Driver Attention Research Articles

Supporting Driver Attention Toward Potential Hazards During Takeover: A Preliminary Result

This study investigates the impact of a supportive system on takeover transitions in conditionally automated driving (SAE Level 3). The supportive system is designed to direct drivers’ attention toward potential hazards in the environment when a takeover request occurs. The study comprises two components: (a) identifying various types of potential hazards using naturalistic driving data, and (b) conducting a driving simulator study to develop and assess a gaze guidance system based on the N-SEEV model of visual attention. Results indicate that drivers using a highly salient attention guidance system were less likely to collide with a secondary hazard during takeover transitions. This suggests that gaze guidance support is an effective approach for assisting drivers during takeover transitions.

Audiovisual messages may improve the processing of traffic information and driver attention during partially automated driving: An EEG study

Partially autonomous vehicles can help minimize human errors. However, being free from some driving subtasks can result in a low vigilance state, which can affect the driver’s attention towards the road. The present study first tested whether drivers of partially autonomous vehicles would benefit from the addition of auditory versions of the messages presented in variable message signs (VMS), particularly, when they find themselves in a monotonous driving situation. A second aim was to test whether the addition of auditory messages would also produce an indirect effect on the driver’s vigilance, improving performance on other driving subtasks not related to the message processing. Forty-three volunteers participated in a driving simulator study. They completed two tasks: (a) a VMS task, where they had to regain manual control of the car if the VMS message was critical, and (b) a car-following task, where they had to pay attention to the preceding car to respond to occasional brake events. Behavioral and EEG data were registered. Overall, results indicated that the addition of audio messages helped drivers process VMS information more effectively and maintain a higher level of vigilance throughout the driving time. These findings would provide useful information for the development of partially automated vehicles, as their design must guarantee that the driver remains attentive enough to assume control when necessary.

THE INFLUENCE OF EVENING TWILIGHT ON THE ATTENTION OF DRIVERS OF DIFFERENT AGES IN CITY CONDITIONS

The article examines the issue of driver safety in cities in the evening twilight. A group of drivers aged 20 to 40 years with a total driving experience of 3 to 16 years was studied. Drivers with 3-5 years of driving experience had an average age of 25 years, and drivers with 10-16 years of driving experience had an average age of 34 years. Drivers drove along known routes at dusk and after dark. We measured drivers’ attention with a Pupil Labs headset, as well as functional state shifts with a respiratory rate monitor. The "Neulog Respiration Monitor Belt" device was used to determine the parameters of external breathing of drivers. Previously, we measured breathing parameters when the driver was in a calm state. Since the morning, the drivers’ breathing rate has been 10-12 breathing cycles. The results of the research indicate a significant difference in the shifts in the functional state during the movement along the routes for both groups. When the lighting changes from the beginning of the evening twilight, the energy consumption by drivers increases by 40%. At the same time, the maximum rate of energy consumption for the driver is 12.6 kJ/min, i.e. 2.9 kcal/min. Also, drivers with less driving experience were less attentive and more emotionally stressed. At the same time, the drivers of both groups experienced significant difficulties in reducing the lighting in the event of conflicting situations while driving. At the same time, energy expenditure significantly exceeded the limit indicators, and attention indicators worsened. This fact was observed after 15-20 minutes of driving in the evening twilight. The experimentally obtained data on changes in the driver’s attention index in the conditions of evening twilight can be used to build multifactorial models taking into account traffic parameters on different categories of streets. In the conditions of the evening twilight, the driver’s attention is significantly reduced. When the illumination changes from 50 lux (driving time 15-20 min.) and less, the driver experiences visual fatigue from constantly searching for objects on the road. At the same time, the number of fixations is significantly reduced, as the driver spends more time recognizing and searching for the necessary elements of the road environment, pedestrians, etc. Danger in the driver causes a state of stress, which is reflected in an increase in the driver’s breathing rate and, as a consequence, a change in the functional state. The main factor affecting the amount of energy spent in such conditions is the interaction of the driver with the road conditions. These factors require the driver to take certain actions when driving a car: acceleration, braking, maintaining speed and certain reactions in the event of a traffic hazard. The results of the analysis of parameters of the functional state of drivers with different years of work showed significant differences between electrophysiological indicators, both when moving in conditions of evening twilight and in background conditions. In the background conditions, lower values of electrophysiological indicators are primarily related to the different age of the drivers. Drivers with 3-5 years of driving experience had an average age of 25 years, and drivers with 10-16 years of driving experience had an average age of 34 years. Keywords: driver attention, traffic flow, human factor.

