The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
L'acquisition automatique de données de stratégie de jeu est importante pour la réalisation de systèmes professionnels d'analyse de stratégie en fournissant des valeurs d'évaluation telles que le statut de l'équipe et l'efficacité des jeux. Le facteur clé qui influence les performances de l'acquisition de données stratégiques dans le jeu de volley-ball est le rôle inconnu des joueurs. Le rôle du joueur désigne la position ayant une signification dans le jeu de chaque joueur dans la formation de l'équipe, comme le passeur, l'attaquant et le bloqueur. Le rôle du joueur inconnu rend chaque joueur peu fiable et perd la contribution de chaque joueur à l’analyse stratégique. Cet article propose une fonctionnalité de mouvement d'équipe au niveau du terrain et une courbe de performance des joueurs pour traiter les rôles inconnus des joueurs dans l'acquisition de données stratégiques. Premièrement, la fonctionnalité de mouvement d'équipe au niveau du terrain est proposée pour la détection du statut tactique de l'équipe. Cette fonctionnalité réduit l'influence des informations individuelles sur les joueurs en additionnant la densité de mouvement relative du ballon de tous les joueurs dans la zone divisée du terrain, ce qui correspond aux différents jeux. Deuxièmement, les courbes de performance des joueurs sont proposées pour l'acquisition des variables d'efficacité en jeu d'attaque. Les candidats aux rôles de joueur sont détectés par trois caractéristiques qui représentent l'ensemble du processus par lequel un joueur commence à se précipiter (ou sauter) vers le ballon et à frapper le ballon : la distance relative du ballon, le mouvement d'approche du ballon et la fonction de mouvement d'attaque. Avec les trajectoires de balle 3D et les positions de plusieurs joueurs suivies à partir de vidéos de jeux de volley-ball multi-vues, le taux de détection expérimentale de l'état de chaque équipe (état d'attaque, prêt à la défense, prêt à l'attaque et état offensif) est de 75.2 %, 84.2 %, 79.7 %. et 81.6%. Et pour l'acquisition des variables d'efficacité de l'attaque, la précision moyenne de la zone définie, le nombre d'attaquants disponibles, le tempo de l'attaque et le nombre de bloqueurs sont de 100 %, 100 %, 97.8 % et 100 %, ce qui permet d'obtenir une amélioration moyenne de 8.3 %. par rapport à l’acquisition manuelle.
Xina CHENG
Waseda University
Takeshi IKENAGA
Waseda University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Xina CHENG, Takeshi IKENAGA, "Court-Divisional Team Motion and Player Performance Curve Based Automatic Game Strategy Data Acquisition for Volleyball Analysis" in IEICE TRANSACTIONS on Fundamentals,
vol. E101-A, no. 11, pp. 1756-1765, November 2018, doi: 10.1587/transfun.E101.A.1756.
