TY - GEN
T1 - Generating defensive plays in basketball games
AU - Chen, Chieh Yu
AU - Zheng, Wen Hao
AU - Lai, Wenze
AU - Wang, Yu-Shuen
AU - Hsieh, Hsin Ying
AU - Chuang, Jung-Hong
N1 - Publisher Copyright:
© 2018 Copyright held by the owner/author(s). Publication rights licensed to ACM.
PY - 2018/10/15
Y1 - 2018/10/15
N2 - In this paper, we present a method to generate realistic defensive plays in a basketball game based on the ball and the offensive team's movements. Our system allows players and coaches to simulate how the opposing team will react to a newly developed offensive strategy for evaluating its effectiveness. To achieve the aim, we train on the NBA dataset a conditional generative adversarial network that learns spatio-temporal interactions between players' movements. The network consists of two components: a generator that takes a latent noise vector and the offensive team's trajectories as input to generate defensive team's trajectories; and a discriminator that evaluates the realistic degree of the generated results. Since a basketball game can be easily identified as fake if the ball handler, who is not defended, does not shoot the ball or cut into the restricted area, we add the wide open penalty to the objective function to assist model training. To evaluate the results, we compared the similarity of the real and the generated defensive plays, in terms of the players' movement speed and acceleration, distance to defend ball handlers and non- ball handlers, and the frequency of wide open occurrences. In addition, we conducted a user study with 59 participants for subjective tests. Experimental results show the high fidelity of the generated defensive plays to real data and demonstrate the feasibility of our algorithm.
AB - In this paper, we present a method to generate realistic defensive plays in a basketball game based on the ball and the offensive team's movements. Our system allows players and coaches to simulate how the opposing team will react to a newly developed offensive strategy for evaluating its effectiveness. To achieve the aim, we train on the NBA dataset a conditional generative adversarial network that learns spatio-temporal interactions between players' movements. The network consists of two components: a generator that takes a latent noise vector and the offensive team's trajectories as input to generate defensive team's trajectories; and a discriminator that evaluates the realistic degree of the generated results. Since a basketball game can be easily identified as fake if the ball handler, who is not defended, does not shoot the ball or cut into the restricted area, we add the wide open penalty to the objective function to assist model training. To evaluate the results, we compared the similarity of the real and the generated defensive plays, in terms of the players' movement speed and acceleration, distance to defend ball handlers and non- ball handlers, and the frequency of wide open occurrences. In addition, we conducted a user study with 59 participants for subjective tests. Experimental results show the high fidelity of the generated defensive plays to real data and demonstrate the feasibility of our algorithm.
KW - Basketball
KW - Conditional adversarial network
KW - Defensive strategies
UR - http://www.scopus.com/inward/record.url?scp=85058242416&partnerID=8YFLogxK
U2 - 10.1145/3240508.3240670
DO - 10.1145/3240508.3240670
M3 - Conference contribution
AN - SCOPUS:85058242416
T3 - MM 2018 - Proceedings of the 2018 ACM Multimedia Conference
SP - 1580
EP - 1588
BT - MM 2018 - Proceedings of the 2018 ACM Multimedia Conference
PB - Association for Computing Machinery, Inc
T2 - 26th ACM Multimedia conference, MM 2018
Y2 - 22 October 2018 through 26 October 2018
ER -