Road Safety Research Articles

Research on high-precision recognition model for multi-scene asphalt pavement distresses based on deep learning

Accurate detection of asphalt pavement distress is crucial for road maintenance and traffic safety. However, traditional convolutional neural networks usually struggle with this task due to the varied distress patterns and complex background in the images. To enhance the accuracy of asphalt pavement distress identification across various scenarios, this paper introduces an improved model named SMG-YOLOv8, based on the YOLOv8s framework. This model integrates the space-to-depth module and the multi-scale convolutional attention mechanism, while optimizing the backbone’s C2f structure with a more efficient G-GhostC2f structure. Experimental results demonstrate that SMG-YOLOv8 outperforms the YOLOv8s baseline model, achieving Pmacro and mAP50 scores of 81.1% and 79.4% respectively, marking an increase of 8.2% and 12.5% over the baseline. Furthermore, SMG-YOLOv8 exhibits clear advantages in identifying various types of pavement distresses, including longitudinal cracks, transverse cracks, mesh cracks, and potholes, when compared to YOLOv5n, YOLOv5s, YOLOv6s, YOLOv8n, and SSD models. This enhancement optimizes the network structure, reducing the number of parameters while maintaining excellent detection performance. In real-world scenarios, the SMG-YOLOv8 model, when applied to image data collected from projects, achieves a Pmacro of 80.5% and an Rmacro of 86.2%. This result demonstrates its excellent generalization capability and practicality. The model provides significant technical support for the intelligent detection of pavement distress.

“Interior lighting can help to improve road safety”

“Interior lighting can help to improve road safety”

Factors associated with speeding behavior of Moroccan drivers: Study guided by the theory of planned behavior

This study investigates the determinants that influence drivers to exceed speed limits by using an extended version of the Theory of Planned Behavior (TPB). Therefore, data about 254 drivers representing various cities in Morocco were collected via a web-based questionnaire. Then, confirmatory factor analysis (CFA) was used to validate the proposed questionnaire, while structural equation modeling (SEM) was conducted to analyze and validate the hypothesized model. The results suggest that the extended TPB, incorporating additional factors of habit, moral norms and descriptive norms, outperforms the original TPB. Moreover, the findings underscore that speeding behavior is directly influenced by both speeding intention and habit, and indirectly influenced by moral norms and habit through the mediation of intention. The result of this study will contribute to developing new behavior change interventions aiming at combating speeding behavior and also contributing to ongoing efforts aiming at promoting road safety.

Multifeatured Electronic Helmet to Enhance Road Safety and Rider’s Comfort

This paper presents a multi-featured electronic helmet designed to tackle critical road safety issues, including accidents, drunk driving, and over-speeding. The design incorporates a global system for mobile communications (GSM) and global positioning system (GPS) modules to accurately capture driver’s current location and send messages to predefined contacts. When encountering an accident, the helmet promptly notifies designated contacts and authorities, ensuring swift assistance. By integrating features for detecting over-speeding, accidents, and drunk driving, the helmet renders real-time alerts to both the driver’s family and traffic police, enhancing accountability and safety measures. Additionally, the helmet includes solar charging functionality for mobile devices receive 100% charged in 3.37 hours, thereby optimizing usability and emergency communication. A rain detection system protects mobile devices, while an internal warming mechanism caters to adverse weather conditions, and proffers enhanced comfort by maintaining internal form temperature between 26-27 ℃ and safety, especially in cold regions or for military personnel.

A Deep Learning-Based Car Accident Detection Framework Using Edge and Cloud Computing

The evolving technological landscape has seen a pivotal shift with the advent of edge computing, transforming various sectors, particularly accident detection. Edge computing enhances road safety by enabling realtime data processing from onboard sensors, cameras, and connected devices, addressing limitations in traditional cloudbased systems. This paper introduces a deep learning-based accident detection framework within an edge-cloud setup. Utilizing a CNN model, accidents are detected at the edge node near the data source, ensuring low latency, reduced network usage, and faster execution times. The model achieves a remarkable 95.91% accuracy.

Transferability of real-time EVT safety models: an investigation using autonomous vehicles data

Recent research has shown that data from autonomous vehicles (AVs) enables proactive, real-time road safety management. However, with low AV market penetration, it's crucial to assess the transferability of AV-based safety models to other locations. This study transfers real-time safety models from a data-rich to a data-scarce environment using vehicular conflict data collected by AVs. Multi-site Bayesian hierarchical Extreme Value Theory models are developed in two cities, with model transfer evaluated using informative priors and parameter recalibration. Both approaches produce reliable results, though the transferability index favors the informed prior method, while predictive deviance shows similar performance for both. Model sensitivity to temporal data limitations is assessed, revealing that the recalibration approach is more sensitive to block size, whereas the informed prior method remains stable. A novel method mimicking data limitations shows transferred models perform well with data utilizations above 20%, promoting transferability to mitigate data inadequacy.

