Action Recognition in Sports Video Considering Location Information

EasyChair Preprint no. 2677

Abstract

The purpose of this study is to develop a tactics analysis system using image recognition for rugby. With the Rugby World Cup in 2019 and the Tokyo Olym-pics in 2020, demand for sports video analysis is increasing. Rugby has more complicated play such as dense play than other sports, and the ball is hidden be-tween players, making it difficult to track. By developing a high-precision analy-sis technology for rugby with few research cases, we thought that it could be used for other sports and industrial fields other than sports. In this research, we propose a method that adds spatial information to time-series information as a new feature. Using the coordinates obtained by projectively transforming the match video onto the bird's-eye view image, play classification was performed using the player position, the ball position, and the dense area position as feature amounts. Also, in order to further improve the detection accuracy of the bounda-ries between plays, attention was paid to the positional relationship of each player on the field.

Keyphrases: Ball position, dense area, Dense play, feature amount, handcraft feature, heatmap feature, Heatmap features, kick counter, Player position, Subdivision of play area

@Booklet{EasyChair:2677,
  author = {Rina Ichige and Yoshimitsu Aoki},
  title = {Action Recognition in Sports Video Considering Location Information},
  howpublished = {EasyChair Preprint no. 2677},

  year = {EasyChair, 2020}}