Artificial Intelligence for Road Anomaly Detection: A Review

India needs shift in thinking to improve road safety

This research paper examines the application of artificial intelligence (AI) in road network inventory and network-wide road safety assessment. An overview of current research related to this field is presented and various aspects of the use of AI in road infrastructure and safety assessment are analysed. In today’s world, where the road network continues to develop and grow, the use of AI can offer significant advantages in the inventory and assessment of road infrastructure and safety. AI can be used to process large volumes of data collected from various sources such as geographic data, photos, documentation and more. One of the main aspects that the article looks at is the use of AI to automatically process data and create a digital inventory of the road network. AI systems can analyse geographic data and photos to identify and classify roads, road signs, markings, and other elements of road infrastructure. This can facilitate engineers and competent authorities in the process of road inventory and maintenance. Another important aspect discussed in the paper is the use of AI for the general assessment of road safety. AI models can analyse road infrastructure inventory data, as well as traffic data, crashes, and other factors, to provide a comprehensive assessment of road network safety. This allows the competent authorities to identify vulnerable places, carry out preventive measures and plan appropriate interventions aimed at improving road safety. In conclusion, the paper highlights the possibilities and advantages of using artificial intelligence in road network inventory and network-wide road safety assessment. Such an approach can contribute to more efficient management of road infrastructure and improvement of road safety.

Road traffic injuries remain a leading cause of death and disability worldwide. At the same time, the mobility landscape is rapidly changing; artificial intelligence (AI), automation, connected vehicles, and big data analytics are opening new opportunities to predict risks, to optimize traffic flow, and to design safer systems. At the same time, persistent human factors such as distraction, fatigue, risk-taking behaviors, and inequalities between different groups of road users, continue to drive most crashes. The critical challenge, today, is how to integrate cutting-edge technologies with a deep understanding of human behavior to create safe, inclusive, and sustainable mobility systems.Global organizations including the European Union (EU) and the World Health Organization (WHO) have set ambitious targets under the EU Road Safety Policy Framework 2021–2030 and the WHO Decade of Action for Road Safety 2021–2030. These emphasize Vision Zero, standardized data-driven indicators, equity for vulnerable users, and system resilience to effectively address emerging crises, such as climate change and extreme urbanization, and other megatrends. Data fragmentation, ethical dilemmas around AI deployment, and the uneven adoption of innovative solutions across regions remain major barriers.New breakthroughs are reshaping the field of safe mobility through innovations such as AI-enabled risk prediction and driver assistance systems, integration of behavioral science into urban mobility planning, large-scale interoperable data sharing platforms for traffic surveillance, and advanced simulation models for safety evaluation. Coordinated efforts within the EU Road Safety Cluster projects (e.g. the EU-funded project AI4CCAM’s for trustworthy AI and models predicting vulnerable road user behaviors, HEIDI’s adaptive human–machine interfaces, PHOEBE’s city-level predictive frameworks, SOTERIA’s inclusive safety intelligence, and ProtAct-Us’ standardized assessments of the long-term physical, cognitive, and mental health impacts of road crashes) demonstrate how AI, simulation, and human factors combine to enhance urban safety. At the same time, EU education and training actions, i.e., namely the ‘IVORY - AI for Vision Zero in Road Safety’ industrial doctorates network, of the Marie-Sklodowska Curie programme, aim to train a new generation of leading researchers with a broad understanding of the interdisciplinary challenges of AI in road safety (engineering, human factors, ethics and data science). These advances promise substantial reductions in human error and transformational improvements in safety management.In parallel, real-time systems enable cross-border vehicle-to-vehicle and vehicle-to-infrastructure communication, facilitating synchronized intelligent transport systems along major European corridors. Smart infrastructure projects use sensor-driven technologies and real-time hazard detection to proactively warn drivers of road risks, markedly lowering accident rates. Meanwhile, the Common European Mobility Data Space and pilot data platforms in Amsterdam, Helsinki, and Porto exemplify efforts to unify scalable, interoperable traffic data ecosystems, supporting effective policymaking and environmental benefits.This session confronts the urgent challenges of safe mobility through the lenses of technology, human behavior, and policy. The panel will illustrate how trustworthy AI and robust system verification can deliver reliable and transparent automation while underscoring the indispensable role of human factors and behavioral insights in crash reduction. Key discussions will tackle pressing issues around governance, cross-system interoperability, societal acceptance, and the integration of vulnerable users’ needs into inclusive safety planning.Drawing on cutting-edge research and policy experience, the discussion will highlight strategies to embed safety into transport systems through data-driven governance, risk analysis, and evidence-based implementation. Beyond reviewing progress, the panel will chart the next steps: harmonizing data across borders, embedding ethical AI into mobility governance, ensuring equity for all road users, and strengthening collaboration between science, policy, and industry. It will conclude with a forward-looking agenda for innovation that keeps human safety and societal needs at the center of mobility transformation.

