Ensure Road Safety Research Articles

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.

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.

Multi-Source Data Fusion for Vehicle Maintenance Project Prediction

Ensuring road safety is heavily reliant on the effective maintenance of vehicles. Accurate predictions of maintenance requirements can substantially reduce ownership costs for vehicle owners. Consequently, this field has attracted increasing attention from researchers in recent years. However, existing studies primarily focus on predicting a limited number of maintenance needs, predominantly based solely on vehicle mileage and driving time. This approach often falls short, as it does not comprehensively monitor the overall health condition of vehicles, thus posing potential safety risks. To address this issue, we propose a deep fusion network model that utilizes multi-source data, including vehicle maintenance record data and vehicle base information data, to provide comprehensive predictions for vehicle maintenance projects. To capture the relationships among various maintenance projects, we create a correlation representation using the maintenance project co-occurrence matrix. Furthermore, building on the correlation representation, we propose a deep fusion network that employs the attention mechanism to efficiently merge vehicle mileage and vehicle base information. Experiments conducted on real data demonstrate the superior performance of our proposed model relative to competitive baseline models in predicting vehicle maintenance projects.

Некоторые особенности осмотра места происшествия по уголовным делам о нарушении правил дорожного движения и эксплуатации транспортных средств

Currently, in conditions of intensive development of infrastructure, the main component of which is transport, one of the main tasks of the state remains to ensure road safety. Decree of the Government of the Russian Federation No. 1-r dated 08.01.2018 approved the Road Safety Strategy in the Russian Federation for 2018-2024, which defines the foundations for the formation and implementation of state policy in the field of road safety at various levels (federal, regional, municipal, intersectoral). Improving road safety and striving to achieve zero deaths in road accidents in 2030 is its goal. For 2024, the social risk indicator has been set as a target – no more than 4 deaths per 100,000 people. The article analyzes some features of the inspection of the scene of an accident in criminal cases of violation of traffic rules and operation.

Multimodal Driver Condition Monitoring System Operating in the Far-Infrared Spectrum

Monitoring the psychophysical conditions of drivers is crucial for ensuring road safety. However, achieving real-time monitoring within a vehicle presents significant challenges due to factors such as varying lighting conditions, vehicle vibrations, limited computational resources, data privacy concerns, and the inherent variability in driver behavior. Analyzing driver states using visible spectrum imaging is particularly challenging under low-light conditions, such as at night. Additionally, relying on a single behavioral indicator often fails to provide a comprehensive assessment of the driver’s condition. To address these challenges, we propose a system that operates exclusively in the far-infrared spectrum, enabling the detection of critical features such as yawning, head drooping, and head pose estimation regardless of the lighting scenario. It integrates a channel fusion module to assess the driver’s state more accurately and is underpinned by our custom-developed and annotated datasets, along with a modified deep neural network designed for facial feature detection in the thermal spectrum. Furthermore, we introduce two fusion modules for synthesizing detection events into a coherent assessment of the driver’s state: one based on a simple state machine and another that combines a modality encoder with a large language model. This latter approach allows for the generation of responses to queries beyond the system’s explicit training. Experimental evaluations demonstrate the system’s high accuracy in detecting and responding to signs of driver fatigue and distraction.

Data fusion for driver drowsiness recognition: A multimodal perspective

Drowsiness is characterized by decreased alertness and an increased inclination to fall asleep, typically from factors such as fatigue, sleep deprivation, or other related influences. In the context of driving, drowsiness poses substantial safety risks. The detection of driver drowsiness is of paramount importance in ensuring road safety, contributing to a significant number of accidents worldwide. Utilizing AI for drowsiness detection offers a potent solution to enhance road safety by identifying driver fatigue and preventing potential accidents. The proposed system addresses the challenge of detecting driver drowsiness using a WACHSens dataset collected from both manual and automated driving modes, encompassing rested and fatigued states. Various data sources, including vehicle-related information, facial expressions, and bio signals are employed to create a robust drowsiness detection system. A novel approach that leverages Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks to effectively detect drowsiness in drivers and achieve a 96 % accuracy level. It helps in enhancing road safety by devising effective drowsiness detection mechanisms, potentially preventing accidents and saving lives. Recall, accuracy, f1-score, and precision are the performance metrics to measure the drowsiness condition.

