Fig 2 - available via license: CC BY
Content may be subject to copyright.
SEM of relationships between visual and cognitive attention and perception of changes in the traffic environment
Source publication
Abstract Drivers are met with numerous elements requiring their attention while driving. The present research focuses on selected visual and cognitive distractions that the driver is faced with, and on their influence on detecting and perceiving changes in the traffic environment. Driver self evaluation data was used to define which elements attrac...
Contexts in source publication
Context 1
... = 0.922, NFI = 0.932, TLI = 0.963, CFI = 0.971, RMSEA = 0.037, SRMR = 0.0636, IFI = 0.972. Figure 2 shows a graphical representation of the standardized SEM model with the estimated path coefficients significant at p ≤ 0.10 level among the variables; insignificant paths are not shown in Fig.2 (amount of years having a driving licence for a car, and how many days a week the respondent drives a car). The SEM model is represented by the path diagram, and it includes the measurement part of the model (influences of measurable variables onto latent variables, e.g. the connections between Eyes-on-road and ATTEN_9, ATTEN_4 in ATTEN_7) and the structural part of the model (influences or connection among latent variables, e.g. the influence of Eyes-on-road to Perceived changes). ...
Context 2
... = 0.922, NFI = 0.932, TLI = 0.963, CFI = 0.971, RMSEA = 0.037, SRMR = 0.0636, IFI = 0.972. Figure 2 shows a graphical representation of the standardized SEM model with the estimated path coefficients significant at p ≤ 0.10 level among the variables; insignificant paths are not shown in Fig.2 (amount of years having a driving licence for a car, and how many days a week the respondent drives a car). ...
Similar publications
In view of the fact that the detection of driver’s distraction is a burning issue, this study chooses the driver’s head pose as the evaluation parameter for driving distraction and proposes a driver distraction method based on the head pose. The effects of single regression and classification combined with regression are compared in terms of accura...
Citations
... Firstly, there is a distraction-free driving session, referred to as the baseline, after which participants navigate under various noisy conditions, encompassing cognitive, visual, visuomotor, and motor distractions. The statistical analysis of drivers' self-evaluation data in [26] reveals that pondering personal problems and observing roadside advertisements and natural scenes are among the most significant sources of distraction for drivers. The impact of smartphones as a potential source of distraction on drivers' attention and performance is explored in [39,93,101]. ...
Ensuring the precise anticipation of a driver’s attention is crucial for upholding safety in diverse human-centric transportation scenarios. This capability proves invaluable for discerning and evaluating accident risks in driver assistance systems, as well as in autonomous driving scenarios. Beyond traditional approaches that consider contextual variables and non-visual cues, such as the driver’s mental state and brain activity patterns, recent groundbreaking advancements in deep learning-based computer vision have propelled the momentum of visual attention prediction. The fundamental concept behind these techniques is to replicate the human visual system’s ability to identify critical objects or regions capturing a driver’s attention. Notably, the integration of salient object detection and attention mechanisms has gained popularity across various application domains. This paper provides a comprehensive overview of the current state of the art in this field. The primary focus of the study is to explore the architectures and workflows of deep learning-based models dedicated to the attention prediction process. To achieve this, we examine recent works in the field, specifically selecting those that have leveraged (simulated) attention mechanisms to estimate the driver’s attention area. Our analysis delves into the contributions of each model, elucidating their architectural design and underlying organization. Additionally, we scrutinize the effectiveness of each model by explaining the reported experimental results.
... According to the Federal Highway Administration (FHWA), expressway use is increasing at a rate of roughly 2% per year, and this trend is expected to continue. The survey also highlighted that traffic congestion has not only increased, but has also become more unstable over the past 20 years [41]. Relevant research has shown that in congested road sections during peak hours, temporarily allowing traffic to run on hard shoulders and implementing coordinated speed control can increase the traffic capacity by 15% to 30% without the need for road expansion [42][43][44], thereby alleviating regular traffic congestion problems. ...
... HVs are often not very capable of obtaining road instructions. This has been reflected in many studies on the acquisition rate of expressway road instruction [41,46]. While connected autonomous vehicles are frequently equipped with on-board units (OBUs) that can be integrated into any car or used as a vehicle simulator in the absence of actual traffic, allowing real-time information exchange between the vehicle and the infrastructure [47] and ensuring full access to road indication. ...
... HVs are often not very capable of obtaining road instructions. This has been refle in many studies on the acquisition rate of expressway road instruction [41,46]. While nected autonomous vehicles are frequently equipped with on-board units (OBUs) tha be integrated into any car or used as a vehicle simulator in the absence of actual tr allowing real-time information exchange between the vehicle and the infrastructure and ensuring full access to road indication. ...
