NTNU SmallSat Lab

In preparation for the HYPSO-2 launch very soon, we have now re-launched our web pages! The most complete information (best viewed on a desktop), you will find on the official website NTNU website https://ntnu.edu/smallsat. Here you find information about our satellites, including some example datasets! You can also read about our related research projects.

We also have filled https://hypso.space with a bit lighter but detailed, information about the satellites and our projects. This is best viewed on your phone.

HYPSO-2 will be launched on the SpaceX transporter-11 mission, from Vandenberg Space Force Base very soon. We will update this space with detailed information when we have it.

Kongsberg NanoAvionics, KSAT - Kongsberg Satellite Services, NTNU - Norges teknisk-naturvitenskapelige universitet, Elektronisk systemdesign og innovasjon NTNU, Institutt for teknisk kybernetikk

The image below is a throwback to when the HYPSO-2 instruments were tested last year.

We now have only a few days left of 2023, and there is time for some reflection. When we enter 2024, our first research satellite, the HYPSO-1, soon pass the two-year orbit mark! We have collected over 2000 observations and are continuously developing both the on-board software and the data processing and distribution pipeline for data sharing. Watch this space for announcements on how you can work with HYPSO-1 data soon! See our image of the western bank of the Black Sea below.

In addition to the ongoing HYPSO-1 operation, our team has also delivered the two payloads for our next satellite: HYPSO-2. Back in August 2022, we shipped an upgraded hyperspectral camera and a software-defined radio to be integrated at Kongsberg NanoAvionics. The integration and environmental tests finished in December, and some of our team went to Vilnius for final testing and “goodbyes”.

Being an academic organization, our team always changes. In 2023, three new PhD candidates, Samuel Boyle, Cameron Penne and Corrado Chiatante joined our team. We are looking forward to following their work! Two of our colleagues recently finished their PhD work, with Marie Henriksen and Bjørn Andreas Kristiansen successfully defending their degrees in December.

The team has been active in publishing and attending conferences and events, both nationally and internationally. Notably, in October, our satellite operator Simen Berg was awarded the Spaceport Norway Young Award for his work both for the HYPSO project and the student projects.
This year, we have also been shaping our education efforts. The Department of Electronic Systems and the Department of Engineering Cybernetics have a close collaboration on specializations studies for space systems. The first students started their 4th year this August. We are also working with our colleagues nationally and we have been active contributors in space education workshops together with Tekna, Andøya Space Education, University of Oslo (UiO), UiT- The Arctic University of Norway, and others.

A big thanks to our partners and suppliers, at NTNU departments, research groups and centres, in addition to external partners such as Kongsberg NanoAvionics, Andøya Space, KSAT – Kongsberg Satellite Services, Kongsberg Defence & Aerospace, Alén Space, Space Norway, EIDEL AS, Nammo AS, Norwegian Space Agency, Tekna, ESA, Nanovac AB, Spaceport Norway, Forsvarets forskningsinstitutt - FFI, UiT, UiO, The University Centre in Svalbard and many more.

God jul til alle!

🛰️🤖🐟🌍
Curious about how we see the Earth from the HYPSO-1 satellite?

The HYPSO-1 satellite has acquired so far more than a thousand images worldwide. We are excited to share a portion of our data with the public, offering both raw and calibrated radiance information. We introduce the "HYPSO-1 Sea-Land-Cloud-Labeled Dataset", a collection of 200 calibrated hyperspectral captures spanning all continents. Among these, 38 captures come with pixel-level ground-truth labels, facilitating precise segmentation of Sea/Land/Cloud areas by Machine Learning and Deep Learning models in addition to supporting other applications like super-resolution, anomaly detection, image fusion, and unmixing.
--------------------------------------------------------------------
Read more on our article on Computer Vision and Pattern Recognition. Links below.
💻 Website with the open dataset (access from PC): https://ntnu-smallsat-lab.github.io/hypso1_sea_land_clouds_dataset/
📄 Article's abstract: https://arxiv.org/abs/2308.13679
📄 Article in PDF:https://arxiv.org/pdf/2308.13679.pdf

Jon Alvarez Justo, Joseph L Garrett, Dennis Langer, Marie Henriksen, Radu Ionescu, Tor Arne Johansen

An Open Hyperspectral Dataset with Sea-Land-Cloud Ground-Truth from the HYPSO-1 Satellite Hyperspectral Imaging, employed in satellites for space remote sensing, like HYPSO-1, faces constraints due to few labeled data sets, affecting the training of AI models demanding these ground-truth annotations. In this work, we introduce The HYPSO-1 Sea-Land-Cloud-Labeled Dataset, an open dataset w...