Driver Attention Research Articles

An Intelligent System for Preventing Accidents Due to Driver Distractions

The paper presented introduces an innovative accident prevention system that employs deep learning models and sensors to identify and alert drivers who lose concentration while driving for a variety of reasons. The system targets drowsiness, cell phone use, and alcohol consumption, which are among the leading causes of automobile accidents. The proposed solution employs neural networks to identify specific patterns associated with driver inattention and generates an audible alert to refocus the driver’s attention on the road. In addition, the system utilizes alcohol-detection sensors, as alcohol consumption is another significant cause of accidents. This system seeks to reduce the number of casualties by enhancing road safety considering the high number of daily collisions, which are primarily caused by speeding. The paper describes the design, architecture, and implementation of the system on a modest scale to provide a lifesaving, cost-effective solution.

Cognitive Aspect of Emotion Estimation of a Driver

Despite rapid advancements in the automotive industry, traffic safety risks persist. Addressing this challenge requires innovative driver assistance technologies. Common accidents result from driver inattention, fatigue, and stress, leading to issues like falling asleep at the wheel and improper acceleration and braking. Our study aims to contribute to advanced driver assistance systems that adapt to drivers' emotional needs, ultimately enhancing road safety. In this paper, we mention the result of our research to estimate drivers' emotions using sensors. For that purpose, we developed a sensor network containing sensors such as EEG, eye tracker, and driving simulator. We explored the relationship. As a result, we confirmed the relation between the driver's emotions, especially sleep conditions, driving speed, duration, and brain wave behavior.

Developing a multifunctional wearable system consisting of a helmet and clothing for two-wheeled vehicle users' safety assistance

Purpose This study aims to develop a safe, wearable clothing system that combines visibility-enhancing and emergency–accident-responding functions for two-wheeled vehicle (TWV) users' safety assistance.Design/methodology/approach First, the wearable system (WS) allowing users to control turn signals, brake lights and emergency flasher only with head movements was developed. Second, multiconnected systems were developed between WSs and a smartphone application (AS), providing accident occurrence recognition, driving photo capture–storage and emergency notification functions. Third, usability testing in each function was performed to assess the operability of the systems.Findings The intuitive interface, which uses head movement as gesture commands, was effectively operated for controlling turn signals, brake lights and emergency flasher when driving, despite differences in user physique and boarding structure among TWVs. In addition, using Bluetooth low energy and Wi-Fi protocols simultaneously can establish automatic accident recognition–notification and driving photo capture–storage–display functions by linking two WSs with one AS.Research limitations/implications This study presents a case using relatively accessible technologies within the fashion industry to improve users' safety and provide fundamental data for convergence education for smart fashion products, highlighting the significance of this study in this convergence era.Originality/value The WSs and the AS of a TWV user visually evoke the attention of other drivers and pedestrians, reducing the risk of accidents; social contribution regarding public safety will be possible by allowing the system to autonomously inform emergencies and receive emergency medical treatment quickly when the accident occurred.

Drowsiness detection of EEG signals using image-based convolutional neural network

With the continuous development of autonomous driving technology, more drivers relax their attention while driving, resulting in a continuous accumulation of the number of vehicle accidents. The detection of driver's attention can be used as a condition for whether to execute autonomous driving, to help to reduce the probability of major accidents. This study compares the performance of image-based and traditional drowsiness detection trained on the same dataset. Total 5 participants were told to control a computer-simulated train with a 12-channel real-time EEG acquisition device on their heads. We transferred their EEG signals into images with the coordinates of every useful electrode as the training and testing data for our Convolutional Neural Network (CNN). Our results indicated that the CNN model trained on image-based EEG signals achieved much higher accuracy (83.49%) compared with SVM model trained on raw EEG signals, providing an effective method for improving driving safety.

