[visionlist] [Competition] Spot the GEO satellites

[Tat-Jun Chin]

In this "Spot the GEO satellites" (spotGEO) challenge, you are asked to
develop an algorithm to detect Geostationary orbiting objects from simple
png images (or frames) acquired by an unkown, low-cost ground-based
telescope.

Can you learn on how to cope with cloud cover, atmospheric/weather effects,
light pollution, sensor noise/defects, star occlusions and more?

Check out the detailed problem description, dataset and starter-kit at
the competition
website <https://kelvins.esa.int/spot-the-geo-satellites/>.

Competition starts on 7 June and ends on 31 August.

The challenge is jointly organised by the Advanced Concepts Team
<https://www.esa.int/gsp/ACT/> at the European Space Agency (ESA), the AI
for Space team <https://cs.adelaide.edu.au/~tjchin> at The University of
Adelaide, and other collaborators.

See news coverage
<https://www.esa.int/Enabling_Support/Space_Engineering_Technology/Telescope-peering_AI_challenged_to_spot_mystery_space_objects>
by
ESA.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://visionscience.com/pipermail/visionlist_visionscience.com/attachments/20200529/dc3c11cb/attachment.html>