With the development of vehicle-road network technologies, the future traffic flow will appear in the form of hybrid network traffic flow for a long time. Due to the change in traffic characteristics, the current hard shoulder running strategy based on traditional traffic characteristics cannot effectively serve the hybrid network traffic flow scenario, and will even lead to the further deterioration of traffic congestion. In order to propose a hard shoulder running strategy suitable for a hybrid network environment, a traffic breakdown prediction method based on a hidden Markov model was established. Secondly, the characteristics of traffic breakdown in a hybrid network environment were analyzed. Finally, based on the traffic breakdown characteristics in a hybrid network environment, a dynamic hard shoulder running method based on the hidden Markov model was proposed. The effectiveness of HMMD-HSR was verified by simulation and comparison with HMM-HSR, LMD-HSR, and N-HSR. The simulation results show that the HMMD-HSR proposed in this paper can improve operation efficiency and reduce travel time in a congested expressway.
... This suggests some empirical evidence that drivers do not change states in the lateral movement instantaneously, taking an average lag of 4-5 s. in response to urgent or threatening stimuli (like traffic lights 42 or approaching pedestrians 43 ). This result implies that the assumption of reasonable bounds for reaction time of 0-3 s for lifethreatening 36,37,[42][43][44][45][46][47] may need to be revised for non-life-threatening stimuli to consider less demanding or urgent behavior in driver reactions to other vehicles. ...
This study presents comprehensive analysis of car-following behavior on roads, utilizing Granger causality and transfer entropy techniques to enhance the validity of existing car-following models. It was found that most leader–follower relationships exhibit a delay in lateral movement by 4–5 s and last for short periods of around 3–5 s. These patterns are exhibited for all types of relationship found in the dataset, as well as for followers of all types. These findings imply that lateral movement reactions are governed by a different set of rules from braking and acceleration reactions, and the advantage in following lateral changes is short-lived. This also suggests that mixed traffic conditions may force drivers to slow down and calibrate reactions, as well as limiting the speed advantage gained by following a leader. Our methods were verified against random sampling as a method of selecting leader–follower pairs, decreasing the percent error in predicted speeds by 9.5% using the optimal velocity car-following model. The study concludes with a set of recommendations for future work, including the use of a diversity of car-following models for simulation and the use of causation entropy to distinguish between direct and indirect influences.
... Professional drivers need to maintain their attention on many traffic circumstances while driving. Cvahte Ojsteršek and Topolšek [26] analyzed the influence of drivers' visual and cognitive attention on their perception of changes in the traffic environment. Further, Milošević and Gajić [27] considered how different situations in traffic impacts the perception of road signs. ...
... Candidates Step 4. The aggregated normalization is calculated by Equation (26), where we considered the parameter β to be 0.5. The results are in Table 14. ...
Professional drivers play a crucial role in many businesses and the lives of people. They are responsible for transferring people and goods between distant points, enabling safe and efficient flows. The road traffic death rate is from 8.3 to 27.5 per 100,000 inhabitants in the countries globally. Because professional drivers spend a significant amount of time on the road, their appropriate selection may contribute to general traffic safety. In addition, an adequate selection of candidates significantly impacts the financial costs of the employing company. However, the recruitment procedure is a very complex task where multiple criteria should be considered. By its nature, this is a typical multi-criteria decision-making problem. The purpose of this paper is twofold: to contribute to the methodological, as well as to the professional field. Considering the professional, we propose a decision-making tool in the procedure of professional driver selection. There are several method-ological contributions. By reviewing the literature, we identified 14 criteria for candidate selection. In the proposed model, by using expert opinion and implementing DEMATEL and Fuller's pairwise comparisons, we ranked these criteria and determined the seven most important for further calculation procedure. Here, we introduced an original approach for measuring the reliability of obtained answers. Then, to rank the candidates, the fuzzy AROMAN approach is applied for the first time in the literature. The input data were obtained in the form of a survey, where the experts evaluated the importance of criteria and their interrelation. We used MS Excel and MATLAB for data processing. An additional methodological contribution of this study is an advancement of the AROMAN method by the proposal of an algorithm for the calculation of parameter λ used in the final ranking formula. To illustrate the applicability of the proposed model, a case study is provided. Based on the results, we can conclude that the new methodological approaches can be successfully used in the procedure of professional driver selection, as well as in solving other multi-criteria decision-making problems.