A comparison of glance coding approaches for driver attention assessment

Eye tracking is a common tool to assess drivers’ attentional state, either in real-time with the goal to prevent incidents, or offline, to understand underlying processes. While seemingly objective, eye tracking data can be coded and interpreted in different ways, which can have substantial effects on the results. The objective of this paper is to highlight and discuss the possibilities and limitations of three different approaches to code glance data: the direction-based encoding, the target-based approach, and the purpose-based approach. The direction-based coding scheme describes glances relative to the direction of travel. The target-based approach classifies the glance targets into different categories. The purpose-based approach needs additional layers of information to deduce the reason for the glance. This information encompasses road layout, traffic rules, and the presence and relevance of other traffic. Data from a field study with 23 participants driving an instrumented vehicle on an urban route was used to illustrate differences between the three methods. The results showed that the coding approach clearly affected the interpretation of the measured glance data. A purely target-based approach is limited by its inability to account for spare visual capacity and that also the absence of a target constitutes valuable information, and a purely direction-based approach does not account for the need to scan areas located off forward. The purpose-based approach requires contextual information that can be cumbersome to integrate. Regardless of the approach used, additional layers of contextual information increase understanding and interpretability, potentially at the cost of increased complexity. The three approaches are suitable for different contexts and their feasibility also depends on the availability of additional data. A key message is that context awareness improves the accuracy of driver attention monitoring and inattention identification.

Transfer Learning-based Drowsiness Detection System for Driver Assistance and Classification of Traffic Signs Employing a Deep Convolutional Neural Network

In this research paper, a comparative analysis of various image enhancements in the spatial domain techniques was performed based on three-dimensional image quality statistics such as mean squared error (MSE), peak signal-to-noise ratio (PSNR), and structural similarity for measuring the image quality (SSIM). The conditions for choosing the best method are low mean square error (MSE) and high peak signal-to-noise ratio as well as the structural similarity for measuring the image quality. The pre-processed image was subjected to a classification task using a stepwise version of pre-trained deep convolutional neural networks. The problem of driver drowsiness caused by fatigue, lack of sleep, medication, etc. will have to be solved by improving the efficiency of driver drowsiness detection. Many traffic accidents are largely caused by drowsy drivers. Driver fatigue and distraction can cause a lack of alertness, which can lead to driver inattention. In this paper, we proposed a new deep-learning technique for driver drowsiness detection. Two methods using convolutional deep neural network and GoogleNet transfer learning are compared to achieve a better accuracy of 99%.

The presence of signage in the control of visual pollution in urban areas: A case study in the M.T Haryono street corridor, Kendari City, Indonesia

Signage expanded with the growth of the city, where its presence is required because it is regarded as an effective medium for conveying commercial and non-commercial messages and is also anticipated to be one of the factors that contribute positively to a region’s image. This study seeks to determine the presence of signage, specifically advertising boards, in the corridor of M.T Haryono street, Kendari City, in relation to three factors: the impact of advertisement boards on the visual image of the area, its location, and its design. This approach is used to dig up and reveal the impact of advertising boards existence as elements and physical components of space. The results of the study revealed that the presence of advertising boards along the M.T Haryono road corridor did not contribute to reinforcing the visual theme of the area; its layout was overlapping and unclear; it did not provide clear information on the message it conveyed; its design was neither communicative nor harmonious; it lacked elements of unity with the architectural characteristics of the surrounding buildings; and its presence affected the attention of drivers.

Real Time Driver Gaze Tracking and Eyes off the Road Detection System

Abstract: Driver Gaze Tracking and Eyes Off the Road Detection System is a technology-driven solution designed to enhance road safety by monitoring driver behavior and detecting instances when the driver's attention is diverted from the road. The system utilizes computer vision techniques and machine learning algorithms to track the driver's eye movements and identify potential distractions. By providing real-time alerts and warnings, this system aims to mitigate the risk of accidents caused by distracted driving. Distracted driving poses a significant risk to road safety, and traditional methods have limitations in ensuring immediate compliance. By leveraging computer vision and machine learning, the system provides a proactive approach to detect distractions and alert drivers, ultimately reducing the occurrence of accidents caused by diverted attention. In conclusion, the Driver Gaze Tracking and Eyes Off the Road Detection System offers a technological solution to enhance road safety by monitoring driver behavior and detecting distractions. By promptly alerting drivers when their attention is diverted, this system contributes to mitigating the risks associated with distracted driving and promoting safer road environments.