Road Safety is one of the major challenge in Nepal with fatalities rate of 8 per/day (Traffic Police, 2023) and 23 per/day (WHO, 2023). With three tier of government, Road...

Road safety systems are critical engineering solutions designed to minimize the effects of traffic accidents and increase the safety of transportation infrastructures. Traditional road safety structures are generally manufactured using steel, concrete and polymer materials. However, manufacturing processes with these materials are high-cost, limited in terms of design flexibility and can lead to material waste. In recent years, rapidly developing additive manufacturing (AM) technologies stand out as an important alternative in the production of road safety systems. AM enables the production of complex geometries and enables the development of lightweight and high-strength structures that can absorb impact energy more effectively. This study focuses on the use of AM methods in road safety systems, examining the performance and applicability of polymer, metal and composite materials. The advantages of AM-produced road safety barriers, traffic signs, speed bumps and shock absorbing structures, depending on the material type, are evaluated. In addition, the advantages offered by AM, such as design flexibility, sustainable production processes and material efficiency, are discussed, and technical challenges and applicability limitations are also discussed. This review evaluates the current and potential applications of AM for road safety systems, providing insights into how this technology can be used more effectively in the future. The findings of the study provide significant contributions towards improving the integration of AM technologies into road safety systems from both academic and industrial perspectives. The findings of the study provide important contributions to the development of the integration of AM technologies into road safety systems from both academic and industrial perspectives. Future research can further enhance the innovative potential of AM in road safety systems, with a particular focus on sustainable material use, design optimization and energy efficiency in manufacturing processes. However, overcoming technical challenges in large-scale applications and compliance with regulatory standards are critical research areas for the widespread adoption of this technology.

Road accidents, often involving one or more vehicles, can result in property damage, injuries, or even fatalities. These incidents can occur due to a range of factors, including human errors, adverse weather conditions, or mechanical failures, despite precautions taken by road users. Consequently, early education on road safety is crucial, especially for children. This research focuses on assessing children's knowledge of road accidents in Malaysia and evaluating the impact of augmented reality (AR) experiences on their understanding. To support this project, we developed an AR application using the Pendidikan Keselamatan Jalan Raya (PKJR) Year 2 Guidebook as a medium for students to learn about road safety. Selected pages in the book serve as markers, enabling students to engage with AR content while using the book. The study aims to determine the effectiveness of the AR application as an educational tool for children. A group of school children participated in testing this AR application, and their experiences were assessed using an adapted Game Experience Questionnaire (GEQ) model. The results indicate that after using the AR application, the group of 8-year-old children exhibited improved awareness of the road environment. This paper also explores the emotional aspects of participant experiences as emphasized by the GEQ. These findings highlight the potential of AR as an innovative tool for educating children about road safety, challenging traditional approaches, and promoting safer road behaviors among young individuals. Furthermore, this project aligns with the strategies outlined in the Malaysian Road Safety Plan 2020-2030, particularly in reducing risks to pedestrians. In a broader context, this study contributes to the evolving landscape of technology-driven safety initiatives, underscoring the importance of adapting contemporary educational mediums to address complex societal issues like road accidents. In conclusion, we discuss the potential for future studies involving road safety education and interactive technology.

Introduction: In today's fast-paced technology, road safety demands intelligent, efficient response systems.An advanced Road Accident Detection System by combining Generative Adversarial Networks (GANs) for real-time image dehazing with YOLOv11 for precise object detection. The GAN-based model enhances visibility in adverse weather, enabling accurate accident detection even in low-visibility scenarios. YOLOv11 effectively identifies various objects, including vehicles, pedestrians, and collision events. Upon detecting an accident, the system triggers automated emergency notifications, sending real-time alerts with precise location details to responders such as police stations, hospitals, Regional Transport Offices (RTOs) and traffic management authorities, facilitating prompt traffic clearance. By minimizing response time, this system enhances survivability rates. Extensive experimental evaluations confirm its robustness across diverse environmental conditions, outperforming traditional dehazing and object detection methods, thereby improving accident detection and optimizing emergency response mechanisms. Objectives: The objective of this project is to develop a real-time road accident detection system using GAN-based dehazing and YOLOv11 for precise object detection. The system enhances visibility in adverse weather conditions and ensures quick emergency response by automatically notifying relevant authorities, reducing response time, and improving survivability rates. Methods :The proposed system integrates Generative Adversarial Networks (GANs) for real-time image dehazing and YOLOv11 for high-speed object detection. Video frames from surveillance cameras or dashcams are preprocessed using GAN-based dehazing to improve visibility under adverse weather conditions. A transformer-based attention mechanism prioritizes critical areas for detection, enhancing precision. When an accident is detected, the system triggers automated emergency notifications with precise location details, alerting police stations, hospitals, Regional Transport Offices (RTOs), and traffic management authorities. This approach ensures rapid response, minimizing casualties Results: The proposed system effectively enhances road accident detection by integrating GAN-based dehazing and YOLOv11 object detection. The dehazing model improves image clarity, allowing for better feature extraction in low-visibility conditions, while YOLOv11 ensures accurate identification of vehicles, pedestrians, and collision events. The system significantly reduces false positives and enhances detection accuracy compared to traditional methods. Additionally, the automated emergency notification mechanism enables faster response times, demonstrating the model’s reliability in real-world scenarios and its potential for improving road safety and intelligent transportation systems. Conclusions: Enhancing road safety through real-time accident detection plays a vital role in minimizing casualties and improving emergency response efficiency. The developed system ensures accurate accident identification, even in challenging weather conditions. It delivers instant alerts to relevant authorities, significantly improving response time and making it a reliable solution for road safety and emergency management.

