Simon9/football-player-detection-roboflow

Football Player Detection (Roboflow)

YOLOv8 model for detecting players, goalkeepers, referees, and the ball in football/soccer videos.

Model Details

• Model ID: football-players-detection-3zvbc/11
• Platform: Roboflow
• Architecture: YOLOv8
• Classes: Ball (0), Goalkeeper (1), Player (2), Referee (3)

Quick Start

Installation

pip install inference-gpu  # or inference for CPU
pip install supervision

Basic Usage

from inference import get_model
import supervision as sv

# Initialize model
api_key = "YOUR_ROBOFLOW_API_KEY"
model = get_model(
    model_id="football-players-detection-3zvbc/11",
    api_key=api_key
)

# Run inference
result = model.infer("image.jpg", confidence=0.3)[0]
detections = sv.Detections.from_inference(result)

print(f"Detected {len(detections)} objects")

Using the Wrapper

from player_inference import FootballPlayerDetector
import os

detector = FootballPlayerDetector(api_key=os.getenv("ROBOFLOW_API_KEY"))
results = detector.predict("image.jpg", confidence=0.3)

Use Cases

• Player tracking and identification
• Team classification
• Ball tracking
• Referee detection
• Sports analytics and statistics
• Tactical analysis

Model Performance

This model has been trained on the Roboflow Football Players Detection dataset with high accuracy for real-time detection.

API Key

You need a Roboflow API key to use this model. Get one at roboflow.com.

Citation

If you use this model, please cite:

@misc{football-players-detection,
    title={Football Players Detection},
    author={Roboflow},
    year={2024},
    url={https://universe.roboflow.com/roboflow-jvuqo/football-players-detection-3zvbc}
}