Phase II Amount
$1,000,000
At a high level, the primary technical objective of the proposed effort is to Identify, obtain, evaluate, and improve datasets; Investigate the use of Meta-Learning to improve the low-shot detection performance of the feed forward network; Extend research in multi-branch multi-domain embedding networks and semantic layouts for low-shot detection in remote sensing imagery; and Develop and implement a feedback mechanism to process nearby geographic regions in areas where low-shot objects are confirmed. Use the tool (blender rendering tool for 3D CAD models) to build CAD models to be rendered from any perspective, resolution, and with a background model and point spread function representative of remote sensing imagery.