Subjective assessment of traffic rules compliance in Bulgaria: Role of personality and driving style

It is generally accepted that driving is safer when the rules are obeyed. Therefore, the pursuit of greater compliance with traffic rules is often seen as an intermediate goal in ensuring road safety. The article presents two studies that aim to investigate the subjective assessment of traffic rules compliance and the role of personality and behavioural factors such as anxiety, sensation seeking, driving anger, aggressive driving, and risky driving (Study 1; N=1433) on the one hand, and driving style (Study 2; N=456) on the other hand. The studies also examine the differences in traffic rules compliance by age, sex, driving experience, and negative driving outcomes such as registered violations, driving licence suspensions, and involvement traffic accidents. Self-report methods are used to assess personality factors, driving style, traffic rules compliance, and negative driving outcomes. The results show a generally positive assessment of compliance with traffic rules among the participants, with the majority reporting compliance in their daily driving behaviour. Study 1 indicates that all personality factors investigated are significant predictors of traffic rules compliance. Study 2 demonstrates that the risky style, the irrational style, the distress-reduction style, and the patient and careful style are significant predictors of traffic rule compliance. Demographic differences are also observed, with women being significantly more likely than men to perceive themselves as compliant drivers. In terms of negative driving outcomes, both studies demonstrate that individuals with a record of driving violations in the last three years, a suspended driving licence, and involvement in a traffic accident are significantly less likely to rate themselves as compliant. The results can contribute to the development of prevention programmes and road safety strategies to promote safer driving behaviour.

Pavement Crack Detection and Solution with Artificial Intelligence

Detecting and repairing pavement cracks is essential to ensure road safety and longevity. Traditional inspection and maintenance methods are time-consuming, expensive and often inaccurate. In recent years, there has been a growing trend to use artificial intelligence (AI) to automate the process of pavement crack detection and repair. The article focuses on using AI techniques to detect pavement cracks and provide solutions to repair them. The proposed solution is based on using deep learning algorithms to analyze high-resolution images of the road surface. Photos are taken with a vehicle camera or a drone. The deep learning algorithm is trained using a large data set of tagged sidewalk crack images. Once trained, the algorithm can accurately detect and classify the type of cracks on the pavement surface, including longitudinal, transverse, block and crocodile cracks. The algorithm can also determine the severity of each crack and help prioritize repairs. When cracks are detected, the AI system can make recommendations for repair solutions. This includes identifying the appropriate caulk or filler material to use depending on the type and severity of the crack. The AI system can also recommend the most efficient and cost-effective repair method, such as B. Crack sealing, crack filling or deep repair. Overall, using AI to detect and repair cracks in sidewalks offers a more accurate, efficient, and cost-effective solution to keep roads safe and sustainable. By automating the inspection and repair process, this technology can help prevent accidents, reduce maintenance costs, and improve overall road safety.

CAR ACCIDENTS IN THE CZECH REPUBLIC AND LIGHT AS A CONTRIBUTORY FACTOR

Ensuring road safety and preventing car accidents are vital concerns for public health and safety. Despite advancements in vehicle technology and traffic management, the number of road accidents remains alarmingly high, leading to significant loss of life and injuries. The study aims to assess the relationship between causes and types of car accidents depending on lighting conditions when an accident happens. The quantitative content analysis of the car accidents recorded by the POLICE between October 2022 and October 2023 provided relevant data, processed by cluster analysis and illustrated via a heat map. Road safety and preventing car accidents have always been a public priority. The authors analysed crucial aspects of traffic safety and alarming numbers of casualties, including 440 deaths, 1,466 badly and 18,389 slightly injured people. The most common types of accidents involved head-on collisions with solid obstacles and ongoing non-rail vehicles. Careless drivers were the main provokers of the tragic events over the monitored period. Looking at the time of accidents, we can see interesting parallels in their causes, irrespective of the day or nighttime. Our recommendations included raising drivers’ awareness and police imposing preventative measures against the common causes of accidents. The study did not consider other factors behind traffic collisions.