BackgroundIn the beginning of 90’s the Baltic states’ road safety fatality records were among the worst in Europe. After that period, the situation has been improved essentially, but despite of...

This study focuses on investigating the significant impacts of speed breakers on various parameters, including travel time delays, vehicle speeds, fuel consumption, pavement maintenance costs, and vehicular exhaust emissions. Field data was collected and analyzed to assess the effects of different types of traffic calming measures on these parameters. The findings provide valuable insights into the implications of speed breakers on road safety, environmental pollution, and overall road infrastructure management. The results reveal that the implementation of speed humps, speed bumps, and triple bumps effectively slows down vehicles, as evidenced by considerable reductions in the 85th percentile speeds. The reduction percentages were 41.65% for speed humps, 73.52% for speed bumps, and 86.27% for triple bumps. This indicates the effectiveness of these traffic calming measures in improving road safety by reducing vehicle speeds. However, the presence of speed breakers also leads to increased travel time delays. On average, traversing stretches with speed humps, speed bumps, and triple bumps resulted in delays of 9.31, 16.42, and 29.51 seconds, respectively. While the individual delay times may appear relatively short, the cumulative effect of multiple speed obstacles along a road needs to be considered. Another significant impact observed is the increased fuel consumption associated with speed breakers. The study found that for every 100 km of travel, motorcycles and passenger cars consumed approximately 12.07 km and 27.37 km of additional fuel, respectively, when the density of speed breakers was 1.33/km. This translates to a fuel consumption increase of 13.73% for motorcycles and 37.74% for passenger cars. Furthermore, the presence of speed humps was found to contribute to pavement deterioration, as indicated by decreased Pavement Condition Index (PCI) values. The study also revealed that sections with speed humps incurred significantly higher maintenance costs compared to sections without speed humps. The increase in maintenance cost ranged from 100 to 264% across different road sections, with higher traffic volumes leading to greater cost escalation. Additionally, the study confirms that lower vehicle speeds, particularly between 0-15 km/hr, are associated with higher emissions of pollutants, including carbon monoxide (CO) and other pollutants. This highlights the environmental implications of speed breakers and their contribution to urban air pollution. Doi: 10.28991/CEJ-2024-010-07-07 Full Text: PDF

Accident prediction is one of the most critical aspects of road safety, whereby an accident can be predicted before it actually occurs and precautionary measures taken to avoid it. For this purpose, accident prediction models are popular in road safety analysis. Artificial intelligence (AI) is used in many real world applications, especially where outcomes and data are not same all the time and are influenced by occurrence of random changes. This paper presents a study on the existing approaches for the detection of unsafe driving patterns of a vehicle used to predict accidents. The literature covered in this paper is from the past 10 years, from 2004 to 2014. AI techniques are surveyed for the detection of unsafe driving style and crash prediction. A number of statistical methods which are used to predict the accidents by using different vehicle and driving features are also covered in this paper. The approaches studied in this paper are compared in terms of datasets and prediction performance. We also provide a list of datasets and simulators available for the scientific community to conduct research in the subject domain. The paper also identifies some of the critical open questions that need to be addressed for road safety using AI techniques.

