Safe Road Research Articles

Auxcoformer: Auxiliary and Contrastive Transformer for Robust Crack Detection in Adverse Weather Conditions

Crack detection is integral in civil infrastructure maintenance, with automated robots for detailed inspections and repairs becoming increasingly common. Ensuring fast and accurate crack detection for autonomous vehicles is crucial for safe road navigation. In these fields, existing detection models demonstrate impressive performance. However, they are primarily optimized for clear weather and struggle with occlusions and brightness variations in adverse weather conditions. These problems affect automated robots and autonomous vehicle navigation that must operate reliably in diverse environmental conditions. To address this problem, we propose Auxcoformer, designed for robust crack detection in adverse weather conditions. Considering the image degradation caused by adverse weather conditions, Auxcoformer incorporates an auxiliary restoration network. This network efficiently restores damaged crack details, ensuring the primary detection network obtains better quality features. The proposed approach uses a non-local patch-based 3D transform technique, emphasizing the characteristics of cracks and making them more distinguishable. Considering the connectivity of cracks, we also introduce contrastive patch loss for precise localization. Then, we demonstrate the performance of Auxcoformer, comparing it with other detection models through experiments.

Automatic cross section extraction and cross slope measurement for curved ramps using light detection and ranging point clouds

Road cross section and slope are essential for ensuring both safe road operations and effective drainage. This paper presents a method that integrates the point clouds processing and geometric information computation derived from LiDAR point cloud data. The contributions are as follows: (1) a road marking detection method is developed to extract pavement points and remove the noisy points; (2) the centroid of road markings is extracted and defined as the road axis, determined by both road markings and boundaries utilizing the index-based classification technique; (3) knot and region of interest within the cross-sectional profile are generated to extract cross section points. A Principal component analysis algorithm is used to measure the cross slope. Based on the 13 locations of two sites within the interchange ramp, differences between the proposed method and field surveys range from 0.02 % to 0.46 %, indicating the accuracy of the proposed method for cross slope measurement.

Perceptions of vulnerable roadway users on autonomous vehicle regulations

Introduction: Development and implementation of autonomous vehicle (AV) related regulations are necessary to ensure safe AV deployment and wide acceptance among all roadway users. Assessment of vulnerable roadway users’ perceptions on AV regulations could inform policymakers the development of appropriate AV regulations that facilitate the safety of diverse users in a multimodal transportation system. Method: This research evaluated pedestrians’ and bicyclists’ perceptions on six AV regulations (i.e., capping AV speed limit, operating AV in manual mode in the sensitive areas, having both pilot and co-pilot while operating AVs, and three data-sharing regulations). In addition, pedestrians’ and bicyclists’ perceptions of testing AVs in public streets were evaluated. Statistical testing and modeling techniques were applied to accomplish the research objectives. Results: Compared to the other AV regulations assessed in this research, strong support for AV-related data sharing regulations was identified. Older respondents showed higher approval of AV testing on public roadways and less support for regulating AVs. AV technology familiarity and safe road sharing perceptions with AVs resulted in lower support for AV regulations. Conclusions: Policymakers and AV technology developers could develop effective educational tools/resources to inform pedestrians and bicyclists about AV technology reliability and soften their stance, especially on AV regulations, which could delay technology development. Practical Applications: The findings of this research could be used to develop informed AV regulations and develop policies that could improve pedestrians’ and bicyclists’ attitudes/perceptions on regulating AVs and promoting AV technology deployments.

