arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2601.00748cs.LG
收藏

一种用于足球比赛中非球位防守角色及表现评估的机器学习框架

A Machine Learning Framework for Off Ball Defensive Role and Performance Evaluation in Football

Sean Groom School of Computer Science, The University of Birmingham, Birmingham, UK(Sean Groom 计算机科学学院,英国伯明翰大学);Nottingham Forest Football Club, Nottingham, UK(诺丁汉森林足球俱乐部,英国诺丁汉);Francisco Belo Nottingham Forest Football Club, Nottingham, UK(Francisco Belo 诺丁汉森林足球俱乐部,英国诺丁汉);Axl Rice Nottingham Forest Football Club, Nottingham, UK(Axl Rice 诺丁汉森林足球俱乐部,英国诺丁汉);Liam Anderson School of Sport, Exercise and Rehabilitation Sciences, The University of Birmingham, Birmingham, UK(Liam Anderson 运动、运动康复科学学院,英国伯明翰大学)

Sean Groom, Shuo Wang, Francisco Belo, Axl Rice, Liam Anderson

AI总结:

本文提出了一种基于协变量依赖隐藏马尔可夫模型的机器学习框架,用于评估足球比赛中非球位防守角色及表现,通过直接从球员跟踪数据推断出球员标记和区域分配,实现对防守贡献的可解释评估。

摘要:

评估足球比赛中非球位防守表现具有挑战性,因为传统指标无法捕捉到限制对手行动选择和成功概率的细微协调运动。尽管广泛使用的控球价值模型在评估球位动作方面表现出色,但将其应用于防守仍受到限制。现有的反事实方法,如幽灵模型,有助于扩展这些分析,但往往依赖于模拟

英文摘要:

Evaluating off-ball defensive performance in football is challenging, as traditional metrics do not capture the nuanced coordinated movements that limit opponent action selection and success probabilities. Although widely used possession value models excel at appraising on-ball actions, their application to defense remains limited. Existing counterfactual methods, such as ghosting models, help extend these analyses but often rely on simulating "average" behavior that lacks tactical context. To address this, we introduce a covariate-dependent Hidden Markov Model (CDHMM) tailored to corner kicks, a highly structured aspect of football games. Our label-free model infers time-resolved man-marking and zonal assignments directly from player tracking data. We leverage these assignments to propose a novel framework for defensive credit attribution and a role-conditioned ghosting method for counterfactual analysis of off-ball defensive performance. We show how these contributions provide a interpretable evaluation of defensive contributions against context-aware baselines.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