⬢github Python · 593 ★ +13 since we first saw it · pushed 4 d ago · Apache-2.0
jeremyipark/vision-demos
Fun real-world computer vision demos!
A collection of Python computer vision demos applied to real sports and activities: counting chin-up and deadlift reps, checking deadlift back form, measuring running cadence, scoring dance synchronization, and tracking rock climbing routes (including a 3D reconstruction from iPhone LiDAR). Demos combine pose estimation, segmentation, and multimodal models, with setup instructions per project.
Why now: It was shared on Hacker News as a 'Show HN' post, specifically showcasing the deadlift form-evaluation tool.
Who it is for: Developers and fitness enthusiasts interested in applying computer vision and pose estimation to real-world athletic video.
Stars over our 306 snapshots: 580 to 593, since 3 d ago.
Where people talked about it
API: https://socialmediatrends-api.osmike.com/v1/repos/jeremyipark/vision-demos