TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Real-time hidden gaze point correction

Tutkimustuotosvertaisarvioitu

Standard

Real-time hidden gaze point correction. / Špakov, Oleg; Gizatdinova, Yulia.

Proceedings of the Symposium on Eye Tracking Research and Applications, ETRA 2014. Association for Computing Machinery, 2014. s. 291-294.

Tutkimustuotosvertaisarvioitu

Harvard

Špakov, O & Gizatdinova, Y 2014, Real-time hidden gaze point correction. julkaisussa Proceedings of the Symposium on Eye Tracking Research and Applications, ETRA 2014. Association for Computing Machinery, Sivut 291-294, Safety Harbor, FL, Yhdysvallat, 26/03/14. https://doi.org/10.1145/2578153.2578200

APA

Špakov, O., & Gizatdinova, Y. (2014). Real-time hidden gaze point correction. teoksessa Proceedings of the Symposium on Eye Tracking Research and Applications, ETRA 2014 (Sivut 291-294). Association for Computing Machinery. https://doi.org/10.1145/2578153.2578200

Vancouver

Špakov O, Gizatdinova Y. Real-time hidden gaze point correction. julkaisussa Proceedings of the Symposium on Eye Tracking Research and Applications, ETRA 2014. Association for Computing Machinery. 2014. s. 291-294 https://doi.org/10.1145/2578153.2578200

Author

Špakov, Oleg ; Gizatdinova, Yulia. / Real-time hidden gaze point correction. Proceedings of the Symposium on Eye Tracking Research and Applications, ETRA 2014. Association for Computing Machinery, 2014. Sivut 291-294

Bibtex - Lataa

@inproceedings{0ecad7392b8a466581eda5a8eae2353b,
title = "Real-time hidden gaze point correction",
abstract = "The accuracy of gaze point estimation is one of the main limiting factors in developing applications that utilize gaze input. The existing gaze point correction methods either do not support real-time interaction or imply restrictions on gazecontrolled tasks and object screen locations. We hypothesize that when gaze points can be reliably correlated with object screen locations, it is possible to gather and leverage this information for improving the accuracy of gaze pointing. We propose an algorithm that uses a growing pool of such collected correlations between gaze points and objects for real-time hidden gaze point correction. We tested this algorithm assuming that any point inside of a rectangular object has equal probability to be hit by gaze. We collected real data in a user study to simulate pointing at targets of small (80px) size. The results showed that our algorithm can significantly improve the hit rate especially in pointing at middle-sized targets. The proposed method is real-time, person- and taskindependent and is applicable for arbitrary located objects.",
keywords = "Accuracy correction, Algorithms, Cumulative distribution function, Eye tracking, Gaze point, Pointing",
author = "Oleg Špakov and Yulia Gizatdinova",
year = "2014",
doi = "10.1145/2578153.2578200",
language = "English",
isbn = "9781450327510",
pages = "291--294",
booktitle = "Proceedings of the Symposium on Eye Tracking Research and Applications, ETRA 2014",
publisher = "Association for Computing Machinery",

}

RIS (suitable for import to EndNote) - Lataa

TY - GEN

T1 - Real-time hidden gaze point correction

AU - Špakov, Oleg

AU - Gizatdinova, Yulia

PY - 2014

Y1 - 2014

N2 - The accuracy of gaze point estimation is one of the main limiting factors in developing applications that utilize gaze input. The existing gaze point correction methods either do not support real-time interaction or imply restrictions on gazecontrolled tasks and object screen locations. We hypothesize that when gaze points can be reliably correlated with object screen locations, it is possible to gather and leverage this information for improving the accuracy of gaze pointing. We propose an algorithm that uses a growing pool of such collected correlations between gaze points and objects for real-time hidden gaze point correction. We tested this algorithm assuming that any point inside of a rectangular object has equal probability to be hit by gaze. We collected real data in a user study to simulate pointing at targets of small (80px) size. The results showed that our algorithm can significantly improve the hit rate especially in pointing at middle-sized targets. The proposed method is real-time, person- and taskindependent and is applicable for arbitrary located objects.

AB - The accuracy of gaze point estimation is one of the main limiting factors in developing applications that utilize gaze input. The existing gaze point correction methods either do not support real-time interaction or imply restrictions on gazecontrolled tasks and object screen locations. We hypothesize that when gaze points can be reliably correlated with object screen locations, it is possible to gather and leverage this information for improving the accuracy of gaze pointing. We propose an algorithm that uses a growing pool of such collected correlations between gaze points and objects for real-time hidden gaze point correction. We tested this algorithm assuming that any point inside of a rectangular object has equal probability to be hit by gaze. We collected real data in a user study to simulate pointing at targets of small (80px) size. The results showed that our algorithm can significantly improve the hit rate especially in pointing at middle-sized targets. The proposed method is real-time, person- and taskindependent and is applicable for arbitrary located objects.

KW - Accuracy correction

KW - Algorithms

KW - Cumulative distribution function

KW - Eye tracking

KW - Gaze point

KW - Pointing

UR - http://www.scopus.com/inward/record.url?scp=84899672400&partnerID=8YFLogxK

U2 - 10.1145/2578153.2578200

DO - 10.1145/2578153.2578200

M3 - Conference contribution

SN - 9781450327510

SP - 291

EP - 294

BT - Proceedings of the Symposium on Eye Tracking Research and Applications, ETRA 2014

PB - Association for Computing Machinery

ER -