Amateur football analytics using computer vision

In recent years, there has been an interest in visual sports analytics, and especially in player and ball detection, action recognition, and camera pose estimation in various sports. The greatest interest is associated with football or soccer. The purpose of this work is the design and implementation of a low-cost methodology that extracts football analytics from simple TV broadcasts, using solely computer vision techniques. In the paper, we discuss the state of the art in this field and propose an integrated pipeline that solves the problem of player localization in the court and extracts useful insights. Technical details concerning the proposed methods that enhance track player-ball movement and camera pose, along with post-analytic results, are presented. The paper concludes with some future expansions of the proposed pipeline.

Automated summary

In recent years, there has been a growing interest in visual sports analytics, particularly in the field of football, involving player and ball detection, action recognition, and camera pose estimation. This paper proposes a low-cost methodology using computer vision techniques to extract football analytics from simple TV broadcasts. It discusses the state of the art in this field and presents an integrated pipeline for player localization and insights extraction, along with technical details and post-analytic results. The paper also suggests potential future expansions for the proposed pipeline.