Search

Abstract Distracted driving is the leading cause of road traffic accidents. It is essential to monitor the driver's status to avoid traffic accidents caused by distracted driving. Current research on detecting distracting behaviours focuses on analysing image features using convolutional neural networks (CNNs). However, the generalisation ability of the current distracted driving models is limited. This paper aims to improve the generalisation ability of distracted driving models that are affected by factors such as the driver himself, the background, the monitoring angle, and so on. A new driver distraction detection method, which is referred to as multi‐scale domain adaptation network (MSDAN), was proposed to improve model adaptability. The method consists of three stages: first, multi‐scale convolution was introduced to build a new backbone to accommodate better the valuable feature of the target on different scales. Secondly, the authors designed the domain adaptation network to improve the model's adaptability to the difference in data sources through adversarial training. Finally, dropout is added to the fully connected layer to increase the model's generalisation ability. The comparison results on the large‐scale driver distraction detection dataset show that the authors’ method can accurately detect driver distraction and has good generalisation performance, with an accuracy improvement in the cross‐driver and cross‐dataset experiments.

Abstract This paper develops a pedestrian potentially dangerous behaviour prediction method based on attention‐long‐short‐term memory (Attention‐LSTM) architecture to predict pedestrian trajectory and intention for the unexpected pedestrian crossing accident avoidance. To extract the road scene information for short periods of time, and improve the accuracy of subsequent intention inference and trajectory prediction, the panoramic segmentation is used to extrapolate pedestrian instances and segment areas of the environment. Next, an encoder–decoder framework based on Attention‐LSTM model is proposed to infer a pedestrian's intention to run or walk out into oncoming traffic straight and to predict the future trajectory. The proposed network involves two parts: temporal feature encoder and multi‐task decoder. The temporal feature encoder is mainly used to selectively emphasize the temporal features using attention mechanism, and then LSTM is employed for its encoding. In the multi‐task decoder, a multi‐head self‐attention mechanism and LSTM are used to forecast the pedestrians’ intention and future trajectory, respectively. Extensive experiments on pedestrian intention estimation (PIE) datasets demonstrate that the authors’ proposed approach surpasses prior studies in terms of prediction accuracy in trajectory and intention. This study can not only effectively avoid serious accidents caused by illegal road crossing but also achieve early warning for collision avoidance.

Recognizing speed limit information is crucial for advanced driver assistance systems (ADAS) as it directly affects the safety planning and decision-making process of intelligent driving systems. However, traditional image recognition-based solutions confront inherent restrictions and precision issues due to uncontrolled external factors. This paper endeavors to present a novel, data-driven solution for speed limit information recognition that leverages the stability and maturity of data-driven technologies, overcoming these challenges. We introduce Pareto-GBDTMO, a cutting-edge method that synergistically blends Gradient Boosting Decision Trees for Multiple Output (GBDT-MO) and Fast Pareto Feature Selection (FPFS). This integration is instrumental in discerning salient features to direct and expedite the learning process of GBDT-MO. When coupled with Bayesian optimization, the feature set undergoes dynamic updates at each boosting iteration, allowing GBDT-MO to concentrate on the most prominent features. This adaptive, relevance-guided feature space regularization mechanism enhances the efficiency and precision of speed limit recognition. Fujian Province highway electronic toll collection (ETC) data is used for further validation, and the experimental results emphasize the effectiveness of our model, with an high accuracy of 97%, a low loss rate of 0.7%, and minimal latency. These findings affirm the feasibility and scientific validity of our data-driven approach, offering a reliable and redundant solution for speed limit information recognition in ADAS. This study not only contributes to the practical application of ADAS but also lays the groundwork for future large-scale lane-level data research

Many modern automated vehicle sensor systems use light detection and ranging (LiDAR) sensors. The prevailing technology is scanning LiDAR, where a collimated laser beam illuminates objects sequentially point-by-point to capture 3D range data. In current systems, the point clouds from the LiDAR sensors are mainly used for object detection. To estimate the velocity of an object of interest (OoI) in the point cloud, the tracking of the object or sensor data fusion is needed. Scanning LiDAR sensors show the motion distortion effect, which occurs when objects have a relative velocity to the sensor. Often, this effect is filtered, by using sensor data fusion, to use an undistorted point cloud for object detection. In this study, we developed a method using an artificial neural network to estimate an object's velocity and direction of motion in the sensor's field of view (FoV) based on the motion distortion effect without any sensor data fusion. This network was trained and evaluated with a synthetic dataset featuring the motion distortion effect. With the method presented in this paper, one can estimate the velocity and direction of an OoI that moves independently from the sensor from a single point cloud using only one single sensor. The method achieves a root mean squared error (RMSE) of 0.1187 m s−1 and a two-sigma confidence interval of [ − 0.0008 m s−1, 0.0017 m s−1] for the axis-wise estimation of an object's relative velocity, and an RMSE of 0.0815 m s−1 and a two-sigma confidence interval of [ 0.0138 m s−1, 0.0170 m s−1] for the estimation of the resultant velocity. The extracted velocity information (4D-LiDAR) is available for motion prediction and object tracking and can lead to more reliable velocity data due to more redundancy for sensor data fusion. [ABSTRACT FROM AUTHOR]

Detecting drowsiness among drivers is critical for ensuring road safety and preventing accidents caused by drowsy or fatigued driving. Research on yawn detection among drivers has great significance in improving traffic safety. Although various studies have taken place where deep learning-based approaches are being proposed, there is still room for improvement to develop better and more accurate drowsiness detection systems using behavioral features such as mouth and eye movement. This study proposes a deep neural network architecture for drowsiness detection employing a convolutional neural network (CNN) for driver drowsiness detection. Experiments involve using the DLIB library to locate key facial points to calculate the mouth aspect ratio (MAR). To compensate for the small dataset, data augmentation is performed for the 'yawning' and 'no_yawning' classes. Models are trained and tested involving the original and augmented dataset to analyze the impact on model performance. Experimental results demonstrate that the proposed CNN model achieves an average accuracy of 96.69%. Performance comparison with existing state-of-the-art approaches shows better performance of the proposed model. [ABSTRACT FROM AUTHOR]

