Installation Guide

Installation Guide

Step 1 — Enter the Project Directory

cd bradykinesia_cam

Step 2 — Create and Activate a Virtual Environment

Python 3.8 to 3.11 is required. Python 3.12 is not supported by MediaPipe.

python -m venv venv

Activate on macOS or Linux:

source venv/bin/activate

Activate on Windows:

venv\Scripts\activate

Step 3 — Install Python Dependencies

pip install -r requirements.txt

On Apple Silicon Macs, if the standard mediapipe package fails to install, use this instead:

pip install mediapipe-silicon

Step 4 — Configure Environment Variables

cp .env.example .env

Open the .env file and set a strong SECRET_KEY. All other defaults are suitable for local development.

Step 5 — Run Database Migrations

python manage.py migrate

Step 6 — Create a Superuser

Quick setup with default credentials (admin / admin1234):

python manage.py create_default_superuser

Custom credentials:

python manage.py create_default_superuser --username doctor --password secure123

Step 7 — Load Demo Patient Data (Optional)

This loads 3 demo patients with pre-computed analysis results so you can explore the dashboard immediately.

python manage.py loaddata core/fixtures/demo_patients.json

Step 8 — Start Redis

Using Docker (recommended):

docker run -d -p 6379:6379 redis:7-alpine

Using Homebrew on macOS:

brew services start redis

If Redis is not available, the system automatically falls back to synchronous video processing. No configuration change is needed.

Step 9 — Start the Celery Worker

Open a separate terminal window and run:

celery -A bradykinesia_cam worker --loglevel=info

Step 10 — Start the Django Development Server

python manage.py runserver

Open your browser and go to http://127.0.0.1:8000. Sign in with the superuser credentials you created in Step 6.

Recording a Finger-Tap Video for Testing

• Record for exactly 10 seconds
• Hold the palm facing the camera with the hand clearly visible
• Tap the thumb and index finger together as fast and as wide as possible
• Ensure good lighting and avoid motion blur

Production Deployment Checklist

• Set DEBUG=False and configure ALLOWED_HOSTS in .env
• Run python manage.py collectstatic
• Switch DATABASE_URL to a PostgreSQL connection string
• Configure Nginx to serve the media/videos/ directory
• Use supervisor or systemd to manage the Celery worker process