Counter-UAS & defenceUAV & Aerial View: Battle Tank Detection
Synthetic aerial dataset for battle tank detection from UAV and drone perspectives. 3,000 YOLO-annotated images with 164 open-source samples on Kaggle.
- Size
- 3,000 images
- Format
- YOLO
Drone and counter-UAS datasets
4 datasets
Counter-UAS & defenceSynthetic aerial dataset for battle tank detection from UAV and drone perspectives. 3,000 YOLO-annotated images with 164 open-source samples on Kaggle.
Counter-UAS & defenceSynthetic airport drone detection dataset: 1,200 YOLO images, small-object focus, adverse weather, bird-vs-drone labels. GDPR compliant.
Counter-UAS & defenceSynthetic drone swarm dataset for Counter-UAS training. 5-15 drones per frame, 10-50 pixel objects, adverse weather. 1,000+ YOLO-annotated images.
Counter-UAS & defenceSynthetic drone-perspective dataset distinguishing civilians from armed personnel. 800 YOLO images for aerial surveillance AI training.
Public drone datasets (Anti-UAV, DUT Anti-UAV, Drone-vs-Bird) are small, filmed at one or two sites, and licensed for research. The sets below are synthetic, so they cover the scenes a counter-UAS system actually watches: runway approaches, perimeter fences, skies with birds and aircraft as hard negatives, and swarms of small targets a few pixels wide.
Labels are YOLO boxes; the airport set includes evaluation clips. Licences are one-time, research or commercial, with larger packs for teams training on many scenes.
Prices
| Images | Research | Commercial | Order |
|---|---|---|---|
| 1,000 | $149 | $590 | On the dataset page |
| 5,000 | Not offered | $2,400 | Order 5,000 |
| 10,000 | Not offered | $4,500 | Order 10,000 |
| 20,000 | Not offered | $8,500 | Order 20,000 |
Larger packs are assembled for your order and delivered as a download link within five working days. Prices in USD, excl. VAT, one-time, per dataset.
Read next
Guide
Synthetic Data for YOLO Training: A Step-by-Step Guide
Train YOLOv8 or YOLOv11 on synthetic data — dataset layout, data.yaml, training commands, domain-gap fixes, and synthetic vs manual labeling results.
Guide
Synthetic Data vs Real Data for Computer Vision: A Practical Comparison
Head-to-head comparison of synthetic and real data for CV — cost, privacy, edge cases, annotation quality, and how to close the domain gap.
Questions
Labelled images or clips of unmanned aircraft seen from ground cameras, other aircraft or radar-cued EO sensors, used to train detectors that separate drones from birds, aircraft and clutter.
Yes. The airport drone set labels birds and aircraft so a detector learns not to alarm on them; the swarm set adds clutter, haze and distance.
Yes. The commercial licence ($590 per 1,000 images, one-time) covers one organisation; larger packs and custom scenes are available. The data is synthetic and carries no sensor signatures or geolocation.
More collections
Send five frames from your cameras. We reply within one working day with the fastest way to fix it — a catalogue dataset, a stress test or a custom pack.