In recent years, a strong push towards driverless mobility solutions can be seen in many transportation sectors including railways. While the European Train Control System already specifies the necessary interfaces to open up the possibility of Automatic Train Operation (ATO) for mainline railway vehicles, required infrastructure-side upgrades of interlocking systems are time- and cost-intensive. Alternatively, a pure vehicle-side Automatic Train Operation solution can be conceptualized that relies on processing the same audio-visual input a human train driver would normally base his decisions on. This would require the vehicle-side detection of track-side railway signals to determine the vehicle's movement authority and allowed maximum speed. Such a signal detection system could furthermore be employed as an Advanced Driver Assistance System (ADAS) or support autonomous shunting operations. To enable such a system, this paper presents GERALD, a novel dataset for a neural network based detection approach of railway signals. The dataset contains 5000 images from a wide variety of railway scenes as well as annotations for the most common types of German mainline railway signals. The material was gathered using publicly available cab-view recordings uploaded by railway enthusiasts on YouTube. Using a state of the art neural network architecture for evaluation, we notice promising detection accuracies despite GERALD being a comparably small dataset. The dataset is freely available for research and non-commercial purposes at: https://github.com/ifs-rwth-aachen/GERALD [ABSTRACT FROM AUTHOR]

Introduction: PD is a progressive neurodegenerative disorder that affects, according to the ICF, body systems (cognitive, visual, and motor), and functions (e.g., decreased executive functions, decreased visual acuity, impaired contrast sensitivity, decreased coordination)-all which impact driving performance, an instrumental activity of daily living in the domain of "Activity" and "Participation" according to the ICF. Although there is strong evidence of impaired driving performance in PD, few studies have explored the real-world benefits of invehicle automation technologies, such as in-vehicle information systems (IVIS) and advanced driver assistance systems (ADAS), for drivers with PD. These technologies hold potential to alleviate driving impairments, reduce errors, and improve overall performance, allowing individuals with PD to maintain their mobility and independence more safely and for longer periods. This preliminary study aimed to fill the gap in the literature by examining the impact of IVIS and ADAS on driving safety, as indicated by the number of driving errors made by people with PD in an on-road study. Methods: Forty-five adults with diagnosed PD drove a 2019 Toyota Camry equipped with IVIS and ADAS features (Toyota Safety Sense 2.0) on a route containing highway and suburban roads. Participants drove half of the route with the IVIS and ADAS systems activated and the other half with the systems deactivated. Results: The results suggest that systems that assume control of the driving task, such as adaptive cruise control, were most effective in reducing driving errors. Furthermore, individual differences in cognitive abilities, particularly memory, were significantly correlated with the total number of driving errors when the systems were deactivated, but no significant correlations were present when the systems were activated. Physical capability factors, such as rigidity and bradykinesia, were not significantly correlated with driving error. Discussion: Taken together, these results show that in-vehicle driver automation systems can benefit drivers with PD and diminish the impact of individual differences in driver cognitive ability. [ABSTRACT FROM AUTHOR]

Cooperative adaptive cruise control (CACC) realizes efficient, intelligent control of vehicle acceleration, deceleration, and steering, through inter‐vehicle communication and cooperative control. However, the close combination of the platoon makes it difficult for other vehicles to cut‐in, which can lead to severe traffic jams on certain sections of the road. The control effect of the CACC depends on the platoon penetration rate, which is the percentage of connected and autonomous vehicles (CAVs) in the total number of platoon members. There is no quantitative control method for different penetration rates, and it is difficult to quantify the impact of CACC vehicles on traffic. Therefore, this paper proposes an innovative CACC control method based on deep reinforcement learning (DRL). First, the altruism control and the quantitative control of the car‐following strategy are realized by the virtual car‐following distance method to reduce the exclusivity of the CACC platoon or improve the road utilization efficiency. Second, a more appropriate platoon reward function and collision avoidance method are proposed. Finally, the Car Learning to Act (CARLA) simulator is used. The obtained results confirm that the CACC control of CAVs based on DRL can absorb speed oscillation and improve fuel economy. [ABSTRACT FROM AUTHOR]

Situation awareness (SA) describes an individual’s understanding of their surroundings and actions in the near future based on the individual’s comprehension and understanding of the surrounding inputs. SA measurements can be applied to improve system performance or human effectiveness in many fields of study, including driving. However, in some scenarios drivers might need to drive in unfamiliar traffic regulations (UFTRs), where the traffic rules and vehicle configurations are a bit different from what the drivers are used to under familiar traffic regulations. Such driving conditions require drivers to adapt their attention, knowledge, and reactions to safely reach the destination. This ability is influenced by the degree of handedness. In such tasks, mixed-/left-handed people show better performance than strong right-handed people. This paper aims to explore the influence of the degree of handedness on SA when driving under UFTRs. We analyzed the SA of two groups of drivers: strong right-handed drivers and mixed-/left-handed drivers. Both groups were not familiar with driving in keep-left traffic regulations. Using a driving simulator, all participants drove in a simulated keep-left traffic system. The participants’ SA was measured using a subjective assessment, named the Participant Situation Awareness Questionnaire PSAQ, and performance-based assessment. The results of the study indicate that mixed-/left-handed participants had significantly higher SA than strong right-handed participants when measured by performance-based assessment. Also, in the subjective assessment, mixed-/left-handed participants had significantly higher PSAQ performance scores than strong right-handed participants. The findings of this study suggest that advanced driver assistance systems (ADAS), which show improvement in road safety, should adapt the system functionality based on the driver’s degree of handedness when driving under UFTRs.

