• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.3
• /
• pp.123-129
• /
• 2023

if we know what we're looking at, we can get a lot of information. Due to the development of eye tracking, Information on gaze point can be obtained through software provided by various eye tracking equipments. However, it is difficult to estimate accurate information such as the actual gaze depth. If it is possible to calibrate the eye tracker with the actual gaze depth, it will enable the derivation of realistic and accurate results with reliable validity in various fields such as simulation, digital twin, VR, and more. Therefore, in this paper, we experiment with acquiring and calibrating raw gaze depth using an eye tracker and software. The experiment involves designing a Deep Neural Network (DNN) model and then acquiring gaze depth values provided by the software for specified distances from 300mm to 10,000mm. The acquired data is trained through the designed DNN model and calibrated to correspond to the actual gaze depth. In our experiments with the calibrated model, we were able to achieve actual gaze depth values of 297mm, 904mm, 1,485mm, 2,005mm, 3,011mm, 4,021mm, 4,972mm, 6,027mm, 7,026mm, 8,043mm, 9,021mm, and 10,076mm for the specified distances from 300mm to 10,000mm.

• The Journal of the Korea Contents Association
• /
• v.16 no.12
• /
• pp.10-18
• /
• 2016

The cognitive ability of humans depends much on the vision. 'Vision' refers to the sense that receives stimulus of light through eyes. 'Gaze' refers to a function of a straight line that connects the central point of the pupil and a viewpoint in the external world, and, in general, it means a straight line that connects an object that is viewed and the eyes. There are active studies on the gaze in various academic circles including 'psychology' and 'cognitive linguistics.' As a method to objectively analyze the gaze, studies on 'eye tracking' are revitalized. A device for studies on eye tracking is an 'eye tracker.' As the fields of the study expand from development and analysis of Web pages to analysis of stores, methods of traffic signal processing, transport equipment, analysis of user experiences on image contents, and marketing analysis, there occurs a greater demand for a glasses eye-tracking than that for a fixed eye tracker. This study identifies the overview and characteristics of eye tracking and presents a way for spreading studies on eye tracking.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.3C
• /
• pp.125-132
• /
• 2005

This paper describes a computer vision system based on active IR illumination for real-time gaze discrimination system. Unlike most of the existing gaze discrimination techniques, which often require assuming a static head to work well and require a cumbersome calibration process for each person, our gaze discrimination system can perform robust and accurate gaze estimation without calibration and under rather significant head movement. This is made possible by a new gaze calibration procedure that identifies the mapping from pupil parameters to screen coordinates using generalized regression neural networks (GRNNs). With GRNNs, the mapping does not have to be an analytical function and head movement is explicitly accounted for by the gaze mapping function. Futhermore, the mapping function can generalize to other individuals not used in the training. To further improve the gaze estimation accuracy, we employ a reclassification scheme that deals with the classes that tend to be misclassified. This leads to a 10% improvement in classification error. The angular gaze accuracy is about 5°horizontally and 8°vertically. The effectiveness of our gaze tracker is demonstrated by experiments that involve gaze-contingent interactive graphic display.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.3 no.1
• /
• pp.38-46
• /
• 2010

This paper describes a computer vision system based on active IR illumination for real-time gaze discrimination system. Unlike most of the existing gaze discrimination techniques, which often require assuming a static head to work well and require a cumbersome calibration process for each person, our gaze discrimination system can perform robust and accurate gaze estimation without calibration and under rather significant head movement. This is made possible by a new gaze calibration procedure that identifies the mapping from pupil parameters to screen coordinates using generalized regression neural networks (GRNNs). With GRNNs, the mapping does not have to be an analytical function and head movement is explicitly accounted for by the gaze mapping function. Furthermore, the mapping function can generalize to other individuals not used in the training. To further improve the gaze estimation accuracy, we employ a reclassification scheme that deals with the classes that tend to be misclassified. This leads to a 10% improvement in classification error. The angular gaze accuracy is about $5^{\circ}$horizontally and $8^{\circ}$vertically. The effectiveness of our gaze tracker is demonstrated by experiments that involve gaze-contingent interactive graphic display.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.2
• /
• pp.322-329
• /
• 2005

This paper describes a computer vision system based on active IR illumination for real-time gaze discrimination system. Unlike most of the existing gaze discrimination techniques, which often require assuming a static head to work well and require a cumbersome calibration process for each person, our gaze discrimination system can perform robust and accurate gaze estimation without calibration and under rather significant head movement. This is made possible by a new gaze calibration procedure that identifies the mapping from pupil parameters to screen coordinates using generalized regression neural networks (GRNNS). With GRNNS, the mapping does not have to be an analytical function and head movement is explicitly accounted for by the gaze mapping function. furthermore, the mapping function can generalize to other individuals not used in the training. To further improve the gaze estimation accuracy, we employ a reclassification scheme that deals with the classes that tend to be misclassified. This leads to a 10$\%$ improvement in classification error. The angular gaze accuracy is about $5^{circ}$horizontally and $8^{circ}$vertically. The effectiveness of our gaze tracker is demonstrated by experiments that involve gaze-contingent interactive graphic display.

