Driver Attention Research Articles

A Novel Driving Behavior Learning and Visualization Method With Natural Gaze Prediction

Driving behavior analysis is vital for the advanced driving assistance system, aiming to improve driving behavior and decrease traffic accidents. Most existing driving behavior learning methods focus on either vehicle sensor information or driver's attention information, and provide a classification result on the current time data samples. The visualization of driving behavior on time series data samples could give an understanding and review of the driver's continuous actions. However, there has been little progress in combining the multi-modal vehicle and driver information on driving behavior learning and visualization. A multi-information driving behavior learning and visualization method with natural gaze prediction is proposed in this paper, which automatically integrates driver's gaze direction estimated from face camera, and various vehicle sensor data collected from on-board diagnostics (OBD) system. To accurately estimate the eye gaze under large head movement, a novel head pose-free eye gaze prediction method without calibration is proposed based on global and local scale sparse encoding, which treats the direction mapping as small gaze region classification. To understand driving behavior more intuitively, the latent features that represent different driving behaviors are extracted by FastICA from the fused time series data, and mapped into RGB color space for distinguished visualization. Experimental results demonstrate the effectiveness of the proposed method, and show that the proposed method performs better than the compared methods.

Modeling Required Driver Attention Level Based On Environmental Risk Factors Using Deep Convolutional Neural Networks

Modeling Required Driver Attention Level Based On Environmental Risk Factors Using Deep Convolutional Neural Networks

RANCANG BANGUN APLIKASI SI-WAJA BERBASIS ANDROID UNTUK MENCEGAH KECELAKAAN LALU LINTAS DI KOTA SURAKARTA

The needs of land transportation grows rapidly each year, along with the increasing population and mobility. It threatens the safety of road users if not handled appropriately. From 2015 to 2018 accidents in the city of Surakarta were relatively increased by the number of accidents in 2018 was 834 events. 55% of accident events caused by road users are not orderly. There is already handling done, but not effective. No one has overcome the blackspot with technology. Si Waja application is designed to reduce traffic accidents. Si Waja application serves to improve the driver's attention. The process of designing this application using methods of research and development. Application design Si Waja uses Android Studio integrated with Firebase. There are two tests conducted to test the Si Waja application Black Box Testing and Usability Testing. All elements in the application go well, evidenced by the Black Box Testing. This usability test uses the System Usability Testing (SUS) method which provides adequate results based on the consideration of small sample quantities, time, and cost. The SUS calculation result will be converted to certain values. This conversion result will give the app information that is made worthy or unfeasible to implement. From the 100 total value, Si Waja obtained 71,833, with index B. It means that this application is eligible to be applied in Surakarta.

Comparative Analysis of Kinect-Based and Oculus-Based Gaze Region Estimation Methods in a Driving Simulator.

Driver’s gaze information can be crucial in driving research because of its relation to driver attention. Particularly, the inclusion of gaze data in driving simulators broadens the scope of research studies as they can relate drivers’ gaze patterns to their features and performance. In this paper, we present two gaze region estimation modules integrated in a driving simulator. One uses the 3D Kinect device and another uses the virtual reality Oculus Rift device. The modules are able to detect the region, out of seven in which the driving scene was divided, where a driver is gazing at in every route processed frame. Four methods were implemented and compared for gaze estimation, which learn the relation between gaze displacement and head movement. Two are simpler and based on points that try to capture this relation and two are based on classifiers such as MLP and SVM. Experiments were carried out with 12 users that drove on the same scenario twice, each one with a different visualization display, first with a big screen and later with Oculus Rift. On the whole, Oculus Rift outperformed Kinect as the best hardware for gaze estimation. The Oculus-based gaze region estimation method with the highest performance achieved an accuracy of 97.94%. The information provided by the Oculus Rift module enriches the driving simulator data and makes it possible a multimodal driving performance analysis apart from the immersion and realism obtained with the virtual reality experience provided by Oculus.

