SentryVision - AI-Powered Threat Detection System

Overview

SentryVision is an advanced AI-powered security monitoring system that provides real-time weapon detection using YOLOv8m deep learning models. The system offers live camera streaming, intelligent threat detection, and comprehensive alert management through a modern web interface.

🚀 Key Features

• 🎯 Advanced Threat Detection: Custom-trained YOLOv8m model with 47.08% mAP@0.5 for detecting knives, pistols, and long weapons
• 📹 Multi-Camera Support: Real-time streaming from multiple camera sources with DirectShow backend support
• ⚡ Intelligent Filtering: Per-class confidence thresholds to reduce false positives (phones/pens detected as knives)
• 🔐 User Authentication: Secure login and registration system with Flask-Login
• 🚨 Real-Time Alerts: Instant notifications with detection snapshots and audio alerts
• 📱 Responsive Dashboard: Modern web interface optimized for desktop and mobile devices
• 🔧 GPU Acceleration: CUDA-optimized training and inference for RTX GPUs
• 📊 Performance Monitoring: Comprehensive model evaluation and training metrics

---

Project Structure

├── instance/                  # SQLite database and other instance-specific files
├── static/                    # Static files (CSS, JS, images, snapshots)
│   ├── snapshots/             # Directory for storing detection snapshots
│   ├── bg.jpg                # Background image for UI
│   └── alert.mp3             # Sound for alert notifications
├── templates/                 # HTML templates for Flask
│   ├── index.html            # Main dashboard
│   ├── login.html            # Login page
│   ├── register.html         # Registration page
│   └── alerts.html           # Standalone alerts page
├── camera_processor.py       # Handles camera processing and YOLO detection
├── config.py                 # Configuration settings
├── forms.py                  # Flask-WTF forms for authentication
├── main.py                   # Main Flask application
├── models.py                 # SQLAlchemy database models
├── requirements.txt          # Python dependencies
└── README.md                 # This file

---

Installation

1. Clone the Repository:

   git clone https://github.com/hibaanwer07/SentryVision.git
   cd flask-security-monitoring

2. Set Up a Virtual Environment:

   python -m venv venv
   source venv\Scripts\activate

3. Install Dependencies:

   pip install -r requirements.txt

4. Configure Environment Variables (create .env file):

   SECRET_KEY=your-secret-key
   DATABASE_URL=sqlite:////path/to/site.db
   MAIL_USERNAME=your-email@gmail.com
   MAIL_PASSWORD=your-app-password

5. Initialize the Database:

   flask db init
   flask db migrate
   flask db upgrade

---

Running the Application

1. Start the Flask Server:

   python main.py

   Access the dashboard at http://localhost:5000.

2. Toggle Security Modes and view live feeds and alerts.

---

Configuration

• Camera Sources: Add webcam indices or RTSP URLs in config.py.
• Threat Classes: Modify PRIMARY_THREAT_CLASSES for detection.
• Alert Settings: Adjust alert intervals for email and real-time updates.
• MQTT Settings: Configure MQTT broker for IoT integration.

---

Contributing

1. Fork the repository.
2. Create a branch (git checkout -b feature/your-feature).
3. Commit changes (git commit -m 'Add feature').
4. Push to the branch (git push origin feature/your-feature).
5. Open a Pull Request.

---

License

This project is licensed under the MIT License.

---

Acknowledgments

• YOLOv8: For object detection.
• Flask: For the web framework.
• OpenCV: For video processing.
• Paho MQTT: For MQTT integration.