Proposal of a Cost-Effective and Adaptive Customized Driver Inattention Detection Model Using Time Series Analysis and Computer Vision

Advanced Driver Assistance Systems, such as Forward Collision Warning and Lane Departure Warning, play a crucial role in accident prevention by alerting drivers to potential hazards. With the advent of fully autonomous driving technology that requires no driver input, there is now a greater emphasis on monitoring the state of vehicle occupants. This is particularly important because, in emergency situations where control must suddenly be transferred to an unprepared occupant, the risk of accidents increases significantly. To mitigate this risk, new monitoring technologies are being developed to analyze driver behavior and detect states of inattention or drowsiness. In response to the emerging demands of driver monitoring technology, we have developed the Customized Driver Inattention Detection Model (CDIDM). This model employs video analysis and statistical techniques to accurately and rapidly classify information on drivers’ gazes. The CDIDM framework defines the components of inattentive or drowsy driving based on the Driver Monitoring System (DMS) safety standards set by the European New Car Assessment Programme (EuroNCAP). By defining six driving behavior-related scenarios, we have improved the accuracy of driver inattention assessment. The CDIDM estimates the driver’s gaze while simultaneously analyzing data in real-time. To minimize computational resource usage, this model incorporates a series of preprocessing steps that facilitate efficient time series data analysis, utilizing techniques such as DTW Barycenter Averaging (DBA) and K-means clustering. This results in a robust driver attention monitoring model based on time series classification.

Driver distraction and fatigue detection in images using ME‐YOLOv8 algorithm

AbstractDriving while inattentive or fatigued significantly contributes to traffic accidents and puts road users at a significantly higher risk of collision. The rise in road accidents due to driver inattention resulting from distractive objects, for example, mobile phones, drinking, or tiredness, requires intelligent traffic monitoring systems to promote road safety. However, outdated detection technologies cannot handle the poor accuracy and the lack of real‐time processing possibility especially when combined with the variations of driving environment. This paper introduces “ME‐YOLOv8” which operates driver`s distraction and fatigue through a modified version of YOLOv8, which includes modules multi‐head self‐attention (MHSA) and efficient channel attention (ECA) modules applied, where the goal of MHSA is to improve the sensitivity of global features and the ECA attentions focus on critical features. Additionally, a dataset was created containing 3660 images covering multiple distracted and drowsy driver scenarios. The results reflect the enhanced detection capabilities of ME‐YOLOv8 and demonstrate its effectiveness in real‐time scenarios. This study demonstrates a significant advancement in the application of AI to public safety and highlights the critical role that state‐of‐the‐art deep learning algorithms play in lowering the risks associated with distracted and tired driving.

A gaze-based driver distraction countermeasure: Comparing effects of multimodal alerts on driver's behavior and visual attention

This study, introduces and evaluates different countermeasures using real-time eye-tracking data. The countermeasures detect when driver gaze deviates from the road for longer than a predetermined threshold and then redirect the driver's attention back to the road. The countermeasures include bimodal and trimodal alerts using combinations of auditory, tactile, and visual modalities. These countermeasures showcase the utility of adopting eye-tracking technologies in the context of driver monitoring and advanced driver's assistance systems. They enhance safety as a safeguard for the increased use of devices such as in-vehicle infotainment systems. Results show that countermeasures effectively redirect drivers’ attention to the road, with higher on-road gaze time. Additionally, bimodal alerts that include the visual modality are less effective at redirecting participants’ gaze on-road and result in poorer driving performance.

