<rss version="2.0" xmlns:atom="https://www.w3.org/2005/Atom">
  <channel>
    <title>Transport Research International Documentation (TRID)</title>
    <link>https://trid.trb.org/</link>
    <atom:link href="https://trid.trb.org/Record/RSS?s=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" rel="self" type="application/rss+xml" />
    <description></description>
    <language>en-us</language>
    <copyright>Copyright © 2026. National Academy of Sciences. All rights reserved.</copyright>
    <docs>http://blogs.law.harvard.edu/tech/rss</docs>
    <managingEditor>tris-trb@nas.edu (Bill McLeod)</managingEditor>
    <webMaster>tris-trb@nas.edu (Bill McLeod)</webMaster>
    <image>
      <title>Transport Research International Documentation (TRID)</title>
      <url>https://trid.trb.org/Images/PageHeader-wTitle.jpg</url>
      <link>https://trid.trb.org/</link>
    </image>
    <item>
      <title>Study on the critical rollover conditions of trucks on curved highway segments under sand-accumulated road conditions based on LSTM</title>
      <link>https://trid.trb.org/View/2686634</link>
      <description><![CDATA[Sand on highways changes friction and superelevation, increasing rollover and skid risks. This study explores how sand accumulation affects truck driving stability and predicts the critical threshold at which rollover may occur under different road conditions and load scenarios. This paper is based on Trucksim simulations of truck driving conditions on the Umal Highway’s sand-prone curved sections (with curve radii of 60/100/215/400 m) under sand accumulation. Combining simulation data and using Long Short-Term Memory (LSTM) neural network algorithms, it predicts the lateral load transfer ratio (LTR) of a six-axle truck on the test section. The LSTM algorithm outperformed others, with superior accuracy metrics (R2 = 0.99644, MAE = 0.0050118, MAPE = 0.00026711, RMSE = 0.0063982). Sand accumulation is classified into thin and thick stages. The thin stage primarily affects road friction, while the thick stage increases curve superelevation. When the sand just covers the asphalt pavement pores and the thickness of the sand is more than 166 mm or more, the loading quality of more than 25 tons six-axle trucks are more prone to rollover, when the rollover speed and the normal road state rollover speed compared to significantly lower, compared with the standard speed limit, and the magnitude of the drop even up to 33%. The impact of varying sand accumulation conditions on speed thresholds differs significantly. Failure to promptly adjust speed limits during sand accumulation events may lead to rollovers even when drivers adhere to standard limits. The findings provide critical guidance for sand-prone highway management, recommending adaptive variable speed limits based on real-time sand thickness and road conditions to mitigate desert-related safety risks.]]></description>
      <pubDate>Tue, 14 Apr 2026 16:59:47 GMT</pubDate>
      <guid>https://trid.trb.org/View/2686634</guid>
    </item>
    <item>
      <title>Ground LED flashing lights prevent children aged 9–12 wearing smartwatches from being distracted while crossing the street — An experiment in a real-road environment</title>
      <link>https://trid.trb.org/View/2681464</link>
      <description><![CDATA[Although many countries set the minimum age for children to cross streets alone at 9, the increasing popularity of smartwatches among children aged 9 to 12 has introduced new safety concerns. These wearable devices often distract young pedestrians, making them more susceptible to traffic-related hazards. To address this issue, the authors explored the use of ground-embedded flashing light emitting diode (LED) lights at pedestrian crossings—a relatively novel approach intended to recapture the attention of children distracted by their devices and to encourage safer crossing behavior. In this field-based study, the authors installed flashing LEDs at both signal-controlled and uncontrolled urban intersections. A total of 32 children (mean age = 10.35 years) participated in the experiment. Each child completed 8 crossing trials, which involved 2 types of intersections and 4 distinct distraction tasks. The 32 children recruited for the study were divided into two groups: one exposed to the LED-intervention condition, and the other assigned to the non-intervention (no-LED) condition, serving as the control group. The visual behavior of each child pedestrian while crossing was tracked using an eye-tracking system. The findings revealed that children in the LED-intervention group, compared to those in the no-LED condition, crossed the street approximately 14% faster, scanned for traffic 71.8% more often, and demonstrated an 8.4% higher visual sweep rate. Visualization