Investigation on the Impact of Ancillary Roadworks on Road Safety in Uganda: A Case of Kampala –Jinja Road

Increased accidents on Ugandan roads compelled the construction of road ancillaries, with a major aim of improving road safety, to attain sustainable economic development and further achieve SDG target 3.6 and SDG target 9.1. This study investigated the impact of ancillary roadworks on road safety in Uganda, a case of the Kampala – Jinja road. The study used a correlation research design with a quantitative approach. Primary data were collected from 30 field traffic officers, 19 drivers, 03 OC traffic police stations, 36 road engineers, 01 IOV, 01 RTO, and 12 market leaders whereas secondary data were extracted from accident data from Uganda Police. Questionnaire data were analysed with SPSS version 24.0. Results indicated that 39% of installed informatory signs, 47% of installed regulatory signs, and 60% of installed warning signs had been vandalised, exposing road users to the risk of accidents. Guardrails were still existing but some had rusted and others covered with grown grass, making them not seen by road users. The majority of road accidents were serious, accounting for 149 (46.3%) cases, followed by 130 fatal accidents (40.4%) and 43 (13.3%) minor accidents for the period from 2017 to 2022. Correlation results indicated that all ancillary road works were significant except road signs. Yet, regression results indicated that road marking (βeta = 0.307), guardrails (βeta = 0.286), and humps and rumble strips (βeta = 0.360) have a positive significant effect on road safety unlike road lights, road signs, walkways, and service lanes which were insignificant. Police traffic law enforcement and regular improvement on road infrastructure are required. It is concluded that road marking, guardrails, humps, and rumble strips significantly affect road safety. The study recommended that the construction of humps and rumble strips of moderate size, road marking with higher retro reflectivity (>200 mcd/lx/m2), and strong guardrails, can help in ensuring road safety with the support of enforcement of traffic laws of Uganda.

Activities of the militia in Ukraine to ensure road safety in the 1950s

In the 1950s, the daily functions of the militia continued to include combating violations of street traffic rules and controlling the decrease in motor vehicle accidents. The accident rate on the roads of the republic at that time remained high. An analysis of the current state of road safety shows that the level of accidents, injuries and deaths on the roads was influenced by such objective factors as the level of development of the regulatory framework, the technical condition of vehicles, the level of development of the road network, its quality, and weather and climatic conditions. Subjective factors included the level of legal culture of road users (drivers and pedestrians), the degree of their readiness to participate in traffic, the professional qualifications and material and technical equipment of the employees of the State Automobile Inspection. During this period, state bodies carried out significant, but ambiguous in quality, rule-making work, the purpose of which was to develop measures aimed at improving both objective and subjective conditions that affected the state of road safety and were of a mutually agreed nature. The established driver training mechanism was one of the important components of the effective operation of the road safety system. Therefore, the activities of state bodies, in particular the State Automobile Inspection of the Ministry of Internal Affairs of the Ukrainian SSR, were aimed at forming not only stable skills in driving vehicles among the drivers, but also behavioral stereotypes that require compliance with legal norms in the field of road safety. At the same time, it was necessary to develop and legally establish criteria for assessing the quality of their training in the relevant institutions. Militia bodies carried out quite active work to improve the situation with road accidents, which included measures of administrative influence, involvement of the public in monitoring violations of traffic rules, various propaganda activities, but its effectiveness was ultimately insignificant.

Checking the fitness to drive of senior citizens under German law-pending corrective measures to ensure road safety

German driving licence law takes areactive approach to dealing with suitability deficiencies of senior citizens. If the driver is no longer fit to drive and nevertheless participates in traffic, an administrative offence has been committed. If this endangers or injures other people or causes significant damage to property, it may even be acriminal offence. In addition to prosecuting these offences, the driving licence authority may restrict or even withdraw the licence issued. In this respect, senior citizens have ahigh degree of personal responsibility when assessing their fitness to drive. This article presents the current driving license law and discusses the need for changes.Legally, various corrections are required to the current Driving Licence Ordinance and its annexes. At present, there is no clear regulation regarding the general reduction in performance in old age for an event-related assessment of fitness to drive. In addition, in the event of doubts about fitness to drive, the driving licence authority should be expressly granted the power to order standardised driving tests. Furthermore, the legislator must take preventive measures to ensure road safety. He must no longer ignore the current accident situation. In view of the fact that senior citizens aged75 and over are disproportionately involved in traffic accidents with personal injury in terms of their culpable behaviour, it is important to impose moderate restrictions on the personal responsibility of driving licence holders. This is especially true for sensory abilities, which are particularly important in road traffic. Seniors should therefore be required to undergo eye tests from the age of75. From this age onwards, it also seems sensible to introduce compulsory advice on fitness to drive, preferably from your family doctor.