Design and implementation of a driving safety assistant system based on driver behavior

<p>These days, road accidents are one of Morocco's biggest problems. Fatigue, drowsiness, and driver behavior are among the primary causes.This research aims to develop an embedded system by image processing and computer vision to ensure driving safety by monitoring driver behavior and assist drivers to awaken from micro-sleep or fatigue due to long driving hours and various other reasons. Indeed, the driver inattention, drowsiness or driver fatigue can be detected. The suggested method is designed to support drivers if needed, based on the vehicle velocity. Once the driver crosses a certain speed limit, the program starts face detection and analyzing this data to determine whether the driver is tired, sleepy, or inattentive. This activates different alarm depending on the criticality level. It can sound a voice alert to help him wake up and drive more cautiously. The system is based on AI algorithms in image processing based on OpenCV libraries and the Python language to capture the movements of the driver's eyes and head when starting the automobile. Every algorithm is run on a Raspberry-Pi 4 card, and numerous experimentation series have demonstrated overall credible performance with success accuracy of over 93% in EAR and MAR calculations.</p>

Impact of Intersection Left Turn Guide Lines Configuration on Novice Drivers’ Behavior

Novice drivers often face challenges such as misjudgment, inappropriate steering control, distraction, and insufficient speed control when making left turns at intersections, leading to safety hazards. Installing intersection guide lines offers a solution by providing clear path directions, mitigating safety concerns associated with novice drivers’ left-turn actions. This study explored the impact of intersection guide line configurations on the driving behavior of novice drivers during left turns, utilizing large, medium, and small typical intersections to create six categories of left-turn simulation scenarios in a driving simulator. Data on vehicle trajectory, steering angle, steering speed, and eye-tracking were collected and analyzed. The study revealed that guide line arrangement significantly influences novice drivers’ left-turning behavior, enhancing path guidance while reducing trajectory and steering angle fluctuations, speed variations, and driver attention dispersion. This improvement in stability is particularly notable as intersection size and the number of left-turn lanes increase. The study’s findings offer robust theoretical support and guidance for the development and widespread adoption of intersection guide lines.

A real-time vehicle safety system by concurrent object detection and head pose estimation via stereo vision

A considerable number of vehicular accidents occur in low-millage zones like school streets, neighborhoods, and parking lots, among others. Therefore, the proposed work aims to provide a novel ADAS system to warn about dangerous scenarios by analyzing the driver's attention and the corresponding distances between the vehicle and the detected object on the road. This approach is made possible by concurrent Head Pose Estimation (HPE) and Object/Pedestrian Detection. Both approaches have shown independently their viable application in the automotive industry to decrease the number of vehicle collisions. The proposed system takes advantage of stereo vision characteristics for HPE by enabling the computation of the Euler Angles with a low average error for classifying the driver's attention on the road using neural networks. For Object Detection, stereo vision is used to detect the distance between the vehicle and the approaching object; this is made with a state-of-the-art algorithm known as YOLO-R and a fast template matching technique known as SoRA that provides lower processing times. The result is an ADAS system designed to ensure adequate braking time, considering the driver's attention on the road and the distances to objects.

Leveraging Driver Attention for an End-to-End Explainable Decision-Making From Frontal Images

Leveraging Driver Attention for an End-to-End Explainable Decision-Making From Frontal Images

Investigating the impact of fatigue level on visual attention of heavy-duty truck driver: An eye tracking study

Fatigue driving is considered one of the main risk factors leading to truck-involved crashes. A significant correlation between fatigue driving and visual behavior has been established in previous studies. However, the relationship between visual behavior and fatigue levels, especially among truck drivers, has been seldom explored. Therefore, this study conducted a field driving test on heavy-duty truck drivers to assess their visual attention distribution when affected by fatigue. Fatigue levels were measured based on the Percentage of Eye Closure (PERCLOS), and the impact on eye movement was evaluated. The study found that an increase in PERCLOS led to a decrease in the percentage of glances toward the left-wing mirror and the right-hand side of the windshield. Similarly, the number of glances toward the left-hand side of the windshield and left-wing mirror also decreased with the increase in PERCLOS. These findings suggest that a higher level of fatigue results in reduced attention toward the left-wing mirror and windshield, with truck drivers’ focus remaining at the front for longer periods, indicating a reduced alertness to road conditions. These insights could be valuable in monitoring fatigued drivers by examining the visual attention of heavy-duty truck drivers.

Accident Prevention System

Accident prevention system represents a groundbreaking innovation in vehicular safety technology. This advanced system integrates cutting- edge technologies such as eye blink sensors, GPS modules, Arduino and GSM communication to detect and mitigate potential hazards during driving. The accident prevention system incorporates a GPS module, enabling precise location tracking and providing crucial data for emergency responders. The integration of these technologies aims to significantly reduce the risk of accidents caused by driver inattention, fatigue, or other safety-critical factors. This abstract outline the comprehensive approach of accident prevention system, highlighting its potential to revolutionize road safety by leveraging state-of-the-art sensor technologies and intelligent communication systems. Key Words: Eye blink sensor, Arduino, GPS Module, GSM Module.