Artificial intelligence (AI) will change society in so many different aspects that it is not comprehensible to grasp yet. It will be on the same magnitude as the Industrial Revolution (or most likely much larger). AI carries threats and great opportunities. Given the unknown unknowns of AI, we can spot headlines every day with either alarming news or the opposite. AI plays a major role for enabling autonomous vehicles but also for the development of more sophisticated and efficient advanced driver assistance systems (ADASs) by supporting, for example, rapid object detection and classification. Since the mid-20th century, AI has been a research topic, but not until recently has it gained momentum due to, for example, the performance increase in ubiquitous hardware. It is computationally expensive to execute AI algorithms. There are broadly speaking three “types” of AI discussed today, machine learning (ML), deep learning, and generative AI (GenAI), where GenAI is a specialized case of deep learning, which in turn is a subset of ML. The common denominator for all AI is training data, and data fit for purpose are pivotal for the development of AI algorithms. Garbage in will result in garbage out. [ABSTRACT FROM AUTHOR]

IntroductionPD is a progressive neurodegenerative disorder that affects, according to the ICF, body systems (cognitive, visual, and motor), and functions (e.g., decreased executive functions, decreased visual acuity, impaired contrast sensitivity, decreased coordination)—all which impact driving performance, an instrumental activity of daily living in the domain of “Activity” and “Participation” according to the ICF. Although there is strong evidence of impaired driving performance in PD, few studies have explored the real-world benefits of in-vehicle automation technologies, such as in-vehicle information systems (IVIS) and advanced driver assistance systems (ADAS), for drivers with PD. These technologies hold potential to alleviate driving impairments, reduce errors, and improve overall performance, allowing individuals with PD to maintain their mobility and independence more safely and for longer periods. This preliminary study aimed to fill the gap in the literature by examining the impact of IVIS and ADAS on driving safety, as indicated by the number of driving errors made by people with PD in an on-road study.MethodsForty-five adults with diagnosed PD drove a 2019 Toyota Camry equipped with IVIS and ADAS features (Toyota Safety Sense 2.0) on a route containing highway and suburban roads. Participants drove half of the route with the IVIS and ADAS systems activated and the other half with the systems deactivated.ResultsThe results suggest that systems that assume control of the driving task, such as adaptive cruise control, were most effective in reducing driving errors. Furthermore, individual differences in cognitive abilities, particularly memory, were significantly correlated with the total number of driving errors when the systems were deactivated, but no significant correlations were present when the systems were activated. Physical capability factors, such as rigidity and bradykinesia, were not significantly correlated with driving error.DiscussionTaken together, these results show that in-vehicle driver automation systems can benefit drivers with PD and diminish the impact of individual differences in driver cognitive ability.

Distracted driving is the leading cause of road traffic accidents. It is essential to monitor the driver's status to avoid traffic accidents caused by distracted driving. Current research on detecting distracting behaviours focuses on analysing image features using convolutional neural networks (CNNs). However, the generalisation ability of the current distracted driving models is limited. This paper aims to improve the generalisation ability of distracted driving models that are affected by factors such as the driver himself, the background, the monitoring angle, and so on. A new driver distraction detection method, which is referred to as multi‐scale domain adaptation network (MSDAN), was proposed to improve model adaptability. The method consists of three stages: first, multi‐scale convolution was introduced to build a new backbone to accommodate better the valuable feature of the target on different scales. Secondly, the authors designed the domain adaptation network to improve the model's adaptability to the difference in data sources through adversarial training. Finally, dropout is added to the fully connected layer to increase the model's generalisation ability. The comparison results on the large‐scale driver distraction detection dataset show that the authors' method can accurately detect driver distraction and has good generalisation performance, with an accuracy improvement in the cross‐driver and cross‐dataset experiments. [ABSTRACT FROM AUTHOR]

Predicting traffic risk incidents in first-person helps to ensure a safety reaction can occur before the incident happens for a wide range of driving scenarios and conditions. One challenge to building advanced driver assistance systems is to create an early warning system for the driver to react safely and accurately while perceiving the diversity of traffic-risk predictions in real-world applications. In this paper, we aim to bridge the gap by investigating two key research questions regarding the driver's current status of driving through online videos and the types of other moving objects that lead to dangerous situations. To address these problems, we proposed an end-to-end two-stage architecture: in the first stage, unsupervised learning is applied to collect all suspicious events on actual driving; in the second stage, supervised learning is used to classify all suspicious event results from the first stage to a common event type. To enrich the classification type, the metadata from the result of the first stage is sent to the second stage to handle the data limitation while training our classification model. Through the online situation, our method runs 9.60 fps on average with 1.44 fps on standard deviation. Our quantitative evaluation shows that our method reaches 81.87% and 73.43% for the average F1-score on labeled data of CST-S3D and real driving datasets, respectively. Furthermore, the proposed method has the potential to assist distribution companies in evaluating the driving performance of their driver by automatically monitoring near-miss events and analyzing driving patterns for training programs to reduce future accidents. [ABSTRACT FROM AUTHOR]

A new dataset for automated driving, which is the subject matter of this paper, identifies and addresses a gap in existing similar perception datasets. While most state-of-the-art perception datasets primarily focus on the provision of various onboard sensor measurements along with the semantic information under various driving conditions, the provided information is often insufficient since the object list and position data provided include unknown and time-varying errors. The current paper and the associated dataset describe the first publicly available perception measurement data that include not only the onboard sensor information from the camera, Lidar, and radar with semantically classified objects but also the high-precision ground-truth position measurements enabled by the accurate RTK-assisted GPS localization systems available on both the ego vehicle and the dynamic target objects. This paper provides insight on the capturing of the data, explicitly explaining the metadata structure and the content, as well as the potential application examples where it has been, and can potentially be, applied and implemented in relation to automated driving and environmental perception systems development, testing, and validation. [ABSTRACT FROM AUTHOR]

