You can deploy this model and start earning money today!

martinjolif/
yolo-football-ball-detection

Name: yolo-football-ball-detection
Availability: InStock

object-detection

martinjolif/football-ball-detection

Ultralytics/YOLO11

finetune

agpl-3.0

Views

No views yet

version: 0.1.0

Football Ball Detection (YOLO11n)

This model is a fine-tuned YOLO11n object detector trained to identify ball in football (soccer) match images.
It was trained on the martinjolif/football-ball-detection dataset and is suitable to identify football ball.

Detected Classes

ball

Training Details

Base model: Ultralytics YOLO11n
Task: Object Detection
Dataset: martinjolif/football-ball-detection
License: AGPL-3.0

Evaluation Results

Results on the test split using standard object detection metrics (Precision, Recall, F1, mAP50, mAP50-95):

Class	Images	Instances	Box-P	R	F1	mAP50	mAP50-95
ball	125	125	0.8879	0.8000	0.8417	0.8910	0.5510

Prediction Examples:

Notes

Excellent performance on ball detection, with relatively high recall and mAP.
Ball detection is challenging due to small object size and motion blur.

Intended Use

Football match analytics
Ball tracking
Annotation assistance for sports datasets
Research in sports computer vision

Limitations

Performance may drop on non-broadcast footage, unusual camera angles, or low-resolution images.

Usage

wget https://huggingface.co/martinjolif/yolo-football-ball-detection/blob/main/yolo-football-ball-detection.pt

bash

from ultralytics import YOLO
model = YOLO("yolo-football-ball-detection.pt")

Citation

If you use this model or the dataset, please cite the dataset authors and Ultralytics YOLO accordingly.