nuclearshadow/exercise-guide

DE Project

Exercise Guide

A real-time exercise guide application that uses computer vision to track poses and provide feedback.

Features

• Real-time pose tracking using MediaPipe
• Exercise template recording and playback
• Pose similarity scoring
• Real-time feedback on form
• Web-based interface with live video feed

Prerequisites

• Python 3.8 or higher
• Webcam
• pip (Python package manager)

Installation

1. Clone the repository:

git clone https://github.com/nuclearshadow/exercise-guide
cd exercise-guide

2. Create a virtual environment (recommended):

python -m venv venv
source venv/bin/activate  # On Windows, use: venv\Scripts\activate

3. Install the required packages:

pip install -r requirements.txt

Running the Application

1. Start the Flask server:

python app.py

2. Open your web browser and navigate to:

http://localhost:5001

Using the Application

TBD

Acknowledgements

• Using google's Mediapipe for pose detection
• Images of exercise key poses taken from: acefitness.org