ML solution for accurate iris estimation, able to track landmarks involving the iris, pupil and the eye contours using a single RGB camera, in real-time, without the need for specialized hardware. - MediaPipe Iris / Eye Tracking with Mediapipe and OpenCV

see also

• Faster code editors, ep06 - Eye tracking
• 3D Eye Tracking in Python / github
  • 3D Eye Tracking on a Webcam

# Eyes Contact

# Starting Point

# Face Landmark Detection

Using Mediapipe Iris (Face Geometry Module)

• Iris Tracking MediaPipe / part 2 / medium

# 3D Gaze

• gaze-tracking-pipeline / Efficiency in Real-time Webcam Gaze Tracking (pdf)

• Eye gaze estimation using a webcam. 100 lines of code / github

# Iris Localization

• Simple and Accurate Iris Center Localization Method based on Geometric Relationship of Eyeball Model

• Surface MediaPipe Iris model for the web #2526

# Landmark Stabilisation

• Stabilized-Facial-Landmark-Detection-in-Real-Time-Video - use Optical Flow

• Step By Step Guide To Stabilize Facial Landmarks In A Video Using Dlib - ???

# see also

• Real-time eye tracking using OpenCV and Dlib / github

• Tracking your eyes with Python - using haarcascade to detect face + eyes & blobs for pupils

• Eye Gaze Tracking With Head Tracking Solutions On Linux
• Weekend Project: Take a Tour of Open Source Eye-Tracking Software
  • OpenGazer
  • GazePointer
  • Gaze Tracking - a webcam-based eye tracking system. It gives you the exact position of the pupils and the gaze direction, in real time.
• Face Alignment with OpenCV and Python