Exploring the combined effects of driving situations on freeway rear-end crash risk using naturalistic driving study data

The causes and the crash-generating processes of freeway rear-end (FRE) crashes are complicated. Previous studies have highlighted the many contributing factors to crash occurrences on freeways, such as traffic flow conditions, driver-following behavior, driver attention allocation, driver characteristics, the driving environment, and drivers’ interactions with surrounding vehicles, etc. Nevertheless, few studies have looked into the combined effects of these factors on FRE crash risk as a whole. This study focuses on characterizing the sequential crash generating process of the interactions between traffic flow conditions, roadway attributes, driver behavior, event attributes, and precipitating events in FRE crashes. A sequential modeling framework for modeling the sequential and combined effects on FRE crash risk was constructed by applying structural equation modeling (SEM). The Second Highway Strategic Research Program (SHRP2) Naturalistic Driving Study (NDS) data was utilized for this purpose as this data provides extensive information concerning what happened before crashes and near-crashes. A total of 17 and 433 FRE crashes and near-crashes, respectively, were included in this study. It was found that (1) FRE crashes were associated with the sequential and combined effects of those factors above; (2) certain types of speed oscillations were identified as precursors to sudden braking when vehicles ahead decelerated or stopped-and-went; and (3) many factors were identified as being associated with driver perception time and crash occurrence.

Human-Machine Interfaces for Handover from Automated Driving Systems: A Literature Review

New automated driving systems are constantly being developed and integrated into vehicles. At the current state of technology, these features still require drivers to monitor performance and resume control when required by the systems. To cue drivers to take control, a takeover request (TOR) is presented with auditory, visual, and haptic cues. To characterize current TOR practices, a literature review was conducted to review types of human-machine interfaces (HMI’s) and their associated message presentation. Twenty-six articles were identified after searching keywords across journal articles and conference proceedings. HMIs and message types were identified and classified. Results indicated that TORs are more commonly used as general alerts to gain driver attention to driving tasks, rather than to request drivers to engage in a specific action or explain context of the TOR. Literature suggests that future systems may focus more on not only alerting drivers but providing additional context to those alerts.

Improving Driver Gaze Prediction With Reinforced Attention

We consider the task of driver gaze prediction: estimating where the location of the focus of a driver should be, based on a raw video of the outside environment. In practice, we output a probability map that gives the normalized probability of each point in a given scene being the object of the driver attention. Most existing methods ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i.e.</i> , <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Coarse-to-Fine</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Multi-branch</i> ) take an image or a video as input and directly output the fixation map. While successful, these methods can often produce highly scattered predictions, rendering them unreliable for real-world usage. Motivated by this observation, we propose the reinforced attention (RA) model as a regulatory mechanism to increase prediction density. Our method is built directly on top of existing methods, making it complementary to current approaches. Specifically, we first use <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Multi-branch</i> to obtain an initial fixation map. Then, RA is trained using deep reinforcement learning to learn a location prediction policy, producing a reinforced attention. Finally, in order to obtain the final gaze prediction result, we combine the fixation map and the reinforced attention by a mask-guided multiplication. Experimental results show that our framework improves the accuracy of gaze prediction, and provides state-of-the-art performance on the DR(eye)VE dataset.

Scanning the Issue

Driver Inattention Detection in the Context of Next-Generation Autonomous Vehicles Design: A Survey

Eye Gaze Estimation Invisible and IR Spectrum for Driver Monitoring System

Driver monitoring system has gained lot of popularity in automotive sector to ensure safety while driving. Collisions due to driver inattentiveness or driver fatigue or over reliance on autonomous driving features arethe major reasons for road accidents and fatalities. Driver monitoring systems aims to monitor various aspect of driving and provides appropriate warnings whenever required. Eye gaze estimation is a key element in almost all of the driver monitoring systems. Gaze estimation aims to find the point of gaze which is basically,” -where is driver looking”. This helps in understanding if the driver is attentively looking at the road or if he is distracted. Estimating gaze point also plays important role in many other applications like retail shopping, online marketing, psychological tests, healthcare etc. This paper covers the various aspects of eye gaze estimation for a driver monitoring system including sensor choice and sensor placement. There are multiple ways by which eye gaze estimation can be done. A detailed comparative study on two of the popular methods for gaze estimation using eye features is covered in this paper. An infra-red camera is used to capture data for this study. Method 1 tracks corneal reflection centre w.r.t the pupil centre and method 2 tracks the pupil centre w.r.t the eye centre to estimate gaze. There are advantages and disadvantages with both the methods which has been looked into. This paper can act as a reference for researchers working in the same field to understand possibilities and limitations of eye gaze estimation for driver monitoring system.