of their gaze behavior showed broader and more dynamic visual search patterns when the ground LED lights were present, suggesting that the intervention successfully redirected the attention of distracted children toward the road environment. Further analysis showed that the LED lights were particularly effective for distraction types involving auditory tasks with preserved visual attention, such as talking on the phone or listening to stories. In contrast, the effect was less pronounced when children were engaged in visually or cognitively demanding tasks, such as looking at pictures or performing simple calculations. Additionally, when comparing intersection types, the intervention proved more effective at signalized intersections, showing significant improvements across all four distraction scenarios compared to unsignalized ones. In summary, the results suggest that installing ground flashing LED lights on both sides of crosswalks in urban intersections could help distracted pedestrians aged 9–12 cross streets more safely and independently. While the study highlights the behavioral benefits of the intervention in real-world conditions, further research is warranted to assess the feasibility of on-site implementation, as well as how such a system would perform under different traffic cultures and infrastructure settings, in order to support broader application of the findings.]]></description>
      <pubDate>Wed, 08 Apr 2026 15:32:50 GMT</pubDate>
      <guid>https://trid.trb.org/View/2681464</guid>
    </item>
    <item>
      <title>Leveraging Machine Learning and Artificial Intelligence to Improve Roadway Grip Sensing During Winter Weather</title>
      <link>https://trid.trb.org/View/2684250</link>
      <description><![CDATA[Road grip, or friction, is an important variable used to assess numerous implications of winter weather impacts on surface transportation infrastructure and operation. “Grip” represents how well a vehicle’s tires adhere to the road surface and can be a function of road surface temperature and road surface condition, among other variables. Moreover, grip influences vehicle handling, maneuverability, and stopping distance. Thus, grip can be used as a proxy to assess safety and mobility on roadways during adverse weather as well as to provide performance measures for transportation agencies about their winter maintenance operations. An important caveat is that grip observations can be temporally and spatially limited. The objective of this research was to model road grip during winter weather conditions to predict road grip where observations may not be available. This was accomplished using atmospheric and road-based observations in Colorado and Minnesota in the U.S., to deduce road grip conditions to develop state/location-specific grip machine-learning-based models. These algorithms can produce an estimate of grip at locations that are not already equipped with grip sensors. The prediction accuracy is improved when road state and precipitation information are available. Road weather observations—including air temperature, road surface temperature, dew point temperature, relative humidity, road surface condition, road surface state, and precipitation information—can be used to derive an accurate grip model. This framework may further leverage mobile and connected vehicle grip observations to advance grip modeling between fixed locations.]]></description>
      <pubDate>Thu, 26 Mar 2026 09:05:41 GMT</pubDate>
      <guid>https://trid.trb.org/View/2684250</guid>
    </item>
    <item>
      <title>Comparative analysis of the quality of local road repairs in the context of road traffic safety</title>
      <link>https://trid.trb.org/View/2666119</link>
      <description><![CDATA[The number of road accidents has increased significantly over the last decade. The main reasons for this phenomenon are excessive speed, alcohol and failure to give way. The technical condition of roads also has a major impact on road traffic safety, which directly affects the comfort of their use. In this context, it is necessary to ensure the highest possible level of quality of road sections being constructed and repairs of existing ones. Unfortunately, insufficient financial resources are a serious barrier to carrying out repair activities and regular maintenance work. The result is a constantly deteriorating condition of roads, which often leads to degradation of the road pavement structure and creates a real risk of road accidents. Another common phenomenon is carrying out repair works using lower quality materials or in a manner not adapted to the actual road conditions. This results in faster wear of the pavement being used and the need to carry out repairs at short intervals. The aim of this study is to assess the quality of repairs of local roads using comparative analysis. The subject of the research were identified road sections that underwent repairs over the last 18 years. Seven parameters affecting road traffic safety were assessed, and the results were compared with the assessment made in 2021. Based on the research, it was found that the quality of all analyzed parameters decreased except for the parameter "daytime driving" (increase by 0.1). The greatest regression was recorded for the parameters "roadside condition" (by 1.0) and "drainage condition" (by 0.7).]]></description>
