Site is Loading, Please wait...

On-Board AI: Multi-Frame Super Resolution on OPS-SAT

AI Onboard ESA’s satellite – Made in Greece

Project Snapshot

Status

Mission Success / Delivered

Start Date

15/11/2022

End Date

2022

Programme

AI Onboard ESA’s satellite – Made in Greece

Partners

OHB Hellas role

Development & In-Orbit Validation of AI Onboard ESA’s satellite

The Objective

Super-resolution refers to the process of improving the spatial resolution, that is, the level of detail, of an image or an acquisition system. Our innovative idea is to use OPS-SAT’s powerful on-board computer to deploy a machine learning-based super-resolution algorithm directly on-board the satellite. It has the potential of opening new perspectives of EO applications mainly in time-critical domains like safety and security. In the frame of this experiment, we successfully developed and deployed an AI-based multi-frame super resolution algorithm on-board OPS-SAT achieving a notable improvement in image quality and proving the merits of the proposed approach. The study was undertook by OHB Hellas with FORTH as a subcontractor.

OHB Hellas Contributions

OHB Hellas has successfully bridged the gap between theoretical AI and orbital reality. By deploying a machine learning-based super-resolution algorithm directly onto the ESA OPS-SAT powerful on-board computer, we have demonstrated that spatial resolution can be enhanced in real-time, in-situ. This achievement marks a paradigm shift for Earth Observation, particularly for time-critical safety and security applications where ground-side processing delays are not an option.

Related project in Orbital High-Performance Computing