Abstract: Automatic game strategy data acquisition is important for the realization of the professional strategy analysis systems by providing evaluation values such as the team status and the efficacy of plays. The key factor that influences the performance of the strategy data acquisition in volleyball game is the unknown player roles. Player role means the position with game meaning of each player in the team formation, such as the setter, attacker and blocker. The unknown player role makes individual player unreliable and loses the contribution of each player in the strategy analysis. This paper proposes a court-divisional team motion feature and a player performance curve to deal with the unknown player roles in strategy data acquisition. Firstly, the court-divisional team motion feature is proposed for the team tactical status detection. This feature reduces the influence of individual player information by summing up the ball relative motion density of all the players in divided court area, which corresponds to the different plays. Secondly, the player performance curves are proposed for the efficacy variables acquisition in attack play. The player roles candidates are detected by three features that represent the entire process of a player starting to rush (or jump) to the ball and hit the ball: the ball relative distance, ball approach motion and the attack motion feature. With the 3D ball trajectories and multiple players' positions tracked from multi-view volleyball game videos, the experimental detection rate of each team status (attack, defense-ready, offense-ready and offense status) are 75.2%, 84.2%, 79.7% and 81.6%. And for the attack efficacy variables acquisition, the average precision of the set zone, the number of available attackers, the attack tempo and the number of blockers are 100%, 100%, 97.8%, and 100%, which achieve 8.3% average improvement compared with manual acquisition.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E101.A.1756/_p
Copier
@ARTICLE{e101-a_11_1756,
author={Xina CHENG, Takeshi IKENAGA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Court-Divisional Team Motion and Player Performance Curve Based Automatic Game Strategy Data Acquisition for Volleyball Analysis},
year={2018},
volume={E101-A},
number={11},
pages={1756-1765},
abstract={Automatic game strategy data acquisition is important for the realization of the professional strategy analysis systems by providing evaluation values such as the team status and the efficacy of plays. The key factor that influences the performance of the strategy data acquisition in volleyball game is the unknown player roles. Player role means the position with game meaning of each player in the team formation, such as the setter, attacker and blocker. The unknown player role makes individual player unreliable and loses the contribution of each player in the strategy analysis. This paper proposes a court-divisional team motion feature and a player performance curve to deal with the unknown player roles in strategy data acquisition. Firstly, the court-divisional team motion feature is proposed for the team tactical status detection. This feature reduces the influence of individual player information by summing up the ball relative motion density of all the players in divided court area, which corresponds to the different plays. Secondly, the player performance curves are proposed for the efficacy variables acquisition in attack play. The player roles candidates are detected by three features that represent the entire process of a player starting to rush (or jump) to the ball and hit the ball: the ball relative distance, ball approach motion and the attack motion feature. With the 3D ball trajectories and multiple players' positions tracked from multi-view volleyball game videos, the experimental detection rate of each team status (attack, defense-ready, offense-ready and offense status) are 75.2%, 84.2%, 79.7% and 81.6%. And for the attack efficacy variables acquisition, the average precision of the set zone, the number of available attackers, the attack tempo and the number of blockers are 100%, 100%, 97.8%, and 100%, which achieve 8.3% average improvement compared with manual acquisition.},
keywords={},
doi={10.1587/transfun.E101.A.1756},
ISSN={1745-1337},
month={November},}
Copier
TY - JOUR
TI - Court-Divisional Team Motion and Player Performance Curve Based Automatic Game Strategy Data Acquisition for Volleyball Analysis
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1756
EP - 1765
AU - Xina CHENG
AU - Takeshi IKENAGA
PY - 2018
DO - 10.1587/transfun.E101.A.1756
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E101-A
IS - 11
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - November 2018
AB - Automatic game strategy data acquisition is important for the realization of the professional strategy analysis systems by providing evaluation values such as the team status and the efficacy of plays. The key factor that influences the performance of the strategy data acquisition in volleyball game is the unknown player roles. Player role means the position with game meaning of each player in the team formation, such as the setter, attacker and blocker. The unknown player role makes individual player unreliable and loses the contribution of each player in the strategy analysis. This paper proposes a court-divisional team motion feature and a player performance curve to deal with the unknown player roles in strategy data acquisition. Firstly, the court-divisional team motion feature is proposed for the team tactical status detection. This feature reduces the influence of individual player information by summing up the ball relative motion density of all the players in divided court area, which corresponds to the different plays. Secondly, the player performance curves are proposed for the efficacy variables acquisition in attack play. The player roles candidates are detected by three features that represent the entire process of a player starting to rush (or jump) to the ball and hit the ball: the ball relative distance, ball approach motion and the attack motion feature. With the 3D ball trajectories and multiple players' positions tracked from multi-view volleyball game videos, the experimental detection rate of each team status (attack, defense-ready, offense-ready and offense status) are 75.2%, 84.2%, 79.7% and 81.6%. And for the attack efficacy variables acquisition, the average precision of the set zone, the number of available attackers, the attack tempo and the number of blockers are 100%, 100%, 97.8%, and 100%, which achieve 8.3% average improvement compared with manual acquisition.
ER -