... Distraction is the diversion of attention to sources (e.g. an object, person, task or event) unrelated to driving, which could reduce driving performance, decisionmaking, and awareness (Hedlund et al., 2005a,b). Indeed, traffic cameras can be considered as a part of roadside objects besides traffic signs, billboards, vehicles, etc. which are sources of external distractions (Cvahte Ojsteršek & Topolšek, 2019;Mourant et al., 1969). Decorating enforcement cameras may enhance the distracting effect of these cameras compared to the usual ones because they are designed to stand out. ...
Traffic enforcement cameras can lead to unwanted side-effects. For instance, red-light cameras at intersections can increase the chance at rear-end collisions, probably caused by slowing down abruptly. Additionally, on the highways, speed cameras could lead to kangaroo-jumps in driving speed. Warning drivers about cameras is a possible solution. Cameras that are uncommonly decorated (e.g. colored in pink or in yellow) may provide better conspicuity compared to those in standard colors like gray. However, besides warning drivers about their presence, more conspicuity of cameras could also distract drivers from the primary driving task. Therefore, the impact of such decoration on safety is unclear. This study evaluates different decorated designs of the camera housing and how such decoration may influence camera's conspicuity and induce distraction while driving. Three camera colored-designs were evaluated (gray, pink, and a mixture of yellow and black) using a driving simulator. Fifty-four participants drove nine different conditions, i.e. three camera-designs in three roadway-settings (basic highway segments, intersections operating during the amber-phase, and intersections with a bicycle-lane). Subjective and objective measures allowed to assess if: 1) decorated camera housings increased conspicuity, 2) signs of distraction could be found, and 3) driving was influenced. In addition to the detection success rate, other eye-tracking parameters were: time-to-first-fixation, fixation count, and average and total fixation duration. Driving measures, i.e. speed, acceleration or deceleration rate, lane-keeping behavior, and minimum time-to-collision, were included to assess if the tested camera-designs impacted driving behavior. Moreover, a post-drive questionnaire assessed the participants' opinions. Using camera colored-designs improved the camera's conspicuity. However, driving measures remained comparable across the three camera-designs. Although the subjective data indicated some distraction from the decorated cameras, clear indications for an effect on traffic safety were lacking. Meanwhile, a little over half of the respondents supported camera decoration. The current study does not allow firm conclusions, and additional research is recommended.
... The correct perception of the vehicle driver is essential for the safe crossing or performance of a transport service [1][2][3]. In daytime conditions, under natural light, the perception of lane elements is not a challenge, even in complex and specific road layouts [4][5][6]. The problem of visibility, and the decrease in perception, occurs with dusk and night time [7][8][9]. ...
Street lighting should realise normative illuminance levels throughout the roadway. The determination of the illuminance level of a road requires the use of a measurement technique based on classic point measurements at a specific grid of measurement points. Classical stationary measurements using the method indicated in the prescriptive requirements are time-consuming and labor-intensive. The authors of the article have presented a concept of a measurement system that could be used to partially automate road lighting measurements and increase their universality. The proposed measurement system uses the simultaneous measurement of illuminance values from lux meters located on the roof of the vehicle. The measurement is carried out while the vehicle is driving on a lit road, and the illuminance values are localized using a global GPS satellite location system equipped with RTK corrections. The use of GPS RTK localization data corrections allowed the measurement results to be unambiguously assigned to post-measurement fields. On the basis of the collected measurement data, with the use of terrain maps, it is possible to determine in detail the illuminance parameters on the surveyed road sections. The paper presents the construction of a measurement system for the mobile measurement of street lighting intensity using a GPS RTK receiver, along with verification of its correct operation. The correctness of the system’s operation was confirmed on the basis of the Measurement System Analysis (MSA) method. The calculations performed confirmed an R&R result of 11.14%. The proposed solution allows data on the lighting parameters of the surveyed road section to be obtained in a quick and repeatable manner. As a result, it is possible to make a quick assessment of the street lighting condition of the entire road section. The proposed system has been verified under field conditions and the repeatability of the results obtained has been confirmed.
... Transportation-related issues are highly related to the road/driver safety and traffic environment, and are attracting growing interests [1][2][3][4]. For example, fatigue driving can significantly raise the possibility of car accidents [5], and is generally influenced by driverrelated factors such as the state of sleep and health [6]. ...
An advanced driver simulator methodology facilitates a well-connected interaction between the environment and drivers. Multiple traffic information environment language processing aims to help drivers accommodate travel demand: safety prewarning, destination navigation, hotel/restaurant reservation, and so on. Task-oriented dialogue systems generally aim to assist human users in achieving these specific goals by a conversation in the form of natural language. The development of current neural network based dialogue systems relies on relevant datasets, such as KVRET. These datasets are generally used for training and evaluating a dialogue agent (e.g., an in-vehicle assistant). Therefore, a simulator for the human user side is necessarily required for assessing an agent system if no real person is involved. We propose a new end-to-end simulator to operate as a human driver that is capable of understanding and responding to assistant utterances. This proposed driver simulator enables one to interact with an in-vehicle assistant like a real person, and the diversity of conversations can be simply controlled by changing the assigned driver profile. Results of our experiment demonstrate that this proposed simulator achieves the best performance on all tasks compared with other models.