Optimized Convolutional Forest by Particle Swarm Optimizer for Pothole Detection

Poor road maintenance leads to potholes on the road. Potholes are responsible for road accidents and even deaths in developed and developing countries. Detecting and filling road potholes is an essential part of road maintenance. Sustaining a reliable and safe road for communication depends on pothole detection. This study presents a novel combination of a convolutional neural network and an optimized machine-learning model by a heuristic algorithm for pothole detection. The proposed method comprises a shallow convolutional neural network for feature extraction and an optimized random forest model for pothole detection. The proposed model initially uses the shallow convolutional layer to extract feature sets from input pictures. Then, the particle swarm optimizer is used to eliminate irrelevant features. Finally, a combination of random forest and a particle swarm optimizer is used for pothole detection. Particle swarm optimization indicates the best subset of the extracted feature set for final pothole detection. We added 171 pictures to the already available 665 pothole pictures to evaluate the proposed method. The test set was isolated from the training set, and we trained the model on k-fold cross-validation. The experimental result indicates 99.37% accuracy, 99.37% precision, 99.38% sensitivity, and 99.38% F1-score for discriminating potholes from roads without potholes by proposed methods. The response time of the proposed method for pothole detection is 0.02 s. The proposed method can be utilized for real-time pothole detection.

Road safety improving in blackspot of Mount Bromo tourist road access, East Java

Mount Bromo in East Java is one of Indonesia’s priority tourist attractions. Safe, secure, orderly, and smooth traffic access is needed to support tourism. Safe roads can be an essential part of realizing this. This study aims to prioritize handling blackspots to discover safe roads. The research was conducted on three access roads to Mount Bromo from Probolinggo: Jalan Raya Sukapura, Jalan Raya Bromo, and Jalan Raya Lumbang. Analysis of the probability value of accidents, the impact value of the severity of accident victims, and the risk value of accidents are used to determine handling priorities. The results of the analysis obtained priority handling for Blackspot 1 by increasing the width of the road shoulder, Blackspot 2 by providing a crossing integrated with APILL, Blackspot 3 by completing street lighting and increasing lane width, Blackspot 4 by completing street lighting, and Blackspot 5 by increasing lane width. Prioritizing the handling of accident-prone locations in the road and environmental aspects can be done by reviewing the risk value of accidents for each road sub-component. A safe road will be realized at the Blackspot location.

Структура приоритетного национального проекта «Безопасные и качественные дороги» и понятие нормативного транспортно-эксплуатационного состояния автомобильных дорог как основополагающего в первоначальной структуре проекта

The stages of development of the national and priority project "Safe high-quality roads" and the structure are described, indicating the main indicators, composition, as well as the geography of distribution. The topic of the concept of the normative transport and operational condition of highways as the main indicator in the development of the concept of not only this national project, but also the priority project, which was its predecessor, as well as indicators of the transport and operational condition of highways of regional, inter-municipal significance and urban agglomerations in the context of the subjects of the federation, is also disclosed.

Проектная деятельность в органах государственной власти. Национальный проект «Безопасные качественные дороги» и его положительное влияние на обновление парка дорожно-строительной и дорожно-эксплуатационной техники в Российской Федерации

A brief history of the implementation of project activities in the Russian Federation, the standards of project management in the world, the differences between project and process activities, the structure of the program and project management approach in the Russian Federation are described. Analytical data on the introduction of kilometers of highways in the period from 2019 to 2024, provided for by the programs of road activity of the subjects of the Russian Federation within the framework of the national project "Safe high-quality roads" in the context of types of work, are presented, and four distinctive features of project activities in the Russian Federation are described.

Use of geogrid-stabilized aggregate layers in roadway application projects, Honduras case studies

This document shows at least three roadway application projects that show the benefit of using geogrid-stabilized aggregate layers to build safe roads while reducing the carbon footprint construction and engineering. Most of these projects are located in conditions of narrow streets conditions where construction procedures tend to be more critical because alternative routes during construction are limited and traffic is high. Thus, where traditionally chemical stabilization or soil substitution has been used, mechanically stabilizaded layers with geogrids have been gaining importance, increasing their use because more previsibility, good performance, quick installation, carbon footprint reduction and others. These experiences could be helpful to planners and the engineering community for the implementation of more sustainable pavement projects.

