https://github.com/aarambhdevhub/multi-cam-face-tracker
Real-time multi-camera face tracking system with PyQt5 interface and alert notifications. Supports webcams, RTSP streams, and provides face recognition with InsightFace models.
https://github.com/aarambhdevhub/multi-cam-face-tracker
camera-tracking face-detection face-recognition multi-camera multi-camera-tracking multi-person-tracking opencv-projects person-recognition person-tracking python-surveillance real-time-alerts security-system
Last synced: 4 months ago
JSON representation
Real-time multi-camera face tracking system with PyQt5 interface and alert notifications. Supports webcams, RTSP streams, and provides face recognition with InsightFace models.
- Host: GitHub
- URL: https://github.com/aarambhdevhub/multi-cam-face-tracker
- Owner: AarambhDevHub
- License: mit
- Created: 2025-05-21T03:31:00.000Z (5 months ago)
- Default Branch: main
- Last Pushed: 2025-05-21T04:06:16.000Z (5 months ago)
- Last Synced: 2025-05-21T04:36:32.035Z (5 months ago)
- Topics: camera-tracking, face-detection, face-recognition, multi-camera, multi-camera-tracking, multi-person-tracking, opencv-projects, person-recognition, person-tracking, python-surveillance, real-time-alerts, security-system
- Language: Python
- Homepage:
- Size: 1.55 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
Awesome Lists containing this project
README
# Multi-Camera Face Tracker System đ
A robust real-time face tracking system with multi-camera support, facial recognition, age & gender detection, and intelligent alerting capabilities including Telegram notifications.
## đ Key Features
### Core Functionality
- **Multi-Camera Support**: Simultaneously monitor multiple video sources (webcams, RTSP streams, video files)
- **Real-Time Face Detection**: Powered by InsightFace with GPU acceleration support
- **Face Recognition**: Identify known individuals with configurable confidence thresholds
- **Age & Gender Detection**: Estimate demographic attributes for each detected face
### Alert System
- ⨠**Telegram Notifications**: Get instant alerts with snapshots on your phone
- đ **Visual & Audio Alerts**: Customizable popups and sound notifications
- đ¸ **Automatic Evidence Capture**: Saves screenshots of recognition events
- đ **Comprehensive Logging**: Detailed event records with timestamps and confidence levels
### User Interface
- đĨī¸ **Live Monitoring Dashboard**: View all camera feeds in real-time
- đ¤ **Face Management**: Add/remove known faces with photo uploads
- âąī¸ **History Viewer**: Filter events by date, camera, or individual
## đ ī¸ Technical Stack
| Component | Technology Used |
|-------------------------|-------------------------------|
| Face Detection | InsightFace |
| Machine Learning | PyTorch |
| Computer Vision | OpenCV |
| GUI Framework | PyQt5 |
| Database | SQLite |
| Audio Alerts | Pygame |
| Telegram Alerts | python-telegram-bot |
| **Alert Channels** | Telegram Bot |
| Demographics | Age & Gender via InsightFace |
## đĻ Installation Guide
### Prerequisites
- Python 3.8+
- NVIDIA GPU (recommended for best performance)
- FFmpeg (for RTSP streams)
### Step-by-Step Setup
1. **Clone the repository**:
```bash
git clone https://github.com/AarambhDevHub/multi-cam-face-tracker.git
cd multi-cam-face-tracker
```
2. **Create virtual environment**:
```bash
python -m venv venv
source venv/bin/activate # Linux/Mac
venv\Scripts\activate # Windows
```
3. **Install dependencies**:
```bash
pip install -r requirements.txt
```
4. **Configure the system**:
- Edit `config/config.yaml` for application settings
- Edit `config/camera_config.yaml` for camera configurations
5. **Directory setup**:
```bash
mkdir -p data/{known_faces,screenshots} config logs
```
6. Run the application:
```
python main.py
```
## âī¸ Configuration
### Application Settings (`config/config.yaml`)
```yaml
app:
name: "Multi-Cam Face Tracker"
version: "1.0.0"
threshold: 0.6
screenshot_dir: "data/screenshots"
known_faces_dir: "data/known_faces"
database_path: "data/database.db"
alert_sound: "assets/alert.wav"
log_dir: "logs"
recognition:
detection_threshold: 0.5
recognition_threshold: 0.6
max_batch_size: 8
device: "cpu" # or "cuda"
age_estimation: true
gender_detection: true
```
### Camera Configuration (`config/camera_config.yaml`)
```yaml
cameras:
- id: 0
name: "Front Camera"
source: 0 # Camera index or RTSP URL # Camera index or "rtsp://..."
enabled: true
resolution:
width: 1280
height: 720
fps: 30
rotate: 0 # Degrees (0,90,180,270)
```
## âī¸ Telegram Configuration
### Add to `config/config.yaml`:
```yaml
telegram:
enabled: true
bot_token: "YOUR_BOT_TOKEN" # From @BotFather
chat_id: "YOUR_CHAT_ID" # Get from @getidsbot
rate_limit: 30 # Seconds between alerts
```
## Setup Guide:
- Create bot with @BotFather
- Get chat ID with @getidsbot
- Add bot to your alert channel as admin
- Enable in config and restart app
## đ Learn More on DeepWiki
Want to dive deeper into how this system works, including architecture insights and real-world deployment tips?
đ Explore the project on DeepWiki:
đ [https://deepwiki.com/AarambhDevHub/multi-cam-face-tracker](https://deepwiki.com/AarambhDevHub/multi-cam-face-tracker)
## đĨī¸ User Manual
### Adding Known Faces
1. Click "Face Manager" in the Tools menu
2. Select "Add Face" and upload a clear photo
3. Enter the person's name and save
### Camera Controls
Button Functionality
âļī¸ Start Activates selected camera feed
âšī¸ Stop Halts camera processing
âī¸ Settings Adjust resolution/FPS
### Alert Management
- Configure sound preferences in Alert Panel
- Set minimum confidence threshold (0.5-1.0)
- Enable/disable screenshot capture
- View age and gender next to each recognized face
## đ Performance Tips
1. For RTSP Streams:
- Use tcp transport protocol for stability
- Example: `rtsp://user:pass@ip:port/stream?tcp`
2. GPU Acceleration:
```yaml
recognition:
device: "cuda" # In config.yaml
```
3. Optimization:
- Lower processing intervals for fewer cameras
- Reduce resolution for distant facial recognition
- Use JPEG compression for RTSP streams
## đ Sample Use Cases
- Office Security: Monitor entrances for unauthorized personnel
- Smart Home: Get alerts when family members arrive
- Retail Analytics: Track customer demographics
## đ License
MIT License - See [LICENSE](LICENSE) for details.
## đ¤ Contributing
We welcome contributions! Please see our [Contribution Guidelines](CONTRIBUTING.md)
## â Support the Project
If you find this project helpful, consider buying me a coffee!
[Buy Me a Coffee](https://buymeacoffee.com/aarambhdevhub)