Benchmarking road safety performances of countries

Ensuring road safety of existing road is crucial to preventing accidents and improving the long-term usability of roadways. This study focuses on a road safety audit (RSA) conducted during the existing phase of the Tika Bhairab-Baguwa section of Kanti Rajmarg in Lalitpur, Nepal. The main aim is to assess the safety performance of the road, identify potential hazards, and highlight design flaws that may lead to accidents in its operation level. Through field observations, surveys, and interviews with road users and experts, the research identified several key safety concerns. These include poor road alignment, narrow lanes, limited visibility, and insufficient signage or markings. Additionally, gaps in traffic law enforcement, coupled with inadequate training for traffic police, contribute to heightened road safety risks. Key findings highlight critical safety concerns such as poor visibility at curves, inadequate pedestrian crossings, lack of proper signage, and hazardous roadside encroachments. Based on questionnaire survey major problems associated with road safety of Kanti Rajmarga with highest RII value were narrow lane width, poor road signage and marking both with RII value 0.85. Similarly, poor road signage and marking, improper alignment both with RII value 0.8. The main cause of narrow lane width was found due to budget constraint, poor plaining and hilly terrain. Based on the results, practical recommendations are proposed, including improved road markings, installation of guardrails, enhanced street lighting, and better traffic management at conflict zones, increasing law enforcement efforts, and providing better training for traffic police and drivers are critical steps to making the road safer. A good drainage system should be created to prevent flooding and erosion, and strong barriers should be placed near steep drops. These recommendations aim to reduce risks and ensure the safety of all road users. Thus this study contributes to the broader discourse on road safety in Nepal by providing a case-specific assessment and actionable solutions. The findings can aid local authorities in implementing effective safety upgrades, ultimately reducing accidents and ensuring safer mobility on Kanti Rajmarg.

This study examines the role of human factors in road safety among students of the Faculty of Entrepreneurship and Business (FEB) at Universiti Malaysia Kelantan (UMK). Road accidents remain a major issue among young drivers, particularly students, due to factors such as driver fatigue, speed compliance, driver distraction, and visibility conditions. The research aims to address the knowledge gap concerning how these factors specifically affect university students, a demographic often overlooked in road safety studies. A questionnaire was employed as the data collection instrument within a quantitative research design. A total of 331 students from FEB participated in the study using a combination of convenience and stratified sampling approaches. The Statistical Package of Social Science (SPSS) version 30 was used to assess the relationships between variables through Spearman’s Correlation and to describe the demographic background of respondents using descriptive analysis. The findings revealed significant effects of driver fatigue, speed compliance, driver distraction, visibility conditions, and road safety. Driver distraction and limited visibility were identified as the main contributors to road accidents. The study highlights the importance of targeted interventions, including road safety education, awareness campaigns, and infrastructure improvements, in reducing road safety risks among university students.

Road safety is a critical concern worldwide, directly influencing public health, economic stability, and overall quality of life. As the number of vehicles on the road continues to rise, the quality of infrastructure—roads, bridges, signage, and traffic control systems—plays a pivotal role in determining safety outcomes. This study investigates how age and gender influence road safety perceptions, behaviors, and experiences among 1,490 respondents in Iraq. Females constituted 56.5% of participants, with a majority (40.9%) aged 18–25, reflecting Iraq’s youthful demographics. Findings reveal significant age and gender disparities: middle-aged respondents (46–55 years) perceived roads as less safe than younger groups, contrasting with trends in high-income countries. Gender differences emerged, with females rating roads as safer (159 vs. 100 males) and males reporting more risky behaviors (e.g., phone use while driving: 22 males vs. 7 females). Seatbelt non-use was unexpectedly rare among males (0 cases vs. 36 females), suggesting cultural or reporting biases. Factor analysis identified three key components: (1) satisfaction with road safety infrastructure and efforts, (2) personal safety compliance (e.g., seatbelt use), and (3) a paradoxical link between high-risk perception and risky behaviors, possibly due to risk normalization. The study highlights the need for targeted interventions, such as awareness campaigns and stricter enforcement, to address these disparities and improve road safety in Iraq. It is vital for policymakers, municipal planners, and the public to understand the complex relationship between road safety and the quality of infrastructure to create a safer road environment and minimize the catastrophic impact of traffic-related accidents.

Due to the progressive increase in the population and the complexity of their mobility needs, the evolution of transportation systems to solve advanced mobility problems has been necessary. Additionally, there are many situations where the application of traditional solutions is not entirely effective, e.g., when the processing of large amounts of data collected from in-vehicle sensors and network devices is required. To overcome these issues, several Artificial Intelligence-based techniques have been applied to different areas related to the transportation environment. In this paper, we present a study of the diverse Artificial Intelligence (AI) techniques which have been implemented to improve Intelligent Transportation Systems (ITS). In particular, we grouped them into three main areas depending on the main field where they were applied: (i) Vehicle control, (ii) Traffic control and prediction, as well as (iii) Road safety and accident prediction. The results of this study reveal that the combination of different AI techniques seems to be very promising, especially to manage and analyze the massive amount of data generated in transportation.