Comprehensive Analysis of Road Surface Irregularities: Cause, Effect and Mitigation Strategies

Abstract: The quality of road facilities is a critical measure of a nation's economic development and overall quality of life. In India, where road transportation is the strength of connectivity, the prevalence of road surface irregularities has emerged as a significant challenge. The present paper aims to systematically examine the multifaceted aspects of road surface irregularities in India. The study begins by providing an overview of the importance of road infrastructure in the Indian context and its insinuations for economic growth and societal well-being. It then delves into the various factors contributing to road surface irregularities, including construction materials, climatic conditions, and traffic volume and maintenance practices. Furthermore, the literature highlights the hostile heightened transportation costs Finally, this paper concludes with insights into the future prospects and challenges in managing effects of road surface irregularities on road users, such as increased accidents, vehicle tear and wear, and road surface irregularities in the Indian context, emphasizing the need for holistic approaches that integrate technological advancements, policy reforms, and sustainable practices to ensure safe and efficient road transportation. This paper serves as a comprehensive examination of the complexities surrounding road surface quality in India and provides valuable insights for policymakers, researchers, and practitioners working towards improving the nation's road infrastructure.

МЕЖДУНАРОДНЫЕ ИНИЦИАТИВЫ ООН В ОБЛАСТИ ОБЕСПЕЧЕНИЯ БЕЗОПАСНОСТИ ДОРОЖНОГО ДВИЖЕНИЯ НА ПЕРИОД ДО 2030 ГОДА

The article discusses international UN initiatives in the field of road safety until 2030. A comparative analysis of two projects was carried out: the Global Plan “Decade of Action for Road Safety 2011-2020” and the Global Plan “Decade of Action for Road Safety 2021-2030”. It is noted that the second project was developed on the basis of an integrated approach, has a clear structure, a number of components and is aimed at implementing the concept: road traffic as a “Safe System”. The positive results of the implementation in the Russian Federation of two Federal target programs designed for the periods 2006-2012 are argued. and 2013-2020, which made it possible to significantly reduce the number of victims of road accidents. Modern projects are being considered, including the NP “Safe Quality Roads”, aimed at solving national problems in the field of road safety. Conclusions are drawn about the feasibility of international initiatives and the implementation of national programs and projects in order to improve road safety and minimize social risk for its participants.

The Role of Road Safety Units in the Prevention of Child Traffic Injuries

This article describes a number of issues devoted to the role of units responsible for ensuring road safety in the prevention of child road traffic injuries. The author examines the issue of the importance and effectiveness of the activities of units responsible for ensuring road safety in the context of preventing child road traffic injuries. The author analyzes in detail the key aspects of the role of these units in carrying out preventive measures aimed at reducing the risk of injury to children on the roads. A wide range of methods and technologies are discussed, including video surveillance systems, smart traffic lights and automated means of recording traffic violations, which are seen as integral tools for improving safety. Automated means of recording violations of traffic rules further strengthen control over compliance with the rules, recording violations with high accuracy. Together, these technologies form a comprehensive approach to security, based on the use of advanced tools and techniques. Such consideration contributes to the creation of a more effective system for preventing child road traffic injuries. The author highlights the importance of collaboration between safety departments and community organizations in the development and implementation of effective strategies to combat childhood road traffic injuries. The result highlights the need for concerted efforts to create a safe road environment and reduce the risk of injury to children in road situations. In conclusion, the author emphasizes that only through an integrated approach and the introduction of advanced technologies can the safety of children on the roads be ensured, emphasizing the importance of cooperation with the public to achieve this important goal.

Automatic System for Roadway Safety – ASRS 01

One of the objectives of the European Union (EU) as well as of other state authorities is to create safe roads for vehicles all over the EU space. Considering the rapid development of road traffic and, regrettably, an increase in the number of accidents, the system presented in this paper has the role of informing road traffic participants about infrastructure and environmental conditions. Hardware support, software support as well and further development of the ASRS 01 system are presented.

Оценка реализации национальных проектов в сфере транспортной инфраструктуры (на примере регионов ЮФО)