A Decentralized Digital Watermarking Framework for Secure and Auditable Video Data in Smart Vehicular Networks

Thanks to the rapid advancements in Connected and Automated Vehicles (CAVs) and vehicular communication technologies, the concept of the Internet of Vehicles (IoVs) combined with Artificial Intelligence (AI) and big data promotes the vision of an Intelligent Transportation System (ITS). An ITS is critical in enhancing road safety, traffic efficiency, and the overall driving experience by enabling a comprehensive data exchange platform. However, the open and dynamic nature of IoV networks brings significant performance and security challenges to IoV data acquisition, storage, and usage. To comprehensively tackle these challenges, this paper proposes a Decentralized Digital Watermarking framework for smart Vehicular networks (D2WaVe). D2WaVe consists of two core components: FIAE-GAN, a novel feature-integrated and attention-enhanced robust image watermarking model based on a Generative Adversarial Network (GAN), and BloVA, a Blockchain-based Video frames Authentication scheme. By leveraging an encoder–noise–decoder framework, trained FIAE-GAN watermarking models can achieve the invisibility and robustness of watermarks that can be embedded in video frames to verify the authenticity of video data. BloVA ensures the integrity and auditability of IoV data in the storing and sharing stages. Experimental results based on a proof-of-concept prototype implementation validate the feasibility and effectiveness of our D2WaVe scheme for securing and auditing video data exchange in smart vehicular networks.

Improved lane detection for autonomous vehicles using deep learning, semantic segmentation, edge detection and multi-sensor data fusion

Automated driving has gained significant attention because it can eliminate severe driving risks in real time. While autonomous vehicles rely heavily on sensors for lane detection, obstacle identification, and environmental awareness, accurate lane recognition remains a persistent challenge due to factors such as noise from shadows, poor lane markings, and obstructed views. Despite advances in computer vision, this problem is yet to be fully resolved, presenting a gap in the current literature. The primary objective of this research is to address these challenges by developing an enhanced lane-detection system. To achieve this, the study integrates advanced techniques, including semantic segmentation, edge detection, and deep learning, coupled with multi-sensor data fusion from cameras, LIDAR, and radar. By employing this methodology, the research examines various lane-detection methods and benchmarks the proposed model against existing systems in terms of accuracy, specificity and processing speed. Initial findings demonstrate that the combination of semantic segmentation and multi-sensor fusion improves lane detection in real-time scenarios. The proposed model achieved a lane detection accuracy of 97.8%, a specificity of 99.28%, and an average processing time of 0.0047 seconds per epoch. This study not only addresses the limitations of existing lane detection systems but also offers insights into improving road safety for autonomous vehicles.

Inclusive intervention design for vulnerable road users: Applying co-design and behaviour change model in Bangladesh

In developing countries, it is debatable whether poor design of facilities or violation of traffic rules by road users is the leading cause of pedestrian injuries and deaths. Professionals, pedestrians and drivers tend to blame each other. Shared responsibility for road safety is crucial for protecting vulnerable road users such as commuting students and workers who face higher injury risks while crossing highways. While the Safe System approach emphasises authorities’ responsibility for safe facilities, understanding user needs and promoting behaviour change remain underexplored. This study investigates the current design practices in Bangladesh. It compares the impact of conventional design with co-design on intervention quality and examines the further benefits of integrating a behaviour change model ‘COM-B’.Local road agency professionals applied the design process and suggested interventions at four highway sites. Subsequently, four focus group sessions were conducted with students and workers, followed by four design workshops. In each workshop, participants were randomly assigned to two design groups (without and with the application of the behaviour change model), where they designed interventions facilitated by professionals. Lastly, perception ratings of stakeholders and safety assessments by four experts were conducted to evaluate the efficacy of all interventions.The findings highlight major usability problems in conventional designs, while co-designed interventions demonstrate clear improvements. Notably, integrating a behaviour change model further enhances effectiveness. Stakeholder interviews reveal that co-design fosters shared responsibility and addresses the blame culture. The co-design approach and application of the behaviour change model can address design flaws and promote the proper use of facilities.

