PitcherNet helps researchers throw strikes with AI analysis
Baltimore Orioles tasks 蓝莓视频 Engineering researchers to develop AI tech that can monitor pitchers using low-resolution video captured by smartphones
By
Media Relations
University of 蓝莓视频 researchers have developed PitcherNet, a new AI-powered system that analyzes pitcher performance using low-resolution broadcast and smartphone video鈥攐vercoming the limitations of stadium-exclusive, high-end systems like Hawk-Eye.听
Developed for the Baltimore Orioles, PitcherNet converts regular game footage into detailed two-dimensional and three-dimensional models of pitcher mechanics. The AI then extracts data such as pitch velocity and release point, enabling the Orioles to assess player performance during away games or minor league scouting without specialized equipment.
鈥淓xisting systems are limited to home games,鈥 says PhD student Jerrin Bright. 鈥淧itcherNet fills that gap with a flexible, scalable tool for any setting.鈥 Led by Professor John Zelek and the Vision and Image Processing (VIP) Lab, the project has gained continued support from the Orioles and may soon expand to other sports like hockey and basketball.
To read the full article, click here!