3D Tracking of Multiple Drones Based on Particle Swarm Optimization

Dataset is available under the Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) license.

=======================Summary=======================This dataset contains data showing a group of one or more drones (drone swarm) roaming around closed 3D space.The purpose of this dataset is to train and validate the position tracking of drones on images. This can be done using the 3D coordinates of each drone or using segmentation masks for a machine learning related approach.Training data is split across three sequences (S1, S2, and S3) which were generated using Unreal Engine with Microsoft AirSim plugin. Each sequence is slightly modified to introduce more diversity in the dataset.Validation data (S4, S5) is based on recordings performed in the Human Motion Laboratory located inside the Research and Development Center of the Polish-Japanese Academy of Information Technology.The simulation sequences used a drone model DJI Mavic 2 Pro by MattMaksymowicz, CC Attribution, https://sketchfab.com/3d-models/dji-mavic-2-pro-3e5b8566dbe24f4ba65473179650abd1.

All documents and papers that use the dataset must acknowledge the use of the dataset by including a citation of the following paper: Krzeszowski, T., Switonski, A., Zielinski, M., Wojciechowski, K., Rosner, J. (2023). 3D Tracking of Multiple Drones Based on Particle Swarm Optimization. In: Mikyška, J., de Mulatier, C., Paszynski, M., Krzhizhanovskaya, V.V., Dongarra, J.J., Sloot, P.M. (eds) Computational Science – ICCS 2023. ICCS 2023. Lecture Notes in Computer Science, vol 10476. Springer, Cham. https://doi.org/10.1007/978-3-031-36027-5_18

=======================Dataset sequences=======================S1: 2 enlarged drones based on DJI Mavic 2 Pro. The second drone follows the first one with a delay of about 1.5 seconds.Length: 20 secondsFramerate: 25 FPSNumber of cameras: 8Tracking from frame: 60

S2: 4 drones based on DJI Mavic 2 Pro. The second drone follows the first one and the fourth drone follows the third one. Each drone has a fixed z position (with small fluctuations)Length: 10 secondsFramerate: 25 FPSNumber of cameras: 8Tracking from frame: 35

S3: 10 drones with custom model. All drones move the same path however, each one has some fixed offset applied in all axes.Additionally, the scene was expanded to a 2:1 scale.Length: 10 secondsFramerate: 25 FPSNumber of cameras: 8Tracking from frame: 20

S4: 1 real drone. It is controlled in real-time.Length: 59 secondsFramerate: 25 FPSNumber of cameras: 4Tracking from frame: 60

S5: 1 real drone (DJI Mavic 2). It is controlled in real-time.Length: 120 secondsFramerate: 25 FPSNumber of cameras: 4Tracking from frame: 130

More details regarding data format are stored inside the "file description" directory.

=======================Further information=======================For any questions, comments or other issues please contact  Tomasz Krzeszowski .