Improving the robustness of gaze tracking under unconstrained illumination conditions

Kwang Hyun Uhm; Mun Cheon Kang; Joon Yeon Kim; Sung Jea Ko

doi:10.1007/s11042-020-08679-y

Improving the robustness of gaze tracking under unconstrained illumination conditions

Kwang Hyun Uhm, Mun Cheon Kang, Joon Yeon Kim, Sung Jea Ko

School of Electrical Engineering

Research output: Contribution to journal › Article › peer-review

5 Citations (Scopus)

Abstract

In human-computer interaction (HCI) applications, the performance degradation of gaze trackers in real-world environments is a critical issue. Typically, gaze trackers utilize the pupil center and corneal reflection (CR) obtained from an infrared (IR) light source to estimate the point of regard (POR). However, false CRs are often generated due to extraneous light sources such as sunlight or lamps. In this study, we propose a method of improving the robustness of gaze tracking under unconstrained illumination conditions. First, the proposed method generates a coded CR pattern by utilizing time-multiplexed IR light sources. Next, the CR candidates are detected in eye images, and their coordinates are compensated based on the head and eye movements of the user. Finally, true CRs are selected from the motion-compensated CR candidates by utilizing a novel cost function. Experimental results indicate that the gaze-tracking performance of the proposed method under various light conditions is considerably better than those of the conventional methods.

Original language	English
Pages (from-to)	20603-20616
Number of pages	14
Journal	Multimedia Tools and Applications
Volume	79
Issue number	29-30
DOIs	https://doi.org/10.1007/s11042-020-08679-y
Publication status	Published - 2020 Aug 1

Bibliographical note

Funding Information:
This work was supported by the Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No. 2014-3-00077, Development of global multi-target tracking and event prediction techniques based on real-time large-scale video analysis).

Publisher Copyright:
© 2020, Springer Science+Business Media, LLC, part of Springer Nature.

Keywords

Gaze tracking
Human computer interaction

ASJC Scopus subject areas

Software
Media Technology
Hardware and Architecture
Computer Networks and Communications

Access to Document

10.1007/s11042-020-08679-y

Cite this

@article{75674a6f311b4eccb8e1e6c08ca07fd2,

title = "Improving the robustness of gaze tracking under unconstrained illumination conditions",

abstract = "In human-computer interaction (HCI) applications, the performance degradation of gaze trackers in real-world environments is a critical issue. Typically, gaze trackers utilize the pupil center and corneal reflection (CR) obtained from an infrared (IR) light source to estimate the point of regard (POR). However, false CRs are often generated due to extraneous light sources such as sunlight or lamps. In this study, we propose a method of improving the robustness of gaze tracking under unconstrained illumination conditions. First, the proposed method generates a coded CR pattern by utilizing time-multiplexed IR light sources. Next, the CR candidates are detected in eye images, and their coordinates are compensated based on the head and eye movements of the user. Finally, true CRs are selected from the motion-compensated CR candidates by utilizing a novel cost function. Experimental results indicate that the gaze-tracking performance of the proposed method under various light conditions is considerably better than those of the conventional methods.",

keywords = "Gaze tracking, Human computer interaction",

author = "Uhm, {Kwang Hyun} and Kang, {Mun Cheon} and Kim, {Joon Yeon} and Ko, {Sung Jea}",

note = "Funding Information: This work was supported by the Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No. 2014-3-00077, Development of global multi-target tracking and event prediction techniques based on real-time large-scale video analysis). Publisher Copyright: {\textcopyright} 2020, Springer Science+Business Media, LLC, part of Springer Nature.",

year = "2020",

month = aug,

day = "1",

doi = "10.1007/s11042-020-08679-y",

language = "English",

volume = "79",

pages = "20603--20616",

journal = "Multimedia Tools and Applications",

issn = "1380-7501",

publisher = "Springer Netherlands",

number = "29-30",

}

TY - JOUR

T1 - Improving the robustness of gaze tracking under unconstrained illumination conditions

AU - Uhm, Kwang Hyun

AU - Kang, Mun Cheon

AU - Kim, Joon Yeon

AU - Ko, Sung Jea

N1 - Funding Information: This work was supported by the Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No. 2014-3-00077, Development of global multi-target tracking and event prediction techniques based on real-time large-scale video analysis). Publisher Copyright: © 2020, Springer Science+Business Media, LLC, part of Springer Nature.

PY - 2020/8/1

Y1 - 2020/8/1

N2 - In human-computer interaction (HCI) applications, the performance degradation of gaze trackers in real-world environments is a critical issue. Typically, gaze trackers utilize the pupil center and corneal reflection (CR) obtained from an infrared (IR) light source to estimate the point of regard (POR). However, false CRs are often generated due to extraneous light sources such as sunlight or lamps. In this study, we propose a method of improving the robustness of gaze tracking under unconstrained illumination conditions. First, the proposed method generates a coded CR pattern by utilizing time-multiplexed IR light sources. Next, the CR candidates are detected in eye images, and their coordinates are compensated based on the head and eye movements of the user. Finally, true CRs are selected from the motion-compensated CR candidates by utilizing a novel cost function. Experimental results indicate that the gaze-tracking performance of the proposed method under various light conditions is considerably better than those of the conventional methods.

AB - In human-computer interaction (HCI) applications, the performance degradation of gaze trackers in real-world environments is a critical issue. Typically, gaze trackers utilize the pupil center and corneal reflection (CR) obtained from an infrared (IR) light source to estimate the point of regard (POR). However, false CRs are often generated due to extraneous light sources such as sunlight or lamps. In this study, we propose a method of improving the robustness of gaze tracking under unconstrained illumination conditions. First, the proposed method generates a coded CR pattern by utilizing time-multiplexed IR light sources. Next, the CR candidates are detected in eye images, and their coordinates are compensated based on the head and eye movements of the user. Finally, true CRs are selected from the motion-compensated CR candidates by utilizing a novel cost function. Experimental results indicate that the gaze-tracking performance of the proposed method under various light conditions is considerably better than those of the conventional methods.

KW - Gaze tracking

KW - Human computer interaction

UR - http://www.scopus.com/inward/record.url?scp=85084085853&partnerID=8YFLogxK

U2 - 10.1007/s11042-020-08679-y

DO - 10.1007/s11042-020-08679-y

M3 - Article

AN - SCOPUS:85084085853

SN - 1380-7501

VL - 79

SP - 20603

EP - 20616

JO - Multimedia Tools and Applications

JF - Multimedia Tools and Applications

IS - 29-30

ER -

Improving the robustness of gaze tracking under unconstrained illumination conditions

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this