Distracted by familiarity: Implications of ‘autopilot’ as a default cognitive mode

Most trips are made, and most travel is done on roads and paths well-known. To provide insight in the cognitive processes involved in visual information processing of familiar traffic environments this paper considers a series of four consecutive empirical studies. The aim of this paper is 1) to discuss the implications of these insights on research methodologies used to measure driver attention and distraction and 2) to provide recommendations for policymaking, road design and vehicle design. This line of work consists of three studies on car driver behaviour (two driving simulator studies and a video-based study) and an observational study on pedestrian behaviour. The recurring theme in the results of these studies is that the progressive exposure to the same traffic environment enables participants to automatise their behavioural performance in traffic up to the point that it could be executed at skill-based level. As a result, attention is easily diverted away from traffic participation, while participating in traffic. Participants could act without thinking about it, so they didn’t always even remember what they had done. People get used to familiar traffic environments so much that they don’t have to think about walking or driving with much conscious focus. Hence, when studying road user behaviour and particularly driver distraction, it is crucial to mimic these natural circumstances as closely as possible. It is therefore proposed that within driver distraction research, route familiarity should be regarded as a context that enables distraction. What is more, is that the results point in the direction of a familiarity paradox: deviating from what is very familiar likely results in involuntary distraction, but being very familiar may lead to underload resulting in (voluntarily) diverting attention elsewhere.

Impact of urban tunnel sidewall effect on drivers: Examining visual characteristics and driving behavior across different lanes

Urban tunnels have been widely used as special transportation infrastructure. This study investigated the impact of the urban tunnel sidewall effect on drivers, focusing on the drivers’ visual characteristics and driving behavior as the primary research objectives. In this study, numerous real vehicle tests were conducted in the middle section of an urban tunnel, focusing on different lanes. The drivers’ visual characteristics were examined through the distribution of gaze points and fixation duration, and driving behavior was assessed using the vehicles’ lateral offset and acceleration. The drivers’ visual characteristics and driving behavior were analysed together to investigate the impact of the sidewall effect on the relationship between the visual information input and driving behavior output. A questionnaire was administered after the experiment to assess the subjective experiences of each participant. The results indicated significant variations in the impact of the sidewall effect on driver attention distribution and vehicle stability across different lanes. Drivers in the left lane were the most affected and had the highest driving risk, followed by those in the right lane; those in the middle lane had the least driving risk. Meanwhile, when drivers in the left or right lanes focus their gaze on the adjacent sidewall or shortly afterwards, the vehicle experiences a higher lateral acceleration away from the sidewall compared to other areas.

Latent Hazard Notification for Highly Automated Driving: Expected Safety Benefits and Driver Behavioral Adaptation

Although latent hazard notification for highly automated driving is expected to enhance traffic safety, its practical effects have yet to be verified. This study systemically investigated the expected safety benefits and driver behavioral adaptation based on structural equation modeling. First, we developed a notification system to inform drivers of latent hazards with auditory alerts and conducted a driving simulation experiment involving eyes-off-road situations. To test the system, we adopted two types of events (i.e., the collision avoidance function working or failure) in which latent hazards transform into immediate risks. Then, a measurement model was developed to evaluate driver trust, driver attention, and traffic safety. Subsequently, we examined the corresponding causal relationships. On the one hand, latent hazard notification significantly improves driver attention (i.e., more fixations on latent hazards, less engagement in non-driving-related tasks, and faster notice of immediate risks), which significantly enhances traffic safety. On the other hand, latent hazard notification significantly increases driver trust, which lowers driver attention and consequently impairs traffic safety. This causality reveals driver behavioral adaptation, although driver trust does not directly affect traffic safety. Overall, we find that latent hazard notification for highly automated driving can improve traffic safety, but the consequent driver behavioral adaptation impairs 15.12% of the expected safety benefits.

Analysis of the principle of mechanical transmissions and their advantages and disadvantages

As the proportion of cars in our lives gradually increases, the proportion of cars in the market also gradually increases. How to make it an efficient transportation is the problem we need to consider as well as solve. In order to study the improvement direction of the three transmissions (MT, AT, CVT) which are more common in the market, this paper uses the internet to collect and integrate the information, from the structure and principles of the transmission as the research direction, to analyze the advantages and disadvantages of the transmission so as to find out the areas that can be improved. It was found that MT gearboxes offer a higher degree of freedom than AT gearboxes, but the more complex driving conditions in the city can lead to frequent gear changes in MT gearboxes, thus affecting the driver's attention to a certain extent.

Exploratory Development of Algorithms for Determining Driver Attention Status.

