Brightness-And motion-Based blink detection for head-mounted eye trackers

Tobias Appel; Thiago Santini; Enkelejda Kasneci

doi:10.1145/2968219.2968341

Brightness-And motion-Based blink detection for head-mounted eye trackers

Tobias Appel
, Thiago Santini
, Enkelejda Kasneci

University of Töbingen

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

20 Scopus citations

Abstract

Blinks are an indicator for fatigue or drowsiness and can assis in the diagnose of mental disorders, such as schizophrenia Additionally, a blink that obstructs the pupil impairs th performance of other eye-Tracking algorithms, such as pupi detection, and often results in noise to the gaze estimation In this paper, we present a blink detection algorithm that i tailored towards head-mounted eye trackers and is robust t calibration-based variations like translation or rotation of th eye. The proposed approach reached 96,35% accuracy fo a realistic and challenging data set and in real-Time even o low-end devices, rendering the proposed method suited for pervasive eye tracking.

Original language	English
Title of host publication	UbiComp 2016 Adjunct - Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing
Publisher	Association for Computing Machinery, Inc
Pages	1726-1735
Number of pages	10
ISBN (Electronic)	9781450344623
DOIs	https://doi.org/10.1145/2968219.2968341
State	Published - 12 Sep 2016
Externally published	Yes
Event	2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2016 - Heidelberg, Germany Duration: 12 Sep 2016 → 16 Sep 2016

Publication series

Name	UbiComp 2016 Adjunct - Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing

Conference

Conference	2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2016
Country/Territory	Germany
City	Heidelberg
Period	12/09/16 → 16/09/16

Keywords

Blink detection
Image processing
Pervasive eye tracking
Real time

Access to Document

10.1145/2968219.2968341

Cite this

Appel, T., Santini, T., & Kasneci, E. (2016). Brightness-And motion-Based blink detection for head-mounted eye trackers. In UbiComp 2016 Adjunct - Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing (pp. 1726-1735). (UbiComp 2016 Adjunct - Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing). Association for Computing Machinery, Inc. https://doi.org/10.1145/2968219.2968341

Appel, Tobias ; Santini, Thiago ; Kasneci, Enkelejda. / Brightness-And motion-Based blink detection for head-mounted eye trackers. UbiComp 2016 Adjunct - Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing. Association for Computing Machinery, Inc, 2016. pp. 1726-1735 (UbiComp 2016 Adjunct - Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing).

@inproceedings{829b7d58a871475aaca3981ad582c141,

title = "Brightness-And motion-Based blink detection for head-mounted eye trackers",

abstract = "Blinks are an indicator for fatigue or drowsiness and can assis in the diagnose of mental disorders, such as schizophrenia Additionally, a blink that obstructs the pupil impairs th performance of other eye-Tracking algorithms, such as pupi detection, and often results in noise to the gaze estimation In this paper, we present a blink detection algorithm that i tailored towards head-mounted eye trackers and is robust t calibration-based variations like translation or rotation of th eye. The proposed approach reached 96,35\% accuracy fo a realistic and challenging data set and in real-Time even o low-end devices, rendering the proposed method suited for pervasive eye tracking.",

keywords = "Blink detection, Image processing, Pervasive eye tracking, Real time",

author = "Tobias Appel and Thiago Santini and Enkelejda Kasneci",

note = "Publisher Copyright: {\textcopyright} 2016 ACM.; 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2016 ; Conference date: 12-09-2016 Through 16-09-2016",

year = "2016",

month = sep,

day = "12",

doi = "10.1145/2968219.2968341",

language = "English",

series = "UbiComp 2016 Adjunct - Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing",

publisher = "Association for Computing Machinery, Inc",

pages = "1726--1735",

booktitle = "UbiComp 2016 Adjunct - Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing",

}

Appel, T, Santini, T & Kasneci, E 2016, Brightness-And motion-Based blink detection for head-mounted eye trackers. in UbiComp 2016 Adjunct - Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing. UbiComp 2016 Adjunct - Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing, Association for Computing Machinery, Inc, pp. 1726-1735, 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2016, Heidelberg, Germany, 12/09/16. https://doi.org/10.1145/2968219.2968341

Brightness-And motion-Based blink detection for head-mounted eye trackers. / Appel, Tobias; Santini, Thiago; Kasneci, Enkelejda.
UbiComp 2016 Adjunct - Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing. Association for Computing Machinery, Inc, 2016. p. 1726-1735 (UbiComp 2016 Adjunct - Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing).

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

TY - GEN

T1 - Brightness-And motion-Based blink detection for head-mounted eye trackers

AU - Appel, Tobias

AU - Santini, Thiago

AU - Kasneci, Enkelejda

PY - 2016/9/12

Y1 - 2016/9/12

N2 - Blinks are an indicator for fatigue or drowsiness and can assis in the diagnose of mental disorders, such as schizophrenia Additionally, a blink that obstructs the pupil impairs th performance of other eye-Tracking algorithms, such as pupi detection, and often results in noise to the gaze estimation In this paper, we present a blink detection algorithm that i tailored towards head-mounted eye trackers and is robust t calibration-based variations like translation or rotation of th eye. The proposed approach reached 96,35% accuracy fo a realistic and challenging data set and in real-Time even o low-end devices, rendering the proposed method suited for pervasive eye tracking.

AB - Blinks are an indicator for fatigue or drowsiness and can assis in the diagnose of mental disorders, such as schizophrenia Additionally, a blink that obstructs the pupil impairs th performance of other eye-Tracking algorithms, such as pupi detection, and often results in noise to the gaze estimation In this paper, we present a blink detection algorithm that i tailored towards head-mounted eye trackers and is robust t calibration-based variations like translation or rotation of th eye. The proposed approach reached 96,35% accuracy fo a realistic and challenging data set and in real-Time even o low-end devices, rendering the proposed method suited for pervasive eye tracking.

KW - Blink detection

KW - Image processing

KW - Pervasive eye tracking

KW - Real time

UR - https://www.scopus.com/pages/publications/84991094178

U2 - 10.1145/2968219.2968341

DO - 10.1145/2968219.2968341

M3 - Conference contribution

AN - SCOPUS:84991094178

T3 - UbiComp 2016 Adjunct - Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing

SP - 1726

EP - 1735

BT - UbiComp 2016 Adjunct - Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing

PB - Association for Computing Machinery, Inc

T2 - 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2016

Y2 - 12 September 2016 through 16 September 2016

ER -

Appel T, Santini T, Kasneci E. Brightness-And motion-Based blink detection for head-mounted eye trackers. In UbiComp 2016 Adjunct - Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing. Association for Computing Machinery, Inc. 2016. p. 1726-1735. (UbiComp 2016 Adjunct - Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing). doi: 10.1145/2968219.2968341

Brightness-And motion-Based blink detection for head-mounted eye trackers

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this