This paper develops a pedestrian potentially dangerous behaviour prediction method based on attention‐long‐short‐term memory (Attention‐LSTM) architecture to predict pedestrian trajectory and intention for the unexpected pedestrian crossing accident avoidance. To extract the road scene information for short periods of time, and improve the accuracy of subsequent intention inference and trajectory prediction, the panoramic segmentation is used to extrapolate pedestrian instances and segment areas of the environment. Next, an encoder–decoder framework based on Attention‐LSTM model is proposed to infer a pedestrian's intention to run or walk out into oncoming traffic straight and to predict the future trajectory. The proposed network involves two parts: temporal feature encoder and multi‐task decoder. The temporal feature encoder is mainly used to selectively emphasize the temporal features using attention mechanism, and then LSTM is employed for its encoding. In the multi‐task decoder, a multi‐head self‐attention mechanism and LSTM are used to forecast the pedestrians' intention and future trajectory, respectively. Extensive experiments on pedestrian intention estimation (PIE) datasets demonstrate that the authors' proposed approach surpasses prior studies in terms of prediction accuracy in trajectory and intention. This study can not only effectively avoid serious accidents caused by illegal road crossing but also achieve early warning for collision avoidance. [ABSTRACT FROM AUTHOR]

Abstract To use the benefits of Advanced Driver Assistance Systems (ADAS)-Tests in simulation and reality a new approach for using Augmented Reality (AR) in an automotive vehicle for testing ADAS is presented in this paper. Our procedure provides a link between simulation and reality and should enable a faster development process for future increasingly complex ADAS tests and future mobility solutions. Test fields for ADAS offer a small number of orientation points. Furthermore, these must be detected and processed at high vehicle speeds. That requires high computational power both for developing our method and its subsequent use in testing. Using image segmentation (IS), artificial intelligence (AI) for object recognition, and visual simultaneous localization and mapping (vSLAM), we aim to create a three-dimensional model with accurate information about the test site. It is expected that using AI and IS will significantly improve performance as computational speed and accuracy for AR applications in automobiles.

Lane Keeping Assist System (LKAS) enhances comfort and safety while driving. It plays a significant role in the Advanced Driver Assistance System (ADAS) and future Automated Driving (AD). The LKAS solution aims to help the driver keep the vehicle within the road lines, preventing unintentional lane departure. Despite LKAS being an important solution for comfortable driving, robust LKAS steering control is still lacking, requiring constant driver intervention or premature LKAS deactivation. LKAS require optimal control solutions with real-time constraints. This paper comprehensively analyzes Model Predictive Control (MPC) for real-time LKAS applications. Classical and parameterized MPC schemes with distinct Quadratic Programming (QP) solvers are combined to evaluate LKAS closed-loop control performance and real-time constraints. A sideslip and lateral speed bicycle modes were used to evaluate classical, trivial, and exponential MPC schemes. Experimental results highlight the three MPC and QP-appropriate solutions with satisfactory reference tracking without steering command and real-time constraints violation.

Recent advanced driver assistance systems' (ADASs) control cars to avoid accidents, but few of them consider driver's comfort. To realize comfortable driving, an ADAS must sense the driver's emotions, especially when they are negative. Since emotions are reflected in a person's physiological signals, they are informative for sensing emotions. However, it is unclear which signals are most useful for detecting a driver's negative emotions. To examine the usefulness of each physiological signal, we implemented an emotion classifier (negative or non-negative) using sparse logistic regression for multimodal signals. This classifier was trained using a multimodal physiological signal dataset with negative emotion labels collected, while subjects were driving a vehicle. The resulting classifier successfully classifies emotions with an area under the curve of 0.74 and identifies the physiological signals that are useful for detecting negative emotions. [ABSTRACT FROM AUTHOR]

Advanced Driver Assistance Systems (ADASs) are crucial components of intelligent vehicles, equipped with a vast code base. To enhance the security of ADASs, it is essential to mine their vulnerabilities and corresponding exploitation methods. However, mining buffer overflow (BOF) vulnerabilities in ADASs can be challenging since their code and data are not publicly available. In this study, we observed that ADAS devices commonly utilize unencrypted protocols for module communication, providing us with an opportunity to locate input stream and buffer data operations more efficiently. Based on the above observation, we proposed a communication-traffic-assisted ADAS BOF vulnerability mining and exploitation method. Our method includes firmware extraction, a firmware and system analysis, the locating of risk points with communication traffic, validation, and exploitation. To demonstrate the effectiveness of our proposed method, we applied our method to several commercial ADAS devices and successfully mined BOF vulnerabilities. By exploiting these vulnerabilities, we executed the corresponding commands and mapped the attack to the physical world, showing the severity of these vulnerabilities. [ABSTRACT FROM AUTHOR]

Artificial Intelligence (AI) in the automotive industry allows car manufacturers to produce intelligent and autonomous vehicles through the integration of AI-powered Advanced Driver Assistance Systems (ADAS) and/or Automated Driving Systems (ADS) such as the Traffic Sign Recognition (TSR) system. Existing TSR solutions focus on some categories of signs they recognise. For this reason, a TSR approach encompassing more road sign categories like Warning, Regulatory, Obligatory, and Priority signs is proposed to build an intelligent and real-time system able to analyse, detect, and classify traffic signs into their correct categories. The proposed approach is based on an overview of different Traffic Sign Detection (TSD) and Traffic Sign Classification (TSC) methods, aiming to choose the best ones in terms of accuracy and processing time. Hence, the proposed methodology combines the Haar cascade technique with a deep CNN model classifier. The developed TSC model is trained on the GTSRB dataset and then tested on various categories of road signs. The achieved testing accuracy rate reaches 98.56%. In order to improve the classification performance, we propose a new attention-based deep convolutional neural network. The achieved results are better than those existing in other traffic sign classification studies since the obtained testing accuracy and F1-measure rates achieve, respectively, 99.91% and 99%. The developed TSR system is evaluated and validated on a Raspberry Pi 4 board. Experimental results confirm the reliable performance of the suggested approach. [ABSTRACT FROM AUTHOR]

