JRKagumba/2D-video-based-exercise-classification

A biomechanics based movement detection algorithm that only requires 2D video and uses machine learning to perform classification on 5 common at-home exercises

18
/ 100
Experimental

Analyze exercise form and track progress using standard 2D video. You upload a video of someone performing an exercise, and it provides instant Range of Motion (ROM) analysis, joint angle plots, and identifies the exercise. This tool is perfect for fitness enthusiasts, coaches, researchers, and students interested in human movement.

Use this if you want to automatically analyze and classify common at-home exercises from standard video footage without needing specialized 3D equipment.

Not ideal if you require absolute 3D motion reconstruction or highly precise medical-grade biomechanical analysis that requires specialized hardware.

fitness-tracking exercise-coaching biomechanics-research sports-science physical-therapy-support
No License No Package No Dependents
Maintenance 6 / 25
Adoption 4 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

8

Forks

Language

Jupyter Notebook

License

Last pushed

Nov 03, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/JRKagumba/2D-video-based-exercise-classification"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.