---
title: HockeyRink
emoji: ⛸️
colorFrom: purple
colorTo: purple
sdk: gradio
sdk_version: 5.12.0
app_file: app.py
pinned: false
license: mit
short_description: ' A model for Precise Ice Hockey Rink Keypoint detection'
---

# Hockey Rink Keypoint Detection

<div style="background-color:#f8f9fa; color:black; border-left: 6px solid #ff9800; padding: 10px; margin: 10px 0;">

🔗 This interactive demo is powered by the <span style="color:red">HockeyRink</span> model and dataset.

- 📂 Download the dataset used in this project: <a href="https://huggingface.co/datasets/SimulaMet-HOST/HockeyRink" style="color:blue;">https://huggingface.co/datasets/SimulaMet-HOST/HockeyRink</a>
- 🤖 View details of the trained <span style="color:red">model</span>: <a href="https://huggingface.co/SimulaMet-HOST/HockeyRink" style="color:blue;">https://huggingface.co/SimulaMet-HOST/HockeyRink</a>

</div>



This repository contains a YOLOv8-based model for detecting and mapping keypoints on ice hockey rinks. The model is trained on the HockeyRink dataset, which comprises precise annotations of hockey rink landmarks.

## Features

- Accurate detection of 56 keypoint landmarks on hockey rinks
- Real-time keypoint visualization with confidence scores
- Support for various camera angles and lighting conditions
- Handles player occlusions and dynamic game situations
- Trained on diverse SHL (Swedish Hockey League) game footage

## Model Details

- Architecture: YOLOv8-Large pose estimation
- Input: RGB images (any resolution)
- Output: 56 keypoint coordinates with confidence scores
- Average Performance:
  - mAP@0.5: 97.48%
  - mAP@0.5:0.95: 76.45%
  - Precision: 96.21%
  - Recall: 96.24%

## Applications

- Camera calibration and homography estimation
- 2D/3D scene mapping
- Player tracking and analysis
- Broadcast overlay generation
- Game analytics and statistics
- AR/VR applications

## Usage

1. Upload an image containing a hockey rink view
2. The model will detect and visualize keypoints
3. Each keypoint is displayed with its ID and confidence score
4. Results can be used for further spatial analysis or visualization

## Examples

The space includes example images demonstrating the model's performance in different scenarios:
- Wide-angle rink views
- Partially occluded scenes
- Various lighting conditions
- Dynamic game situations

## Model Performance

- Performance tested across different hardware setups
- 13.64 FPS on Tesla T4 GPU
- 6.4 FPS on M3 MacBook Pro
- Handles varying lighting conditions and occlusions


<div style="background-color:#e7f3ff; color:black; border-left: 6px solid #0056b3; padding: 12px; margin: 10px 0;">

<span style="color:black; font-weight:bold;">📩 For any questions regarding this project, or to discuss potential collaboration and joint research opportunities, please contact:</span>

<ul style="color:black;">
  <li><span style="font-weight:bold; color:black;">Mehdi Houshmand</span>: <a href="mailto:mehdi@forzasys.com" style="color:blue; text-decoration:none;">mehdi@forzasys.com</a></li>
  <li><span style="font-weight:bold; color:black;">Cise Midoglu</span>: <a href="mailto:cisemidoglu@gmail.com" style="color:blue; text-decoration:none;">cisemidoglu@gmail.com</a></li>
  <li><span style="font-weight:bold; color:black;">Pål Halvorsen</span>: <a href="mailto:paalh@simula.no" style="color:blue; text-decoration:none;">paalh@simula.no</a></li>
</ul>

</div>