Objective detection of high-risk tackle in rugby by combination of pose estimation and machine learning

DOI
  • NISHIO Monami
    Advanced Data Science Project, RIKEN Information R&D and Strategy Headquarters
  • NONAKA Naoki
    Advanced Data Science Project, RIKEN Information R&D and Strategy Headquarters
  • FUJIHIRA Ryo
    Advanced Data Science Project, RIKEN Information R&D and Strategy Headquarters
  • MURAKAMI Hidetaka
    Murakami Surgical Hospital
  • TAJIMA Takuya
    Division of Orthopaedic Surgery, Department of Sensory and Motor Organs, Faculty of Medicine, University of Miyazaki
  • YAMADA Mutsuo
    Faculty of Health and Sport Sciences, Ryutsu Keizai University
  • MAEDA Akira
    Hakata Knee & Sports Clinic Department of Sports Medicine and Science, Faculty of Human Health, Kurume University
  • SEITA Jun
    Advanced Data Science Project, RIKEN Information R&D and Strategy Headquarters

Description

<p>To provide suitable care for concussion, objective and timely detection of high-risk tackle is crucial in the field of contact sports, such as rugby. Currently it depends on monitoring by match officials, and there is a certain risk of missing high-risk events. A few attemps introducing video analysis have been reported, but those approaches require labeling by experts, which is skill-dependent, and also time and cost consuming. To achieve objective and timely detection of high-risk tackle, we developed a method combining pose estimation by deep-learning and pose evaluation by machine learning. From match videos of Japan Rugby Top League in 2016~2018 seasons, 238 low-risk tackle and 155 high-risk tackle were extracted. Poses of tackler and ball carrier were estimated by deep learning, then were evaluated by machine learning. The proposed method resulted AUROC-score 0.85 and outperformed the previously reported rule-based method. Also, the features extracted by the machine learning model, such as upright positions of tackler/ball carrier, tackler's arm dropped in extended position, were consistent with the known risk factors. This result indicates that our approach combining deep-learning and machine learning opens the way for objective and real-time detection of high-risk tackle in rugby and other contact sports.</p>

Journal

Keywords

Details 詳細情報について

Report a problem

Back to top