Investigating the influence of eye-catching effect on mental workload in highway tunnel entrances: a comprehensive analysis of eye blink behavior

Objective The objective of this study was to investigate the relationship between eye-catching effects and mental workload at highway tunnel entrances. Specifically, the study aimed to analyze drivers’ eye blink behavior to gain a comprehensive understanding of how visual attraction at tunnel entrances affects cognitive workload. Methods 50 participants were recruited for the naturalistic driving experiment. Four different visually attractive driving scenarios (baseline, landscape-style architecture, tip slogan, and billboard) were selected. Eye-tracking technology was utilized to record and analyze the eye blink behavior of participating drivers. Various metrics, including blink frequency, blink duration, inter-blink interval, and pupil diameter after a blink, were measured and compared across different scenarios. Results The results of the study demonstrated significant differences in drivers’ eye blink behavior across the different experimental scenarios, indicating the influence of visual attraction conditions on mental workload. The presence of eye-catching stimuli (landscape-style architecture, tip slogan, and billboard scenarios) at tunnel entrances resulted in decreased blink frequency, shorter blink duration, longer inter-blink intervals, and larger pupil diameter after a blink compared to when no specific eye-catching stimuli were present (baseline condition). These findings suggest that visual attractions capture drivers’ attention, leading to increased cognitive workload and attentional demands. Conclusions The findings of this study contribute to the existing literature on driver attention and mental workload, particularly in relation to eye-catching effect in tunnel environments. The presence of eye-catching stimuli at tunnel entrances can distract drivers and increase their mental workload, potentially compromising driving performance and safety. It is crucial for transportation authorities and designers to carefully consider the design and placement of visual attractions in tunnel entrances to minimize distraction and cognitive workload. By doing so, driving safety and performance can be enhanced in tunnel entrances.

How do visual and cognitive non-driving related tasks affect drivers’ visual attention and takeover performance in conditionally automated driving?

This study examines changes in visual attention during drivers’ engagement in visual or cognitive NDRTs during conditionally automated driving, and determines how these changes affect takeover performance. Seventy-five participants took part in a driving simulator study, performing three pre-takeover tasks: the three pre-takeover tasks: an auditory-imagery-verbal task (cognitive NDRT); a video-watching task (visual NDRT); and a monitoring task (baseline/non NDRT). Also, there were two hazardous events (breakdown or sudden merging of the vehicle ahead) leading to takeover requests issued with 7-s or 5-s lead times. The results revealed that NDRTs negatively affected visual attention, which caused lower saccade frequency between different areas of interest and shorter saccade amplitude. Drivers paid more visual attention to the road ahead and in-vehicle information system when performing cognitive and visual NDRTs, respectively. The visual attention of drivers performing NDRTs negatively affected takeover performance (e,g longer reaction time, heavier maximal brake pedal input, etc.). The reduction in takeover request lead time impaired takeover performance. The findings will support the design of eye tracker-based “out-of-loop” discrimination techniques and human-machine interaction interfaces in automated vehicles. This study contributes to the literature by examining how different types of NDRTs affect takeover performance, specifically focusing on drivers’ visual attention.

57‐3: Driver's Attention Retargeting for Automotive Displays

While driving, a driver often looks at the display for an emirror, front‐driving camera, rear‐view camera, and night‐vision camera, which may result in a potential safety issue. This paper proposes a retargeting method of driver's attention to important regions, thereby decreasing a potential driving safety issue. Specifically, the proposed method processes the input image to increase the driver's attention on more important regions while decreasing the attention on less important regions. The qualitative and quantitative evaluation proved the advantages and practicability of the proposed framework in retargeting the driver's attention to more important regions from less important regions.

