Soccer Field Line Segmentation and Localization with Geometrical Consistency Fine-Tuning

This study introduces a framework to the camera calibration problem in broadcast soccer videos, focusing on accurately localizing field line endpoints. These endpoints are crucial for homography estimation. Our proposed framework, a unique two-stage process, involves semantic segmentation-based endpoint prediction and homography computation for estimating camera parameters. We adopt the transformer-based Seg-former-B3 model, fine-tuned on high-resolution field images, and train it using the PyTorch-Lightning framework. To overcome limitations in raw segmentation outputs, we design a dedicated post-processing pipeline that integrates Hough Transform to enforce line-level geometric consistency and morphological operations to eliminate noise and restore spatial continuity of field markings. This hybrid approach significantly improves endpoint precision and results in more reliable camera calibration.