Enhanced Cross Layer Refinement Network for robust lane detection across diverse lighting and road conditions

With the rapid development of autonomous driving technology, lane detection, a key component of intelligent vehicle systems, is crucial for ensuring road safety and efficient vehicle navigation. In this paper, a new lane detection method is proposed to address the problem of degraded performance of existing lane detection methods when dealing with complex road environments. The proposed method evolves from the original Cross Layer Refinement Network (CLRNet) by incorporating two of our carefully designed core components: the Global Feature Optimizer (GFO) and the Adaptive Lane Geometry Aggregator (ALGA). The GFO is a multi-scale attention mechanism that mimics the human visual focusing ability, effectively filtering out unimportant information and focusing on the image regions most relevant to the task. The ALGA is a shape feature-aware aggregation module that utilizes the shape prior of lanes to enhance the correlation of anchor points in an image, better fusing global and local information. By integrating both components into CLRNet, an enhanced version called Enhanced CLRNet (E-CLRNet) is presented, which exhibits higher performance stability in complex roadway scenarios. Experiments on the CULane dataset reveal that E-CLRNet demonstrates superior performance stability over the original CLRNet in complex scenarios, including curves, shadows, missing lines, and dazzling light conditions. In particular, in the curves, the F1 score of E-CLRNet is improved by almost 3% over the original CLRNet. This study not only improves the accuracy and performance stability of lane detection but also provides a new solution for the application of autonomous driving technology in complex environments, which promotes the development of intelligent vehicle systems.

Exploring patterns in older pedestrian involved crashes during nighttime

Nighttime crashes involving older pedestrians pose a significant safety concern due to their age-related vulnerabilities such as reduced vision and slower reaction times. This study analyzes crash data from Texas for six years (2017–2022) using Association Rules Mining (ARM) to identify patterns and associations affecting crash severity for older pedestrians aged 65–74 years and those over 74 years under varying lighting conditions. The findings reveal that high-speed limits and complex road environments significantly increase the risk of fatal or severe injuries for both age groups, particularly under inadequate lighting. Additionally, demographic factors, adverse weather conditions, and specific road features further influence crash outcomes. These insights highlight the need for interventions, including lower speed limits, enhanced street lighting, and the implementation of advanced technologies such as modern pedestrian detection systems, sensor technology, pedestrian bags, accessible pedestrian signals, to improve the safety of older pedestrians. Policymakers should leverage these insights to formulate strategies that improve road safety for older pedestrians, addressing their unique vulnerabilities in various nighttime conditions.

RE-Trace : Re-identification of Modified GPS Trajectories

GPS trajectories are a critical asset for building spatio-temporal predictive models in urban regions in the context of road safety monitoring, traffic management, and mobility services. Currently, reliable and efficient data misuse detection methods for such personal, spatio-temporal data, particularly in data breach cases, are missing. This article addresses an essential aspect of data misuse detection, namely, the re-identification of leaked and potentially modified GPS trajectories. We present RE-Trace —a contrastive learning-based model that facilitates reliable and efficient re-identification of GPS trajectories and resists specific trajectory transformation attacks aimed to obscure a trajectory’s origin. RE-Trace utilizes contrastive learning with a transformer-based trajectory encoder to create trajectory representations, robust to various trajectory modifications. We present a comprehensive threat model for GPS trajectory modifications and demonstrate the effectiveness and efficiency of the RE-Trace re-identification approach on three real-world datasets. Our evaluation results demonstrate that RE-Trace significantly outperforms state-of-the-art baselines on all datasets and identifies modified GPS trajectories effectively and efficiently.

Proceedings of the 2024 Australasian Road Safety Conference - Hobart, Tasmania, Australia

Proceedings of the 2024 annual Australasian Road Safety Conference held in Hobart, Tasmania, Australia. The proceedings provide the Extended Abstracts and Posters describing research, educational and policing program implementation and policy and management strategies related to all aspects of road safety and especially related to the conference theme of Target 2030: What's the pathway forward? Almost 600 delegates from 20 countries attended the face-to-face conference. Authors of accepted Extended Abstracts represented international and local institutions from all aspects of their respective communities including research centres, private companies, government agencies and community groups. These Extended Abstracts provide an indication of the important work being done in Australia, New Zealand and internationally as part of the United Nations, One UN Vision for Road Safety to reduce the number of crashes on the road by 50 percent by 2030. Almost 200 Extended Abstract manuscripts were accepted for long, short and poster sessions. Each Extended Abstract was peer-reviewed by two experts with relevant expertise. Authors were also provided the option of submitting a Full Paper. Those authors who chose to submit a Full Paper for consideration in the Journal of Road Safety (JRS) could do so based on the outcome of the peer review of their Extended Abstract. Submitted Full Papers undergo peer-review by three independent experts matched by their sector. The matching pairs academic authors iwth academic reviewers and practitioner authors with practitioner reivewers. Inclusion in the JRS follows acceptance by the peer-reviewers.The conference covered a comprehensive range of topics including speed, infrastructure and road design, cyclist safety, motorcyclist safety, pedestrian safety, road safety education, licensing, vehicle design, impairment due to distraction from mobile phones, alcohol, drugs as well as the impacts of climate change on future transport systems road safety, road safety issues for Indigenous people groups across New Zealand and Australia, integrating road safety into local Government, automated enforcement, gig economy road safety, older drivers, etc.