      <pubDate>Mon, 23 Mar 2026 15:15:34 GMT</pubDate>
      <guid>https://trid.trb.org/View/2666119</guid>
    </item>
    <item>
      <title>The Application of Pavement Performance Models in Pavement Asset Management System for the Purpose of Improving the Structural Pavement Condition</title>
      <link>https://trid.trb.org/View/2665875</link>
      <description><![CDATA[Pavement degradation is a complex process influenced by several factors such as traffic loads, climatic conditions or the properties of the built-in materials. Degradation is a dynamic process that requires the application of pavement performance models and their regular updating. The article focuses on pavement performance models of variable parameters, their significance and application in the field of pavement asset management. The application of pavement performance models in the decision-making process and development of strategic road network repair plan helps to allocate financial resources efficiently and economically along with achieving satisfactory variable parameters for ensuring safety and driving comfort. This paper discusses the application and importance of pavement performance models, focusing on their benefits in optimizing road network maintenance and reducing the cost of road network management. As part of the research, experimental measurements were carried out at the University of Žilina campus aimed at determining the pavement performance models of the variable parameters of the experimental pavement section. The resulting degradation functions demonstrate the change of the variable parameters depending on the number of repetitions of the design axle load and determine the critical moments when the degradation starts to increase rapidly, which in practice means an increase in repair and maintenance costs and the solution becomes economically ineffective. The aim of this paper is to introduce the selected topic of pavement performance models, to present the degradation functions of variable pavement parameters determined by experiment and to demonstrate their applicability in practice.]]></description>
      <pubDate>Mon, 23 Mar 2026 15:15:33 GMT</pubDate>
      <guid>https://trid.trb.org/View/2665875</guid>
    </item>
    <item>
      <title>The stress resilient membrane (SRM bit) for concrete, paved and asphalt surfaces</title>
      <link>https://trid.trb.org/View/2675934</link>
      <description><![CDATA[The functionality of infrastructure and roads has an impact on road safety, the economy and people’s quality of life. The poor condition of roads in some places is due to a number of factors, including the high volume of traffic, ageing, lack of investment and extreme weather conditions in some places. However, particularly in the context of maintenance and/or repair, wrong decisions are often made in the chosen procedure. For example, due to economic considerations or political decisions, existing road structures are increasingly being rehabilitated or overbuilt with a new asphalt surface course in the course of replacing the top asphalt layer, regardless of the existing condition. However, new asphalt layers that are built over (old) cracked asphalt, concrete or paved surfaces often suffer from reflection cracks after a relatively short period of use, which are caused by the horizontal movements and thermal expansion of the underlying concrete or paved base. This effect is exacerbated by the existing traffic load. The resulting cracks in the asphalt surface layer then allow moisture/water to enter the structure and inevitably lead to an acceleration of crack propagation up to complete system failure. As a result, this process leads to traffic restrictions for road users and to premature and costly renewal measures.  One possible solution is the complete elastic decoupling of two otherwise incompatible layers (e.g. asphalt on concrete/paving etc.). A special stress-relieving and stress-resistant membrane (SRM-bit) based on a bituminous waterproofing mastic with a highly branched polymer matrix was developed for this purpose. This acts as a highly elastic, crack-bridging and water pressure-tight membrane over the entire service temperature range.  