... Understanding fluctuations in sustained attention through different modalities and the extent of their demands is critical for everyday functioning. For example, while driving, we process up to 90% of the information visually, thus, successful driving requires proper functioning of visual sustained attention (Ojsteršek and Topolšek, 2019). On the other hand, academic learning is based on both visual and auditory sustained attention, being a highly demanding task in both modalities. ...
Natural fluctuations in sustained attention can lead to attentional failures in everyday tasks and even dangerous incidences. These fluctuations depend on personal factors, as well as task characteristics. So far, our understanding of sustained attention is partly due to the common usage of laboratory setups and tasks, and the complex interplay between behavior and brain activity. The focus of the current study was thus to test the feasibility of applying a single-channel wireless EEG to monitor patterns of sustained attention during a set of ecological tasks. An EEG marker of attention (BEI—Brain Engagement Index) was continuously recorded from 42 healthy volunteers during auditory and visual tasks from the Test of Everyday Attention (TEA) and Trail Making Test (TMT). We found a descending pattern of both performance and BEI in the auditory tasks as task complexity increases, while the increase in performance and decrease in BEI on the visual task. In addition, patterns of BEI in the complex tasks were used to detect outliers and the optimal range of attention through exploratory models. The current study supports the feasibility of combined electrophysiological and neurocognitive investigation of sustained attention in ecological tasks yielding unique insights on patterns of sustained attention as a function of task modality and task complexity.
... The studies that examine driver perception were carried out using different methodologies, by the experiments conducted in driving simulators (Ben-Bassat and Shinar 2011;Martens and Brouwer 2013;Pešić et al. 2019;Rudin-Brown 2004;Wu et al. 2017;Zheng et al. 2018), real traffic situations (Troscianko et al. 1999), tablet PCs and smart boards (Cicevic et al. 2017), by driver self-reports, i.e., questionnaire (Ojsteršek and Topolšek 2019), and also in virtual reality . The sample ranges from 14 to 200 respondents, while statistical analysis was most often used for data processing. ...
The major challenge of this paper is to examine how various forms of speed perception affect motor vehicle crash (MVC) involvement. To model this relationship, we use a type-2 fuzzy inference system (T2FIS). Another general challenge is to improve the performance of seven created T2FISs in a sense of compliance with the empirical data. This is achieved by a proposal of an algorithm based on the bee colony optimization (BCO) metaheuristic. The main novelty of this algorithm is the way how the testing points are selected in a type-2 fuzzy environment, which influences the execution efficiency. Data collection was carried out in twelve experiments. A total of 178 young drivers assessed the speed level from four positions; three of them relate to the speed perception of other vehicles on the road, while the remaining one represents the assessment of their own speed. At each position, three speed levels were assessed: 30, 50, and 70 km/h. As a result of the implemented methodology, a relationship between the various forms of speed perception and participation in MVCs can be quantified. The BCO-based algorithm achieved an average improvement of 21.17% in the performance of the initial T2FIS structures. The final results indicate that the drivers whose speed perception of the vehicle they are looking at from the rear side, as well as of the own vehicle, is poor have an elevated risk toward participation in MVCs compared to other forms of speed perception. This can be useful in various educational and recruitment procedures.
... Distance from stop line, vehicle's approach speed and type of intersection were important factors in drivers' decisions [20]. It is also interesting to note that in highways, advertisements and the natural environment represent the visual elements that most distract the driver [24]. After congestion, the driving behavior tends to be more aggressive and prone to accidents [25]. ...
Recently Augmented-Reality Head-Up Displays (AR-HUDs) has emerged as a next evolution of in-vehicle display technologies. Augmented image should be overlayed onto real-world objects providing alerts that can be viewed in the driver’s line of sight. However, there are currently no guidelines that apply specifically to the Human-Machine Interface (HMI) for AR-HUDs. A review on existing literature on AR-HUD and applicable human factors and human-computer interaction guidelines was conducted, using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) approach. Based on the literature, an initial set of guidelines for developing AR-HUD was derived. The guidelines are grouped into virtual image distance and field of view, brightness, projected information, and legibility. Research gaps are also discussed for future experiments. Taken together, this study is a starting point for developing the interface of AR-HUDs.