An Improved Single Shot Multibox for Video-Rate Head Pose Prediction

Head pose estimation plays a crucial role in attention detection, behavior analysis, human-computer interaction, and eye tracking, etc. The existing landmark-to-pose methods require two steps, not only to detect the key points of the human face, but also to solve the 2D to 3D mapping problem usually by the average head model. We propose an efficient and robust method to monitor the driver's attention. Firstly, the prevailing object detection algorithm SSD which has inherent capabilities of simultaneous classify and regress, is used to create a lightweight network, which avoids the shortcomings of high coupling and time-consuming of the existing methods. Then, single-scale anchors, which have a less computational cost than multi-scale anchors, are adopted for vehicle environments where the ambient light changes dramatically. Finally, by binning continuous angles into specific classes, the 3D angle regression problem is converted into angle classification and face box regression, and our model directly outputs Euler angles (Yaw, Pitch, and Roll) without detecting face landmarks. Experiments on YawDD result that our approach can efficiently perform detection tasks and estimation tasks under the actual driving environment of various luminosity. The mean average errors of prediction in AFLW2000 and 300W-LP are 6.01° and 2.38°, which demonstrates the accuracy of the proposed algorithm.

Initial Testing of a Web-Based Intervention to Reduce Adolescent Driver Inattention: A Randomized Controlled Trial

IntroductionMotor vehicle crashes are the leading cause of adolescent death. Inattention to the roadway contributes to crash risk. The objective of this study was to deploy an initial study of a web-based intervention (Let’s Choose Ourselves) designed to improve adolescent driver attention to the roadway. MethodsWe used a randomized controlled trial design in a sample of adolescent drivers to test if a web-based intervention decreased cell phone engagement in driving simulation at 3 months as compared with controls. As secondary hypotheses, we tested if the intervention increased the use of peer passengers to manage distractions and decreased eyes off the forward roadway in driving simulation and decreased self-reported risky driving behaviors. Adolescents, aged 16-17 years, licensed for ≤90 days were randomized to Let’s Choose Ourselves with distractions in the simulator protocol at baseline, Let’s Choose Ourselves with no distractions, an attention control intervention on healthy eating with distractions, or attention control with no distractions. We used Poisson regression modeling to test the primary and secondary hypotheses. ResultsThe trial included 60 adolescents (66.7% female, 78.3% non-Hispanic white subjects, mean age 16.8 years, licensed 50.8 days). In Poisson regression, controlling for sex, we found no significant effects of Let’s Choose Ourselves on primary or secondary outcomes. However, there was a significant effect of visit on self-report outcomes, with self-reported distracted driving behaviors increasing over time. DiscussionAlthough there were no significant effects of Let’s Choose Ourselves, self-reported risky driving behaviors increased over time. Further investigation of the relationship between driving experience and increasing inattention to the road in adolescents is warranted.

Measuring Driver Perception: Combining Eye-Tracking and Automated Road Scene Perception.

ObjectiveTo investigate how well gaze behavior can indicate driver awareness of individual road users when related to the vehicle’s road scene perception.BackgroundAn appropriate method is required to identify how driver gaze reveals awareness of other road users.MethodWe developed a recognition-based method for labeling of driver situation awareness (SA) in a vehicle with road-scene perception and eye tracking. Thirteen drivers performed 91 left turns on complex urban intersections and identified images of encountered road users among distractor images.ResultsDrivers fixated within 2° for 72.8% of relevant and 27.8% of irrelevant road users and were able to recognize 36.1% of the relevant and 19.4% of irrelevant road users one min after leaving the intersection. Gaze behavior could predict road user relevance but not the outcome of the recognition task. Unexpectedly, 18% of road users observed beyond 10° were recognized.ConclusionsDespite suboptimal psychometric properties leading to low recognition rates, our recognition task could identify awareness of individual road users during left turn maneuvers. Perception occurred at gaze angles well beyond 2°, which means that fixation locations are insufficient for awareness monitoring.ApplicationFindings can be used in driver attention and awareness modelling, and design of gaze-based driver support systems.