The special properties of the SRM-bit across the entire service temperature range were demonstrated in laboratory tests using physical and rheological analyses and dynamic and static tests on composite systems. The enormous elastic potential, the extreme adhesion and cohesion forces and self-healing effects were demonstrated. In addition, these results have already been validated in several construction projects.  Sustainable construction methods that are both resource-saving and economical are required to maintain the infrastructure. A newly developed stress-resistant membrane for asphalt, concrete and paved roads can be used for this purpose, which guarantees very good performance properties at low and high temperatures. Laboratory and practical results will be shown.]]></description>
      <pubDate>Thu, 12 Mar 2026 08:52:53 GMT</pubDate>
      <guid>https://trid.trb.org/View/2675934</guid>
    </item>
    <item>
      <title>Research on Automatic Recognition of Subgrade and Pavement Distress Based on Unmanned Aerial Vehicle Inspection and Deep Learning</title>
      <link>https://trid.trb.org/View/2613024</link>
      <description><![CDATA[The accurate identification and treatment of pavement and subgrade distress is of great importance to ensure traffic safety as highway mileage in China grows. In this study, pavement images were captured by the Road Condition Information Collecting System (CiCS), subgrade images were captured by an unmanned aerial vehicle (UAV), and pavement distress data set and subgrade distress data set were trained based on the You Only Look Once version 3 (YOLOv3) algorithm. The experimental results show that the YOLOv3 algorithm outperforms other algorithms in terms of precision, recall rate, and F1-score on different test sets, demonstrating its effectiveness and robustness in automatic recognition of pavement distress. The algorithm achieved a precision value of 89.63%, a recall rate of 48.52%, and an F1-score of 62.96% for subgrade distress, indicating potential ability in automatic recognition of subgrade images captured by UAV during inspection, which will greatly improve the inspection efficiency and decrease difficulty.]]></description>
      <pubDate>Fri, 20 Feb 2026 15:28:20 GMT</pubDate>
      <guid>https://trid.trb.org/View/2613024</guid>
    </item>
    <item>
      <title>Assessment of hydroplaning potential in coastal regions using roadway characteristics and related datasets</title>
      <link>https://trid.trb.org/View/2663101</link>
      <description><![CDATA[Hydroplaning is a critical pavement safety concern that occurs when a layer of water builds up between the vehicle's tires and the pavement surface, leading to a loss of traction and vehicle control. It is a significant contributor to wet-weather crashes and thereby poses a serious challenge to highway safety, especially for coastal regions where rainfall is more abundant and more frequent. Hydroplaning risk assessment fundamentally depends on the integration of multiple diverse datasets that reflect the interaction among crash occurrences, pavement conditions, and vehicle dynamics. These data items are typically recorded in different datasets maintained by various owners or agencies, each with their unique collection methods and standards. This research will develop data-driven likelihood models based on a verification check of the reliability of the important data variables, and a fusion of the available history data from diverse data sources to assess hydroplaning risks for coastal highways. The proposed research will also develop recommendations to be considered for roadway design and construction in association with wet-weather accident reduction procedures for transportation agencies.]]></description>
      <pubDate>Thu, 29 Jan 2026 17:13:08 GMT</pubDate>
      <guid>https://trid.trb.org/View/2663101</guid>
    </item>
    <item>
      <title>Literature overview of road marking performance with emphasis on application technique and used materials</title>
      <link>https://trid.trb.org/View/2627539</link>
