Cursor Detection YOLOv8n
A YOLOv8n model trained to detect mouse cursors in screenshots and video frames.
Training Details
- Base Model: YOLOv8n (3.2M parameters)
- Training Data: Synthetic dataset generated by compositing 366 different cursor types onto 1688 website screenshots
- Dataset Size: 500 train / 100 val / 50 test
- Image Size: 640x640
- Epochs: 30
- Hardware: NVIDIA T4 GPU
Performance
| Metric | Value |
|---|---|
| mAP50 | 92.1% |
| mAP50-95 | 58.2% |
| Precision | 84.8% |
| Recall | 89.5% |
Dataset Generation
The synthetic dataset was created by:
- Loading cursor images from Fraser/cursors (366 cursor types with hotspot info)
- Loading background screenshots from naorm/website-screenshots
- Compositing cursors at random positions with alpha blending
- Generating YOLO format bounding box labels
Usage
from ultralytics import YOLO
# Load model
model = YOLO("AdithyaSK/cursor-detection-yolov8n/best.pt")
# Detect cursor in an image
results = model("screenshot.jpg")
results[0].show()
License
AGPL-3.0 (same as Ultralytics YOLOv8)