• Examination of impact of advancing vehicle technologies on use of seatbelts. • Theoretically informed investigation based on extended Theory of Planned Behaviour (TPB) • Predictors of intentions to not wear seatbelts included TPB standard constructs and trust (in vehicle technology) and perceived risk (of death/injury from crash) • Critical beliefs analysis of behavioural, normative, and control beliefs underpinning seatbelt non-use intentions. • Standard TPB constructs and trust significantly predicted seatbelt non-use intentions. • Discomfort was a significant critical belief that positively predicted seatbelt non-use intentions. Approximately one in five Australians killed in motor vehicle crashes will not be wearing a seatbelt. A circulating lay theory suggests that drivers may be questioning the continued necessity of seatbelts given advances in other advanced vehicle technologies. This belief is deeply concerning given the implementation of advanced driver assistance systems in new cars is rapidly increasing. The objective of this research was to apply an extended Theory of Planned Behaviour (TPB), including the additional constructs of trust in vehicle technology and perceived risk of death or injury in the event of a crash, to assess the influence of attitudes, subjective norms, perceived behavioural control (PBC), trust, and perceived risk on drivers' intentions to engage in seatbelt non-use. The study also aimed to examine if the predictive utility of the extended TPB differed according to the presence of passive (e.g., airbags) active (e.g., lane keeping assist) technologies in vehicles, Further, the influence of underlying behavioural belief, control beliefs, and normative beliefs on driver's intentions to engage in seatbelt non-use were also explored. Participants (N = 182, 83 males, M age = 44.23 years) completed a 25-minute online questionnaire. The study was a cross-sectional, between groups design in which all participants were exposed to a baseline control scenario, then randomly allocated to one of four experimental scenarios which manipulated the type of vehicle technologies present in a hypothetical vehicle. Consistent with theoretical expectations of the standard TPB, a hierarchal regression revealed that the constructs of attitude, subjective norms, and PBC (self-efficacy only) significantly and positively predicted seatbelt non-use intentions. Of the extended constructs, trust, but not perceived risk, exhibited a significant effect, and positively predicted seatbelt non-use intentions in the control condition and the active technology condition. Additionally, a critical beliefs analysis found that discomfort was a significant positive predictor of seatbelt non-use intentions. Overall, the findings offer support for the use of the TPB to explain seatbelt non-use intentions and suggest that trust in vehicle technology may influence drivers' decisions to not wear a seatbelt. This research offers a novel determinant of seatbelt non-use that may be more responsive behavioural change interventions. [ABSTRACT FROM AUTHOR]

Advanced driver assistance systems (ADASs) have recently gained popularity as they assist vehicle operators in staying within safe boundaries, helping them thereby to prevent possible collisions. However, despite their success and development, most ADAS use common and deterministic warning thresholds for all drivers in all driving environments. This may occasionally lead to the issuance of annoying inadequate warnings, due to the possible differences between drivers, the changing environments and driver statuses, thus reducing their acceptance and effectiveness. To fill this gap, this paper proposes adaptive algorithms for commonly used warnings based on real-time traffic environments and driver status including distraction and fatigue. We proposed adaptive algorithms for headway monitoring, illegal overtaking, over-speeding, and fatigue. The algorithms were then tested using a driving simulator. Results showed that the proposed adaptive headway warning algorithm was able to automatically update the headway warning thresholds and that, overall, the proposed algorithms provided the expected warnings. In particular, three or four different warning types were designed to distinguish different risk levels. The designed real-time intervention algorithms can be implemented in ADAS to provide warnings and interventions tailored to the driver status to further ensure driving safety.

Line-of-sight (LOS) sensors developed in newer vehicles have the potential to help avoid crash and near-crash scenarios with advanced driving-assistance systems; furthermore, connected vehicle technologies (CVT) also have a promising role in advancing vehicle safety. This study used crash and near-crash events from the Second Strategic Highway Research Program Naturalistic Driving Study (SHRP2 NDS) to reconstruct crash events so that the applicable benefit of sensors in LOS systems and CVT can be compared. The benefits of CVT over LOS systems include additional reaction time before a predicted crash, as well as a lower deceleration value needed to prevent a crash. This work acts as a baseline effort to determine the potential safety benefits of CVT-enabled systems over LOS sensors alone.

Accurate perception and awareness of the environment surrounding the automobile is a challenge in automotive research. This article presents A3CarScene, a dataset recorded while driving a research vehicle equipped with audio and video sensors on public roads in the Marche Region, Italy. The sensor suite includes eight microphones installed inside and outside the passenger compartment and two dashcams mounted on the front and rear windows. Approximately 31 h of data for each device were collected during October and November 2022 by driving about 1500 km along diverse roads and landscapes, in variable weather conditions, in daytime and nighttime hours. All key information for the scene understanding process of automated vehicles has been accurately annotated. For each route, annotations with beginning and end timestamps report the type of road traveled (motorway, trunk, primary, secondary, tertiary, residential, and service roads), the degree of urbanization of the area (city, town, suburban area, village, exurban and rural areas), the weather conditions (clear, cloudy, overcast, and rainy), the level of lighting (daytime, evening, night, and tunnel), the type (asphalt or cobblestones) and moisture status (dry or wet) of the road pavement, and the state of the windows (open or closed).This large-scale dataset is valuable for developing new driving assistance technologies based on audio or video data alone or in a multimodal manner and for improving the performance of systems currently in use. The data acquisition process with sensors in multiple locations allows for the assessment of the best installation placement concerning the task. Deep learning engineers can use this dataset to build new baselines, as a comparative benchmark, and to extend existing databases for autonomous driving.