PATTERNS OF ATTENTION AND ENERGY CONSUMPTION CHANGES IN TWILIGHT DURING DRIVING URBAN STREETS

The dynamic process of movement of vehicles in cities is associated with interaction with objects of the road environment. Road conditions, traffic and pedestrians require certain actions from the driver to ensure road safe-ty. Under such circumstances, the reliability and safety of road traffic in human-machine systems mainly depends on the functional state of the driver (provided that the technical component, the subsystem is “car”) and his ability to respond to changes in the traffic situation when obstacles arise (conflict situations). The development of states of tension and fatigue of the driver is associated with an increase in energy costs, which leads to a natural in-crease in the heart rate, respiration and other parameters indicating changes in the energy balance of the driver's body. Eye Tracking technology has been applied to detect attention. Energy costs were determined using a method that takes into account the frequency of the driver's external respiration when driving on the road and in the background. As a result, a model of change in the attention of drivers with driving experience and a model of en-ergy consumption when driving in the evening twilight at a certain level of illumination were obtained. To determine the influence of conflict situations during movement in the evening twilight on the indicator of attention and energy consumption of the driver, a study was carried out in real conditions on city streets. A group of drivers with experience of 3-5 years and 10-16 years performed arrivals in the evening twilight on passenger cars "C" class. Experimental studies of the indicator of drivers' attention and functional state in conditions of evening twilight were carried out on different categories of city streets. The study involved drivers between the ages of 20 and 40. The obtained dependences of the change in the driver's functional state on illumination showed that at low illumination levels in the evening twilight, a rapid increase in the driver's functional state shifts. Thus, the energy consumption of the driver while driving depends on the types of conflict situations and the level of illumination. It was found that for drivers with less than 5 years of driving experience, shifts in functional state were more im-portant than other drivers. Also, such drivers had lower attention indicators compared to experienced drivers with more than 10 years of driving experience. It was found that when the illumination changes at dusk, the energy consumption increases on average to 3.3 kcal / min for drivers with less than 5 years of experience, and for drivers with more than 10 years of experience, it increases by 2.4 kcal / min on average. Keywords: driver, conflict situations, attention, energy costs.

Effects of Music on Driver Behavior

The attention level of car drivers is affected by many factors. Music is one of the most importantones, but its effect is rarely studied. Music can affect driving style in both positive and negative ways, as itcan reduce fatigue but also increase the level of distraction or aggression. This article presents anexperimental investigation of the effects of music on driver attention level. Several measurements on avehicle simulator were done to collect data that demonstrates the relationship between music and theperformance of the car driver. The simulation measured performance under three conditions - relaxationmusic, rock music and silence. Additionally, the measurements were repeated in both fresh and tired states.The results are, in some aspects, different from our expectations - for example, relaxation music improvedreaction time but also correlated with a higher occurrence of inappropriate steering actions. Deeperunderstanding of how the music and noise affect the driver’s actions and decisions will help to improveroad safety and reduce the probability of accidents

A novel public dataset for multimodal multiview and multispectral driver distraction analysis: 3MDAD

Driver distraction and fatigue have become one of the leading causes of severe traffic accidents. Hence, driver inattention monitoring systems are crucial. Even with the growing development of advanced driver assistance systems and the introduction of third-level autonomous vehicles, this task is still trending and complex due to challenges such as the illumination change and the dynamic background. To reliably compare and validate driver inattention monitoring methods, a limited number of public datasets are available. In this paper, we put forward a public, well-structured and complete dataset, named Multiview, Multimodal and Multispectral Driver Action Dataset (3MDAD). The dataset is mainly composed of two sets: the first one recorded in daytime and the second one at nighttime. Each set consists of two synchronized data modalities, both from frontal and side views. More than 60 drivers are asked to execute 16 in-vehicle actions under a wide range of naturalistic driving settings. In contrast to other public datasets, 3MDAD presents multiple modalities, spectrums and views under different time and weather conditions. To highlight the utility of our dataset, we independently analyze the driver action recognition results adapted to each modality and those obtained of several combinations of modalities.

Driver Attention Area Extraction Method Based on Deep Network Feature Visualization

The current intelligent driving technology based on image data is being widely used. However, the analysis of traffic accidents occurred in intelligent driving vehicles shows that there is an explanatory difference between the intelligent driving system based on image data and the driver’s understanding of the target information in the image. In addition, driving behavior is the driver’s response based on the analysis of road information, which is not available in the current intelligent driving system. In order to solve this problem, our paper proposes a driver attention area extraction method based on deep network feature visualization. In our method, we construct a Driver Behavior Information Network (DBIN) to map the relation between image information and driving behavior. Then we use the Deep Network Feature Visualization method (DNFV) to determine the driver’s attention area. The experimental results show that our method can extract effective road information from a real traffic scene picture and obtain the driver’s attention area. Our method can provide a useful theoretical basis and related technology of visual perception for future intelligent driving systems, driving training and assisted driving systems.