The article analyzes the preliminary results of the implementation of the “Safe Quality Roads” and “Comprehensive Plan for the Modernization and Expansion of Main Infrastructure” projects, and identifies the regional features of their implementation for individual regions of the Southern Federal District - the Rostov region, the Krasnodar Territory, the Republic of Crimea. By 2022, the basic values ​​for individual target indicators have been achieved and, in general, given the existing positive dynamics in 2024, the rest will most likely be achieved. At the same time, project passports require revision taking into account regional characteristics. In Crimea, the share of roads that meet regulatory requirements is determined at a fairly low level - 38.8%, and with the current trend towards an increase in freight turnover, motorization, and tourist flow, road safety is significantly reduced, as evidenced by high accident rates. In this regard, target indicators for the quality of the road network should be revised upward. For the Rostov region, the federal project “Road Network” should include a list of agglomerations and for each of them the values ​​of basic indicators should be determined. Particular attention should be paid to the issue of transport support for small isolated settlements in all regional passports. “Safe Quality Roads” and “Comprehensive Plan for the Modernization and Expansion of Trunk Infrastructure” are labor-intensive and capital-intensive projects that require modern equipment and technologies. Infrastructure development will support the overall economic strategy. However, to achieve the assigned tasks, it is necessary to mobilize industrial production so that the modernization and creation of infrastructure is provided with domestic equipment and technologies. Based on the results of 2021, it can be argued that a qualitative transformation of the economy, accompanied by an acceleration in the growth rate of labor productivity, did not occur.

Machine learning-based pavement crack detection, classification, and characterization: a review

The detection, classification, and characterization of pavement cracks are critical for maintaining safe road conditions. However, traditional manual inspection methods are slow, costly, and pose risks to inspectors. To address these issues, this article provides a comprehensive overview of state-of-the-art machine vision and machine learning-based techniques for pavement crack detection, classification, and characterization. The paper explores the process flow of these systems, including both machine learning and traditional methodologies. The paper focuses on popular artificial intelligence (AI) techniques like support vector machines (SVM) and neural networks. It underscores the significance of utilizing image processing methods for feature extraction in order to detect cracks. The paper also discusses significant advancements made through deep learning strategies. The main objectives of this research are to improve efficiency and effectiveness in pavement crack detection, reduce inspection costs, and enhance safety. Additionally, the article presents data gathering approaches, various datasets for developing road crack detection models, and compares different models to demonstrate their advantages and limitations. Finally, the paper identifies open challenges in the field and provides valuable insights for future research and development efforts. Overall, this paper highlights the potential of AI-based techniques to revolutionize pavement maintenance practices and significantly improve road safety.

Analisis Kelaikan Fungsi Jalan Menggunakan Metode AHP dan Maut pada Ruas Jalan A.H. Nasution (Medan) dan Jalan Ngumban Surbakti (Medan)

Road infrastructure is a vital component in fostering economic growth and human mobility. Well-maintained and safe roads enhance transportation effectiveness and efficiency. However, in reality, several road segments fall short of stringent standards, both in terms of suitability and safety. The road sections A.H. Nasution (Medan) and Ngumban Surbakti (Medan) have never undergone prior fitness assessments. Thus, this study aims to establish a ranking to determine their fitness levels. This research assesses the suitability of A.H. Nasution (Medan) and Ngumban Surbakti (Medan) roads using the Analytical Hierarchy Process (AHP) and the Multi-Attribute Utility Theory (MAUT) methods. The collected data is processed and analyzed using both AHP and MAUT methods to determine the relative weights of factors influencing road suitability. The AHP method, when applied to respondent data, revealed the highest weights for road geometric technical aspects, scoring 3,36 for A.H. Nasution and 3.04 for Ngumban Surbakti. Conversely, the lowest weights were assigned to road equipment technical aspects, with 0,592 for A.H. Nasution, and road section utilization, with 0,3 for Ngumban Surbakti. When employing the MAUT method, the highest weights were attributed to complementary road structure, scoring 1,265 for A.H. Nasution and 1,140 for Ngumban Surbakti, whereas the lowest weights pertained to road section utilization, with 0,04 for A.H. Nasution and 0,413 for Ngumban Surbakti. In future research, it is advisable to conduct a comparative study between AHP and MAUT in scenarios with a higher number of criteria or increased complexity. This may also explore the potential development of new methods that integrate the strengths of both approaches to address these issues.

