Scoring framework of soccer matches using possession trajectory data
Geng Deng, Licheng Liu, Jie Zuo · Proceedings of the ACM Turing Celebration Conference - China · 2019
It is one of the most important activities for experts and fans to retrospect wonderful soccer matches through videos and statistical data. With the situation of football match changing rapidly, simple data combination cannot truly reflect the situation of the field. More detailed data extraction has become an important research branch in sports analysis area. In this paper, we propose a scoring frame-work for players' performance, which includes the extraction of ball-possession trajectories, the correlation analysis of possession trajectories and statistics of players' scores. The framework aims to explore a more intelligent soccer scoring system, helping the mainstream sports media improve the quality of post-game scoring and reducing the entry door threshold of score experts.