selection of coherent processing interval and data adaptive ISAR focusing and assesses potential benefits of multi-look ISAR fusion. The Phase I program lays the groundwork for algorithm maturation, system integration, and assessment against relevant measured data sets in Phase II.