An intelligent surveillance analysis tool that automatically detects and describes key events in video footage using Moondream Vision AI.
- 🎬 Smart frame extraction from surveillance videos
- 🤖 AI-powered scene description generation
- 🎯 Intelligent key frame detection using similarity analysis
- 📊 Comprehensive data visualization with interactive tables
- ⌚ Precise timestamp tracking
- 📈 Frame-by-frame similarity comparison
- 🔄 Support for multiple video formats (MP4, AVI, MOV)
- 📱 Clean, responsive web interface
- Python 3.11 or higher
- Web Browser
- Moondream API key from Moondream Console or download the model file from here
- Clone the repository:
git clone https://github.com/smaranjitghose/sightguardai.git
cd sightguardai- Create and activate virtual environment:
# Windows
python -m venv env
.\env\Scripts\activate
# Linux/Mac
python3 -m venv env
source env/bin/activate- Install required packages:
pip install streamlit moondream python-dotenv pillow opencv-python scikit-learn pandas- Launch the application:
streamlit run app.py- Access the web interface:
http://localhost:8501
- Enter your Moondream API key in the sidebar
- Upload a surveillance video file
- Click "Analyze" to begin processing
- View results in the interactive table and key frames grid
-
Memory Issues
- Adjust frame extraction interval for longer videos
- Ensure sufficient system RAM
- Close other memory-intensive applications
-
API Errors
- Verify API key validity
- Check internet connection
- Confirm API usage limits
-
Video Processing
- Ensure video format compatibility
- Check file corruption
- Verify file permissions
Contributions are welcome! Please follow these steps:
- Fork the project
- Create your feature branch (
git checkout -b feature/AmazingFeature) - Commit your changes (
git commit -m 'Add some AmazingFeature') - Push to the branch (
git push origin feature/AmazingFeature) - Open a Pull Request
This project is licensed under the MIT License - see the LICENSE file for details.
Made with ❤️ by Smaranjit Ghose