Views
No views yet
quadcopter (class 0) — Multirotor drones (DJI Mavic, Mini, etc.)fixed-wing (class 1) — Military fixed-wing drones (Shahed-131/136, Lancet, Orlan-10)| Metric | Value |
|---|---|
| mAP50 | 91.3% |
| mAP50-95 | 62.1% |
| Precision | 94.6% |
| Recall | 85.9% |
distance = (real_wingspan * focal_length) / bbox_width_px1from ultralytics import YOLO
2
3# Load model
4model = YOLO('TomSmail/drone-yolo-v1')
5
6# Run inference
7results = model.predict('image.jpg', conf=0.3)
8
9# Get detections
10for result in results:
11 for box in result.boxes:
12 class_name = result.names[int(box.cls[0])]
13 confidence = float(box.conf[0])
14 x1, y1, x2, y2 = box.xyxy[0].tolist()
15 print(f"{class_name}: {confidence:.2%}")1from drone_cv import Detector
2
3detector = Detector(config_path="configs/")
4result = detector.predict(frame)
5
6for detection in result.detections:
7 print(f"{detection.class_name}: {detection.distance_m:.1f}m")1@misc{drone-yolo-v1,
2 author = {FRAID Labs},
3 title = {Drone Detection & Distance Estimation Model},
4 year = {2026},
5 publisher = {HuggingFace},
6 url = {https://huggingface.co/TomSmail/drone-yolo-v1}
7}