Spot the GEO Satellites: From Dataset to Kelvins SpotGEO Challenge

Bo Chen, Daqi Liu, Tat-Jun Chin, Mark Rutten, Dawa Derksen, Marcus Martens, Moritz von Looz, Gurvan Lecuyer, Dario Izzo; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2021, pp. 2086-2094

The Geosynchronous Equatorial Orbit (GEO) is home to many important space assets such as telecommunication and navigational satellites. Monitoring Resident Space Objects (RSOs) in GEO is a crucial aspect in achieving Space Situational Awareness (SSA) and in protecting critical space assets. However, ground-based GEO object detection is challenging due to the extreme distance of the targets, as well as nuisance factors including cloud coverage, atmospheric/weather effects, light pollution, sensor noise/defects, and star occlusions. The Kelvins SpotGEO Challenge is designed to establish to what extent images coming from a low-cost ground-based telescope can be used to detect GEO and near-GEO RSOs solely from photometric signals that are without any additional meta-data. At the same time, the SpotGEO dataset also addresses the lack of publicly available datasets from a computer vision perspective on the satellite detection problem; by assembling and releasing such a dataset, we hope to spur more efforts on the optical detection of RSOs and enable objective benchmarking for existing and future methods. In this work, we present details of the SpotGEO dataset development, challenge design, evaluation metric, and result analysis.