Compared with conventional phosphor‐converted near‐infrared light‐emitting diodes (NIR pc‐LEDs), near‐infrared persistent phosphor‐converted LEDs (NIR ppc‐LEDs) are applicable not only in conventional systems but also novel devices in the fields of intelligent security, driverless vehicle technology, and virtual reality. However, NIR ppc‐LEDs have not been extensively investigated. Herein, a novel NIR ppc‐LEDs with the prepared SrAl12O19: Fe3+, Mg2+, Ti4+ NIR persistent phosphors is designed. In relation to pc‐LEDs, the new ppc‐LED exhibits full‐spectral responsive sensing ability during the photostimulated mediation of lattice defects. Furthermore, using the ppc‐LED as a smart sensing LED in a digital NIR imaging system, optical feedback could be converted to a digital signal in a self‐regulated visible‐to‐NIR operation mode. These results imply that the designed ppc‐LED, as a smart sensing LED with full‐spectral responsive ability, greatly enhances the sensitivity of digital NIR imaging, particularly low‐light digital NIR imaging, which has recently drawn considerable attention in the fields of advanced driver assistance systems and VR/AR technology.

Virtual scenario-based testing has become an acceptable method for evaluating safety effectiveness of advanced driver assistance systems (ADAS). Due to the complexity of the ADAS operating environment, the scenarios that an ADAS could face are almost infinite. Therefore, it is crucial to find critical scenarios to improve the efficiency of testing without compromising credibility. One popular method is to explore the parameterized scenario space using various intelligent search methods. Selecting parameters to parameterize the scenario space is particularly important to achieve good coverage and high efficiency. However, an extensive collection of (relevant) influence parameters is missing, which allows a thorough consideration when selecting parameters regarding specific scenarios. In addition, the general importance definition for individual influence parameters is not provided, regarding the potential influence of their variations on the safety effectiveness of ADAS, which can also be used as a reference while selecting parameters. Combining knowledge from different sources (the published literature, standardized test scenarios, accident analysis, autonomous vehicle disengagement, accident reports, and specific online surveys), this paper has summarized, in total, 94 influence parameters, given the general definitions of importance for 77 influence parameters based on cluster analysis algorithms. The list of influence parameters provides researchers and system developers a comprehensive basis for pre-selecting influence parameters for evaluating the safety effectiveness of ADAS by virtual scenario-based testing and helps check whether certain influence parameters can be a meaningful extension for the evaluation.

Object detection is one of the most important tasks in computer vision‐based automation, such as advanced driver assistance systems in driving automation. It is preferable to detect traffic‐related objects at a far distance that appear small in the recorded scene in order to ensure maximum road safety while driving. As drivers tend to miss more traffic‐related objects at nighttime driving, this work focuses on nighttime in‐vehicle camera images. Because videos were recorded using an in‐vehicle camera, objects to be detected in this study, such as traffic signs and pedestrians, occupy a small size in the frame when far away from the own vehicle. Furthermore, it is necessary to take into account time‐series information to detect objects in sequential frames. Therefore, this research proposes an object detection model that combines the RefineDet small object detection model and the TSSD video detection model. Experimental results confirm the effectiveness of the proposed model. Moreover, a publicly available benchmark dataset is used to confirm the performance of the proposed model regardless of daytime or nighttime images. © 2022 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]

Copyright of Technisches Messen is the property of De Gruyter and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In recent years, computer vision algorithms have become more powerful, which enabled technologies such as autonomous driving to evolve rapidly. However, current algorithms mainly share one limitation: They rely on directly visible objects. This is a significant drawback compared to human behavior, where visual cues caused by objects (e. g., shadows) are already used intuitively to retrieve information or anticipate occurring objects. While driving at night, this performance deficit becomes even more obvious: Humans already process the light artifacts caused by the headlamps of oncoming vehicles to estimate where they appear, whereas current object detection systems require that the oncoming vehicle is directly visible before it can be detected. Based on previous work on this subject, in this paper, we present a complete system that can detect light artifacts caused by the headlights of oncoming vehicles so that it detects that a vehicle is approaching providently (denoted as provident vehicle detection). For that, an entire algorithm architecture is investigated, including the detection in the image space, the three-dimensional localization, and the tracking of light artifacts. To demonstrate the usefulness of such an algorithm, the proposed algorithm is deployed in a test vehicle to use the detected light artifacts to control the glare-free high beam system proactively (react before the oncoming vehicle is directly visible). Using this experimental setting, the provident vehicle detection system's time benefit compared to an in-production computer vision system is quantified. Additionally, the glare-free high beam use case provides a real-time and real-world visualization interface of the detection results by considering the adaptive headlamps as projectors. With this investigation of provident vehicle detection, we want to put awareness on the unconventional sensing task of detecting objects providently (detection based on observable visual cues the objects cause before they are visible) and further close the performance gap between human behavior and computer vision algorithms to bring autonomous and automated driving a step forward. [ABSTRACT FROM AUTHOR]

Automated vehicles, predicted to be fully electric in future, are expected to reduce road fatalities and road traffic emissions. The lane departure warning system, an important feature of automated vehicles, utilize lane detection and tracking algorithms. Researchers are constrained to test their lane detection algorithms because of the small publicly available datasets. Additionally, those datasets may not represent differences in road geometries, lane marking and other details unique to a particular geographic location. Existing methods to develop the ground truth datasets are time intensive. To address this gap, this study proposed a framework for an interpolation approach for quickly generating reliable ground truth data. The proposed method leverages the advantage of the existing manual and time-slice approaches. A detailed framework for the interpolation approach is presented and the performance of the approach is compared with the existing methods. Video datasets for performance evaluation were collected in Melbourne, Australia. The results show that the proposed approach outperformed four existing approaches with a reduction in time for generating ground truth data in the range from 4.8% to 87.4%. A reliable and quick method for generating ground truth data, as proposed in this study, will be valuable to researchers as they can use it to test and evaluate their lane detection and tracking algorithms. [ABSTRACT FROM AUTHOR]

