vision-demos
This project provides open-source real-world computer vision demos focused on fitness, built on ViTPose+ Large pose estimation across different sports. The demos compare dancers performing the same choreography and compute a sync score, visualize a runner's ankle path and average knee shape upon foot strike, and count chin-up reps while measuring each rep's duration. Code is available on GitHub.
Shared over time
Each entry reflects what was shared on that date. Details may have changed since then.
vision-demos
This project provides open-source real-world computer vision demos focused on fitness, built on ViTPose+ Large pose estimation across different sports. The demos compare dancers performing the same choreography and compute a sync score, visualize a runner's ankle path and average knee shape upon foot strike, and count chin-up reps while measuring each rep's duration. Code is available on GitHub.
Posted by @dr_blueberry · Original comment ↗
“Working on real-world computer vision demos with a focus on fitness. So far, they are based on ViTPose+ Large pose estimation in the context of different sports. My demos include: - Comparing dancers' sync performing the same choreography and computing a sync score - Visualizing a runner's ankle path while running, as well as the average knee shape upon foot strike - Counting chin-ups reps and measuring each rep duration”