Soccer line mark segmentation and classification with stochastic watershed transform

TL;DR

This paper introduces a robust stochastic watershed transform method for accurate segmentation and classification of soccer line markings, improving camera calibration for augmented reality sports applications.

Contribution

A novel stochastic watershed approach that effectively handles radial distortion and occlusions for soccer line detection, outperforming existing methods.

Findings

More robust line detection in challenging conditions

Higher accuracy than traditional edge and Hough transform methods

Effective on a diverse public dataset

Abstract

Augmented reality applications are beginning to change the way sports are broadcast, providing richer experiences and valuable insights to fans. The first step of augmented reality systems is camera calibration, possibly based on detecting the line markings of the playing field. Most existing proposals for line detection rely on edge detection and Hough transform, but radial distortion and extraneous edges cause inaccurate or spurious detections of line markings. We propose a novel strategy to automatically and accurately segment and classify line markings. First, line points are segmented thanks to a stochastic watershed transform that is robust to radial distortions, since it makes no assumptions about line straightness, and is unaffected by the presence of players or the ball. The line points are then linked to primitive structures (straight lines and ellipses) thanks to a very efficient procedure that makes no assumptions about the number of primitives that appear in each image. The strategy has been tested on a new and public database composed by 60 annotated images from matches in five stadiums. The results obtained have proven that the proposed strategy is more robust and accurate than existing approaches, achieving successful line mark detection even in challenging conditions.