17:40 〜 18:00
[1S5-IS-2a-05] Objective detection of high-risk tackle in rugby by combination of pose estimation and machine learning
Regular
キーワード:machine learning, pose estimation, sports
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.
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.
講演PDFパスワード認証
論文PDFの閲覧にはログインが必要です。参加登録者の方は「参加者用ログイン」画面からログインしてください。あるいは論文PDF閲覧用のパスワードを以下にご入力ください。