Probabilistic approach to robust wearable gaze tracking

This paper presents a method for computing the gaze point using camera data captured with a wearable gaze tracking device. The method utilizes a physical model of the human eye, advanced Bayesian computer vision algorithms, and Kalman filtering, resulting in high accuracy and low noise. Our C++ implementation can process camera streams with 30 frames per second in realtime. The performance of the system is validated in an exhaustive experimental setup with 19 participants, using a self-made device. Due to the used eye model and binocular cameras, the system is accurate for all distances and invariant to device movement. We also test our system against a best-in-class commercial device which is outperformed for spatial accuracy and precision. The software and hardware instructions as well as the experimental data are published as open source.

Download Full-text

VP203 Performance Evaluation Of Eye-Tracking Devices

International Journal of Technology Assessment in Health Care ◽

10.1017/s0266462317004299 ◽

2017 ◽

Vol 33 (S1) ◽

pp. 245-245

Author(s):

Luciano Recalde ◽

José Núñez ◽

César Yegros ◽

Carolina Villegas

Keyword(s):

Eye Tracking ◽

Interface Design ◽

Vertical Axis ◽

Horizontal Axis ◽

Precision Data ◽

Limited Mobility ◽

The Gaze ◽

Accuracy And Precision ◽

Tracking Device ◽

Tracking Devices

INTRODUCTION:There are different devices, systems and technologies for people with disabilities. It's necessary to provide information on the effectiveness of products in the market and competitiveness in terms of price-quality, and providing an endorsement in the acquisition of technologies that improve their quality of life. The use of eye tracking devices is growing and its implementation in different areas has attracted the attention of several developers. Therefore the need to generate a product that evaluates the functionality of such devices is necessary in order to avoid unnecessary expenses when acquiring or repairing one of these devices.METHODS:An interface was created with different functionalities such as the location of the coordinates in which the pointer is located, standardized graphic interface design to provide statistical data that allow an objective result for its subsequent analysis and an endless number of design possibilities.The tests performed were of accuracy and precision where the subject was asked to follow the instructions given and observe a sequence of points, especially the points located at the ends of the monitor as these are the critical points in which there is less coincidence between the cursor and the gaze.RESULTS:The results obtained provided information on the performance of the tracking device. In this way it was possible to establish that the accuracy of the ocular tracker: it was ± 12.83 pixels on the horizontal axis and ± 10.66 pixels on the vertical axis. The precision was ± 9.8 pixels on the horizontal axis and ± 14.23 pixels on the vertical axis.This shows the use phenomenon caused due to the limited mobility of the eyes in the vertical axis in comparison to the horizontal mobility. The precision data obtained indicate that, because the movement on the vertical axis is smaller, there is a less continuous spectrum of positions on the axis, which translates to less precision.CONCLUSIONS:The data obtained can be used to compare with the results of the test with other eye tracking devices and thus this could serve as a tool to select an eye tracking device according to the user's need and his economical capabilities.

Download Full-text

A Method of Free-Space Point-of-Regard Estimation Based on 3D Eye Model and Stereo Vision

Applied Sciences ◽

10.3390/app8101769 ◽

2018 ◽

Vol 8 (10) ◽

pp. 1769

Author(s):

Zijing Wan ◽

Xiangjun Wang ◽

Lei Yin ◽

Kai Zhou

Keyword(s):

Tracking System ◽

Estimation Method ◽

Estimation Algorithm ◽

Model Parameters ◽

Gaze Tracking ◽

Calibration Process ◽

Eye Model ◽

Stereo Cameras ◽

Spatial Coordinates ◽

Tracking Device

This paper proposes a 3D point-of-regard estimation method based on 3D eye model and a corresponding head-mounted gaze tracking device. Firstly, a head-mounted gaze tracking system is given. The gaze tracking device uses two pairs of stereo cameras to capture the left and right eye images, respectively, and then sets a pair of scene cameras to capture the scene images. Secondly, a 3D eye model and the calibration process are established. Common eye features are used to estimate the eye model parameters. Thirdly, a 3D point-of-regard estimation algorithm is proposed. Three main parts of this method are summarized as follows: (1) the spatial coordinates of the eye features are directly calculated by using stereo cameras; (2) the pupil center normal is used to the initial value for the estimation of optical axis; (3) a pair of scene cameras are used to solve the actual position of the objects being watched in the calibration process, and the calibration for the proposed eye model does not need the assistance of the light source. Experimental results show that the proposed method can output the coordinates of 3D point-of-regard more accurately.

