Contextual Sprint Classification in Soccer Based on Deep Learning
This work addresses a scalability issue for sports science researchers and practitioners in soccer by automating sprint classification, though it is incremental as it builds on existing contextualization efforts.
The paper tackles the problem of manually classifying hundreds of sprints in soccer matches by proposing a deep learning framework that automatically categorizes sprints into 15 contextual categories with 77.65% accuracy, enabling scalable analysis of physical-tactical requirements.
The analysis of high-intensity runs (or sprints) in soccer has long been a topic of interest for sports science researchers and practitioners. In particular, recent studies suggested contextualizing sprints based on their tactical purposes to better understand the physical-tactical requirements of modern match-play. However, they have a limitation in scalability, as human experts have to manually classify hundreds of sprints for every match. To address this challenge, this paper proposes a deep learning framework for automatically classifying sprints in soccer into contextual categories. The proposed model covers the permutation-invariant and sequential nature of multi-agent trajectories in soccer by deploying Set Transformers and a bidirectional GRU. We train the model with category labels made through the collaboration of human annotators and a rule-based classifier. Experimental results show that our model classifies sprints in the test dataset into 15 categories with the accuracy of 77.65%, implying the potential of the proposed framework for facilitating the integrated analysis of soccer sprints at scale.