THE IMPROVED ROAD DEFECT DETECTION ALGORITHM BASED ON YOLOv8s

Road defect detection is a key task to ensure road safety and repair damage in a timely manner. However, traditional manual inspection methods are inefficient and costly. To address such problems, a BL-YOLOv8 enhanced road defect detection algorithm is proposed. By integrating the BiFPN concept, the neck structure of the YOLOv8s model is reconstructed, reducing model parameters, computational load and overall size, and introducing a dynamic large convolution kernel attention mechanism (LSK-attention) to expand the model's receptive field and improve the accuracy of target detection. The experimental results show that on the road defect data set (KITTI), the number of parameters is reduced by 23.03 %, the amount of calculation is reduced by 5.85 %, and the average accuracy of mAP@0.5 is increased by 2.1 %, verifying the effectiveness of this method for automatic road defect detection technology effectiveness.

Optimization of Aggregate Composition of Asphalt Concrete Mixtures to Ensure Maximum Density

high strength and stability of asphalt concrete, but also at ensuring optimal characteristics of its structure.The main principles for the optimization of the grain composition are based on the parameters of the size and shape of thе stone aggregate particles included in the composition of asphalt concrete mixtures. An in-depth analysis of the grain composition helps to achieve an optimal balance between coarse and fine fractions, which in turn ensures the stability and durability of the asphalt concrete pavement. The maximum density of an asphalt concrete mixture plays a key role, influen-cing its physical and mechanical properties and ability to withstand aggressive environmental influences and traffic loads. In addition, the density of the mixture significantly affects its resistance to static and dynamic loads and deformations, which is important for ensuring road safety. The paper provides an analytical review of the basic principles and methodology for determining the grain composition of fine-grained asphaltic concrete mixtures with grain sizes up to 10 mm in order to achieve their maximum density. Both domestic and foreign methods for optimizing mixture design parameters are considered. Based on the consideration of ideal mathematical curves the grain composition, the main regularity for fine-grained asphalt concrete has been established, which has similar parameters to the mathematical Fourier curve. Understanding and practical application of the principles of constructing the grain composition of asphalt concrete mixtures of maximum density not only improves the quality of road construction, but also contributes to a more efficient use of resources, ensuring the stability and durability of the pavement. This leads to a reduction in road maintenance and repair costs, which is an important aspect in the context of the economic efficiency of infrastructure projects. Thus, improving the methods for investigating and controlling the grain composition of asphalt concrete is important for the sustainable development of road construction.

Analysis and Prediction of Risky Driving Behaviors Using Fuzzy Analytical Hierarchy Process and Machine Learning Techniques

Driver behavior plays a pivotal role in ensuring road safety as it is a significant factor in preventing traffic crashes. Although extensive research has been conducted on this topic in developed countries, there is a notable gap in understanding driver behavior in developing countries, such as Pakistan. It is essential to recognize that the cultural nuances, law enforcement practices, and government investments in traffic safety in Pakistan are significantly different from those in other regions. Recognizing this disparity, this study aims to comprehensively understand risky driving behaviors in Peshawar, Pakistan. To achieve this goal, a Driver Behavior Questionnaire was designed, and responses were collected using Google Forms, resulting in 306 valid responses. The study employs a Fuzzy Analytical Hierarchy Process framework to evaluate driver behavior’s ranking criteria and weight factors. This framework assigns relative weights to different criteria and captures the uncertainty of driving thought patterns. Additionally, machine learning techniques, including support vector machine, decision tree, Naïve Bayes, Random Forest, and ensemble model, were used to predict driver behavior, enhancing the reliability and accuracy of the predictions. The results showed that the ensemble machine learning approach outperformed others with a prediction accuracy of 0.84. In addition, the findings revealed that the three most significant risky driving attributes were violations, errors, and lapses. Certain factors, such as clear road signage and driver attention, were identified as important factors in improving drivers’ risk perception. This study serves as a benchmark for policymakers, offering valuable insights to formulate effective policies for improving traffic safety.

YOLOv8-PD: an improved road damage detection algorithm based on YOLOv8n model.