Exploring Monitoring Systems Data for Driver Distraction and Drowsiness Research.

Driver inattention is a major contributor to road crashes. The emerging of new driver monitoring systems represents an opportunity for researchers to explore new data sources to understand driver inattention, even if the technology was not developed with this purpose in mind. This study is based on retrospective data obtained from two driver monitoring systems to study distraction and drowsiness risk factors. The data includes information about the trips performed by 330 drivers and corresponding distraction and drowsiness alerts emitted by the systems. The drivers’ historical travel data allowed defining two groups with different mobility patterns (short-distance and long-distance drivers) through a cluster analysis. Then, the impacts of the driver’s profile and trip characteristics (e.g., driving time, average speed, and breaking time and frequency) on inattention were analyzed using ordered probit models. The results show that long-distance drivers, typically associated with professionals, are less prone to distraction and drowsiness than short-distance drivers. The driving time increases the probability of inattention, while the breaking frequency is more important to mitigate inattention than the breaking time. Higher average speeds increase the inattention risk, being associated with road facilities featuring a monotonous driving environment.

Cognitive load estimation using ocular parameters in automotive

In automotive, usage of electronic devices increased visual inattention of drivers while driving and might lead to accidents. It is often challenging to detect if a driver experienced a change in cognitive state requiring new technology that can best estimate driver's cognitive load. In this paper, we investigated the efficacy of various ocular parameters to estimate cognitive load and detect cognitive state of driver. We derived gaze and pupil-based metrics and evaluated their efficacy in classifying different levels of cognitive states while performing psychometric tests in varying light conditions. We validated the performance of our metrics in simulation as well as in-car environments. We compared the accuracy (from confusion matrix) of detecting cognitive state while performing secondary task using our proposed metrics and Machine Learning models. It was found that a Neural Network model combining multiple ocular metrics showed better accuracy (75%) than individual ocular metrics. Finally, we demonstrated the potential of our system to alert drivers in real-time under critical distractions.

Legal and psychological aspects of accident prevention

In my study I give a description of a relatively new psychological personality test. The low or high value of the scales shows what dangerous tendencies are supposed in accidents. Traffic accidents can be explained by human errors, especially due to failure to comply with traffic rules. In most collisions can be discerned inattention of drivers. In our culture the killing of a person is a big sin, punished even if it is not an intentional action.

Influence of Advertising Billboard Images on Driver Performance

Background: The high demand for brand and brand promotion in Ghana seems to be on the rise. Advertisers are making use of every available space to promote and sell their brands, not knowing the silent contribution of some of these billboards to the occurrence of road accidents on the highways of Ghana. External distractions appear to play a major role in at least 6-9% of distraction-affected motor vehicle collisions (MVCs). Driver inattentiveness and distraction are known to be the two main life-threatening factors for road safety globally. Aim: The aim of this study is to explore how the visual elements (images) on billboards distract drivers and influence their performance. Although roadside advertising has been identified as a potential source of driver distraction, little attention has been given to what specifically on the billboard that causes the distraction. Method: For the study to ascertain the influence of advertising billboard images on driver performance, a standard designed questionnaires were administered to 200 drivers at the major bus/truck terminals in Kumasi; both commercial and private drivers who ply the Kumasi -Accra highway on regular basis. Information obtained from the questionnaires was analyzed using Statistical Package for Social Sciences (SPSS). The questionnaires and also to some private car drivers. Results: The study revealed that images on roadside advertising billboards do not only attract the driver’s attention, but also influence the driver’s psyche and consequently take their concentration and focus from their primary driving task. This was evident in the results where 123 (representing 61.5%) of the respondents indicated that they get attracted to the images on the billboards more. Conclusion: The study dealt specifically with the influence billboard images have on drivers and the road user in general. There is the need for further research to be done specifically on the type of images that advertisers should be encouraged to display on the advertising billboards. Keywords: Driver Performance, Drivers attention, Advertising Billboards Images, Traffic Safety, Road Accidents DOI: 10.7176/DCS/10-6-01 Publication date: June 30 th 2020