Driver's blink detection using doppler sensor

Kohei Yamamoto, Kentaro Toyoda, Tomoaki Ohtsuki

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

2 Citations (Scopus)

Abstract

Blink is a physiological signal that reflects drowsiness and concentration. It is important to detect driver's blinks without any wearable devices. For this purpose, a Doppler sensor has been used and several blink detection methods where a subject sits in front of such sensor have been proposed. However, it is challenging to detect driver's blinks because of face and body movement. In this paper, we propose a Doppler sensor-based driver's blink detection method in existence of face and body movement in a car. In the proposed method, blinks are detected through two steps: pre-detection and classification. In the first step which we call pre-detection, the time candidates of subject's blinks are detected based on spectrograms calculated from a received signal. Then, in the second one which we call classification, a set of features are calculated from a spectrogram and are fed into a supervised machine learning classifier to identify which time candidates are truly blinks. We leverage the fact that the distribution of the energy on a spectrogram differs between a blink and non-blink. Specifically, features are extracted based on the distribution of energy on a spectrogram. We conducted a series of experiments for the evaluation in the situation where a subject drives a real car in public road. As a result, we confirmed our method outperforms the conventional one in terms of F-measure calculated from recall rate and precision rate.

Original languageEnglish
Title of host publication2017 IEEE International Symposium on Personal, Indoor and Mobile Radio Communications
Subtitle of host publicationEngaged Citizens and their New Smart Worlds, PIMRC 2017 - Conference Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-6
Number of pages6
Volume2017-October
ISBN (Electronic)9781538635315
DOIs
Publication statusPublished - 2018 Feb 14
Event28th Annual IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC 2017 - Montreal, Canada
Duration: 2017 Oct 82017 Oct 13

Other

Other28th Annual IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC 2017
CountryCanada
CityMontreal
Period17/10/817/10/13

Fingerprint

Sensors
Railroad cars
Learning systems
Classifiers
Experiments

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Yamamoto, K., Toyoda, K., & Ohtsuki, T. (2018). Driver's blink detection using doppler sensor. In 2017 IEEE International Symposium on Personal, Indoor and Mobile Radio Communications: Engaged Citizens and their New Smart Worlds, PIMRC 2017 - Conference Proceedings (Vol. 2017-October, pp. 1-6). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/PIMRC.2017.8292496

Driver's blink detection using doppler sensor. / Yamamoto, Kohei; Toyoda, Kentaro; Ohtsuki, Tomoaki.

2017 IEEE International Symposium on Personal, Indoor and Mobile Radio Communications: Engaged Citizens and their New Smart Worlds, PIMRC 2017 - Conference Proceedings. Vol. 2017-October Institute of Electrical and Electronics Engineers Inc., 2018. p. 1-6.

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

Yamamoto, K, Toyoda, K & Ohtsuki, T 2018, Driver's blink detection using doppler sensor. in 2017 IEEE International Symposium on Personal, Indoor and Mobile Radio Communications: Engaged Citizens and their New Smart Worlds, PIMRC 2017 - Conference Proceedings. vol. 2017-October, Institute of Electrical and Electronics Engineers Inc., pp. 1-6, 28th Annual IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC 2017, Montreal, Canada, 17/10/8. https://doi.org/10.1109/PIMRC.2017.8292496
Yamamoto K, Toyoda K, Ohtsuki T. Driver's blink detection using doppler sensor. In 2017 IEEE International Symposium on Personal, Indoor and Mobile Radio Communications: Engaged Citizens and their New Smart Worlds, PIMRC 2017 - Conference Proceedings. Vol. 2017-October. Institute of Electrical and Electronics Engineers Inc. 2018. p. 1-6 https://doi.org/10.1109/PIMRC.2017.8292496
Yamamoto, Kohei ; Toyoda, Kentaro ; Ohtsuki, Tomoaki. / Driver's blink detection using doppler sensor. 2017 IEEE International Symposium on Personal, Indoor and Mobile Radio Communications: Engaged Citizens and their New Smart Worlds, PIMRC 2017 - Conference Proceedings. Vol. 2017-October Institute of Electrical and Electronics Engineers Inc., 2018. pp. 1-6
@inproceedings{289633a9271746919c628d72a3becb1b,
title = "Driver's blink detection using doppler sensor",
abstract = "Blink is a physiological signal that reflects drowsiness and concentration. It is important to detect driver's blinks without any wearable devices. For this purpose, a Doppler sensor has been used and several blink detection methods where a subject sits in front of such sensor have been proposed. However, it is challenging to detect driver's blinks because of face and body movement. In this paper, we propose a Doppler sensor-based driver's blink detection method in existence of face and body movement in a car. In the proposed method, blinks are detected through two steps: pre-detection and classification. In the first step which we call pre-detection, the time candidates of subject's blinks are detected based on spectrograms calculated from a received signal. Then, in the second one which we call classification, a set of features are calculated from a spectrogram and are fed into a supervised machine learning classifier to identify which time candidates are truly blinks. We leverage the fact that the distribution of the energy on a spectrogram differs between a blink and non-blink. Specifically, features are extracted based on the distribution of energy on a spectrogram. We conducted a series of experiments for the evaluation in the situation where a subject drives a real car in public road. As a result, we confirmed our method outperforms the conventional one in terms of F-measure calculated from recall rate and precision rate.",
author = "Kohei Yamamoto and Kentaro Toyoda and Tomoaki Ohtsuki",
year = "2018",
month = "2",
day = "14",
doi = "10.1109/PIMRC.2017.8292496",
language = "English",
volume = "2017-October",
pages = "1--6",
booktitle = "2017 IEEE International Symposium on Personal, Indoor and Mobile Radio Communications",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Driver's blink detection using doppler sensor