• Sizable amount of data are collected by analyzing crash reports. • Estimated models offer insights into crash injury severity from automated vehicles. • Comparing factors impacting injury severity in crashes with ADAS and ADS vehicles. Vehicles equipped with automated driving capabilities have shown potential to improve safety and operations. Advanced driver assistance systems (ADAS) and automated driving systems (ADS) have been widely developed to support vehicular automation. Although the studies on the injury severity outcomes that involve automated vehicles are ongoing, there is limited research investigating the difference between injury severity outcomes for the ADAS and ADS equipped vehicles. To ensure a comprehensive analysis, a multi-source dataset that includes 1,001 ADAS crashes (SAE Level 2 vehicles) and 548 ADS crashes (SAE Level 4 vehicles) is used. Two random parameters multinomial logit models with heterogeneity in the means of random parameters are considered to gain a better understanding of the variables impacting the crash injury severity outcomes for the ADAS (SAE Level 2) and ADS (SAE Level 4) vehicles. It was found that while 67 percent of crashes involving the ADAS equipped vehicles in the dataset took place on a highway, 94 percent of crashes involving ADS took place in more urban settings. The model estimation results also reveal that the weather indicator, driver type indicator, differences in the system sophistication that are captured by both manufacture year and high/low mileage as well as rear and front contact indicators all play a role in the crash injury severity outcomes. The results offer an exploratory assessment of safety performance of the ADAS and ADS equipped vehicles using the real-world data and can be used by the manufacturers and other stakeholders to dictate the direction of their deployment and usage. [ABSTRACT FROM AUTHOR]

Many modern automated vehicle sensor systems use light detection and ranging (LiDAR) sensors. The prevailing technology is scanning LiDAR, where a collimated laser beam illuminates objects sequentially point-by-point to capture 3D range data. In current systems, the point clouds from the LiDAR sensors are mainly used for object detection. To estimate the velocity of an object of interest (OoI) in the point cloud, the tracking of the object or sensor data fusion is needed. Scanning LiDAR sensors show the motion distortion effect, which occurs when objects have a relative velocity to the sensor. Often, this effect is filtered, by using sensor data fusion, to use an undistorted point cloud for object detection. In this study, we developed a method using an artificial neural network to estimate an object’s velocity and direction of motion in the sensor’s field of view (FoV) based on the motion distortion effect without any sensor data fusion. This network was trained and evaluated with a synthetic dataset featuring the motion distortion effect. With the method presented in this paper, one can estimate the velocity and direction of an OoI that moves independently from the sensor from a single point cloud using only one single sensor. The method achieves a root mean squared error (RMSE) of 0.1187 m s−1 and a two-sigma confidence interval of [−0.0008 m s−1, 0.0017 m s−1] for the axis-wise estimation of an object’s relative velocity, and an RMSE of 0.0815 m s−1 and a two-sigma confidence interval of [0.0138 m s−1, 0.0170 m s−1] for the estimation of the resultant velocity. The extracted velocity information (4D-LiDAR) is available for motion prediction and object tracking and can lead to more reliable velocity data due to more redundancy for sensor data fusion.

Detecting drowsiness among drivers is critical for ensuring road safety and preventing accidents caused by drowsy or fatigued driving. Research on yawn detection among drivers has great significance in improving traffic safety. Although various studies have taken place where deep learning-based approaches are being proposed, there is still room for improvement to develop better and more accurate drowsiness detection systems using behavioral features such as mouth and eye movement. This study proposes a deep neural network architecture for drowsiness detection employing a convolutional neural network (CNN) for driver drowsiness detection. Experiments involve using the DLIB library to locate key facial points to calculate the mouth aspect ratio (MAR). To compensate for the small dataset, data augmentation is performed for the ‘yawning’ and ‘no_yawning’ classes. Models are trained and tested involving the original and augmented dataset to analyze the impact on model performance. Experimental results demonstrate that the proposed CNN model achieves an average accuracy of 96.69%. Performance comparison with existing state-of-the-art approaches shows better performance of the proposed model.

Future vehicles will be increasingly connected to enable new applications and improve safety, traffic efficiency and comfort, through the use of several wireless access technologies, ranging from vehicle-to-everything (V2X) connectivity to automotive radar sensing and Internet of Things (IoT) technologies for intra-car wireless sensor networks. These technologies span the radiofrequency (RF) range, from a few hundred MHz as in intra-car network of sensors to hundreds of GHz as in automotive radars used for in-vehicle occupant detection and advanced driver assistance systems. Vehicle occupants and road users in the vicinity of the connected vehicle are thus daily immersed in a multi-source and multi-band electromagnetic field (EMF) generated by such technologies. This paper is the first comprehensive and specific survey about EMF exposure generated by the whole ensemble of connectivity technologies in cars. For each technology we describe the main characteristics, relevant standards, the application domain, and the typical deployment in modern cars. We then extensively describe the EMF exposure scenarios resulting from such technologies by resuming and comparing the outcomes from past studies on the exposure in the car. Results from past studies suggested that in no case EMF exposure was above the safe limits for the general population. Finally, open challenges for a more realistic characterization of the EMF exposure scenario in the connected car are discussed.

Driver assistance systems, such as adaptive cruise control, are an increasing commodity in modern vehicles. Our earlier experience of radar-based adaptive cruise control has indicated repeatable abrupt behavior when approaching a stopped vehicle at high speed, which is typical for extra-urban roads. Abrupt behavior in assisted driving not only decreases the passenger trust but also reduces the comfort levels of such systems. We present a design and proof-of-concept of a machine vision-enhanced adaptive cruise controller. A machine vision-based brake light detection system was implemented and tested in order to smoothen the transition from coasting to braking and ensure speed reduction early enough. The machine vision system detects the brake lights in front, then transmits a command to the cruise controller to reduce speed. The current paper reports the speed control system design and experiments carried out to validate the system. The experiments showed the system works as designed by reducing abrupt behavior. Measurements show that brake light-assisted cruise control was able to start deceleration about three seconds earlier than a cruise controller without brake light detection. Measurements also showed increased ride comfort with the maximum deceleration and minimum jerk levels improving from 5% to 31%.