Analysis of the environmental factors contributing to road traffic accidents involving school-aged pedestrian children in urban Algerian settings

Despite efforts by the Algerian government and civil society to improve road safety, traffic accidents remain a significant issue, particularly affecting children and youth. Data from the National Delegation for Road Safety (NDSR) reveals that this demographic is especially vulnerable, with 371 child fatalities recorded during the 2020-2021 school year. This study evaluated road safety around twelve primary schools in Oued El Abtal district, Mascara province, and aimed to identify effective interventions through a participatory approach involving 1,074 students. An anonymous questionnaire was used to capture students' perceptions of road risks, and the data were analyzed using IBM SPSS Statistics V27. Chi-square and Fisher’s exact tests were applied to examine associations between gender and variables like travel mode, school accompaniment, student behavior, and crossing locations. The sample was balanced by gender, consisting of 50.9% boys and 49.1% girls. Walking was the predominant travel mode (75.2%; n=808). Key risk factors included inadequate infrastructure (3.2%), insufficient signage (11.7%), sidewalk obstructions (5.1%), dangerous driving behaviors (12.2%, with speeding at 29.5%), heavy traffic (16.2%), and poor urban planning (e.g., lack of speed bumps and low visibility). These findings highlight the urgent need for targeted interventions to improve the safety of school commutes. This research identifies critical risk factors in school travel, providing a foundation for developing strategies aimed at enhancing road safety for children in Algeria.

Analyzing Protection Motivation Theory and Cognitive Failures in Texting While Driving Behavior Among Young Drivers

ABSTRACTTexting while driving (TWD) poses a significant hazard, particularly among young adults, as it requires simultaneous engagement in competing tasks. Despite widespread awareness of its dangers, drivers continue to engage in TWD. This study investigates the psychological and cognitive factors that influence TWD, employing the protection motivation theory (PMT). Structural equation modeling was conducted on a sample of 674 survey respondents aged 18–25. Factors influencing TWD behavior were revealed, including response cost, threat vulnerability, cognitive failure, self‐efficacy, and threat severity. Response cost was the primary barrier. Notably, not all subdimensions of threat appraisal and coping appraisal have a direct impact on TWD; cognitive failures serve as a mediator solely between threat vulnerability and response cost. An understanding of TWD provides insights into the TWD behavior of young drivers. By integrating the PMT with cognitive failure, this approach informs the development of interventions and regulations aimed at discouraging TWD and improving road safety.

Low and intermediate temperature fracture performance of hot mix asphalt (HMA) reinforced with nano-reduced graphene oxide (NRGO) under freeze-thaw cycles and aging conditions

ABSTRACT This study evaluates the effect of nano-reduced graphene oxide (NRGO) and conditions of short- and long-term (three freeze-thaw cycles (3 FTC)) failure and six days of ageing (6 AM) on bituminous mixtures from the viewpoint of fracture toughness (KIIC and KIIIC) and fracture energy (FEII and FEIII) at ±15 °C. The results showed the fracture stiffness was improved at ±15 °C (under three conditioning states). However, the fracture flexibility was decreased and increased at low and medium temperatures, respectively. At low temperatures, the results indicated that FEIII and KIIC had the lowest resistance under unconditioned and AM conditions, while FEII and KIIC had the lowest resistance under FTC. At intermediate temperatures, FEIII and KIIC under non-conditioned and FTC conditions and FEII and KIIC under AM conditions obtained the lowest resistance. Therefore, it was recommended to check both loading states in determining the shear performance (in-plane and out-of-plane) of asphalt mixtures. Finally, by providing the minimum short- and long-term properties required to control shear and tear cracks, reinforced mixtures lead to increased service life, reduced maintenance costs and improved road safety in cold and tropical regions.

