2026-06-23 GOLF☀ AM
Golf swing data at 30 body points: Bryson DeChambeau trains with Google Cloud vision models
📰 THE BRIEF
The system runs deep learning models on 2D and 3D video. It tracks over 30 keypoints on body, club, and ball during top of swing, impact, follow-through, and finish. Shot outcome data is recorded for later analysis.
💡 WHY IT MATTERS
Athletes move from subjective coaching cues to quantified movement metrics. Training decisions shift from feel-based adjustments to data-driven corrections that repeat across sessions.
👥 WHO'S DOING IT
Bryson DeChambeau partnered with Google Cloud to test the models on his own swing data and reported measurable consistency gains during practice rounds.
⚡ TRY IT
- Open Google Cloud Vision API documentation at https://cloud.google.com/vision and enable the Pose Detection endpoint.
- Upload a 2D or 3D swing video and request keypoint extraction for at least 30 body and equipment landmarks.
- Export the JSON output and import the coordinates into a spreadsheet or notebook to compare swing phases across multiple takes.