Parallax error compensation for head-mounted gaze trackers based on binocular data

Dan Su; Youfu Li; Caihua Xiong

doi:10.1109/RCAR.2016.7784004

Parallax error compensation for head-mounted gaze trackers based on binocular data

Dan Su
, Youfu Li^*
, Caihua Xiong

^*Corresponding author for this work

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

1 Citation (Scopus)

Abstract

The parallax error caused by the spatial offset between the eye monitoring camera and the scene camera is a common challenge for head-mounted gaze trackers. To address this problem, the parallax error is investigated based on the epipolar geometry at first and two parallax compensation methods for binocular gaze tracking setups are proposed in this paper to ensure the accurate gaze point estimation over a wide range of distances without on-line manual adjustments. A comparative study is conducted on these two methods, and simulation results demonstrate that our proposed compensation methods can be effectively applied on the binocular gaze trackers.

Original language	English
Title of host publication	2016 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2016
Publisher	IEEE
Pages	76-81
ISBN (Print)	9781467389594
DOIs	https://doi.org/10.1109/RCAR.2016.7784004
Publication status	Published - 6 Jun 2016
Event	2016 IEEE International Conference on Real-Time Computing and Robotics (IEEE-RCAR 2016) - Angkor Wat, Cambodia Duration: 6 Jun 2016 → 9 Jun 2016

Conference

Conference	2016 IEEE International Conference on Real-Time Computing and Robotics (IEEE-RCAR 2016)
Abbreviated title	IEEE-RCAR 2016
Place	Cambodia
City	Angkor Wat
Period	6/06/16 → 9/06/16

Access Output

10.1109/RCAR.2016.7784004

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{6ccbaaf5c9f34a758b237d53c7653693,

title = "Parallax error compensation for head-mounted gaze trackers based on binocular data",

abstract = "The parallax error caused by the spatial offset between the eye monitoring camera and the scene camera is a common challenge for head-mounted gaze trackers. To address this problem, the parallax error is investigated based on the epipolar geometry at first and two parallax compensation methods for binocular gaze tracking setups are proposed in this paper to ensure the accurate gaze point estimation over a wide range of distances without on-line manual adjustments. A comparative study is conducted on these two methods, and simulation results demonstrate that our proposed compensation methods can be effectively applied on the binocular gaze trackers.",

author = "Dan Su and Youfu Li and Caihua Xiong",

year = "2016",

month = jun,

day = "6",

doi = "10.1109/RCAR.2016.7784004",

language = "English",

isbn = "9781467389594",

pages = "76--81",

booktitle = "2016 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2016",

publisher = "IEEE",

address = "United States",

note = "2016 IEEE International Conference on Real-Time Computing and Robotics (IEEE-RCAR 2016), IEEE-RCAR 2016 ; Conference date: 06-06-2016 Through 09-06-2016",

}

Su, D , Li, Y & Xiong, C 2016, Parallax error compensation for head-mounted gaze trackers based on binocular data. in 2016 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2016., 7784004, IEEE, pp. 76-81, 2016 IEEE International Conference on Real-Time Computing and Robotics (IEEE-RCAR 2016), Angkor Wat, Cambodia, 6/06/16. https://doi.org/10.1109/RCAR.2016.7784004

Parallax error compensation for head-mounted gaze trackers based on binocular data. / Su, Dan ; Li, Youfu; Xiong, Caihua.
2016 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2016. IEEE, 2016. p. 76-81 7784004.

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Parallax error compensation for head-mounted gaze trackers based on binocular data

AU - Su, Dan

AU - Li, Youfu

AU - Xiong, Caihua

PY - 2016/6/6

Y1 - 2016/6/6

N2 - The parallax error caused by the spatial offset between the eye monitoring camera and the scene camera is a common challenge for head-mounted gaze trackers. To address this problem, the parallax error is investigated based on the epipolar geometry at first and two parallax compensation methods for binocular gaze tracking setups are proposed in this paper to ensure the accurate gaze point estimation over a wide range of distances without on-line manual adjustments. A comparative study is conducted on these two methods, and simulation results demonstrate that our proposed compensation methods can be effectively applied on the binocular gaze trackers.

AB - The parallax error caused by the spatial offset between the eye monitoring camera and the scene camera is a common challenge for head-mounted gaze trackers. To address this problem, the parallax error is investigated based on the epipolar geometry at first and two parallax compensation methods for binocular gaze tracking setups are proposed in this paper to ensure the accurate gaze point estimation over a wide range of distances without on-line manual adjustments. A comparative study is conducted on these two methods, and simulation results demonstrate that our proposed compensation methods can be effectively applied on the binocular gaze trackers.

UR - https://www.scopus.com/pages/publications/85010069999

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85010069999&origin=recordpage

U2 - 10.1109/RCAR.2016.7784004

DO - 10.1109/RCAR.2016.7784004

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9781467389594

SP - 76

EP - 81

BT - 2016 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2016

PB - IEEE

T2 - 2016 IEEE International Conference on Real-Time Computing and Robotics (IEEE-RCAR 2016)

Y2 - 6 June 2016 through 9 June 2016

ER -

Parallax error compensation for head-mounted gaze trackers based on binocular data

Abstract

Conference

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this