Download Full-text

A Novel Method for Estimating Free Space 3D Point-of-Regard Using Pupillary Reflex and Line-of-Sight Convergence Points

Sensors ◽

10.3390/s18072292 ◽

2018 ◽

Vol 18 (7) ◽

pp. 2292 ◽

Cited By ~ 1

Author(s):

Zijing Wan ◽

Xiangjun Wang ◽

Kai Zhou ◽

Xiaoyun Chen ◽

Xiaoqing Wang

Keyword(s):

Free Space ◽

Estimation Method ◽

Measurement Model ◽

Line Of Sight ◽

Gaze Estimation ◽

Gaze Tracking ◽

The Gaze ◽

Convergence Point ◽

Spatial Coordinates ◽

Tracking Device

In this paper, a novel 3D gaze estimation method for a wearable gaze tracking device is proposed. This method is based on the pupillary accommodation reflex of human vision. Firstly, a 3D gaze measurement model is built. By uniting the line-of-sight convergence point and the size of the pupil, this model can be used to measure the 3D Point-of-Regard in free space. Secondly, a gaze tracking device is described. By using four cameras and semi-transparent mirrors, the gaze tracking device can accurately extract the spatial coordinates of the pupil and eye corner of the human eye from images. Thirdly, a simple calibration process of the measuring system is proposed. This method can be sketched as follows: (1) each eye is imaged by a pair of binocular stereo cameras, and the setting of semi-transparent mirrors can support a better field of view; (2) the spatial coordinates of the pupil center and the inner corner of the eye in the images of the stereo cameras are extracted, and the pupil size is calculated with the features of the gaze estimation method; (3) the pupil size and the line-of-sight convergence point when watching the calibration target at different distances are computed, and the parameters of the gaze estimation model are determined. Fourthly, an algorithm for searching the line-of-sight convergence point is proposed, and the 3D Point-of-Regard is estimated by using the obtained line-of-sight measurement model. Three groups of experiments were conducted to prove the effectiveness of the proposed method. This approach enables people to obtain the spatial coordinates of the Point-of-Regard in free space, which has great potential in the application of wearable devices.

Download Full-text

3D Eye Model-Based Gaze Tracking System with a Consumer Depth Camera

2020 3rd International Conference on Advanced Electronic Materials, Computers and Software Engineering (AEMCSE) ◽

10.1109/aemcse50948.2020.00070 ◽

2020 ◽

Author(s):

Liming Xu ◽

Jiannan Chi

Keyword(s):

Tracking System ◽

Depth Camera ◽

Gaze Tracking ◽

Eye Model ◽

Model Based

Download Full-text

The Suggestion for the Design of Eye Tracker to Promote the Study on the Gaze Tracking Interface

Journal of Cultural Product and Design ◽

10.18555/kicpd.2017.50.13 ◽

2017 ◽

Vol 50 (1) ◽

pp. 145-152

Author(s):

Eun Sun Seo, ◽

Keyword(s):

Eye Tracker ◽

Gaze Tracking ◽

The Gaze

Download Full-text

Defining gaze tracking metrics by observing a growing divide between 2D and 3D tracking

Electronic Imaging ◽

10.2352/issn.2470-1173.2020.11.hvei-129 ◽

2020 ◽

Vol 2020 (11) ◽

pp. 129-1-129-10

Author(s):

William Andrew Blakey ◽

Stamos Katsigiannis ◽

Navid Hajimirza ◽

Naeem Ramzan

Keyword(s):

