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
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.
Stars
8
Forks
—
Language
Jupyter Notebook
License
—
Category
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.
Higher-rated alternatives
yakupzengin/fitness-trainer-pose-estimation
An AI-powered fitness tracker that uses real-time pose estimation to count reps, monitor form,...
nevinbaiju/pose_estimation_android_app
A native android application for pose estimation and detection using mlkit. The app can detect...
giaongo/RepDetect
AI Android application crafted with Kotlin that harnesses the power of MediaPipe Pose Landmark...
sidex15/PoseExercise-WebApp
A collaboration between the proponents of the thesis titled "DEVELOPMENT OF WEB BASED APP FOR...
SohamPrajapati/Posture-Detection-Pose-Classification-Project
"Welcome to our posture detection and pose classification web application repository! Utilizing...