AI Takes the Lead in Hockey: Waterloo Researchers and Stathletes Partner to Automate Player Tracking Revolutionizing Hockey Analytics: University of Waterloo Utilizes AI for Lightning-Fast Data Analysis

A Snapshot of a Professional Hockey Game Broadcast by the National Hockey League
Credit: Stathletes

A team of experts from the University of Waterloo received significant help from cutting-edge artificial intelligence (AI) tools in collecting and examining data from high-level hockey matches with unprecedented speed and precision, which could prove immensely beneficial for the sports industry. Their research, titled "Tracking and Identification of Players in Ice Hockey," has been published in the journal Expert Systems With Applications.

Currently, the rapidly growing field of hockey analytics relies on labor-intensive video analysis of games. This information plays a crucial role in making important decisions about players' careers, especially in the National Hockey League (NHL).

Hockey players are known for their fast and dynamic movement on the ice, often making sudden and unpredictable changes in direction. In addition, identifying players based on their jersey numbers and names can be challenging due to the fast pace of the game. This makes manually tracking and analyzing players during a game extremely difficult and prone to human error.

To overcome these challenges, the team of researchers, led by Dr. Alexander Clausi, collaborated with Dr. John Zelek, a professor in the Department of Systems Design Engineering at Waterloo, research assistant professor Yuhao Chen, and a team of graduate students to develop an AI tool that uses deep learning techniques to automate and enhance player tracking analysis.

Their partner in this research is Stathletes, a company based in Ontario that specializes in providing professional hockey performance data and analytics. The team manually annotated the video footage of NHL games frame-by-frame, identifying teams, players, and their movements on the ice. This data was then used to train the AI system to analyze and produce accurate predictions.

The system was put to the test, and the results were impressive. It achieved an accuracy rate of 94.5% in player tracking, 97% in team identification, and 83% in identifying individual players.

While the team continues to refine the prototype, Stathletes is already using the system to annotate video footage of hockey games. Moreover, the potential for commercialization extends beyond hockey as the system can be retrained to analyze other team sports such as soccer or field hockey.

David Lamy
David Lamy Author
David Lamy owns the Bachelor in Atmospheric Science Degree. He is associated with Industry News USA from last 2 years. With proficiency in his work, David obtained a strong position at Industry News USA and heads the Science section. “Weather forecasting” is the field of his interest. He bags total 5 years of experience in this field. Apart from his routine work, David loves to explore his cooking skills. He has participated in various cookery shows.