2026-05-30 GOLF☾ PM
Bryson DeChambeau Uses Google Cloud Vision Models to Quantify Every Swing
📰 THE BRIEF
Google Cloud’s deep learning pipeline ingests 2D and 3D video to track 30 skeletal, club, and ball keypoints through top-of-swing, impact, follow-through, and finish phases. The system outputs positional coordinates and outcome metrics that feed directly into swing-adjustment models.
💡 WHY IT MATTERS
Athletes stop relying on feel alone and start iterating on millimeter-level data. The workflow shifts from post-round video review to same-day algorithmic feedback loops.
👥 WHO'S DOING IT
Bryson DeChambeau partnered with Google Cloud to run these models on his practice footage, shortening swing diagnosis time from hours to minutes.
⚡ TRY IT
- Upload swing video to Google Cloud Vision API at https://cloud.google.com/vision.
- Call the Pose Detection endpoint to extract the 30 keypoints and timestamps.
- Export the JSON coordinates into a spreadsheet and calculate angle deltas between sessions to measure swing changes.