This is a Python (2 and 3) library that provides a webcam-based eye tracking system. It gives you the exact position of the pupils and the gaze's direction, in real time.

Clone this project:

git clone https://github.com/antoinelame/GazeTracking.git

GazeTracking requires these dependencies:

• NumPy
• OpenCV 3.4
• Dlib

To install them:

pip install -r requirements.txt

The Dlib library has four primary prerequisites: Boost, Boost.Python, CMake and X11/XQuartx. If you doesn't have them, you can read this article to know how to easily install them.

OpenCV 4 is not supported yet, make sure to install version 3.4

Run the demo:

python example.py

import cv2
from gaze_tracking import GazeTracking


gaze = GazeTracking()

while True:
    gaze.refresh()

    frame = gaze.main_frame(True)
    text = ""

    if gaze.is_right():
        text = "Looking right"
    elif gaze.is_left():
        text = "Looking left"
    elif gaze.is_center():
        text = "Looking center"

    cv2.putText(frame, text, (60, 60), cv2.FONT_HERSHEY_DUPLEX, 2, (255, 0, 0), 2)
    cv2.imshow("Demo", frame)

    if cv2.waitKey(1) == 27:
        break

In the following examples, gaze refers to an instance of the GazeTracking class.

gaze.refresh()

Captures a new frame with the webcam and analyzes it.

gaze.pupil_left_coords()

Returns the coordinates (x,y) of the left pupil.

gaze.pupil_right_coords()

Returns the coordinates (x,y) of the right pupil.

gaze.is_left()

Returns True if the user is looking to the left.

gaze.is_right()

Returns True if the user is looking to the right.

gaze.is_center()

Returns True if the user is looking at the center.

ratio = gaze.horizontal_ratio()

Returns a number between 0.0 and 1.0 that indicates the horizontal direction of the gaze. The extreme right is 0.0, the center is 0.5 and the extreme left is 1.0.

ratio = gaze.vertical_ratio()

Returns a number between 0.0 and 1.0 that indicates the vertical direction of the gaze. The extreme top is 0.0, the center is 0.5 and the extreme bottom is 1.0.

gaze.is_blinking()

Returns True is the user's eyes are closed.

# Without pupils highlighting
frame = gaze.main_frame(False)

# With pupils highlighting
frame = gaze.main_frame(True)

Returns the main frame from the webcam.

This project is released by Antoine Lamé under the terms of the MIT Open Source License. View LICENSE for more information.