SatMod: Bayesian Inference of Spacecraft Geometry and Pose

Increases in space traffic have caused an ever-growing need to recognize, track, and inspect both known and unknown satellites in-situ. Imagery from ground observation platforms provide a convenient and versatile data source for such characterization but is often limited in both quantity and quality. Rapid and automated 3D reconstruction of satellite models from limited 2D imagery would significantly reduce the burden of manual satellite characterization for both analysts and decision makers. VSI, with support from Texas A&M University and ExoAnalytic Solutions, proposes SatMod, a 3D space object modeling capability from ground captured imagery based on Bayesian inference of spacecraft geometry and pose. The VSI team is well suited to program challenges, with expertise in remote sensing, atmospheric distortion, 3D modeling, and machine learning.