AU - Yamamoto, Kohei

AU - Toyoda, Kentaro

AU - Ohtsuki, Tomoaki

PY - 2018/2/14

Y1 - 2018/2/14

N2 - Blink is a physiological signal that reflects drowsiness and concentration. It is important to detect driver's blinks without any wearable devices. For this purpose, a Doppler sensor has been used and several blink detection methods where a subject sits in front of such sensor have been proposed. However, it is challenging to detect driver's blinks because of face and body movement. In this paper, we propose a Doppler sensor-based driver's blink detection method in existence of face and body movement in a car. In the proposed method, blinks are detected through two steps: pre-detection and classification. In the first step which we call pre-detection, the time candidates of subject's blinks are detected based on spectrograms calculated from a received signal. Then, in the second one which we call classification, a set of features are calculated from a spectrogram and are fed into a supervised machine learning classifier to identify which time candidates are truly blinks. We leverage the fact that the distribution of the energy on a spectrogram differs between a blink and non-blink. Specifically, features are extracted based on the distribution of energy on a spectrogram. We conducted a series of experiments for the evaluation in the situation where a subject drives a real car in public road. As a result, we confirmed our method outperforms the conventional one in terms of F-measure calculated from recall rate and precision rate.

AB - Blink is a physiological signal that reflects drowsiness and concentration. It is important to detect driver's blinks without any wearable devices. For this purpose, a Doppler sensor has been used and several blink detection methods where a subject sits in front of such sensor have been proposed. However, it is challenging to detect driver's blinks because of face and body movement. In this paper, we propose a Doppler sensor-based driver's blink detection method in existence of face and body movement in a car. In the proposed method, blinks are detected through two steps: pre-detection and classification. In the first step which we call pre-detection, the time candidates of subject's blinks are detected based on spectrograms calculated from a received signal. Then, in the second one which we call classification, a set of features are calculated from a spectrogram and are fed into a supervised machine learning classifier to identify which time candidates are truly blinks. We leverage the fact that the distribution of the energy on a spectrogram differs between a blink and non-blink. Specifically, features are extracted based on the distribution of energy on a spectrogram. We conducted a series of experiments for the evaluation in the situation where a subject drives a real car in public road. As a result, we confirmed our method outperforms the conventional one in terms of F-measure calculated from recall rate and precision rate.

UR - http://www.scopus.com/inward/record.url?scp=85045277086&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045277086&partnerID=8YFLogxK

U2 - 10.1109/PIMRC.2017.8292496

DO - 10.1109/PIMRC.2017.8292496

M3 - Conference contribution

AN - SCOPUS:85045277086

VL - 2017-October

SP - 1

EP - 6

BT - 2017 IEEE International Symposium on Personal, Indoor and Mobile Radio Communications

PB - Institute of Electrical and Electronics Engineers Inc.

ER -