SafeDrive Pro IoT Based Driver Verification System

SafeDrive Pro is an IoT-based Driver Verification System designed to address the rise in vehicular accidents involving underage and unlicensed drivers. By integrating multi-factor authentication, including age verification, facial recognition, and driver license validation, SafeDrive Pro ensures only authorized individuals can operate vehicles. The system aims to improve vehicle security, reduce unauthorized usage, and enhance road safety. The proposed system leverages IoT technology, machine learning for facial recognition, and RFID for license validation. Initial results indicate that the system can effectively prevent unauthorized access, offering a robust approach to reducing road accidents and promoting vehicle security

On the Road Safety: Gender Differences in Risk-Taking Driving Behaviors Among Seniors Aged 65 and Older.

Background/Objectives: Life expectancies have increased in most countries, leading to a higher accident rate among older drivers than their younger counterparts. While numerous studies have analyzed the decline in cognitive abilities and physical limitations as contributing factors, there are other considerations. For instance, younger male drivers tend to take more risks than younger female drivers. However, there is a lack of research and evidence regarding the role of gender in risk-taking among individuals over 65. Given this gap, our current study aims to investigate the relationship between gender and risk propensity in this particular age group. The primary goal was to determine if driving experience affects the gender gap in risk attitude; Methods: We studied risk behavior in both car drivers and pedestrians. Our sample included 200 individuals (101 women), all over 65, with the same weekly driving times. After a brief demographic and anamnestic interview, they completed the Driver Road Risk Perception Scale (DRPS) and the Pedestrian Behavior Appropriateness Perception Scale (PBAS) questionnaires. They also provided information about traffic violations and road crashes; Results: Our research revealed that older male drivers continue to tend to risky behavior, highlighting the need for targeted interventions to improve risk awareness, especially among older men; Conclusions: Our findings suggest that road safety messages should specifically target male drivers as they are less likely to view responsible driving actions, such as observing speed limits, as desirable.

Research on the Optimization Method of Bus Travel Safety Considering Drivers’ Risk Characteristics

Bus drivers have an important role in ensuring road safety, as their driving circumstances fluctuate due to the combined influence of physiological, psychological, and environmental dynamics, which can cause complex and varied driving dangers. Quantifying and assessing drivers’ risk characteristics under various scenarios, as well as finding the best fit with their work schedules, is critical for enhancing bus safety. This research first uses the entropy weight method, which is based on historical warning data, to examine the risk characteristics of bus drivers in various complicated contexts. It then creates an objective function targeted at minimizing the operational risk for a specific bus route. This function uses the quasi-Vogel approach and an improved simulated annealing algorithm to optimize and restructure the scheduling table, taking individual driver risk characteristics into account. Finally, the analysis is confirmed and examined with actual operational data from the Zhenjiang Bus Line 3. The data show that enhanced bus operations resulted in a 7.22% gain in overall safety and a 33.76% improvement in balancing levels. These insights provide valuable theoretical guidance as well as practical references for the safe operation and administration of public buses.

Dynamic clustering based risk aware congestion control technique for vehicular network

In order to improve road safety and offer extra services to cars and their users, vehicular ad hoc networks, or VANETs, are essential parts of intelligent transportation systems (ITS). The primary aim of this research is to suggest and assess a new approach for mitigating network congestion in VANET technology through the implementation of dynamic grouping of vehicles for safety (DGVS). To do this, virtual regions are created around cars using the DBSCAN and K Mean method. This allows vehicles to communicate directly with others within the same DGVS, eliminating the need to broadcast messages across the entire network.The ultimate goal is to drastically decrease traffic while preserving vital data transfer for VANET traffic control and safety. The suggested technique determines the optimal transmission rate in accordance with the existing channel circumstances, yielding a balanced performance concerning both packet delivery and channel congestion. With this novel method, cars may only talk to other vehicles that are in the same DGVS, thus there’s no need to broadcast messages to the whole network. With the use of this technique, the efficacy of DGVS in reducing VANET congestion and enhancing network performance will be thoroughly assessed. The study’s conclusions demonstrate how well the suggested dynamic grouping of vehicles for safety (DGVS) technique works to reduce VANET congestion. It was shown through simulation-based studies that, in comparison to current approaches, DGVS dramatically decrease network congestion, resulting in notable gains in network performance and decreased communication delay. Additionally, the study found a number of possible uses for DGVS in the transportation industry, such as emergency response, traffic management, and accident prevention.