High-performance computer vision modules for real-time tracking and gesture interaction
 |
 |
 |
| Face Mesh (468 pts) | Hand Tracking (21 pts) | Pose Estimation (33 pts) |
- 🎯 Precision Face Mesh: Tracks 468 facial landmarks in real-time with sub-pixel accuracy.
- 🖐️ Multi-Hand Tracking: Simultaneous tracking of multiple hands with gesture recognition support.
- 🏃 Holistic Pose Detection: Full-body skeleton tracking using 33 body keypoints.
- 🎨 AirDraw Web App: Interactive canvas that allows drawing in digital space via hand gestures.
- 🛠️ Unified Launcher: Smart
run.pyscript that handles environment setup and module selection automatically.
| Layer | Technologies Used |
|---|---|
| Core Engine | Python 3.8+, MediaPipe, OpenCV |
| Interface | CLI Menu (Python), Web Canvas (HTML5/JS) |
| Logic | Modular Class-based Python Architecture |
| Deployment | Local Environment with Automated Dependency Check |
- Python: 3.8 or higher
- Web Browser: Chrome or Firefox (for AirDraw)
- Webcam: Standard USB or Integrated camera
The project includes a smart launcher that manages dependencies and runs any module.
# Clone the repository
git clone https://github.com/your-repo/Advanced-CV-Projects.git
# Run the launcher (It will check and install requirements automatically)
python run.py- Face Mesh Detection: High-density facial mapping for AR/VR and expression analysis.
- Hand Detection: Landmark-based tracking for touchless interfaces and gesture control.
- Pose Detection: Body keypoint mapping for fitness tracking or motion capture.
- Face Detection: Fast, robust face localization with bounding boxes.
- AirDraw: A unique web-based creative tool utilizing hand landmarks for virtual painting.
The suite leverages MediaPipe's state-of-the-art ML solutions:
- Model Efficiency: Optimized for CPU/GPU inference, ensuring high FPS even on standard hardware.
- Coordinate Mapping: Advanced landmark smoothing to prevent jitter in tracking.
- Auto-Installer: The
run.pyscript ensures all 3rd-party libraries are correctly configured before execution.
Contributions are welcome! If you're adding a new CV module, ensure it follows the modular pattern used in handTrackingModule.py and is integrated into the run.py launcher.
MIT License. See LICENSE for details.