An analysis platform for baseball teams short of both coaching and money. Pose estimation from video turns a player's movement into numbers, replacing instruction based on feel with feedback in figures and words. It also fields position-specific questions and suggests training menus, on a serverless setup that keeps costs low.
The theme of supporting players who want to get better drew sympathy from judges. They credited a clear solution to a visible problem, from pose-estimation analysis to training suggestions, and an architecture chosen with real operation in mind.
Plenty of teams have players who want to improve and nobody able to coach them, and naming that gap is much of why the entry resonates. Turning movement into numbers from video is less about replacing a coach's eye than about giving a squad a shared yardstick to argue from. Choosing a low-cost serverless setup from the outset also answers the question every hackathon project eventually faces, whether anyone can keep it running after the event.
See all winners of 第4回 Agentic AI Hackathon with Google Cloud →
Summaries are written by this site. Project pages include demo videos, screenshots and the team's own write-up (videos may autoplay).