• Communications of Mathematical Education
• /
• v.32 no.3
• /
• pp.275-296
• /
• 2018

The purpose of this study is to investigate the change of gaze and the change of the proof learning achievement after learning the analytic method for proof to mathematical gifted students using eye tracking technique. In order to complete the purpose of this study, a mixed method research was used, that is a combination of quantitative and qualitative research methods. Quantitative analysis was conducted based on the data obtained through the eye tracker, and qualitative analysis was also done using post interview data to make up for the quantitative analysis. The subjects of this study were 8 mathematical gifted 3rd grade middle school students in the gifted education center. The conclusions of this study are as follows. First, the learning of analysis leads to a change of gaze in the proof learning of students. The students, after learning the analysis, moved their gaze from the bottom to the top when solving the proof problem, and the occupancy rate of the gaze to the bottom of the proof was higher than the higher part. Second, the change of gaze caused by the learning of the analysis have a correlation with the achievement of the proof learning and it can be seen that the method learning improves the achievement of the proof learning of the students.

• Journal of Korea Multimedia Society
• /
• v.25 no.2
• /
• pp.421-431
• /
• 2022

The purpose of this research is to determine the point of fixation of the driver during the process of driving. Based on the results of this research, the driving instructor can make a judgement on what the trainee stare on the most. Traffic accidents have become a serious concern in modern society. Especially, the traffic accidents among unskilled and elderly drivers are at issue. A driver should put attention on the vehicles around, traffic signs, passersby, passengers, road situation and its dashboard. An eye-tracking-based application was developed to analyze the driver's gaze behavior. It is a prototype for real-time eye tracking for monitoring the point of interest of drivers in driving practice. In this study, the driver's attention was measured by capturing the movement of the eyes in real road driving conditions using these tools. As a result, dwelling duration time, entry time and the average of fixation of the eye gaze are leading parameters that could help us prove the idea of this study.

• KIISE Transactions on Computing Practices
• /
• v.21 no.9
• /
• pp.610-615
• /
• 2015

The accuracy and precision of video-based remote gaze trackers is affected by numerous factors (e.g. the head movement of the participant). However, it is challenging to control all factors that have an influence, and doing so (e.g., using a chin-rest to control geometry) could lead to losing the benefit of using gaze trackers, i.e., the ecological validity of their unobtrusive nature. We propose an adaptive zoom-based gaze tracking technique, ZoomTrack that addresses this problem by improving the resolution of the gaze tracking results. Our approach magnifies a region-of-interest (ROI) and retrieves gaze points at a higher resolution under two different zooming modes: only when the gaze reaches the ROI (temporary) or whenever a participant stares at the stimuli (omnipresent). We compared these against the base case without magnification in a user study. The results are then used to summarize the advantages and limitations of our technique.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.07a
• /
• pp.139-140
• /
• 2019

난독증은 정상적인 지능에도 불구하고 문장을 읽기가 어려운 독서 장애다. 난독증 진단 방법은 ADHD처럼 증상 체크리스트가 없다. 지적장애를 판정할 때 사용하는 웩슬러 지능검사 같은 전 세계인이 사용하는 아주 보편화된 심리검사도 없다. 미국 진단기준의 최신판인 DSM-5에도 어떤 검사를 해서 기준점수 아래여야 진단할 수 있다고 명확히 써놓지 않았다. 본 논문에서는 이를 해결하기 위해 글자, 단어, 문장, 문단의 단위를 설정하여 화면에 출력하고 아이트래커를 활용하여 읽는 사람의 시선 데이터를 수집하여 히트맵으로 분석한다.

• Journal of Korean Elementary Science Education
• /
• v.36 no.4
• /
• pp.303-315
• /
• 2017

The purpose of this study is to analyze elementary teachers' science class objectively and quantitatively using Mobile Eye Tracker. The mobile eye tracker is easy to wear in eyeglasses form. And experiments are collected in video form, so it is very useful for realizing objective data of teacher's class situation in real time. Participants in the study were 2 elementary teachers, and they are teaching sixth grade science in Seoul. Participants took a 40-minute class wearing a mobile eye tracker. Eye movements of participants were collected at 60 Hz, and the collected eye movement data were analyzed using SMI BeGaze 3.7. In this study, the area related to the class was set as the area of interest, we analyzed the visual occupancy of teachers. In addition, we analyzed the linguistic interaction between teacher and students. The results of the study are as follows. First, we analyze the visual occupancy of meaningful areas in teaching-learning activities by class stage. Second, the analysis of eye movements when teachers interacted with students showed that teacher A had a high percentage of students' faces, while teacher B had a high visual occupation in areas not related to classes. Third, the linguistic interaction of the participants were analyzed. Analysis areas include questions, attention-focused language, elementary science teaching terminology, daily interaction, humor, and unnecessary words. This study shows that it is possible to analyze elementary science class objectively and quantitatively through analysis of visual occupancy using mobile eye tracking. In addition, it is expected that teachers' visual attention in teaching activities can be used as an index to analyze the form of language interaction.