Road damage detection is an crucial task to ensure road safety. To tackle the issues of poor performance on multi-scale pavement distresses and high costs in detection task, this paper presents an improved lightweight road damage detection algorithm based on YOLOv8n, named YOLOv8-PD (pavement distress). Firstly, a BOT module that can extract global information of road damage images is proposed to adapt to the large-span features of crack objects. Secondly, the introduction of the large separable kernel attention (LKSA) mechanism enhances the detection accuracy of the algorithm. Then, a C2fGhost block is constructed in the neck network to strengthen the feature extraction of complex road damages while reducing the computational load. Furthermore, we introduced lightweight shared convolution detection head (LSCD-Head) to improve feature expressiveness and reduce the number of parameters. Finally, extensive experiments on the RDD2022 dataset yield a model with parametric and computational quantities of 2.3M and 6.1 GFLOPs, which are only 74.1% and 74.3% of the baseline, and the mAP reaches an improvement of 1.4 percentage points from the baseline. In addition, experimental results on the RoadDamage dataset show that the mAP increased by 4.2% and this algorithm has good robustness. This method can provide a reference for the automatic detection method of pavement distress.

Evaluation of data representation techniques for vibration based road surface condition classification

The accurate classification of road surface conditions plays a vital role in ensuring road safety and effective maintenance. Vibration-based techniques have shown promise in this domain, leveraging the unique vibration signatures generated by vehicles to identify different road conditions. In this study, we focus on utilizing vehicle-mounted vibration sensors to collect road surface vibrations and comparing various data representation techniques for classifying road surface conditions into four classes: normal road surface, potholes, bad road surface, and speedbumps. Our experimental results reveal that the combination of multiple data representation techniques results in higher performance, with an average accuracy of 93.4%. This suggests that the integration of deep neural networks and signal processing techniques can produce a high-level representation better suited for challenging multivariate time series classification issues.

Assessing the Legibility of Arabic Road Signage Using Eye Gazing and Cognitive Loading Metrics

This research study aimed to evaluate the legibility of Arabic road signage using an eye-tracking approach within a virtual reality (VR) environment. The study was conducted in a controlled setting involving 20 participants who watched two videos using the HP Omnicept Reverb G2. The VR device recorded eye gazing details in addition to other physiological data of the participants, providing an overlay of heart rate, eye movement, and cognitive load, which in combination were used to determine the participants’ focus during the experiment. The data were processed through a schematic design, and the final files were saved in .txt format, which was later used for data extraction and analysis. Through the execution of this study, it became apparent that employing eye-tracking technology within a VR setting offers a promising method for assessing the legibility of road signs. The outcomes of the current research enlightened the vital role of legibility in ensuring road safety and facilitating effective communication with drivers. Clear and easily comprehensible road signs were found to be pivotal in delivering timely information, aiding navigation, and ultimately mitigating accidents or confusion on the road. As a result, this study advocates for the utilization of VR as a valuable platform for enhancing the design and functionality of road signage systems, recognizing its potential to contribute significantly to the improvement of road safety and navigation for drivers.

Automatic Braking System

With the proliferation of vehicles and the integration of technology into daily transportation, ensuring road safety has become paramount. Traffic accidents, often resulting in substantial damage and casualties, persist as a global concern. The Automatic Braking System (ABS) stands as a pivotal safety innovation adopted by vehicle manufacturers worldwide. This paper explores the significance and functionality of ABS in preventing wheel lock-up during braking, thereby enabling drivers to maintain steering control. Through an examination of ABS technology, its effectiveness, limitations, and potential advancements, this research aims to contribute to the ongoing discourse on enhancing road safety measures in the modern automotive landscape.

Improved RSA dynamic cryptographic accumulator-based anonymous batch authentication scheme for Internet of Vehicles

The Internet of Vehicles (IoV) provides various services to vehicles through information sharing to ensure road safety and improve traffic efficiency. However, malicious attackers can challenge the privacy and security systems of the IoV by conducting security attacks. Currently, many schemes use bilinear pairing or elliptic curves to construct authentication systems, ensuring anonymity of vehicle identities and message security. However, these schemes suffer drawbacks such as low computational efficiency and high communication overhead in highly dynamic IoV. Therefore, we propose a new efficient certificateless message authentication scheme. The proposed scheme constructs a lightweight security authentication protocol by improving the RSA dynamic accumulator and combining it with non-interactive discrete logarithm zero-knowledge proofs. In addition, our scheme eliminates the need for bilinear pairing operations, thereby reducing computational overhead. Simultaneously, it enables real-time tracking and revocation of malicious vehicle identities. Security analysis shows that our scheme can be reduced to a secure S-RSA assumption under the random oracle model, meeting various security requirements of the IoV. Performance analysis shows that our scheme diminishes not only the computational overhead but also the communication overhead.