Space-based Image Matching

Develops an image matching algorithm tailor-made to space-based applications, improving capabilities in remote sensing, terrain-relative navigation, and multimodal data fusion. This single model can be applied to tasks across JSC to support mission planning, operations, and science. ​

Image matching is a foundational component of coregistration as well as localization and reconstruction algorithms. Current SoA image matching algorithms are deep learning based and show strong performance in ground-based applications like stitching panoramas, traversing rooms, and reconstructing heritage sites. Yet, these models do not perform as well in the more challenging spaceflight environment, including lighting, on tasks like coregistering imagery of planetary surfaces. ​ Project aims to set a new SoTA, which will enable new applications in localization systems.

This is a mature technology (TRL 7+) — the realistic path in is usually NASA's Technology Transfer Program: licensing an existing NASA patent, or a Space Act Agreement to use NASA facilities/expertise directly. NASA also runs a startup licensing program with no upfront fee for companies formed to commercialize a specific NASA technology.

None of these are guaranteed paths for this specific project — TechPort itself doesn't have an "apply" button. Reaching out to the contact(s) above with a specific question is usually the fastest way to find out what's actually open.