Official confirmed
The dataset for drone based detection and tracking is released, including both image/video, and annotations.
License: Unknown Unknown Checked 16d ago
Reviewing Aerial AI and Dataset Sources
A provenance-first review flow for aerial datasets and model repositories.
Last reviewed 8/7/2026. Data checked within the review cycle.
Review cycles are documented on the Methodology page. Methodology
validation Reviewed 8/7/2026
Problem definition
Aerial datasets and models are published with varying metadata quality; how do I verify the ones I plan to use?
Steps
- Inspect the dataset record
Open the dataset repository and confirm the annotation format and license before training.
- Inspect the model record
Check the model framework repository license and its documented training flow.
- Keep provenance
Record the dataset version and model export settings so results are reproducible.
Guide
Evidence
Check the repository description, license object, last update and response hash before using a model or dataset.
Judgment criteria
- A dataset is usable when its license and annotation format are explicit.
- A model record is usable when the training and export flow is documented.
Common risks
- Training on a dataset whose license does not permit the intended use.
- Reporting results without recording dataset version and evaluation protocol.
Checklist
Related technical resources
Official confirmed
Ultralytics YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking
AGPL-3.0 Inferred Checked 16d ago