HockeyRink: A Dataset for Precise Ice Hockey Rink Keypoint Mapping and Analytics

🏒 Overview

The HockeyRink dataset consists of 661 high-resolution frames (1920×1080) from SHL (Swedish Hockey League) games. The dataset is specifically designed for detecting and mapping 56 keypoints on hockey rinks to facilitate camera calibration, homography estimation, and advanced sports analytics.

📥 Access the Dataset

The dataset is hosted on Hugging Face:

🔗 Dataset Path: HockeyRink on Hugging Face

🎯 Pretrained Model

We provide a trained keypoint detection model, available on Hugging Face.

🔗 Trained Model: HockeyRink Model

🚀 Live Demo

Explore the HockeyRink keypoint detection demo on Hugging Face Spaces.

🔗 HockeyRink Demo: Hugging Face Space

🤝 Citation

If you use this dataset or model in your research, please cite:

@inproceedings{HockeyRink,
    title = {{HockeyRink: A Dataset for Precise Ice Hockey Rink Keypoint Mapping and Analytics}},
    author = {Houshmand Sarkhoosh, Mehdi and Gautam, Sushant and Midoglu, Cise and Sabet, Saeed Shafiee and Kupka, Tomas and Halvorsen, Pål},
    publisher = {Association for Computing Machinery},
    booktitle = {Proceedings of the 16th ACM Multimedia Systems Conference},
    address = {New York, NY, USA},
    url = {https://doi.org/10.1145/3712676.3718338},
    isbn = {9798400714672},
    location = {Stellenbosch, South Africa},
    year = {2025},
    doi={10.1145/3712676.3718338}
}

📩 Contact

For inquiries, collaborations, or questions:

• 📧 Mehdi Houshmand: mehdi@forzasys.com
• 📧 Cise Midoglu: cise@forzasys.com
• 📧 Pål Halvorsen: paalh@simula.no

---

⚡ HockeyRink is part of ongoing AI-driven sports analytics research.