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 150 open-source samples on Kaggle.
- Size
- 3,000 images
- Format
- YOLO
Drone and aerial
From a moving drone, three civilians walk a track and near the end a main battle tank drives in beside the houses.
This clip uses the same aerial scene as the armed person clip. A drone flies over dry farmland with dirt tracks and scrub, and a village of flat-roofed houses sits at the horizon. The camera keeps moving, so the horizon and the fields shift throughout the six seconds.
For most of the clip the only subjects are three civilians walking along a track. Each is boxed in green and labelled civilian. They are there to show that the scene has people in it, and that a detector looking for vehicles should not react to them.
Near the end, a main battle tank drives in from the right edge of the frame, beside the houses. It is boxed in red and labelled military tank. The tank is large and has a clear outline from above, and it enters at the edge of the frame, where a detector has to pick it up as soon as it appears. The boxes are the output of a trained detector, drawn onto the clip for illustration.
The original drone footage, without the tank, is shown lower on this page, and the tank was generated into the empty scene. The dataset behind this clip holds 3,000 images with the single class battle_tank in YOLO format. A free 150-image sample is published on Kaggle and Hugging Face so you can test your own model before licensing the full set.
The generated clip above uses this same camera and scene.
Dataset
Counter-UAS & defenceSynthetic aerial dataset for battle tank detection from UAV and drone perspectives. 3,000 YOLO-annotated images with 150 open-source samples on Kaggle.
More clips

A person walks along a lit shop front at night with a handgun in the right hand, followed frame by frame by a red weapon box.

A person turns and walks past a shop door at night with a large kitchen knife held low in the right hand.

From a moving drone, three civilians walk a dirt track and a group of armed figures enters from the left.
Send 5–20 photos of your empty scenes and we render the event into them, as images or video clips with boxes, tracking IDs and event times.