Comparative Study ◽

3D Tracking ◽

Gaze Tracking ◽

The Gaze ◽

Huge Impact ◽

Intersection Points ◽

Accuracy Measures ◽

2D And 3D ◽

Tracking Technology

This work examines the different terminology used for defining gaze tracking technology and explores the different methodologies used for describing their respective accuracy. Through a comparative study of different gaze tracking technologies, such as infrared and webcam-based, and utilising a variety of accuracy metrics, this work shows how the reported accuracy can be misleading. The lack of intersection points between the gaze vectors of different eyes (also known as convergence points) in definitions has a huge impact on accuracy measures and directly impacts the robustness of any accuracy measuring methodology. Different accuracy metrics and tracking definitions have been collected and tabulated to more formally demonstrate the divide in definitions.

Download Full-text

Ku-Band Low Noise Block Converter (LNB) Sync Application Design Using Android Based Solid Dish

Budapest International Research and Critics Institute (BIRCI-Journal) Humanities and Social Sciences ◽

10.33258/birci.v4i1.1725 ◽

2021 ◽

Vol 4 (1) ◽

pp. 1135-1150

Author(s):

Junaidi Salat ◽

Cut Lilis Setiawati ◽

Zikrul Khalid

Keyword(s):

Mobile Phone ◽

Programming Language ◽

Satellite Tracking ◽

Low Noise ◽

Monitoring Tool ◽

Java Programming Language ◽

Java Programming ◽

The Creation ◽

Tracking Device ◽

Ku Band

Mobile phone users, especially the Android version of the smartphone, are increasingly spoiling their users. It is undeniable that users do not know their age, even many children have an Android version of the smartphone to play with. Meanwhile, in the satellite tracking world, the satellite tracking is still using TV when tracking the satellite so that it feels difficult. ApplicationLow Noise Block Converter is a video view application from a receiver to an Android smartphone that was built to make it easier for tracking satellites to track one of the satellites that you want to lock. This application also includes satellite tracking information facilities such as tracking guides, frequency updates, and satellite location. ApplicationLow Noise Block Converterbuilt with the Android Studio application using the Java programming language. With the creation of the applicationLow Noise Block Converter seas a new alternative to replace TV as a satellite tracking device or monitoring tool.

Download Full-text

A Study on the Mechanism of Social Robot Attitude Formation through Consumer Gaze Analysis: Focusing on the Robot Face

SHS Web of Conferences ◽

10.1051/shsconf/202213201017 ◽

2022 ◽

Vol 132 ◽

pp. 01017

Author(s):

Sangjip Ha ◽

Eun-ju Yi ◽

In-jin Yoo ◽

Do-Hyung Park

Keyword(s):

Eye Tracking ◽

Social Robots ◽

Social Robot ◽

Attitude Formation ◽

Consumer Attitude ◽

Robot Design ◽

Gaze Tracking ◽

The Gaze ◽

Consumer Beliefs ◽

The Social

This study intends to utilize eye tracking for the appearance of a robot, which is one of the trends in social robot design research. We suggest a research model with the entire stage from the consumer gaze response to the perceived consumer beliefs and further their attitudes toward social robots. Specifically, the eye tracking indicators used in this study are Fixation, First Visit, Total Viewed Stay Time, and Number of Revisits. Also, Areas of Interest are selected to the face, eyes, lips, and full-body of a social robot. In the first relationship, we check which element of the social robot design the consumer’s gaze stays on, and how the gaze on each element affects consumer beliefs. The consumer beliefs are considered as the social robot’s emotional expression, humanness, and facial prominence. Second, we explore whether the formation of consumer attitudes is possible through two major channels. One is the path that the consumer beliefs formed through the gaze influence their attitude, and the other is the path that the consumer gaze response directly influences the attitude. This study made a theoretical contribution in that it finally analysed the path of consumer attitude formation from various angles by linking the gaze tracking reaction and consumer perception. In addition, it is expected to make practical contributions in the suggestion of specific design insights that can be used as a reference for designing social robots.

Download Full-text