Varying driver distraction algorithms were developed using vehicle kinematics and driver gaze data obtained from a camera-based driver monitoring system (DMS). Distracted driving characteristics can be difficult to accurately detect due to wide variation in driver behavior across driving environments. The growing availability of information about drivers and their involvement in the driving task increases the opportunity for accurately recognizing attention state. A baseline for driver distraction levels was developed using a video feed of 24 separate drivers in varying naturalistic driving conditions. This initial assessment was used to develop four buffer-based algorithms that aimed to determine a driver's real-time attentiveness, via a variety of metrics and combinations thereof. Of those tested, the optimal algorithm included ungrouped glance locations and speed. Notably, as an algorithm's performance of detecting very distracted drivers improved, its accuracy for correctly identifying attentive drivers decreased. At a minimum, drivers' gaze position and vehicle speed should be included when designing driver distraction algorithms to delineate between glance patterns observed at high and low speeds. Distraction algorithms should be designed with an understanding of their limitations, including instances in which they may fail to detect distracted drivers, or falsely notify attentive drivers. This research adds to the body of knowledge related to driver distraction and contributes to available methods to potentially address and reduce occurrences. Machine learning algorithms can build on the data elements discussed to increase distraction detection accuracy using robust artificial intelligence.

How much situation awareness does the driver have when driving autonomously? A study based on driver attention allocation

During the operation of the L3 automated driving system, since there is no need to supervise the vehicle at all times, the driver is often disengaged from the driving task and engages in a variety of non-driving-related tasks (NDRTs). When the autonomous driving system (ADS) encounters an unexpected situation and issues a takeover request (TOR), whether the driver can recover the situation awareness (SA) in time is the key to ensure the safety of the takeover. In this study, the theory of attention resource allocation is introduced to more accurately model the dynamic process of the SA recovery. Moreover, the attention allocation model is further developed, and the affecting factors of attention allocation are quantified. An experiment with 90 participants using driving simulator was conducted for different road scenarios to verify the proposed SA model. The model proposed in this study can accurately predict the SA value of the driver under different road scenarios and the time required for the driver to recover to the maximum SA value, which provides a reference for the scientific design of dynamic takeover lead time. The results also show that as the radius of curvature of the road decreased, the level of SA recovery would become progressively worse.

Driver's visual fixation attention prediction in dynamic scenes using hybrid neural networks

The traffic driving scenario is dynamically varying and experienced drivers can allocate visual attention effectively in brief time intervals, focusing on prominent targets and areas in advance, thus ensuring safe driving. Therefore, it is significant to research the behavior of driver's visual attention allocation in the development of driver assistance systems and autonomous vehicles. Recently, inspired by top-down and bottom-up attention mechanisms, most visual attention models based on neural networks have been proposed. However, these models tend to yield highly distributed predictions for the specific driving scenario, and have relatively low prediction accuracy, making them unfeasible for being used in practice. Hence, to overcome these challenges, we propose a driver's visual attention model (DVAM) built on the encoder-decoder architecture with the utilization of the convolutional neural network (CNN) and the recurrent neural networks (RNN). Specifically, the model leverages the temporal and spatial dimension information to better mimic realistic dynamic driving, and extract abundant feature information, thus ensuring that the final predictions are authentic and effective. Then, extensive experiments demonstrate that our suggested DVAM achieves better robustness and precision in predicting driver attention to areas or targets compared to state-of-the-art methods on the DR(eye)VE dataset. Finally, our model is deployed on the TDV dataset to validate its generalization capabilities, which prove the potential for field adaptation.

Keep your hands on the wheel: The effect of driver supervision strategy on change detection, mind wandering, and gaze behavior

Advanced driver-assist systems (ADAS) enable drivers to relinquish operational control of the vehicle to automation for part of the total drive. While these features are engaged, drivers have an increased risk of losing awareness of their environment. Current ADAS broadly utilizes hands-on-the-wheel or eyes-on-the-road driver supervision strategies to continually monitor steering-wheel torque and drivers’ head and eye positions to ensure driver attention. The current work examines the effect of hands-on-the-wheel and eyes-on-the-road driver supervision strategies on change detection, mind wandering, and gaze behavior in a low-fidelity semi-autonomous driving task.

