13-05-2025
University of Waterloo researchers develop AI technology for Baltimore Orioles
The Baltimore Orioles have called on researchers from the University of Waterloo to help them improve their pitching through the use of artificial intelligence.
PitcherNet uses broadcast camera feeds and combines them with low-resolution footage shot on a smartphone.
Jerrin Bright, lead researcher on the project, said the AI technology tracks different metrics to analyze a pitcher's performance.
'Most specifically, we find 18 joint positions of the human using the Hawk-Eye tracking system, and this skeleton is then basically used to find metrics like the pitching velocity and the spin rate of the ball,' Bright said.
The Hawk-Eye tracking system has 12 high-speed cameras, which capture images at 200 to 300 frames per second that are played at multiple angles on the baseball grounds.
Story continues below advertisement
The U of W-designed system extrapolates the pitcher's entire throwing motion to re-create a level of detail using elaborate and expensive technology installed in most stadiums that host MLB teams. Its goal is to fill gaps in the technology and provide data that is typically available to the team that owns the stadium where a game is played, as is the case with Hawk-Eye.
Get breaking National news
For news impacting Canada and around the world, sign up for breaking news alerts delivered directly to you when they happen. Sign up for breaking National newsletter Sign Up
By providing your email address, you have read and agree to Global News' Terms and Conditions and Privacy Policy
'They wanted to build a system that can basically mimic the sophisticated system like the Hawk-Eye technology itself, but the catch here would be that you wouldn't have any depth information because we are just going to use single monocular camera and have a coach or a scout be anywhere in the ground, and they'll be able to capture the data and do analysis of the players,' Bright said.
The project began in 2022 when the Orioles organization approached Bright and John Zelek, a professor of systems design engineering at the U of W.
Bright said the goal is not to replace humans, but to help elevate a pitcher's game.
'They can use different essential systems to find these metrics, but we are just trying to build this just from a broadcast feed that you can see in your television to try to make it more accessible and easier for the coaches or the scouts,' he said.
The Orioles organization has been very satisfied with the project, according to Bright, resulting in a two-year contract extension with the professional ball club.
Story continues below advertisement
He said their contract is exclusive to Baltimore and the U of W researchers haven't collaborated with other MLB teams.
Bright said the AI technology could be used in other areas of the sport in the future.
He said the AI technology could be expanded to help coaches in amateur leagues and college programs and also help improve scouting.