Analisis Kelaikan Fungsi Jalan Menggunakan Metode AHP dan Maut pada Ruas Jalan A.H. Nasution (Medan) dan Jalan Ngumban Surbakti (Medan)

Road infrastructure is an important aspect in supporting economic growth and human mobility. Good and safe road conditions will increase the effectiveness and efficiency of transportation. However, in reality, some road sections still do not meet fairly strict standards, both in terms of feasibility and safety. The roads of A.H. Nasution (Medan) and Ngumban Surbakti (Medan) have never undergone a feasibility test before. Therefore, in this study a ranking will be formed to determine the level of feasibility of the function of both. This study was conducted to evaluate the feasibility of A.H. Nasution (Medan) and Ngumban Surbakti (Medan) roads using the AHP (Analytical Hierarchy Process) method and the MAUT (Multi-Attribute Utility Theory) method. The data that has been collected will be processed and analyzed using the AHP and MAUT methods. The AHP method and the MAUT method are used to determine the relative weight of each of the factors affecting roadworthiness. Assessment of respondent data using the AHP method obtained the largest weight on road technical by 3.36 on the A.H. Nasution road section and 3.04 on the Ngumban Surbakti road section. While the smallest weight on technical road equipment is 0.592 on the A.H. Nasution road section and the utilization of the road section is 0.3 on the Ngumban Surbakti road section. The assessment of respondents' data using the MAUT method obtained the largest weight on road complementary building structures of 1,265 on the A.H. Nasution road section and 1,140 on the Ngumban Surbakti road section. While the smallest weight on the utilization of road sections is 0.04 on the A.H. Nasution road section and 0.413 on the Ngumban Surbakti road section.

Towards safer streets: A framework for unveiling pedestrians’ perceived road safety using street view imagery

Road safety has become a global concern but its impact in low- and middle-income countries is widespread mainly due to lack of appropriate crash database system and under-reporting. In this context, the primary objective of this paper is to provide a scalable framework for unveiling pedestrians’ perceived road safety that can also be applied in regions where accessible crash data are limited or near-crashes are left unreported. In the first step of our methodology, a deep learning architecture-based semantic segmentation model (HRNet+OCR) is trained using labeled Google Street View (GSV) images from specific study areas in Dhaka, Bangladesh, which facilitates the identification of both man-made components (such as roads, sidewalks, buildings, and vehicles) and natural elements (including trees and sky). The developed model showed excellent performance in identifying different features in an image by achieving high precision (0.95), recall (0.97), F1-score (0.96), and intersection over union (IoU) (91.86). Secondly, a group of trained raters scored the perceived road safety on an ordinal scale from 0 to 10 (extremely unsafe to extremely safe to walk in terms of road crashes) by assessing the GSV images. Then, several regression models have been used on features extracted from GSV images, and socio-demographic factors (i.e., population density, and relative wealth index) to estimate the perceived road safety, and random forest regression model was found to perform the best. Further, Shapley Additive Explanations (SHAP), a model-agnostic technique has been used for examining feature importance by computing the contribution of each feature to the random forest regression model output. The results show that sidewalk, road, population density, wall, and relative wealth index have higher impact on determining the perceived road safety rating. Additionally, the results of t-tests between the average perceived road safety scores for crash-prone and non crash-prone areas revealed the existence of significant differences. This study also provides perceived road safety rating map on a neighborhood scale, which can be a useful visualization tool for policy-makers and practitioners to identify the road safety deficiencies at specific locations, and formulate appropriate and strategic countermeasures to improve pedestrians’ road safety.

Semi-Supervised Drivable Road Segmentation with Expanded Feature Cross-Consistency

Drivable road segmentation aims to sense the surrounding environment to keep vehicles within safe road boundaries, which is fundamental in Advance Driver-Assistance Systems (ADASs). Existing deep learning-based supervised methods are able to achieve good performance in this field with large amounts of human-labeled training data. However, the process of collecting sufficient fine human-labeled data is extremely time-consuming and expensive. To fill this gap, in this paper, we innovatively propose a general yet effective semi-supervised method for drivable road segmentation with lower labeled-data dependency, high accuracy, and high real-time performance. Specifically, a main encoder and a main decoder are trained in the supervised mode with labeled data generating pseudo labels for the unsupervised training. Then, we innovatively set up both auxiliary encoders and auxiliary decoders in our model that yield feature representations and predictions based on the unlabeled data subjected to different elaborated perturbations. Both auxiliary encoders and decoders can leverage information in unlabeled data by enforcing consistency between predictions of the main modules and those perturbed versions from auxiliary modules. Experimental results on two public datasets (Cityspace and CamVid) verify that our proposed algorithm can almost reach the same performance with high FPS as a fully supervised method with 100% labeled data with only utilizing 40% labeled data in the field of drivable road segmentation. In addition, our semi-supervised algorithm has a good potential to be generalized to all models with an encoder–decoder structure.

