Pupil Position by an Improved Technique of YOLO Network for Eye Tracking Application

Abstract

This Eye gaze following is the real-time collection of information about a person's eye movements and the direction of their look. Eye gaze trackers are devices that measure the locations of the pupils to detect and track changes in the direction of the user's gaze. There are numerous applications for analyzing eye movements, from psychological studies to human-computer interaction-based systems and interactive robotics controls. Real-time eye gaze monitoring requires an accurate and reliable iris center localization technique. Deep learning technology is used to construct a pupil tracking approach for wearable eye trackers in this study. This pupil tracking method uses deep-learning You Only Look Once (YOLO) model to accurately estimate and anticipate the pupil's central location under conditions of bright, natural light (visible to the naked eye). Testing pupil tracking performance with the upgraded YOLOv7 results in an accuracy rate of 98.50% and a precision rate close to 96.34% using PyTorch.