Abstract
Eye tracking technology has become increasingly important for psychological analysis, medical diagnosis, driver assistance systems, and many other applications. Various gaze-tracking models have been established by previous researchers. However, there is currently no near-eye display system with accurate gaze-tracking performance and a convenient user experience. In this paper, we constructed a complete prototype of the mobile gaze-tracking system ‘Etracker’ with a near-eye viewing device for human gaze tracking. We proposed a combined gaze-tracking algorithm. In this algorithm, the convolutional neural network is used to remove blinking images and predict coarse gaze position, and then a geometric model is defined for accurate human gaze tracking. Moreover, we proposed using the mean value of gazes to resolve pupil center changes caused by nystagmus in calibration algorithms, so that an individual user only needs to calibrate it the first time, which makes our system more convenient. The experiments on gaze data from 26 participants show that the eye center detection accuracy is 98% and Etracker can provide an average gaze accuracy of 0.53° at a rate of 30–60 Hz.
Highlights
In recent years, eye tracking has become an important research topic in computer vision and pattern recognition, because the human gaze positions are essential information for many applications including human–computer interaction (HCI) [1,2], driver assistance [3], optometry, market data analysis, and medical diagnosis
We propose a combined gaze estimation method based on convolutional neural networks (CNNs) (ResNet-101) and a geometric model
After estimating the coarse gaze positions, we aimed to develop a geometric model between the eye image and near-eye viewing device that can accurately and efficiently calculate the gaze positions
Summary
Eye tracking has become an important research topic in computer vision and pattern recognition, because the human gaze positions are essential information for many applications including human–computer interaction (HCI) [1,2], driver assistance [3], optometry, market data analysis, and medical diagnosis. The fundamental issues of gaze-tracking technology include tracking system, tracking algorithms, and user experiences. These three issues are closely related to each other. User experiences are highly dependent on the tracking systems and algorithms. Most of the current gaze-tracking systems are either table-mounted or mobile systems. A table-mounted system usually works with an external display screen, which makes human–computer interaction convenient, but it is not robust to head movement. A mobile system is Sensors 2018, 18, 1626; doi:10.3390/s18051626 www.mdpi.com/journal/sensors
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