      <description><![CDATA[Road markings represent an essential element of effective traffic management, serving as visual guidance for drivers and playing a key role in road traffic safety. The primary objective of this article is to provide a comprehensive overview of the most relevant previous research related to the performance of road markings, with a particular focus on their durability and skid resistance, depending on the application techniques and materials used. Utilizing the PRISMA methodology and the "Snowballing" method, the literature review encompassed scientific articles published in journals and conference proceedings. The articles were divided into two main groups according to their research focus: (1) articles dealing with the durability of road markings depending on the material and method of application (24 articles), and (2) articles addressing the skid resistance coefficient of road markings depending on the materials used (5 articles). The results of the analysed studies significantly contribute to the optimization of road marking maintenance; however, further research is required to verify and expand the proposed models. Future studies should consider model validation on a larger sample of roads from different climatic regions, as well as the inclusion of additional variables such as the quality of glass beads, type and condition of the road surface, salt application, incorporation of anti-skid particles, and similar factors. This would ensure greater applicability and accuracy of the models under varying conditions, ultimately contributing to the optimization of road marking maintenance and the enhancement of road traffic safety.]]></description>
      <pubDate>Tue, 27 Jan 2026 16:16:16 GMT</pubDate>
      <guid>https://trid.trb.org/View/2627539</guid>
    </item>
    <item>
      <title>Emergency Response and Access Mapping for Rural Navajo Communities </title>
      <link>https://trid.trb.org/View/2658056</link>
      <description><![CDATA[In the Navajo Nation Area, poorly maintained, unpaved, and seasonally hazardous road conditions in rural areas hinder timely response of emergency services. For example, in Crownpoint, heavy snowfall can make it difficult for ambulance services and firefighting vehicles to reach homes, as they must travel through unpaved or unmaintained roads to reach their destinations. Although current routing tools are able to locate the best route between two points, they do not contain pavement condition data or hazard data that would allow for the accurate determination of safe passage for emergency vehicles. Satellite images are also unable to show potholes, ruts, washouts, etc.; therefore, responders are forced to guess which is the best route based on their experience or try different routes until they find one that works. In many cases, this results in substantial delays, especially during severe weather when traditional navigation systems provide little guidance on actual road accessibility. A new platform is needed that has reliable and accessible data to help direct emergency responders to the safest route to the point of origin. Such a system would not only improve response time but also provide agencies with a standardized way to assess roadway risk during rapidly changing environmental conditions. This project will create a reliable, data driven, artificial intelligence (AI)-assisted Road Accessibility Index (RAI), and a geographic information services (GIS)-based routing dashboard utilizing Vialytics' smartphone-based road assessment capabilities, along with data on transportation, crashes, maintenance, and climate to provide real time accessibility ratings for each ten meter section of road within the Crownpoint area (150 miles total) and direct Emergency Medical Services, Fire and Law Enforcement departments towards the safest routes to travel to emergency locations. 
 ]]></description>
      <pubDate>Wed, 04 Feb 2026 19:20:18 GMT</pubDate>
      <guid>https://trid.trb.org/View/2658056</guid>
    </item>
    <item>
      <title>Automatic road damage recognition based on improved YOLOv11 with multi-scale feature extraction and fusion attention mechanism</title>
      <link>https://trid.trb.org/View/2611440</link>
      <description><![CDATA[Rapid urbanization and growing traffic volumes have increased the demand for efficient and accurate road damage detection to ensure traffic safety and optimize maintenance. Traditional manual and vehicle-mounted inspection methods are often inefficient, costly, and prone to error. Deep learning-based approaches have made progress but still face challenges in detecting small objects, handling complex backgrounds, and meeting real-time requirements due to high computational costs and limited generalization. This study proposes an improved road damage detection method based on YOLOv11, incorporating a Tiny Object Detection Layer for enhanced small object recognition through high-resolution and multi-scale feature fusion. A Global Attention Mechanism is integrated to emphasize critical regions and suppress background noise. Additionally, lightweight convolution modules (C3k2CrossConv and C3k2Ghost) optimize the network to reduce computational complexity and improve inference speed. Experimental results on the RDD2022 dataset show that the YOLOv11-ATL model achieves 3.2% and 3.1% gains in mAP@0.50 and mAP@0.50:0.95, respectively, demonstrating robust performance in complex environments while maintaining a favorable balance between accuracy and efficiency. Overall, the proposed approach offers a practical and effective solution for intelligent road damage detection, supporting urban infrastructure management and intelligent transportation systems.]]></description>
