Eye blink detection for different driver states in conditionally automated driving and manual driving using EOG and a driver camera

Schmidt, Jürgen; Laarousi, Rihab; Stolzmann, Wolfgang; Karrer-Gauß, Katja

doi:10.3758/s13428-017-0928-0

Cited by 46 publications

(19 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Car manufacturers such as Mercedes (MERCEDES Attention Assist™) [9] and Volvo (Driver Alert Control) [10] use this technique to evaluate driver drowsiness. Vehicle-based measures have the advantage that they can be easily acquired, however these measures are confounded by geometric properties of the road, by surrounding traffic and also by other driver states such as cognitive load and visual distraction [6], [11]. In addition, with the development of automated driving functions, as conditionally automated driving which gives drivers the freedom to let go of the steering wheel, steering behavior related measures will become less significant.…”

Section: Drowsiness Detection Methodsmentioning

confidence: 99%

Driver drowsiness detection: a comparison between intrusive and non-intrusive signal acquisition methods

Oliveira

Cardoso

Lourenço

et al. 2018

2018 7th European Workshop on Visual Information Processing (EUVIP)

View full text Add to dashboard Cite

Driver drowsiness is a major cause of road accidents, many of which result in fatalities. A solution to this problem is the inclusion of a drowsiness detector in vehicles to alert the driver if sleepiness is detected. To detect drowsiness, physiologic, behavioral (visual) and vehicle-based methods can be used, however, only measures that can be acquired non-intrusively are viable in a real life application. This work uses data from a real-road experiment with sleep deprived drivers to compare the performance of driver drowsiness detection using intrusive acquisition methods, namely electrooculogram (EOG), with camerabased, non-intrusive, methods. A hybrid strategy, combining the described methods with electrocardiogram (ECG) measures, is also evaluated. Overall, the obtained results show that drowsiness detection performance is similar using non-intrusive camerabased measures or intrusive EOG measures. The detection performance increases when combining two methods (ECG + visual) or (ECG + EOG).

show abstract

Section: Drowsiness Detection Methodsmentioning

confidence: 99%

Driver drowsiness detection: a comparison between intrusive and non-intrusive signal acquisition methods

Oliveira

Cardoso

Lourenço

et al. 2018

2018 7th European Workshop on Visual Information Processing (EUVIP)

View full text Add to dashboard Cite

show abstract

“…For example, pulse waves can be used as an indicator to diagnose cardiovascular diseases and diabetes [ 1 , 2 , 3 ], whereas information on respiration is useful for monitoring chronic respiratory diseases such as asthma and chronic obstructive pulmonary disease [ 4 ]. Meanwhile, eye blink detection has several uses such as in the evaluation of drowsiness [ 5 ] and the diagnosis of dry eye disease [ 6 ]. In particular, during and after the current COVID-19 era, wearable devices for physiological monitoring are expected to be useful in mitigating this disease [ 7 , 8 ].…”

Section: Introductionmentioning

confidence: 99%

Mask-Type Sensor for Pulse Wave and Respiration Measurements and Eye Blink Detection

Nguyen

Ichiki

2021

Sensors

View full text Add to dashboard Cite

This paper reports on a mask-type sensor for simultaneous pulse wave and respiration measurements and eye blink detection that uses only one sensing element. In the proposed sensor, a flexible air bag-shaped chamber whose inner pressure change can be measured by a microelectromechanical system-based piezoresistive cantilever was used as the sensing element. The air bag-shaped chamber is fabricated by wrapping a sponge pad with plastic film and polyimide tape. The polyimide tape has a hole to which the substrate with the piezoresistive cantilever adheres. By attaching the sensor device to a mask where it contacts the nose of the subject, the sensor can detect the pulses and eye blinks of the subject by detecting the vibration and displacement of the nose skin caused by these physiological parameters. Moreover, the respiration of the subject causes pressure changes in the space between the mask and the face of the subject as well as slight vibrations of the mask. Therefore, information about the respiration of the subject can be extracted from the sensor signal using either the low-frequency component (<1 Hz) or the high-frequency component (>100 Hz). This paper describes the sensor fabrication and provides demonstrations of the pulse wave and respiration measurements as well as eye blink detection using the fabricated sensor.

show abstract

“…Eye blink detection has long been a hot research topic, attracting interest from both academia and industry. Eye blink detection plays a critical role in many real-life applications such as Human-Computer-Interaction for people with Motor Neuron Disease (MND) [34,49,52,57], drowsy driving prevention [6,20,33,60] and eye disease detection [19,21,48]. MND is a progressive disease that causes muscle weakness and stiffness throughout the body.…”

Section: Introductionmentioning

confidence: 99%

BlinkListener

Liu

Wang

et al. 2021

Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.

View full text Add to dashboard Cite

Eye blink detection plays a key role in many real-life applications such as Human-Computer Interaction (HCI), drowsy driving prevention and eye disease detection. Although traditional camera-based techniques are promising, multiple issues hinder their wide adoption including the privacy concern, strict lighting condition and line-of-sight (LoS) requirements. On the other hand, wireless sensing without a need for dedicated sensors gains a tremendous amount of attention in recent years. Among the wireless signals utilized for sensing, acoustic signals show a unique potential for fine-grained sensing owing to their low propagation speed in the air. Another trend favoring acoustic sensing is the wide availability of speakers and microphones in commodity devices. Promising progress has been achieved in fine-grained human motion sensing such as breathing using acoustic signals. However, it is still very challenging to employ acoustic signals for eye blink detection due to the unique characteristics of eye blink (i.e., subtle, sparse and aperiodic) and severe interference (i.e., from the human target himself and surrounding objects). We find that even the very subtle involuntary head movement induced by breathing can severely interfere with eye blink detection. In this work, for the first time, we propose a system called BlinkListener to sense the subtle eye blink motion using acoustic signals in a contact-free manner. We first quantitatively model the relationship between signal variation and the subtle movements caused by eye blink and interference. Then, we propose a novel method that exploits the "harmful" interference to maximize the subtle signal variation induced by eye blinks. We implement BlinkListener on both a research-purpose platform (Bela) and a commodity smartphone (iPhone 5c). Experiment results show that BlinkListener can achieve robust performance with a median detection accuracy of 95%. Our system can achieve high accuracies when the smartphone is held in hand, the target wears glasses/sunglasses and in the presence of strong interference with people moving around.

show abstract

Eye blink detection for different driver states in conditionally automated driving and manual driving using EOG and a driver camera

Cited by 46 publications

References 50 publications

Driver drowsiness detection: a comparison between intrusive and non-intrusive signal acquisition methods

Driver drowsiness detection: a comparison between intrusive and non-intrusive signal acquisition methods

Mask-Type Sensor for Pulse Wave and Respiration Measurements and Eye Blink Detection

BlinkListener

Contact Info

Product

Resources

About