Artificial intelligence (AI) technology developed at Waterloo Engineering gives baseball scouts a powerful new tool to accurately analyze pitcher performance and biomechanics using low-resolution video.
The system, known as PitcherNet, is the product of a three-year partnership between researchers at the Vision and Image Processing (VIP) Lab and the Baltimore Orioles of Major League Baseball (MLB).
It was designed to plug holes in much more elaborate and expensive technology already installed in MLB stadiums by a company called Hawk-Eye Innovations.
The data that system yields is typically only available to the home team, so the Orioles asked AI experts at Waterloo for help to add away games - and use smartphone video taken by scouts at minor league and college games - to their analytics operation.
“The goal of our project was to try to duplicate Hawk-Eye technology and go beyond it by producing similar output from broadcast video or a smartphone camera used by a scout sitting somewhere in the stands,” said Dr. John Zelek, a professor of systems design engineering and co-director of the VIP Lab.
The Orioles have committed to jointly funding the project for another year.
“Dr. Zelek has been amazing and the students that we’ve worked with have been equally amazing,” Sig Mejdal, the team’s assistant general manager, told the Baltimore Sun. “I am hopeful that we’ll in some way continue working with them even after this project is completed.”
Go to PitcherNet helps researchers throw strikes with AI analysis for the full story.