      <pubDate>Wed, 14 Jan 2026 17:40:49 GMT</pubDate>
      <guid>https://trid.trb.org/View/2611440</guid>
    </item>
    <item>
      <title>Continuous 3D Strain Imaging for Structural Health Monitoring of Pavements </title>
      <link>https://trid.trb.org/View/2646968</link>
      <description><![CDATA[This project proposes to advance road infrastructure monitoring by leveraging distributed fiber optic sensing (DFOS) technologies in conjunction with advanced visualization techniques. While typical assessment tools rely on surface measurements and back calculation methods to infer internal conditions, they cannot measure strains within the pavement layers directly. On the other hand, traditional localized sensors offer limited spatial coverage, missing critical information between sensing points. Embedding distributed fiber optic sensing sensors directly into pavement structures will potentially enable the acquisition of high-resolution, real-time distributed strain measurements across extended lengths, providing an unprecedented, comprehensive understanding of the infrastructure condition under traffic loads. Furthermore, the integration of distributed fiber optic sensing measurements with mapping tools will allow transportation engineers to readily identify potential damage areas and structural deficiencies, which can potentially lead to optimized maintenance scheduling, improved road safety, and reduced long-term infrastructure management costs for highway agencies. 

This project aims to develop methods and tools to advance road infrastructure monitoring by integrating fiber optic strain sensing with 3D visualization. To achieve this goal, laboratory testing of pavement specimens strategically instrumented with distributed fiber optic sensing while trafficked with simulated traffic loads will be conducted to generate detailed strain measurements. Key objectives include developing methods for referencing, acquiring, and processing real-time, distributed strain data from embedded fiber optic sensors to generate insightful maps capable of representing strain distributions and their evolution in response to traffic, environment, and distress. This will facilitate the early identification of structural deficiencies, ultimately supporting proactive maintenance planning for highway agencies.  

The project scope involves developing and validating a comprehensive monitoring and visualization framework. This includes optimizing data acquisition, creating algorithms for efficient data reduction and processing of continuous strain measurements, and designing interactive 3D visualization tools. Laboratory validation of the techniques will be conducted, with the goal of future field testing on actual test sections to demonstrate the practical applicability and benefits of the developed system for highway agencies. ]]></description>
      <pubDate>Tue, 06 Jan 2026 17:23:14 GMT</pubDate>
      <guid>https://trid.trb.org/View/2646968</guid>
    </item>
    <item>
      <title>Impact of Pavement and Weather Conditions on Traffic Speed at Sharp Horizontal Curves  </title>
      <link>https://trid.trb.org/View/2646943</link>
      <description><![CDATA[Lane departure crashes on sharp horizontal curves are a major safety concern on both highways and freeways, accounting for a disproportionately high number of fatal and severe injury crashes. Research has shown that these crashes are often linked to speeds relative to curve geometry. While geometric design factors like curve radius and superelevation have been well studied, less attention has been given to how pavement and weather conditions influence traffic speed on these elements. Particularly, current safety models do not fully account for the effects of pavement surface conditions, such as friction, roughness, and texture, or adverse weather elements like precipitation, temperature drops, and reduced visibility. While the impact of factors like road curvature effects on traffic speed have been studied, current models often fail to integrate the complex interaction of pavement conditions and weather data in predicting traffic speeds. This results in inaccurate speed predictions, which can compromise safety and infrastructure planning. Without comprehensive, data-driven models, interventions such as speed limits, signage, or road maintenance are often poorly targeted, leading to higher risks of crashes, congestion, and inefficient resource allocation. The motivation for this project is to develop a predictive model that integrates pavement conditions, weather effects, and road geometry to estimate traffic speed at horizontal curves. This will provide safer roads by enabling better traffic management, targeted infrastructure improvements, and more efficient interventions. ]]></description>
