Inactive

The U.S Army seeks to shorten the sensor to shooter engagement timeline through use of Machine Learning (ML) based Aided Target Detection and Recognition (AiTDR) algorithms. Traditional ML techniques ... The U.S Army seeks to shorten the sensor to shooter engagement timeline through use of Machine Learning (ML) based Aided Target Detection and Recognition (AiTDR) algorithms. Traditional ML techniques focuses on Aided Target Recognition (AiTR) which requires the burden of a large training image database comprised of a diverse set of specific targets each captured under a comprehensive set of unique conditions (e.g. background terrain, target pose, lighting, partial occlusion etc). This limits the ability to detect new targets or trained targets under new/untrained condition. Although AiTR remains a valuable and required capability, this Request For Information (RFI) seeks to understand the state of AiTDR solutions that have optimized ML AiTD algorithms for the robust (i.e. reliable, intuitive and adaptive) detection of both trained as well as new/untrained targets in both trained as well as untrained conditions. We are prioritizing greater value in being able to reliably detect generic classes of targets than to reliably identify specific targets, but potentially miss a valid, but insufficiently trained-on target.