Vision Zero and Impaired Driving: Near and Longer-Term Opportunities for Preventing Death and Injuries

Vision Zero involves the use of a systems approach to eliminate fatal and serious injuries from motor vehicle crashes by accommodating basic human limitations that lead to crashes through fundamental behavioral expectations, together with sound vehicle and road design.Alcohol-related crashes account for a significant proportion of motor vehicle crash death and injury and can be addressed in a safe road transport system. We look at near-term policy and program interventions that are known to motivate drivers to make safe drinking and driving decisions, and possibilities for using technology over the longer term to address risks resulting from driver impairment that is either inadvertent or willful high-risk behavior.From the Vision Zero perspective,”normal driving” refers to a situation where traffic and road users are operating as desired and planned. A driver in this normal driving envelope operates at a safe speed, wears a seat belt, focuses on the driving task, and is not impaired. A safe system accommodates human errors, mistakes, and misjudgments in the normal driving envelope. However, it may not be capable of compensating for deliberate violations and rule-breaking.A critical role of behavioral programs and policies is to motivate safe decisions by drivers and other road users and keep them in the normal driving envelope where they can be protected from unintentional errors by a safe system. While much progress has been made in developing and implementing impaired driving policies and programs, much potential remains in the their ability to motivate drivers to meet the fundamental expectations required in a safe system. Examples of behavioral programs and policies that have strong evidence of effectiveness but are underutilized in the U.S. include conducting periodic sobriety checkpoints, lowering the blood alcohol concentration limit for driving, and mandating the use of ignition interlock devices. While the specific interventions may differ, it is likely that the same situation of incomplete implementation of behavioral programs and policies - and consequent unrealized value to a comprehensive safe system - applies to many other nations.To reach the goal of zero deaths, a comprehensive Vision Zero program needs to address the problem of deliberate risk-taking, which can include driver impairment from alcohol or other causes and extend to dangerous and reckless driving. Advanced safety technologies offer a range of opportunities for this purpose. Cars available today and in the future will have a plethora of sensors that monitor circumstances inside and around the car. These systems can identify whether a driver is in their safe driving envelope and respond with interventions that are appropriate for the severity and nature of the risk. Interventions could range from those that are not perceivable to the driver, such as putting driver assist systems into active mode, to stronger steps such as limiting or preventing vehicle operation.Zero fatalities or serious injuries in motor vehicle crashes is possible with a systems approach that accommodates human errors and mistakes that occur with the normal driving envelope and incorporates effective responses to deliberate risk-taking outside of this envelope.

U2-Net: A Very-Deep Convolutional Neural Network for Detecting Distracted Drivers

In recent years, the number of deaths and injuries resulting from traffic accidents has been increasing dramatically all over the world due to distracted drivers. Thus, a key element in developing intelligent vehicles and safe roads is monitoring driver behaviors. In this paper, we modify and extend the U-net convolutional neural network so that it provides deep layers to represent image features and yields more precise classification results. It is the basis of a very deep convolution neural network, called U2-net, to detect distracted drivers. The U2-net model has two paths (contracting and expanding) in addition to a fully-connected dense layer. The contracting path is used to extract the context around the objects to provide better object representation while the symmetric expanding path enables precise localization. The motivation behind this model is that it provides precise object features to provide a better object representation and classification. We used two public datasets: MI-AUC and State Farm, to evaluate the U2 model in detecting distracted driving. The accuracy of U2-net on MI-AUC and State Farm is 98.34 % and 99.64%, respectively. These evaluation results show higher accuracy than achieved by many other state-of-the-art methods.