An intelligent driver assistance system is developed in this study, which is able to remind the drivers to turn on the head lights or wipers through situation recognition method when driving at night or on rainy days. Furthermore, the object detection results from multiple perspective views are integrated, and the surrounding object detection results are produced for collision avoidance. The system is able to alarm the drivers based on the lightweight deep learning model and the distance estimation method when surrounding vehicles are too close. Experimental results show that the proposed methods and the chosen lightweight model in our proposed system obtain reliable performance and sufficient computational efficiency under limited computing resource. In conclude, our proposed system obtains high probability to be adopted for the development of advanced driver assistance systems (ADAS). The proposed system can not only assist the driver in determining the vision ahead, but also provide an instant overview of the vehicle’s surrounding conditions to enhance driving safety.

On average 3,700 people lose their lives on roads every day due to car accidents as a result of drivers’ distraction. In this research, a proposed hybrid approach is presented. The approach is based on deep learning to detect the driver’s actions and eliminate the driver’s distraction as a packed solution. The detection is performed by analyzing the driver’s actions and his head pose. The elimination is made by using voice commands that are based on trigger words, speech to text, and text classification models to access the car’s functions such as the air-condition, radio, etc. The results of the driver’s actions classification showed 94.1% accuracy on the AUC benchmark database for driver distraction achieving the state-of-the-art accuracy on this benchmark. The results of the command to text classification is 95.19% while the results of the head pose estimation show a 6.21-degree MAE in face angles detection. With using our car commands dataset, the domain of the speech recognition output is more focused on car commands. The previously mentioned algorithms are beneficial to the safety of the driver. He can use his voice to operate the car accessories. His alert state is monitored and he is warned through an alarm if a distraction is detected. However, this research is not concerned with the detection of retinal abnormalities such as sleeping with eyes open. The results of real-time testing show 0.080 second response time for the driver’s behavior classification and command following with the use of graphical processing units.

The purpose of this study is to propose a framework for accurate and efficient vehicle distance estimation from a monocular camera. The proposed framework consists of a transformer-based object detector, a transformer-based depth estimator, and a distance predictor. The object detector detects various objects that are mostly symmetrical from an image captured by the monocular camera and provides the type of each object and the coordinate information of a bounding box around each object. The depth estimator generates a depth map for the image. Then, the bounding boxes are overlapped with the depth map to extract the depth features of each object, such as the mean depth, minimum depth, and maximum depth of each object. The present study then trained three models—eXtreme Gradient Boosting, Random Forest, and Long Short-Term Memory—to predict the actual distance between the object and the camera based on the type of the object, the bounding box of the object (including its coordinates and size), and the extracted depth features. The present study proposes including the trimmed mean depth of an object to predict the actual distance by excluding the background pixels around an object but within the bounding box of the object. The evaluation results show that the proposed framework outperformed existing studies. [ABSTRACT FROM AUTHOR]

Rear-end collisions account for a significant portion of crashes each year and result in many soft tissue injuries. Several active vehicle safety systems have been developed to prevent rear-end collisions from the perspective of the striking vehicle, but at this time, there are limited vehicle systems designed to improve the safety of occupants in the struck vehicle in the case of an imminent collision. To address this shortcoming, the Pre Rear-End Positioning and Risk Extenuation System (PREPARES) was conceptualized, prototyped, and evaluated. Similar to current in-vehicle warnings, PREPARES was designed to elicit a response from drivers using salient and unexpected auditory and/or visual cues. However, unlike most warnings that inform or direct drivers' attention toward a potential threat exterior to the vehicle, PREPARES attempts to direct drivers' attention to a specific location inside the vehicle that consequently causes the driver to adjust their seating posture. This reactionary motion aims to recover the normal seated position within the seconds prior to impact, thus improving pre-crash positioning and potentially reducing the risk and severity of injuries. During this focused research effort, a proof-of-concept was obtained through human subject testing, which indicated that PREPARES improves driver pre-crash position. These initial results suggest that PREPARES is a potential strategy for mitigating injuries that warrants additional research and development. [ABSTRACT FROM AUTHOR]

The selection of an appropriate method for modeling vehicle dynamics heavily depends on the application. Due to the absence of human intervention, the demand for an accurate and real-time model of vehicle dynamics for intelligent control increases for autonomous vehicles. This paper develops a multibody vehicle model for longitudinal-vertical dynamics applicable to advanced driver assistance (ADAS) applications. The dynamic properties of the chassis, suspension, and tires are considered and modeled, which results in accurate vehicle dynamics and states. Unlike the vehicle dynamics models built into commercial software packages, such as ADAMS and CarSim, the proposed nonlinear dynamics model poses the equations of motion using a subset of relative coordinates. Therefore, the real-time simulation is conducted to improve riding performance and transportation safety. First, a vehicle system is modeled using a semi-recursive multibody dynamics formulation, and the vehicle kinematics and dynamics are accurately calculated using the system tree-topology. Second, a fork-arm removal technique based on the rod-removal technique is proposed to reduce the number of bodies, relative coordinates, and equations constrained by loop-closure. This increase the computational efficiency even further. Third, the dynamic simulations of the vehicle are performed on bumpy and sloping roads. The accuracy and efficiency of the numerical results are compared to the reference data. The comparative results demonstrate that the proposed vehicle model is effective. This efficient model can be utilized for the intelligent control of vehicle ADAS applications, such as forward collision avoidance, adaptive cruise control, and platooning. [ABSTRACT FROM AUTHOR]