MissionLabAirborneDataset-Clouds
<h1>MLAD-C</h1> <div>The <strong>M</strong>ission<strong>L</strong>ab<strong>A</strong>irborne<strong>D</strong>ataset-<strong>C</strong>louds contains aerial images of clouds and associated labeled cloud masks from a flight experiment conducted on October 12, 2023, in the Upper Bavaria region of Germany.</div> <div>The augmented dataset consists of 5488 RGB images captured from forward-looking perspective.</div> <div>MLAD-C is designed to develop models for cloud segmentation.</div> <div>In our cloud detection approach, cloud segmentation functions as a pre-stage to cloud position estimation for sense & avoid purposes.</div> <div><br>More detailed information about MLAD-C and the developed cloud segmentation model can be found in our journal article: <br><a href="https://www.mdpi.com/2504-446X/9/1/55"><strong>A Cloud Detection System for UAV Sense and Avoid: Analysis of a Monocular Approach in Simulation and Flight Tests</strong></a></div> <h2>Directory Structure</h2> <div>MLAD-C is provided in two formats:<br> <ol> <li>augmented sensor recordings prepared for <em>YOLO-v8 </em>framework to reproduce results of journal article</li> <li>non-augmented sensor recordings in Full HD resolution</li> </ol> </div> <div>The directory structure is as follows:</div> <ul> <li>augmented_mladc <ul> <li>train <ul> <li>images</li> <li>labels</li> <li>masks</li> </ul> </li> <li>val <ul> <li>images</li> <li>labels</li> <li>masks </li> </ul> </li> <li>mladc.yaml</li> </ul> </li> <li>full_hd_mladc <ul> <li>images</li> <li>masks</li> </ul> </li> </ul> <h2>Cite</h2> <div>If you use MLAD-C, please cite the following publication: <br><br>Dudek, A.; Stütz, P. A Cloud Detection System for UAV Sense and Avoid: Analysis of a Monocular Approach in Simulation and Flight Tests. <em>Drones</em> <strong>2025</strong>, <em>9</em>, 55. https://doi.org/10.3390/drones9010055<br><br></div> <h2>Funding</h2> <div>The research project MissionLab is funded by dtec.bw – Digitalization and Technology Research Center of</div> <div>the Bundeswehr which we gratefully acknowledge. dtec.bw is funded by the European Union –</div> <div>NextGenerationEU.</div>
ShareScore
32/100
Overall dataset sharing score
Score breakdown
These five areas show where the dataset supports — or may limit — practical reuse.
- Stewardship
- 12
- Harmonization
- 4
- Access
- 16
- Reuse readiness
- 0
- Engagement
- 0
Topics
ScienceDex for faculty
Your academic CV and NIH biosketch
Make your CV in your school's format and your NIH biosketch from it, then download both as Word files.