Detection of Hitting Point Area Using Footwork Trajectory in Badminton Video
Naoki Tanaka, Hidehiko Shishido, Masashi Suita, Takeshi Nishijima, Yoshinari Kameda, Itaru Kitahara · 2022 IEEE 11th Global Conference on Consumer Electronics (GCCE) · 2022
Video analysis is considered necessary in competitive sports, and various studies have been conducted on the subject. Particularly in badminton, shot information is essential primary data for performance analysis. In badminton singles, the base is typically near the center of the court. After releasing a shot, the player returns to the base and prepares for the opponent’s shot. This movement is considered as basic footwork in badminton. Badminton performance analysis using software utilizes player position data of a court area divided into nine sections. This study proposes a method for detecting the hitting point area using the footwork trajectory of the player and nine-division area. In a demonstration experiment using a monocular camera, the hitting point detection accuracy on the front court and backcourt is 85.9 % and 70.5 %, respectively. Thus, we confirm that the hitting point area can be detected with high accuracy from the footwork trajectory of the player.