Home > Research > Publications & Outputs > Towards pervasive eye tracking using low-level ...

Research

Links

Text available via DOI:

View graph of relations

Towards pervasive eye tracking using low-level image features

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Published

Standard

Towards pervasive eye tracking using low-level image features. / Zhang, Yanxia; Bulling, Andreas; Gellersen, Hans.

Proceedings of the Symposium on Eye Tracking Research and Applications. New York, NY, USA : ACM, 2012. p. 261-264 (ETRA '12).

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Harvard

Zhang, Y, Bulling, A & Gellersen, H 2012, Towards pervasive eye tracking using low-level image features. in Proceedings of the Symposium on Eye Tracking Research and Applications. ETRA '12, ACM, New York, NY, USA, pp. 261-264. https://doi.org/10.1145/2168556.2168611

APA

Zhang, Y., Bulling, A., & Gellersen, H. (2012). Towards pervasive eye tracking using low-level image features. In Proceedings of the Symposium on Eye Tracking Research and Applications (pp. 261-264). (ETRA '12). ACM. https://doi.org/10.1145/2168556.2168611

Vancouver

Zhang Y, Bulling A, Gellersen H. Towards pervasive eye tracking using low-level image features. In Proceedings of the Symposium on Eye Tracking Research and Applications. New York, NY, USA: ACM. 2012. p. 261-264. (ETRA '12). doi: 10.1145/2168556.2168611

Author

Zhang, Yanxia ; Bulling, Andreas ; Gellersen, Hans. / Towards pervasive eye tracking using low-level image features. Proceedings of the Symposium on Eye Tracking Research and Applications. New York, NY, USA : ACM, 2012. pp. 261-264 (ETRA '12).

Bibtex

@inproceedings{c26d662276024b25a7ac902fe20130b1,
title = "Towards pervasive eye tracking using low-level image features",
abstract = "We contribute a novel gaze estimation technique, which is adaptable for person-independent applications. In a study with 17 participants, using a standard webcam, we recorded the subjects' left eye images for different gaze locations. From these images, we extracted five types of basic visual features. We then sub-selected a set of features with minimum Redundancy Maximum Relevance (mRMR) for the input of a 2-layer regression neural network for estimating the subjects' gaze. We investigated the effect of different visual features on the accuracy of gaze estimation. Using machine learning techniques, by combing different features, we achieved average gaze estimation error of 3.44° horizontally and 1.37° vertically for person-dependent.",
author = "Yanxia Zhang and Andreas Bulling and Hans Gellersen",
year = "2012",
doi = "10.1145/2168556.2168611",
language = "English",
isbn = "978-1-4503-1221-9",
series = "ETRA '12",
publisher = "ACM",
pages = "261--264",
booktitle = "Proceedings of the Symposium on Eye Tracking Research and Applications",

}

RIS

TY - GEN

T1 - Towards pervasive eye tracking using low-level image features

AU - Zhang, Yanxia

AU - Bulling, Andreas

AU - Gellersen, Hans

PY - 2012

Y1 - 2012

N2 - We contribute a novel gaze estimation technique, which is adaptable for person-independent applications. In a study with 17 participants, using a standard webcam, we recorded the subjects' left eye images for different gaze locations. From these images, we extracted five types of basic visual features. We then sub-selected a set of features with minimum Redundancy Maximum Relevance (mRMR) for the input of a 2-layer regression neural network for estimating the subjects' gaze. We investigated the effect of different visual features on the accuracy of gaze estimation. Using machine learning techniques, by combing different features, we achieved average gaze estimation error of 3.44° horizontally and 1.37° vertically for person-dependent.

AB - We contribute a novel gaze estimation technique, which is adaptable for person-independent applications. In a study with 17 participants, using a standard webcam, we recorded the subjects' left eye images for different gaze locations. From these images, we extracted five types of basic visual features. We then sub-selected a set of features with minimum Redundancy Maximum Relevance (mRMR) for the input of a 2-layer regression neural network for estimating the subjects' gaze. We investigated the effect of different visual features on the accuracy of gaze estimation. Using machine learning techniques, by combing different features, we achieved average gaze estimation error of 3.44° horizontally and 1.37° vertically for person-dependent.

U2 - 10.1145/2168556.2168611

DO - 10.1145/2168556.2168611

M3 - Conference contribution/Paper

SN - 978-1-4503-1221-9

T3 - ETRA '12

SP - 261

EP - 264

BT - Proceedings of the Symposium on Eye Tracking Research and Applications

PB - ACM

CY - New York, NY, USA

ER -