Driver Fatigue Detection Method Based on Human Pose Information Entropy

Li, Taiguo; Zhang, Tiance; Zhang, Yingzhi; Yang, Liben

doi:10.1155/2022/7213841

Cited by 6 publications

(3 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Camera coordinate system to pixel coordinate system: (5) The relationship between the pixel coordinate system and to world coordinate system: (6) Solve for Euler angles after calculating the rotation matrix: (7) The driver's head attitude can be further classified into pitch, yaw, and roll [11] . The Euler angles are generated by rotating the driver's head around the x, y, and z axes in a natural coordinate system with the driver's head as the origin [3] .…”

Section: Head Posture Fatigue Feature Extractionmentioning

confidence: 99%

In-vehicle fatigue driving warning device based on facial recognition fatigue detection system

Zhang,

Zhu

2024

Fourth International Conference on Computer Vision and Data Mining (ICCVDM 2023)

View full text Add to dashboard Cite

According to the data from the China National Bureau of Statistics, traffic accidents caused by fatigued driving account for more than 40% of large-scale traffic accidents [1]. Therefore, how to effectively detect and accurately warn fatigue driving is a very important topic in the field of transport safety. In this paper, we propose a fatigue driving warning device based on a "facial recognition fatigue driving detection system", which improves the accuracy and effectiveness of fatigue driving warning through five steps: facial information pre-entry, face detection, state recognition, fatigue assessment, and warning. Equipped with a Raspberry Pie 4B camera, the device digitizes the collected information using the OpenCV and Dilb libraries and determines the driver's fatigue level by calculating the Eyelid Aspect Ratio (EAR), the Mouth Opening Ratio (MAR), and the Euler Angle of the head. In addition, the warning device also grades different levels of driver fatigue and provides corresponding warnings, reminders, and treatment measures, which are of great significance in reducing traffic accidents and ensuring traffic safety.

show abstract

Section: Head Posture Fatigue Feature Extractionmentioning

confidence: 99%

In-vehicle fatigue driving warning device based on facial recognition fatigue detection system

Zhang,

Zhu

2024

Fourth International Conference on Computer Vision and Data Mining (ICCVDM 2023)

View full text Add to dashboard Cite

show abstract

“…Information entropy is an indicator to quantify the amount of information in information theory, borrowed from thermodynamics and measures the ordering degree of a system. It can be considered that the more orderly the system is, the smaller the information entropy is, and vice versa [46,47]. Similarly, the higher the information entropy of the drivers' fxation area is, the more discrete the distribution of fxation points is, and vice versa, the more concentrated it is.…”

Section: Information Entropy Of Fixation Areamentioning

confidence: 99%

Risk Assessment of Distracted Driving Behavior Based on Visual Stability Coefficient

Wang

Ding

Wang

2023

Journal of Advanced Transportation

View full text Add to dashboard Cite

Cell phone call operations during driving can lead to distraction and cause potential safety hazards. In order to quantitatively characterize the influence of cell phone call mode on the driver’s visual behavior in different traffic conditions and to analyze the risk level of distracted driving from the visual level, a distracted driving simulation test was carried out based on a driving simulator and eye tracker. The eye movement data of drivers during normal driving, hands-free call, and video call under two typical traffic conditions of free flow and congested flow on the urban expressway were collected. Firstly, four visual characteristics indicators that were highly sensitive to traffic conditions and driving states were selected in terms of visual field range, visual recognition, visual search, and visual load, which were the information entropy of fixation area (IEFA), saccade amplitude, peak-to-average ratio of saccade velocity (PARSV), and relative change intensity of pupil area (RCPA). Then, based on the improved CRITIC method, the visual stability coefficient (VSC) was constructed as a new indicator to comprehensively assess the risk level of the driving state, and the assessment criteria were divided. Finally, the grey correlation analysis method was introduced to verify the assessment effect of VSC. The results show that different cell phone call modes increased driving risk in both traffic conditions. Among them, the negative influence of video calls on driving safety was significantly higher than that of hands-free calls, with a significant decrease in VSC, and the drivers’ VSC in the free flow scenario was more sensitive to the impact of cell phone call operation, and the driving risk increased significantly during distracted driving. The VSC can quantitatively assess driving risk from the perspective of visual psychological safety and contributes to the development of corresponding early warning and control measures.

show abstract

“…[1] . Through a comparative analysis of research progress both domestically and internationally, research on detecting drowsy driving can be roughly divided into three categories: based on driving behavior [2] , based on driver physiological characteristics [3] , and based on facial features [4] . Compared with the other two methods, the facial-based method, with its low cost, significant fatigue features, and non-interference with normal driver operations, is currently the most widely used detection method, thanks to the development of computer vision.…”

Section: Introductionmentioning

confidence: 99%

Improved SSD for crew fatigue driving detection algorithm

Liu,

Zhang,

Xiao

et al. 2024

Seventh International Conference on Traffic Engineering and Transportation System (ICTETS 2023)

View full text Add to dashboard Cite

To solve the problems of low recognition accuracy and slow detection of crew fatigue driving behavior in the cockpit of ships during the process of sailing in and out of the port, the SSD model was studied. By replacing its backbone network and improving the prior frame generation mechanism, the MV-SSD model is proposed. Replace the backbone network VGG16 in the original SSD model with MobileNetV3, reducing the network parameters of the backbone network. Using the K-means algorithm to cluster the real detection boxes in the face area dataset, the prior box allocation mechanism of the SSD model was redesigned, reducing the number of prior box generation by nearly half, and the ERT algorithm in the Dlib library is combined to locate the face key points, and finally, the PERCLOS criterion is used to determine whether the driver is fatigued. Experimental results show that the average accuracy (mAP value) of the MV-SSD model is 7.15% higher than that of the original SSD model, and the detection speed (FPS value) is increased by 98frames/s, which is more suitable for the detection of the crew face area, and the average accuracy of the constructed fatigue detection algorithm for fatigue features is more than 94%.

show abstract

Driver Fatigue Detection Method Based on Human Pose Information Entropy

Cited by 6 publications

References 45 publications

In-vehicle fatigue driving warning device based on facial recognition fatigue detection system

In-vehicle fatigue driving warning device based on facial recognition fatigue detection system

Risk Assessment of Distracted Driving Behavior Based on Visual Stability Coefficient

Improved SSD for crew fatigue driving detection algorithm

Contact Info

Product

Resources

About