Yoshimitsu Aoki at Keio University, Japan, describes his approach to using AI technology in sports to analyze and improve the performance of athletes and developing team tactics, with a focus on rugby players.
The Keio Research Highlights website offers more details about this and other recent research being conducted by researchers at Keio University including AI in sports science by Yoshimitsu Aoki.
Keio Research Highlights website
https://research-highlights.keio.ac.jp/2019/12/a.html
YouTube video of Yoshimitsu Aoki discussing his research on AI in sports
https://youtu.be/ofSVsUSLkAU
"In rugby, to analyze formation using ball and player position, it is necessary to detect play events such as scrums and lineouts," explains Yoshimitsu Aoki, a professor at the Faculty of Science and Technology at Keio University. "Until now, these tasks have been carried out by specialist analysts. The aim of my research is to automate these tasks using 'AI image technology.' Specifically, the ball and players are automatically detected from the video, and passages of play such as passes, kicks, and scrums are recognized based on such information."
Aoki and his colleagues are developing an innovative rugby video analysis system using deep learning technology. They are able to track players using an object detection method called 'Faster RCNN.' RCNN, or Regions with Convolutional Neural Networks, are improved version of the more conventional Convolutional Neural Networks (CNN) that allow for object detection in addition to image classification. "We then input rugby images as teacher data and performed additional learning using CNN," says Aoki. "Sequences of play are identified by giving time-series neural networks with extracted features such as player and ball position information."
As shown in the video, the ball and players are accurately detected and tracked, while their positions are mapped on the field. Using this method, passages of play can be automatically estimated and tagged so that a user can easily search for the desired sequence.
"Using this system, statistical information from sports matches can be obtained rapidly. We are planning to apply this technology to other sports and action recognition issues."
References
1. Hakozaki, Noki Kato, Masamoto Tanabiki, Junko Furuyama, Yuji Sato, and Yoshimitsu Aoki, "Swimmer's stroke estimation using CNN and MultiLSTM", Journal of Signal Processing, Vol. 22, No. 4, pp. 219-222, July 2018.
https://doi.org/10.2299/jsp.22.219
2. Christian Lanius, Daisuke Kobayashi, Kazushige Ouchi, and Yoshimitsu Aoki, "Single Image, Context Aware Action Estimation in Sports", 14th International Conference on Signal Image Technology and Internet Based Systems 2018.
https://ieeexplore.ieee.org/document/8706193
3. Shuto Horie, Yuji Sato, Junko Furuyama, Masamoto Tanabiki and Yoshimitsu Aoki, "Shot Detection in Racket Sport Video at the Frame Level Using A Recurrent Neural Network", 15th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS) 2019 (in press).
Websites
Keio University
https://www.keio.ac.jp/en/
Keio Research Highlights
https://research-highlights.keio.ac.jp/
About Keio University
Keio University is a private, comprehensive university with six major campuses in the Greater Tokyo area along with a number of affiliated academic institutions. Keio prides itself on educational and research excellence in a wide range of fields and its state-of-the-art university hospital.
Keio was founded in 1858, and it is Japan's first modern institution of higher learning. Over the last century and a half, it has evolved into and continues to maintain its status as a leading university in Japan through its ongoing commitment to producing leaders of the future. Founder Yukichi Fukuzawa, a highly respected educator and one of the most important intellectuals of modern Japan, aspired for Keio to be a pioneer of new discoveries and contribute to society through learning.
Further information
Keio University
Office of Research Development and Sponsored Projects
2-15-45 Mita, Minato-ku, Tokyo 108-8345 Japan
E-mail: keio-rpr@adst.keio.ac.jp
SOURCE Keio University