Enhancing Soccer Camera Calibration Through Keypoint Exploitation

TL;DR

This paper presents a multi-stage pipeline that improves soccer camera calibration accuracy by exploiting geometric features of the pitch, combining deep learning detection with geometric constraints and a voter algorithm, validated on a large dataset.

Contribution

It introduces a novel pipeline that significantly increases calibration points using geometric features and deep learning, winning the SoccerNet Calibration Challenge 2023.

Findings

Achieved top performance in the SoccerNet Calibration Challenge 2023

Enhanced calibration accuracy by exploiting pitch geometry and geometric constraints

Demonstrated effectiveness on the largest available football broadcast dataset

Abstract

Accurate camera calibration is essential for transforming 2D images from camera sensors into 3D world coordinates, enabling precise scene geometry interpretation and supporting sports analytics tasks such as player tracking, offside detection, and performance analysis. However, obtaining a sufficient number of high-quality point pairs remains a significant challenge for both traditional and deep learning-based calibration methods. This paper introduces a multi-stage pipeline that addresses this challenge by leveraging the structural features of the football pitch. Our approach significantly increases the number of usable points for calibration by exploiting line-line and line-conic intersections, points on the conics, and other geometric features. To mitigate the impact of imperfect annotations, we employ data fitting techniques. Our pipeline utilizes deep learning for keypoint and line detection and incorporates geometric constraints based on real-world pitch dimensions. A voter algorithm iteratively selects the most reliable keypoints, further enhancing calibration accuracy. We evaluated our approach on the largest football broadcast camera calibration dataset available, and secured the top position in the SoccerNet Camera Calibration Challenge 2023 [arXiv:2309.06006], which demonstrates the effectiveness of our method in real-world scenarios. The project code is available at https://github.com/NikolasEnt/soccernet-calibration-sportlight .