Assessing the effects of geometric layout and signing on drivers’ behavior through work zones

Work zones are commonly deployed within or near the traveled way during roadway maintenance, repair, and construction works. Work zones could translate into hazardous spots requiring higher driver attention and possibly leading to increased crash rates and crash severity. This research addresses the effects of various design elements on drivers' behavior through work zones. Chekka diversion, currently implemented along the main Coastal Highway M-51 in Lebanon, is analyzed as it currently presents numerous non-standard design elements. A proposed standard diversion design is compared to the current non-standard diversion layout. A driving simulator has been used to model the current and the proposed diversions. Four driving scenarios involving the combination of the two diversion designs under different visibility conditions are used to evaluate drivers' behavior and responses through the diversion zones. The simulator study results showed that the proposed work zone geometry significantly improved the drivers' behavior compared to the exiting diversion. The visibility conditions have proven to have a more profound effect on driver behavior through the current non-standard diversion design. The pavement markings used along the proposed diversion reduce the vehicles' lateral fluctuations by 50% compared to the current design. The recorded driving patterns prove useful for work zone design to minimize the Lebanese drivers' risky behavior and enhance road safety.

Real-time monitoring of driver distraction: State-of-the-art and future insights

Driver distraction and inattention have been found to be major contributors to a large number of serious road crashes. It is evident that distraction reduces to a great extent driver perception levels as well as their decision making capability and the ability of drivers to control the vehicle. An effective way to mitigate the effects of distraction on crash probability, would be through monitoring the mental state of drivers or their driving behaviour and alerting them when they are in a distracted state. Towards that end, in recent years, several inexpensive and effective detection systems have been developed in order to cope with driver inattention. This study endeavours to critically review and assess the state-of-the-art systems and platforms measuring driver distraction or inattention. A thorough literature review was carried out in order to compare and contrast technologies that can be used to detect, monitor or measure driver's distraction or inattention. The systematic review followed the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) guidelines. The results indicated that in most of the identified studies, driver distraction was measured with respect to its impact to driver behaviour. Real-time eye tracking systems, cardiac sensors on steering wheels, smartphone applications and cameras were found to be the most frequent devices to monitor and detect driver distraction. On the other hand, less frequent and effective approaches included electrodes, hand magnetic rings and glasses.

Naturalistic driving study on the impact of an aftermarket blind spot monitoring system on the driver’s behaviour of heavy goods vehicles and buses on reducing conflicts with pedestrians and cyclists

The risk being severely or fatally injured in crashes with heavy goods vehicle and buses is much higher compared to other vehicles. Especially vulnerable road users such as pedestrian and cyclists are at high risk. In the European Union 4600 pedestrian and more than 2000 cyclists were killed in 2019. 18% of the fatalities were counted in crashes with heavy goods vehicles or buses. Blind spot situations and driver inattention or distraction are causing and contributing crash factors. Driver assistance systems are intended to support drivers and might have a positive effect on the crash avoidance. The objective of the study is the analysis of the change of driver behaviour in heavy goods vehicles and buses due to a aftermarket blind spot monitoring system. In a naturalistic driving study 15 heavy goods vehicles and five buses were equipped with a blind spot monitoring system and data were collected over a period of two years. The results revealed that the system would reduce the number of warnings with vulnerable road users by one third for heavy goods vehicles and 10% for buses. Up to 200 lives annually could potentially be saved with the analysed system, on the assumption that the collision warnings correlate directly with crashes.

Graphic traffic signals—The color design of 3D crosswalks

Distracted driving tests the design of traffic signs and promotes a wide range of safety developments for automobiles, making the visual effects of driving extremely important. Therefore, this study aims to increase the attention of drivers to ensure the safety of pedestrians through a three-dimensional (3D) crosswalk design and to provide the zones of error identified by the lane deviation system as a reference for development. Crosswalk design will be tested with regards to two factors: light and shadow (light-facing vs. shaded) and color (monochrome vs. two-color), for the purpose of creating 3D crosswalk samples. Through a driving environment that simulates the outdoor color temperature, a visual psychological experiment was conducted on 30 subjects to test their visual attention and inclination to brake. The results of multivariate analysis of variance show that within the same color temperature, subjects with driving experience had a significant reaction to the 3D crosswalk, with this response being stronger among females when analyzed in terms of gender. Among the test samples used in the study, the best result was obtained from the combination of yellow light-facing and red-shaded sides for the 3D crosswalk as in addition to increasing drivers’ attention, it can reduce the incorrect identification of the lane deviation system caused by the color white.