Driver’s Fatigue Detection Based on Yawning Extraction

Alioua, Nawal; Amine, Aouatif; Rziza, Mohammed

doi:10.1155/2014/678786

Cited by 86 publications

(33 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Behavioral-based vigilance estimation methods use features that contain mouth states [28], [29], eye states [30]- [32], facial expressions [33], and body posture [34] collected by a video device (e.g., camera, Infrared illuminator) to compute the detection accuracy rate. Alioua et al [28] proposed the circular Hough transform (CHT)-based approach using mouth state feature detected by a circular edge, which showed the mean correct classification rate (MCCR) and kappa statistic (K) as 0.98 and 0.97, respectively. In addition, Flores et al [31] proposed a support vector machine (SVM)based model with eye state features, which were extracted using a condensation algorithm, with an accuracy of 93%.…”

Section: B Behavioral Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A Regression Method With Subnetwork Neurons for Vigilance Estimation Using EOG and EEG

Sun

et al. 2021

IEEE Trans. Cogn. Dev. Syst.

View full text Add to dashboard Cite

In recent years, it has been observed that there is an increasing rate of road accidents due to the low vigilance of drivers. Thus, the estimation of drivers' vigilance state plays a significant role in Public Transportation Safety (PTS). We have adopted a feature fusion strategy that combines the electroencephalogram (EEG) signals collected from various sites of the human brain, including forehead, temporal, and posterior and forehead electrooculogram (forehead-EOG) signals, to address this factor. The level of vigilance is predicted through a new learning model known as double-layered neural network with subnetwork nodes (DNNSN), which comprises several subnetwork nodes, and each node in turn is composed of many hidden nodes that have various capabilities of feature selection (dimension reduced), feature learning, etc. The proposed single modality that uses only forehead-EOG signal exhibits a mean root-mean-square error (RMSE) of 0.12 and a mean Pearson product-moment correlation coefficient (COR) of 0.78. On one hand, an EEG signal achieved a mean RMSE of 0.13 and a mean COR of 0.72. Whereas, on the other, the proposed multimodality achieved values of 0.09 and 0.85 for the mean RMSE and the mean COR, respectively. Experimental results show that the proposed DNNSN with multimodality fusion outperforms the model with single modality for vigilance estimation due to the complementary information between forehead-EOG and EEG. After a favorable learning rate was applied to the input layer, the mean RMSE/COR improved to 0.11/0.79, 0.12/0.74, and 0.08/0.86, respectively. Hence, this quantitative analysis proves that the proposed method provides better feasibility and efficiency learning capability and surmounts other state-of-theart techniques.

show abstract

Section: B Behavioral Methodsmentioning

confidence: 99%

“…To estimate the level of vigilance, typically, methods can be divided into four categories [6]: physiological methods [7]- [27], behavioral methods [28]- [34], subjective methods [35]- [38], and vehicle-based methods [39]- [41].…”

Section: Introductionmentioning

confidence: 99%

A Regression Method With Subnetwork Neurons for Vigilance Estimation Using EOG and EEG

Sun

et al. 2021

IEEE Trans. Cogn. Dev. Syst.

View full text Add to dashboard Cite

show abstract

“…Emotionsensitive facial muscles and regions (e.g., supraorbital, cheek, and perinasal areas) have also been extracted and studied [31][32][33][34][35][36][37]. Subtle changes that occur in the face, such as head motion (shaking), head pose, yawning, eye blink rate, and eye closure duration, have been utilized to detect emotions and fatigue [38][39][40][41][42][43][44]. Deep learning algorithms have also been widely applied in emotion recognition [45] [46].…”

Section: Literature Reviewmentioning

confidence: 99%

Spatial–Spectral–Temporal Framework for Emotion Recognition

Hong

2020

IEEE Access

View full text Add to dashboard Cite

An emotion recognition method based on multispectral imaging technology and tissue oxygen saturation (StO2) is proposed in this study. This method is called spatial-spectral-temporal adjustment convolutional neural network (SACNN). First, we use the algorithm to extract the StO2 content of an emotionally sensitive nose area through real-time multispectral imaging technology. Compared with facial expression data, StO2 data are more objective and cannot be controlled and changed artificially. Second, we construct a clustering algorithm based on the emotional state by extracting the spectral, StO2, and spatial features of the nose image to obtain accurate signals of emotionally sensitive areas. To utilize the correlation between spectral and spatial signals, we propose an adjustment-based CNN module, which reorganizes the relationship between all previous layers of the feature map, thereby making the relationship among layers close and highly quantitative. The features extracted through this method are consistent with spatial-spectral features. Third, we incorporate the extracted temporal feature signal into the long short-term memory module and finally complete the correlation between the spatial-spectral-temporal features. Experimental results show that the accuracy of the SACNN algorithm in emotional recognition reaches 90%, and the proposed method is more competitive than state-of-the-art approaches. To the best of our knowledge, this study is the first to use time-series StO2 signals for emotion recognition. INDEX TERMS Multispectral imaging, oxygen saturation, spatial-spectral-temporal adjustment convolutional neural network. I.

show abstract

“…Significant research has been carried out in the context of traffic safety systems. Video image processing techniques are used to identify distinctive facial expressions; such as eye movements-signs of drooping eyelids, and yawning; to detect drowsy driving [2][3][4][5]. Some systems use on board sensors; such as speed and orientation sensors, GPS, and two-axis accelerometer; to extract information of the vehicle state and detect unsafe driving styles in order to provide feedback with recommended actions [6][7][8].…”

Section: Related Workmentioning

confidence: 99%

Intersection Safety through Traffic Violation Detection

Ozkul¹

2019

IJCA

View full text Add to dashboard Cite

This paper presents a violation detection and collision avoidance system to vehicles at road intersections. The system relies on secure messages to assist vehicles in a constant size neighborhood by detecting traffic rule violations and finding trajectory conflicts at intersections. Each vehicle is modeled as an automaton that, regardless of its visual range, can see the states of other vehicles through on-board sensors and/or by using wireless communications. Traffic rules are encoded in the program of a vehicle and guide the changing state of the vehicle in traffic. Each vehicle can autonomously decide if the vehicles in its neighborhood comply with the traffic rules by observing the movements of the vehicles on the road and then anonymously reporting the observed violations to a traffic authority be further processed. Each vehicle periodically generates shared secrets which are then used as part of messages it sends to achieve security and privacy. The location of these messages is not traceable by any single traffic authority in the system, including the authentication parties and the road infrastructure. Yet, the proposed system is able find the location and real identity of any vehicle whenever it commits a rule violation in traffic with a lightweight protocol. Further, the security analysis is provided and the performance simulation results show that the system allows no false positives.

show abstract

Driver’s Fatigue Detection Based on Yawning Extraction

Cited by 86 publications

References 22 publications

A Regression Method With Subnetwork Neurons for Vigilance Estimation Using EOG and EEG

A Regression Method With Subnetwork Neurons for Vigilance Estimation Using EOG and EEG

Spatial–Spectral–Temporal Framework for Emotion Recognition

Intersection Safety through Traffic Violation Detection

Contact Info

Product

Resources

About