Deep belief network based gaze tracker for auto-aiming system

Chih Wei Chien, Ting Nan Tsai, L. F. Wu, N. C. Fang, C. Y. Liu, Tzuu-Hseng S. Li

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper proposes a design of an auto-aiming system, which is capable of tracking a user's gaze automatically. The auto-aiming system is composed of an electric gun control system and a wearable gaze tracker. According to a user's gaze direction which is captured by the helmet camera, the gun can automatically aim an object which the user is looking at. The mapping model between the user's eye movement and the shooting direction of the gun is established by a Deep Belief Network (DBN). This DBN-based gaze tracking model allows the auto-aiming shooting system to aim the target timely and accurately. Finally, the experiment results demonstrate the proposed auto-aiming system for different users can achieve an average accuracy of 96%.

Original languageEnglish
Title of host publication2017 International Conference on Advanced Robotics and Intelligent Systems, ARIS 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Volume2017-September
ISBN (Print)9781538624197
DOIs
Publication statusPublished - 2018 Feb 20
Event2017 International Conference on Advanced Robotics and Intelligent Systems, ARIS 2017 - Taipei, Taiwan
Duration: 2017 Sep 62017 Sep 8

Other

Other2017 International Conference on Advanced Robotics and Intelligent Systems, ARIS 2017
CountryTaiwan
CityTaipei
Period17-09-0617-09-08

Fingerprint

Bayesian networks
Eye movements
Cameras
Control systems
Experiments

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Artificial Intelligence

Cite this

Chien, C. W., Tsai, T. N., Wu, L. F., Fang, N. C., Liu, C. Y., & Li, T-H. S. (2018). Deep belief network based gaze tracker for auto-aiming system. In 2017 International Conference on Advanced Robotics and Intelligent Systems, ARIS 2017 (Vol. 2017-September). [8297183] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ARIS.2017.8297183
Chien, Chih Wei ; Tsai, Ting Nan ; Wu, L. F. ; Fang, N. C. ; Liu, C. Y. ; Li, Tzuu-Hseng S. / Deep belief network based gaze tracker for auto-aiming system. 2017 International Conference on Advanced Robotics and Intelligent Systems, ARIS 2017. Vol. 2017-September Institute of Electrical and Electronics Engineers Inc., 2018.
@inproceedings{31f9e62f8c33416a87a3d616c662ed07,
title = "Deep belief network based gaze tracker for auto-aiming system",
abstract = "This paper proposes a design of an auto-aiming system, which is capable of tracking a user's gaze automatically. The auto-aiming system is composed of an electric gun control system and a wearable gaze tracker. According to a user's gaze direction which is captured by the helmet camera, the gun can automatically aim an object which the user is looking at. The mapping model between the user's eye movement and the shooting direction of the gun is established by a Deep Belief Network (DBN). This DBN-based gaze tracking model allows the auto-aiming shooting system to aim the target timely and accurately. Finally, the experiment results demonstrate the proposed auto-aiming system for different users can achieve an average accuracy of 96{\%}.",
author = "Chien, {Chih Wei} and Tsai, {Ting Nan} and Wu, {L. F.} and Fang, {N. C.} and Liu, {C. Y.} and Li, {Tzuu-Hseng S.}",
year = "2018",
month = "2",
day = "20",
doi = "10.1109/ARIS.2017.8297183",
language = "English",
isbn = "9781538624197",
volume = "2017-September",
booktitle = "2017 International Conference on Advanced Robotics and Intelligent Systems, ARIS 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Chien, CW, Tsai, TN, Wu, LF, Fang, NC, Liu, CY & Li, T-HS 2018, Deep belief network based gaze tracker for auto-aiming system. in 2017 International Conference on Advanced Robotics and Intelligent Systems, ARIS 2017. vol. 2017-September, 8297183, Institute of Electrical and Electronics Engineers Inc., 2017 International Conference on Advanced Robotics and Intelligent Systems, ARIS 2017, Taipei, Taiwan, 17-09-06. https://doi.org/10.1109/ARIS.2017.8297183

Deep belief network based gaze tracker for auto-aiming system. / Chien, Chih Wei; Tsai, Ting Nan; Wu, L. F.; Fang, N. C.; Liu, C. Y.; Li, Tzuu-Hseng S.

2017 International Conference on Advanced Robotics and Intelligent Systems, ARIS 2017. Vol. 2017-September Institute of Electrical and Electronics Engineers Inc., 2018. 8297183.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Deep belief network based gaze tracker for auto-aiming system

AU - Chien, Chih Wei

AU - Tsai, Ting Nan

AU - Wu, L. F.

AU - Fang, N. C.

AU - Liu, C. Y.

AU - Li, Tzuu-Hseng S.

PY - 2018/2/20

Y1 - 2018/2/20

N2 - This paper proposes a design of an auto-aiming system, which is capable of tracking a user's gaze automatically. The auto-aiming system is composed of an electric gun control system and a wearable gaze tracker. According to a user's gaze direction which is captured by the helmet camera, the gun can automatically aim an object which the user is looking at. The mapping model between the user's eye movement and the shooting direction of the gun is established by a Deep Belief Network (DBN). This DBN-based gaze tracking model allows the auto-aiming shooting system to aim the target timely and accurately. Finally, the experiment results demonstrate the proposed auto-aiming system for different users can achieve an average accuracy of 96%.

AB - This paper proposes a design of an auto-aiming system, which is capable of tracking a user's gaze automatically. The auto-aiming system is composed of an electric gun control system and a wearable gaze tracker. According to a user's gaze direction which is captured by the helmet camera, the gun can automatically aim an object which the user is looking at. The mapping model between the user's eye movement and the shooting direction of the gun is established by a Deep Belief Network (DBN). This DBN-based gaze tracking model allows the auto-aiming shooting system to aim the target timely and accurately. Finally, the experiment results demonstrate the proposed auto-aiming system for different users can achieve an average accuracy of 96%.

UR - http://www.scopus.com/inward/record.url?scp=85054335004&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85054335004&partnerID=8YFLogxK

U2 - 10.1109/ARIS.2017.8297183

DO - 10.1109/ARIS.2017.8297183

M3 - Conference contribution

AN - SCOPUS:85054335004

SN - 9781538624197

VL - 2017-September

BT - 2017 International Conference on Advanced Robotics and Intelligent Systems, ARIS 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Chien CW, Tsai TN, Wu LF, Fang NC, Liu CY, Li T-HS. Deep belief network based gaze tracker for auto-aiming system. In 2017 International Conference on Advanced Robotics and Intelligent Systems, ARIS 2017. Vol. 2017-September. Institute of Electrical and Electronics Engineers Inc. 2018. 8297183 https://doi.org/10.1109/ARIS.2017.8297183