Robust gaze estimation via normalized iris center-eye corner vector

Haibin Cai; Hui Yu; Xiaolong Zhou; Honghai Liu

doi:10.1007/978-3-319-43506-0_26

Robust gaze estimation via normalized iris center-eye corner vector

Haibin Cai, Hui Yu, Xiaolong Zhou, Honghai Liu

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

380 Downloads (Pure)

Abstract

Gaze estimation plays an important role in many practical scenarios such as human robot interaction. Although high accurate gaze estimation could be obtained in constrained settings with additional IR sources or depth sensors, single web-cam based gaze estimation still remains challenging. This paper propose a normalized iris center-eye corner (NIC-EC) vector based gaze estimation methods using a single, low cost web-cam. Firstly, reliable facial features and pupil centers are extracted. Then, the NIC-EC vector is proposed to enhance the robustness and accuracy for pupil center-eye corner vector based gaze estimations. Finally, an interpolation method is employed for the mapping between constructed vectors and points of regard. Experimental results showed that the proposed method has significantly improved the accuracy over the pupil center-eye corner vector based gaze estimation method with average accuracy of 1.66∘ under slight head movements.

Original language	English
Title of host publication	Intelligent Robotics and Applications
Subtitle of host publication	9th International Conference, ICIRA 2016, Tokyo, Japan, August 22-24, 2016, Proceedings, Part I
Editors	Naoyuki Kubota, Kazuo Kiguchi, Honghai Liu, Takenori Obo
Publisher	Springer
Pages	300-309
DOIs	https://doi.org/10.1007/978-3-319-43506-0_26
Publication status	Published - 3 Aug 2016
Event	International Conference on Intelligent Robotics and Applications 2016 - Tokyo Metropolitan University, Tokyo, Japan Duration: 20 Aug 2016 → 25 Aug 2016 http://www.comp.sd.tmu.ac.jp/icira2016/

Publication series

Name	Lecture Notes in Computer Science
Volume	9834
ISSN (Print)	0302-9743

Conference

Conference	International Conference on Intelligent Robotics and Applications 2016
Abbreviated title	ICIRA2016
Country/Territory	Japan
City	Tokyo
Period	20/08/16 → 25/08/16
Internet address	http://www.comp.sd.tmu.ac.jp/icira2016/

Access to Document

10.1007/978-3-319-43506-0_26

Robust Gaze ICIRA2016
The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-43506-0_26.
Accepted author manuscript (Post-print), 392 KB

Cite this

Cai, H., Yu, H., Zhou, X., & Liu, H. (2016). Robust gaze estimation via normalized iris center-eye corner vector. In N. Kubota, K. Kiguchi, H. Liu, & T. Obo (Eds.), Intelligent Robotics and Applications: 9th International Conference, ICIRA 2016, Tokyo, Japan, August 22-24, 2016, Proceedings, Part I (pp. 300-309). (Lecture Notes in Computer Science; Vol. 9834). Springer. https://doi.org/10.1007/978-3-319-43506-0_26

Cai, Haibin ; Yu, Hui ; Zhou, Xiaolong et al. / Robust gaze estimation via normalized iris center-eye corner vector. Intelligent Robotics and Applications: 9th International Conference, ICIRA 2016, Tokyo, Japan, August 22-24, 2016, Proceedings, Part I. editor / Naoyuki Kubota ; Kazuo Kiguchi ; Honghai Liu ; Takenori Obo. Springer, 2016. pp. 300-309 (Lecture Notes in Computer Science).

@inproceedings{bbd75d75d7b041ba9281f90e70d393e2,

title = "Robust gaze estimation via normalized iris center-eye corner vector",

abstract = "Gaze estimation plays an important role in many practical scenarios such as human robot interaction. Although high accurate gaze estimation could be obtained in constrained settings with additional IR sources or depth sensors, single web-cam based gaze estimation still remains challenging. This paper propose a normalized iris center-eye corner (NIC-EC) vector based gaze estimation methods using a single, low cost web-cam. Firstly, reliable facial features and pupil centers are extracted. Then, the NIC-EC vector is proposed to enhance the robustness and accuracy for pupil center-eye corner vector based gaze estimations. Finally, an interpolation method is employed for the mapping between constructed vectors and points of regard. Experimental results showed that the proposed method has significantly improved the accuracy over the pupil center-eye corner vector based gaze estimation method with average accuracy of 1.66∘ under slight head movements.",

