Evaluation of Driver Drowsiness based on Real-Time Face Analysis

Salzillo, Giovanni; Natale, Ciro; Fioccola, Giovanni B.; Landolfi, Enrico

doi:10.1109/smc42975.2020.9283133

Cited by 12 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…So, we propose to derive several features from the eye blink pattern, such as eye blinking frequency and frequency of long eye closure. After detecting 68-landmark points, the focus is on the two landmarks that involve the left and right eye in the real-time video stream [62]. The eyes are represented by 12-coordinate points with 6-(x-y) coordinate points for each eye.…”

Section: Eye Blinkingmentioning

confidence: 99%

A multimodal facial cues based engagement detection system in e-learning context using deep learning approach

Gupta

Kumar

Tekchandani

2023

Multimed Tools Appl

View full text Add to dashboard Cite

Due to the COVID-19 crisis, the education sector has been shifted to a virtual environment. Monitoring the engagement level and providing regular feedback during e-classes is one of the major concerns, as this facility lacks in the e-learning environment due to no physical observation of the teacher. According to present study, an engagement detection system to ensure that the students get immediate feedback during e-Learning. Our proposed engagement system analyses the student's behaviour throughout the e-Learning session. The proposed novel approach evaluates three modalities based on the student's behaviour, such as facial expression, eye blink count, and head movement, from the live video streams to predict student engagement in e-learning. The proposed system is implemented based on deep-learning approaches such as VGG-19 and ResNet-50 for facial emotion recognition and the facial landmark approach for eye-blinking and head movement detection. The results from different modalities (for which the algorithms are proposed) are combined to determine the EI (engagement index). Based on EI value, an engaged or disengaged state is predicted. The present study suggests that the proposed facial cues-based multimodal system accurately determines student engagement in real time. The experimental research achieved an accuracy of 92.58% and showed that the proposed engagement detection approach significantly outperforms the existing approaches.

show abstract

Section: Eye Blinkingmentioning

confidence: 99%

A multimodal facial cues based engagement detection system in e-learning context using deep learning approach

Gupta

Kumar

Tekchandani

2023

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…In most cases, a medium-quality camera can be used to receive images of the eye for recognition algorithms. In case of necessity, different types of cameras can be used to improve the results of eye status assessment such as infrared cameras [17], or glasses with specialized cameras [21]. The work in this paper implements an algorithm for analyzing eye states using a standard camera in normal lighting conditions.…”

Section: Eye State Recognitionmentioning

confidence: 99%

“…In this work, a space-time restriction strategy is designed to restrain the detection window and scale of the AdaBoost method to reduce false-detection cases. Recently, another drowsiness detection system by analyzing the driver's face with a standard camera was proposed [17]. In this case, a set of facial landmark locations are detected by a fuzzy inference system (FIS).…”

Section: Introductionmentioning

confidence: 99%

Effective driver distraction warning system incorporating fast image recognition methods

Nguyen,

Trinh

2024

IJECE

View full text Add to dashboard Cite

Modern cars are equipped with advanced automatic technology featuring various safety measures for car occupants. However, the growing density of vehicles, especially in areas where infrastructure development lags, poses potential dangers, particularly accidents caused by driver subjectivity. These incidents may occur due to driver distraction or the presence of high-risk obstacles on the road. This article presents a comprehensive solution to assist drivers in mitigating these risks. Firstly, the study introduces a novel method to enhance the recognition of a driver's facial features by analyzing benchmarks and the whites of the eyes to assess the distraction level. Secondly, a domain division method is proposed to identify obstacles and lanes in front of the vehicle, enabling the assessment of the danger level. This information is promptly relayed to the driver and relevant individuals, such as the driver's manager or supervisor. An experimental device has also been developed to evaluate the effectiveness of the algorithms, solutions, and processing capabilities of the system.

show abstract

“…Vital monitoring methods for conventional drivers were conducted by cameras and motion sensors inside the vehicle to monitor factors that are external to the body, such as the driver's eyelid closing [5] and nodding of the head or using electromyography (EMG) and electrocardiogram (ECG) sensors [6,7]. However, conventional methods have difficulties in directly recognizing the driver's movements in low-illuminance environments, such as night driving.…”

Section: Introductionmentioning

confidence: 99%

Movement Compensated Driver’s Respiratory Rate Extraction

Yoo

Shin

2022

Applied Sciences

View full text Add to dashboard Cite

In non-contact vital sign monitoring using radar, radar signal distorted by the surrounding unspecified factors is unsuitable for monitoring vital signs. In order to monitor vital signs accurately, it is essential to compensate for distortion of radar signals caused by surrounding environmental factors. In this paper, we propose a driver vital signal compensation method in driving situations, including the driver’s movements using a frequency-modulated continuous-wave (FMCW) radar. Driver’s movement is quantified from the radar signal and used to set a distortion signal compensation index to compensate for the signal distortion induced in the driving situation that the driver’s movement occurs. The experimental results show that the respiration rate estimated from the radar signal compensated through the proposed method is similar to the actual respiration rate than from the signal before calibration. These results confirm the possibility of using the proposed method in a non-statistic situation and effectiveness in estimating respiration rate reflecting human movement in monitoring vital signs using FMCW radar.

show abstract

Evaluation of Driver Drowsiness based on Real-Time Face Analysis

Cited by 12 publications

References 26 publications

A multimodal facial cues based engagement detection system in e-learning context using deep learning approach

A multimodal facial cues based engagement detection system in e-learning context using deep learning approach

Effective driver distraction warning system incorporating fast image recognition methods

Movement Compensated Driver’s Respiratory Rate Extraction

Contact Info

Product

Resources

About