A real-time AI vision processing system with camera management, object detection, and monitoring capabilities.
- Real-time Analysis - Process video streams with AI models (object detection, segmentation, pose estimation)
- Camera Management - Monitor and control multiple camera streams
- Modern UI - React + Vite frontend with Material-UI
- Fast API Backend - RESTful endpoints and real-time processing
- PostgreSQL Database - Reliable data storage
- Docker Support - Easy deployment with docker-compose
- Node.js (v14+ recommended)
- Python (v3.10+ recommended)
- Docker (optional - includes PostgreSQL, or install PostgreSQL separately)
# Copy environment variables
cp .env.example .env
# Create and activate Python virtual environment
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
# Install Python dependencies
pip install -r requirements.txtEdit .env and update passwords and settings as needed.
Option A: Using Docker (Recommended)
docker-compose upAdd -d flag to run in background: docker-compose up -d
Option B: Local PostgreSQL
- Install PostgreSQL and ensure it's running on port 5433
The backend will automatically create the database on first run
source venv/bin/activate # On Windows: venv\Scripts\activate
uvicorn backend.main:app --reloadcd frontend
npm install
npm run dev- Frontend: http://localhost:5173
- Backend API: http://localhost:8000
- API Docs: http://localhost:8000/docs
.
├── backend/ # FastAPI backend
├── frontend/ # React + Vite frontend
├── prometheus/ # Monitoring configuration
├── docker-compose.yml
├── requirements.txt # Python dependencies
├── .env.example # Environment variables template
└── README.md
- Database Connection: Check your
.envfile credentials match your PostgreSQL setup - Port Conflicts: Update ports in
.envordocker-compose.ymlif needed - Dependencies: Ensure Python 3.10+ and Node.js 14+ are installed
MIT License - see LICENSE file for details.