author = "Haibin Cai and Hui Yu and Xiaolong Zhou and Honghai Liu",

year = "2016",

month = aug,

day = "3",

doi = "10.1007/978-3-319-43506-0_26",

language = "English",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "300--309",

editor = "Naoyuki Kubota and Kazuo Kiguchi and Honghai Liu and Takenori Obo",

booktitle = "Intelligent Robotics and Applications",

note = "International Conference on Intelligent Robotics and Applications 2016, ICIRA2016 ; Conference date: 20-08-2016 Through 25-08-2016",

url = "http://www.comp.sd.tmu.ac.jp/icira2016/",

}

Cai, H, Yu, H, Zhou, X & Liu, H 2016, Robust gaze estimation via normalized iris center-eye corner vector. in N Kubota, K Kiguchi, H Liu & T Obo (eds), Intelligent Robotics and Applications: 9th International Conference, ICIRA 2016, Tokyo, Japan, August 22-24, 2016, Proceedings, Part I. Lecture Notes in Computer Science, vol. 9834, Springer, pp. 300-309, International Conference on Intelligent Robotics and Applications 2016, Tokyo, Japan, 20/08/16. https://doi.org/10.1007/978-3-319-43506-0_26

Robust gaze estimation via normalized iris center-eye corner vector. / Cai, Haibin; Yu, Hui; Zhou, Xiaolong et al.
Intelligent Robotics and Applications: 9th International Conference, ICIRA 2016, Tokyo, Japan, August 22-24, 2016, Proceedings, Part I. ed. / Naoyuki Kubota; Kazuo Kiguchi; Honghai Liu; Takenori Obo. Springer, 2016. p. 300-309 (Lecture Notes in Computer Science; Vol. 9834).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Robust gaze estimation via normalized iris center-eye corner vector

AU - Cai, Haibin

AU - Yu, Hui

AU - Zhou, Xiaolong

AU - Liu, Honghai

PY - 2016/8/3

Y1 - 2016/8/3

N2 - Gaze estimation plays an important role in many practical scenarios such as human robot interaction. Although high accurate gaze estimation could be obtained in constrained settings with additional IR sources or depth sensors, single web-cam based gaze estimation still remains challenging. This paper propose a normalized iris center-eye corner (NIC-EC) vector based gaze estimation methods using a single, low cost web-cam. Firstly, reliable facial features and pupil centers are extracted. Then, the NIC-EC vector is proposed to enhance the robustness and accuracy for pupil center-eye corner vector based gaze estimations. Finally, an interpolation method is employed for the mapping between constructed vectors and points of regard. Experimental results showed that the proposed method has significantly improved the accuracy over the pupil center-eye corner vector based gaze estimation method with average accuracy of 1.66∘ under slight head movements.

AB - Gaze estimation plays an important role in many practical scenarios such as human robot interaction. Although high accurate gaze estimation could be obtained in constrained settings with additional IR sources or depth sensors, single web-cam based gaze estimation still remains challenging. This paper propose a normalized iris center-eye corner (NIC-EC) vector based gaze estimation methods using a single, low cost web-cam. Firstly, reliable facial features and pupil centers are extracted. Then, the NIC-EC vector is proposed to enhance the robustness and accuracy for pupil center-eye corner vector based gaze estimations. Finally, an interpolation method is employed for the mapping between constructed vectors and points of regard. Experimental results showed that the proposed method has significantly improved the accuracy over the pupil center-eye corner vector based gaze estimation method with average accuracy of 1.66∘ under slight head movements.

U2 - 10.1007/978-3-319-43506-0_26

DO - 10.1007/978-3-319-43506-0_26

M3 - Conference contribution

T3 - Lecture Notes in Computer Science

SP - 300

EP - 309

BT - Intelligent Robotics and Applications

A2 - Kubota, Naoyuki

A2 - Kiguchi, Kazuo

A2 - Liu, Honghai

A2 - Obo, Takenori

PB - Springer

T2 - International Conference on Intelligent Robotics and Applications 2016

Y2 - 20 August 2016 through 25 August 2016

ER -

Cai H, Yu H, Zhou X, Liu H. Robust gaze estimation via normalized iris center-eye corner vector. In Kubota N, Kiguchi K, Liu H, Obo T, editors, Intelligent Robotics and Applications: 9th International Conference, ICIRA 2016, Tokyo, Japan, August 22-24, 2016, Proceedings, Part I. Springer. 2016. p. 300-309. (Lecture Notes in Computer Science). doi: 10.1007/978-3-319-43506-0_26

Robust gaze estimation via normalized iris center-eye corner vector

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this