This repository contains Python scripts for eye tracking and face detection, likely intended for drone navigation or similar applications. The project uses machine learning, computer vision libraries, and real-time video processing to achieve its goals.
- Python 3.x
- PyTorch
- OpenCV
- dlib
- PIL (Pillow)
- imutils
You can install these packages using pip:
```bash pip install torch torchvision opencv-python dlib Pillow imutils ```
Run trainer.py to train a Convolutional Neural Network (CNN) for eye position classification.
```bash python trainer.py ```
Run main.py to perform real-time eye position prediction using the trained model.
```bash python main.py ```
Run eye_tracking.py for a simpler version of eye and face detection using OpenCV's Haar Cascades.
```bash python eye_tracking.py ```
Run eye_labeler.py to label eye positions in real-time. This will save frames and labels for future use.
```bash python eye_labeler.py ```
Run claude.py for an alternative method of eye and face detection using dlib.
```bash python claude.py ```
Feel free to fork this repository, create a new branch, and submit a pull request.
This project is licensed under the MIT License.