      <pubDate>Mon, 05 Jan 2026 23:07:35 GMT</pubDate>
      <guid>https://trid.trb.org/View/2646943</guid>
    </item>
    <item>
      <title>Assessing Pavement Conditions Impact on Traffic Crashes: An Interpretable Machine-Learning Approach to Identify Crash Risk Factors and Performance Thresholds</title>
      <link>https://trid.trb.org/View/2607835</link>
      <description><![CDATA[Pavement surface condition may have a significant impact on traffic accidents, but its influencing mechanisms remain unclear, and safety-oriented maintenance thresholds are still lacking. To address these gaps, this study develops a highway crash regression model by comparing generalized linear models with tree-based machine learning (ML) approaches to establish the relationship between various factors and crash counts. An interpretability algorithm is employed to examine the combined effects of pavement, traffic, and meteorological conditions, with a particular focus on pavement-related factors. Minimum pavement performance requirements for safety considerations under varying traffic levels are then established, providing guidance for safety-oriented maintenance decision-making. Results reveal that annual average daily traffic (AADT) has the greatest impact, with higher traffic volumes correlating with increased crash counts. Additional risk factors include a higher proportion of trucks, bridge presence, frequent rainfall, and road ages exceeding ten years. Poor skid resistance, excessive roughness, and deep rutting detrimentally affect safety, particularly under high traffic volumes, whereas transverse cracks may reduce crashes by promoting heightened driver caution. For high-AADT roadways (≥30,000), this study identifies minimum performance thresholds of 40 for the side-way force coefficient (SFC), 2  m/km for the international roughness index (IRI), and 10 mm for the rutting depth (RD), whereas lower AADT levels do not necessitate specific requirements. These findings enhance the understanding of pavement-related crash risks and provide actionable insights for developing safety-oriented maintenance planning.]]></description>
      <pubDate>Mon, 15 Dec 2025 10:34:09 GMT</pubDate>
      <guid>https://trid.trb.org/View/2607835</guid>
    </item>
    <item>
      <title>Artificial Intelligence and Mobile Phone-Based Pavement Marking Condition Assessment and Litter Identification</title>
      <link>https://trid.trb.org/View/2626210</link>
      <description><![CDATA[Regular inspection of transportation assets is essential to ensure pavement markings and pavements remain in good, clean, and safe condition. Our previous MPC-funded project (Report No. MPC-668) demonstrated the strong potential of using artificial intelligence (AI) and mobile phone imagery to identify various transportation assets. However, that initial effort was limited in scale, using only ~1,000 images for training and validation. Building upon this foundation, the present project focuses on two targeted assets: pavement marking issues and roadside litter, while expanding the capability of the previously developed AI packages. In this study, the dataset increases to over 6,000 images for each asset type. Using the You Only Look Once (YOLO) deep learning architecture, two detection models were trained and achieved strong accuracy metrics, with F1 scores of 0.88 for pavement marking issues and 0.84 for roadside litter. In addition, counting and geolocation models are developed to quantify detected objects within a road section or video clip and to determine their precise locations by integrating data from a phone-based global positioning system (GPS) tracker. The geolocation model demonstrates high spatial accuracy, achieving an average positional error of only 0.27 meters. To facilitate practical application, an interactive mapping interface is implemented to visualize the geolocation, object class, inspection time, and cropped image of each identified object. This interface enables clear and intuitive assessments of pavement conditions, specifically faded markings and roadside litter. Overall, this project enhances our prior work by extending capabilities in detection, counting, geolocation, and visualization, which supports regular asset inspection, informs maintenance planning, and ultimately improves roadway safety.]]></description>
      <pubDate>Thu, 11 Dec 2025 09:44:50 GMT</pubDate>
      <guid>https://trid.trb.org/View/2626210</guid>
    </item>
  </channel>
</rss>