Traffic safety remains a pressing global concern, with traffic signs playing a vital role in regulating and guiding drivers. However, environmental factors like lighting and weather often compromise their visibility, impacting human drivers and autonomous vehicle (AV) systems. This study addresses critical traffic sign detection (TSD) and classification (TSC) gaps by leveraging the YOLOv8 algorithm to evaluate the detection accuracy and sign quality under diverse lighting conditions. The model achieved robust performance metrics across day and night scenarios using the novel ZND dataset, comprising 16,500 labeled images sourced from the GTSRB, GitHub repositories, and real-world own photographs. Complementary retroreflectivity assessments using handheld retroreflectometers revealed correlations between the material properties of the signs and their detection performance, emphasizing the importance of the retroreflective quality, especially under night-time conditions. Additionally, video analysis highlighted the influence of sharpness, brightness, and contrast on detection rates. Human evaluations further provided insights into subjective perceptions of visibility and their relationship with algorithmic detection, underscoring areas for potential improvement. The findings emphasize the need for using various assessment methods, advanced algorithms, enhanced sign materials, and regular maintenance to improve detection reliability and road safety. This research bridges the theoretical and practical aspects of TSD, offering recommendations that could advance AV systems and inform future traffic sign design and evaluation standards.

This study investigates the critical role of retroreflectivity in traffic signs, particularly in the context of autonomous vehicles (AVs), where accurate detection is paramount for road safety. Retroreflectivity, influencing visibility and legibility, is essential for ensuring safe road conditions. The study aims to assess traffic sign retroreflectivity using handheld retroreflectometers and LiDAR data, offering a comprehensive comparison of results with a specific focus on the RA1 and RA2 traffic sign classes. In a real-world setting, an AV equipped with LiDAR sensors, GPS units, and a stereo camera collects data on traffic signs, including point cloud attributes such as intensity and density. Simultaneously, a handheld retroreflectometer measures retroreflectivity coefficients from identified traffic signs. While retroreflectometers provide precision, they face limitations regarding time-consuming measurements and handling large or elevated signs. In contrast, LiDAR systems efficiently evaluate retroreflective features for numerous signs without such constraints. Despite both methods consistently yielding accurate retroreflectivity, the study reveals a limited correlation between LiDAR point cloud data and handheld retroreflectivity coefficients. The implications of these findings are significant, particularly in the selection and maintenance of retroreflective materials in traffic signs, with direct repercussions on overall road safety. The results offer valuable insights into leveraging LiDAR technology to enhance AVs' detection capabilities. Recommendations for further research include exploring factors influencing LiDAR intensity, establishing a more accurate relationship between intensity and retroreflectivity, correcting the point cloud during intensity calibration, and testing empirical prediction models with a larger sample size. These endeavors aim to generate a robust regression graph and determine correlation coefficients, providing a more nuanced understanding of the intricate relationship between LiDAR data and handheld retroreflectivity coefficients in the context of traffic sign assessment.

Traffic sign classification is indispensable for road traffic systems, including automated ones. There is a fundamental difference in the visual appearance of traffic signs from one country to another. Each dataset has its design standards and regulations based on shape, color, and information content, making implementing classification and recognition techniques more difficult. This paper aims to assess the influence of traffic sign diversity on autonomous vehicles (AVs) by reviewing several previous studies, comparing, summarizing their results, and focusing on classifying and detecting traffic sign datasets based on color, shape, and deep learning spaces using various methods and applications. Furthermore, it covers the main challenges facing road designers and planners considering changes to road safety infrastructure. It will be argued that compiling and standardizing a comprehensive global database of traffic signs is very difficult because it is costly and complex in application. However, it is still one of the possible solutions for the coming decades. Recommendations for future developments are also presented in this study.

Road safety is a serious concern worldwide, and traffic signs play a critical role in confirming road safety, particularly in the context of AVs. Therefore, there is a need for ongoing advancements in traffic sign evaluation methodologies. This paper comprehensively analyzes the relationship between traffic sign retroreflectivity and LiDAR intensity to enhance visibility and communication on road networks. Using Python 3.10 programming and statistical techniques, we thoroughly analyzed handheld retroreflectivity coefficients alongside LiDAR intensity data from two LiDAR configurations: 2LRLiDAR and 1CLiDAR systems. The study focused specifically on RA1 and RA2 traffic sign classes, exploring correlations between retroreflectivity and intensity and identifying factors that may impact their performance. Our findings reveal variations in retroreflectivity compliance rates among different sign categories and color compositions, emphasizing the necessity for targeted interventions in sign design and production processes. Additionally, we observed distinct patterns in LiDAR intensity distributions, indicating the potential of LiDAR technology for assessing sign visibility. However, the limited correlations between retroreflectivity and LiDAR intensity underscore the need for further investigation and standardization efforts. This study provides valuable insights into optimizing traffic sign effectiveness, ultimately contributing to improved road safety conditions.

Virtual Reality (VR) enables immersive, repeatable, and risk-free simulation of haz-ardous driving scenarios. VR is increasingly applied in autonomous vehicle (AV) re-search for safety evaluation, takeover training, and human–machine interaction (HMI) prototyping. This review synthesizes empirical work to assess the contributions of VR to takeover performance, training efficacy, ecological validity, and user ac-ceptance. Evidence suggests that VR interventions can reduce takeover reaction times compared to conventional instruction, support iterative HMI design, and enhance user familiarity and calibrated trust in AV systems. Persistent limitations include simulator sickness, sample homogeneity, fidelity gaps between VR and on-road performance, and inconsistent reporting of scenario design. We recommend standardized reporting (PRISMA flow plus scenario metadata), longitudinal transfer studies, cross-cultural samples, and hybrid VR–AR validation methods to strengthen transferability and reg-ulatory acceptance.