Scaling effectivity in manifold methodologies to detect driver’s fatigueness and drowsiness state

The state of fatigueness and drowsiness relates to the stressed physical and mental condition of a driver that reduces the ability of a driver to drive safely leading to fatal consequences of road accidents. With a rising concerns about the road safety, the premium and modern vehicles are coming up with a sophisticated technology to detect and rise alarm during the positive case of fatigueness and drowsiness. Irrespective of availability of archives of literatures towards solving this problem, it is quite unclear about the strength and weakness of varied methodologies. Therefore, this paper presents a crisp and insightful discussion about the recent methodologies associated with detecting driver's attention, fatigueness, drowsiness along with highlights of commercial devices to realize various limiting factors and constraints associated with them. The paper contributes to introduce a well-structured flow of research trend to realize various patterns of current trend adopted towards solving varied problems and significant research gaps have been identified in this process. The outcome of this paper presents that still there is an open scope of an improvement towards accomplishing the agenda towards safer driving.

P‐64: Research on Displayable Scheme of Camera Under Panel Based on Automobile Display

CUP (Camera Under Panel) is applied to the automobile and can identify the driver's identity, monitor the driver's fatigue, attention, and monitor dangerous driving behaviors. The commonly used blind hole technology now leads to the inability to display the camera hole area. Therefore, we proposes a scheme for camera under panel applied to automobile, which is based on the Mini LED backlight structure design to achieve full screen display. At the same time, optical simulation analysis and related experiments were conducted to verify the feasibility of the scheme.

Enhancing Road Safety: A Driver Fatigue Detection and Behaviour Monitoring System using Advanced Computer Vision Techniques

Driver drowsiness is a major hazard to road safety, necessitating the development of reliable detection technologies. This study describes a revolutionary driver fatigue detection system that uses cutting-edge computer vision technologies. This system uses the MediaPipe framework for accurate face and hand detection and the Eye Aspect Ratio (EAR) for drowsiness detection. Furthermore, it uses the OpenCV solvePnP function for estimating rotation vector, and converting it to a rotation angle of the head, to check driver attention. By continuously monitoring these indicators, when the system successfully detects any instances of driver tiredness or inattention, it records his or her behavior and delivers notifications to help prevent accidents. This study helps to improve road safety by utilizing cutting-edge computer vision techniques to prevent driver fatigue and boost attentive driving practices.

Driver Distraction Detection and Alert System Using Convolutional Neural Networks

Abstract: The Driver Distraction and Alert System Using Convolutional Neural Networks provide a real-time machine learning and webcam-based monitoring system for driver distraction detection. The system uses a sophisticated Convolutional Neural Network (CNN) architecture trained on the State Form of Distracted Driver Detection dataset, which is made possible by utilizing the OpenCV, TensorFlow, and Pandas packages. With improvements like dropout layers and Xavier weight initialization, the model efficiently classifies ten driver attention states through preprocessing stages like image scaling and normalization. The results of the experiment show how well the suggested method works to identify distracted driving behaviors; a revised model on the Kaggle competition platform achieved a competitive public score of 2.67118

Analysis and Prediction of Risky Driving Behaviors Using Fuzzy Analytical Hierarchy Process and Machine Learning Techniques

Driver behavior plays a pivotal role in ensuring road safety as it is a significant factor in preventing traffic crashes. Although extensive research has been conducted on this topic in developed countries, there is a notable gap in understanding driver behavior in developing countries, such as Pakistan. It is essential to recognize that the cultural nuances, law enforcement practices, and government investments in traffic safety in Pakistan are significantly different from those in other regions. Recognizing this disparity, this study aims to comprehensively understand risky driving behaviors in Peshawar, Pakistan. To achieve this goal, a Driver Behavior Questionnaire was designed, and responses were collected using Google Forms, resulting in 306 valid responses. The study employs a Fuzzy Analytical Hierarchy Process framework to evaluate driver behavior’s ranking criteria and weight factors. This framework assigns relative weights to different criteria and captures the uncertainty of driving thought patterns. Additionally, machine learning techniques, including support vector machine, decision tree, Naïve Bayes, Random Forest, and ensemble model, were used to predict driver behavior, enhancing the reliability and accuracy of the predictions. The results showed that the ensemble machine learning approach outperformed others with a prediction accuracy of 0.84. In addition, the findings revealed that the three most significant risky driving attributes were violations, errors, and lapses. Certain factors, such as clear road signage and driver attention, were identified as important factors in improving drivers’ risk perception. This study serves as a benchmark for policymakers, offering valuable insights to formulate effective policies for improving traffic safety.