DeepSpaceYoloDataset is an annotated set of smart telescopes images.
During the MILAN research project [https://www.list.lu/en/recherche/projet/milan2/], we have compiled a large collection of deep sky images during Electronically Assisted Astronomy sessions in Luxembourg, France, Belgium.
We have used two instruments for several months (from March 2022 to September 2023): a Stellina smart telescope (https://vaonis.com/stellina) and a Vespera smart telescope (https://vaonis.com/vespera). We have captured data for a representative set of deep sky objects from the Messier / NGC / IC / Sharpless2 / Barnard catalogues. Different types of celestial objects were considered: emission/reflection/dark/planetary nebula, galaxies, globular/open clusters. Images were obtained after the capture and the stacking of sub-frames of 10 seconds exposure time.
Training images were splitted into 608x608 patches.
Based on the YOLO format, the dataset is a ZIP file containing 4696 RGB images, and the corresponding 4696 labels text files with the positions of deep sky objets in the images.
The dataset was used to train a YOLOv7 model -- allowing to obtain the following results.
AI-powered observation of Dumbbell Nebula (M27) with a Vespera smart telescope (8/7/2024)
AI-powered annotation of a Dwarf Galaxy (NGC185) with a Vespera smart telescope (14/9/2024)
AI-powered annotation of M1 through a Vespera smart telescope (2/2/2025)
AI-powered annotation of NGC2440 Nebula with a Stellina portable smart telescope (3/3/2025)
AI-powered detection of Messier 98 Galaxy through a Vespera portable smart telescope (24/5/2025)
The dataset can be found here:
- [2023] DeepSpaceYoloDataset: an annotated set of smart telescopes images – DOI Link
The following paper describes the dataset:
- [2024] DeepSpaceYoloDataset: Annotated Astronomical Images Captured with Smart Telescopes – DOI Link
The following papers are based on work carried out on DeepSpaceYoloDataset:
- [2023] Détection d'objets célestes dans des images astronomiques par IA explicable – DOI Link
- [2024] Deep Sky Objects Detection with Deep Learning for Electronically Assisted Astronomy – DOI Link
- [2025] Combining AI-powered detection and Immersive Technologies for Robotic Space Mission Planning – DOI Link
- [2025] Исследование возможности детектирования объектов глубокого космоса c помощью методов компьютерного зрения – Link)
- [2025] Deep sky object detection in astronomical imagery using YOLO models: a comparative assessment – DOI Link
- [2025] COSMICA: A Novel Dataset for Astronomical Object Detection with Evaluation Across Diverse Detection Architectures – DOI Link
- [2025] Method and Tools to Collect, Process, and Publish Raw and AI-Enhanced Astronomical Observations on YouTube – DOI Link
- [2025] LVM4CSI: Enabling Direct Application of Pre-Trained Large Vision Models for Wireless Channel Tasks – DOI Link
If you have a publication related to these works, please notify us to include it in this list.
If you use DeepSpaceYoloDataset in your work, please cite it as follows:
@article{parisot2024deepspaceyolodataset,
title={DeepSpaceYoloDataset: Annotated Astronomical Images Captured with Smart Telescopes},
author={Parisot, Olivier},
journal={Data},
volume={9},
number={1},
pages={12},
year={2024},
publisher={MDPI}
}
This dataset is released under the CC Attribution-NonCommercial-NoDerivatives 4.0 International.
See LICENSE
for details.
For questions or collaborations, please contact Olivier Parisot at olivier.parisot@list.lu or open an issue on GitHub.
Copyright 2021-2025 Luxembourg Institute of Science and Technology (LIST - http://www.list.lu/).