<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>Standardized Framework for Winter Weather Road Condition Indices</title>
      <link>https://trid.trb.org/View/2693715</link>
      <description><![CDATA[State and local agencies across the United States have developed winter weather road condition indices (WWRCIs) to support decisions related to roadway operations, public information, road closures, and winter maintenance responses based on prevailing conditions. However, the absence of a standardized national framework for WWRCIs has resulted in substantial variation in how road conditions are defined, assessed, and communicated. These inconsistencies can create confusion for travelers and limit the ability of transportation agencies to compare performance, share best practices, and benchmark winter operations effectively. The objective of this project was to develop a standardized national framework for WWRCIs that reflects both operational realities and safety impacts across diverse climatic and geographic contexts in the United States. The framework is informed by a comprehensive assessment of existing practices, stakeholder input, and advances in data availability, including traditional weather and roadway sensors as well as emerging connected and autonomous vehicle (CAV) data sources. By promoting consistent definitions, indicators, and measurement principles, the proposed framework aims to advance the accuracy, reliability, and usefulness of winter road condition information provided to transportation agencies, policymakers, and the traveling public. Ultimately, this effort supports improved driver safety, reduced crashes and congestion, and more effective and coordinated winter weather response strategies nationwide.]]></description>
      <pubDate>Fri, 17 Apr 2026 08:55:48 GMT</pubDate>
      <guid>https://trid.trb.org/View/2693715</guid>
    </item>
    <item>
      <title>A Novel Low-Cost Double U-Net Model for Predicting Traffic Sign Retro-Intensity from Camera Data</title>
      <link>https://trid.trb.org/View/2691791</link>
      <description><![CDATA[Retroreflectivity is essential for the visibility of transportation infrastructure, ensuring road safety, especially under low-light conditions. Traditional methods for measuring retroreflectivity, such as nighttime visual inspections and retroreflectometer measurements, are labor-intensive, subjective, and pose safety risks. With the introduction of lidar technology, traffic sign retroreflectivity can be assessed more efficiently, as lidar-derived reflectivity values demonstrate a strong linear correlation with retroreflectivity. This study leverages a lidar device to propose a Double U-Net framework for predicting pixel-level reflectivity from daytime red, green, blue (RGB) images, providing a localized and accurate prediction. To train the Double U-Net model, a structured data set of over 7,600 images of transportation infrastructure was created, incorporating lidar-derived depth and reflectivity data. Given the sparsity of low-resolution lidar point clouds, linear interpolation was applied to generate pixel-level depth and reflectivity images. The proposed Double U-Net framework employs a two-stage architecture, where depth is predicted from cropped images in the first stage, and then combined with the original image and class embeddings in the second stage to generate pixel-level reflectivity predictions. A weighted loss function balances depth and reflectivity errors, enhancing prediction accuracy and robustness. The model achieved a median mean square error (MSE) of 0.0162 with interpolated data, 0.02233 with raw data, a median structural similarity index measure (SSIM) of 0.5413, and a Mann-Whitney U Test alignment of 58.2% with raw reflectivity data at a 0.001 significance level. The model effectively captures localized defects on traffic signs, providing a more detailed analysis compared with traditional methods.]]></description>
      <pubDate>Wed, 15 Apr 2026 11:31:04 GMT</pubDate>
      <guid>https://trid.trb.org/View/2691791</guid>
    </item>
    <item>
      <title>Prevalence and predictors of driving under the influence of alcohol in Switzerland: A mandatory roadside survey</title>
      <link>https://trid.trb.org/View/2680644</link>
      <description><![CDATA[This nationwide roadside survey aimed to determine the prevalence of driving under the influence of alcohol (DUI) among car drivers in Switzerland and identify associated factors. Adhering to the European study Baseline guidelines, the survey was stratified by road type, time window, and language region. Fourteen police corps conducted controls across areas representing 59% of the Swiss population. Locations were determined in randomly selected municipalities. Drivers were stopped randomly or via road blockage, and all were tested for alcohol. Logistic regression models were used to analyze predictors of DUI, both in terms of driving with a detectable alcohol concentration [>0 milligram of alcohol per liter of breath (mg/l)] and driving with concentrations above the legal limit (0.25 mg/l for most drivers; 0.05 mg/l for specific groups, e.g., novice drivers). The models accounted for potential influencing factors, and data were weighted to ensure representativeness. Of 4,847 drivers tested, 3.6% had detectable alcohol levels, and 0.4% exceeded the legal limit. Male drivers, individuals aged 31 years or older, and those departing from restaurants, bars, or parties had a higher prevalence of driving with detectable alcohol levels or levels above the legal limit. Drivers in the French-speaking region were more likely to have detectable alcohol concentrations than those in the German-speaking region, although no significant regional difference was found for exceeding the legal limit. The prevalences of driving with a detectable alcohol concentration and of exceeding the alcohol limit were higher at night, on weekends, and tended to be higher on urban roads compared to rural roads or motorways. Exceeding the limit was more common in fine weather than in cloudy or rainy conditions. Switzerland has a relatively low prevalence of exceeding the alcohol limit compared to other European countries. However, male gender, older age, nighttime and weekend driving, and social drinking contexts increased DUI risk. Continued monitoring and targeted interventions addressing high-risk groups, locations, and times are essential for enhancing road safety.]]></description>
      <pubDate>Wed, 15 Apr 2026 10:29:29 GMT</pubDate>
      <guid>https://trid.trb.org/View/2680644</guid>
    </item>
    <item>
      <title>Research on nighttime road visibility monitoring based on video images</title>
      <link>https://trid.trb.org/View/2680643</link>
      <description><![CDATA[Road traffic accidents have become a serious social problem, with a significant proportion of accidents caused by insufficient visibility on roads at night. Therefore, nighttime road visibility detection based on video images has become one of the difficulties and a key issue in domestic and international research. This study analyzes the importance of nighttime road visibility monitoring, introduces the structure, working principle, and monitoring method of a video image nighttime visibility monitoring system, and proposes a nighttime road visibility monitoring method based on video images. Based on the characteristics of nighttime images, an improved dark channel prior method was adopted to calculate the nighttime road visibility. This method mainly includes eight steps: video image acquisition, image grayscale processing, calculation of image average variance, image average gradient, drawing grayscale histograms, image enhancement based on the calculated values, calculation of transmittance, and calculation of visibility. The experimental results show that the proposed night road visibility monitoring method based on video images can effectively realize real-time monitoring of night road visibility, effectively overcome the inherent defects of traditional methods, and the constructed night visibility monitoring framework can realize high-precision visibility calculation, and has broad application prospects. Through adaptive threshold and adaptive filtering technology, the improved dark channel algorithm has shown competitive advantages in both image quality index and practical application effect, especially in noise suppression and edge preservation. However, under extreme illumination conditions, the algorithm still has room for improvement in the processing of the strong light source region, and the dark channel prior may lead to bias in the transmission estimation.]]></description>
      <pubDate>Wed, 15 Apr 2026 10:29:29 GMT</pubDate>
      <guid>https://trid.trb.org/View/2680643</guid>
    </item>
    <item>
      <title>Analyzing extreme multi-vehicle rear-end collision risks in adverse weather through Generalized Pareto Regression Trees</title>
      <link>https://trid.trb.org/View/2686646</link>
      <description><![CDATA[The study seeks to explore rear-end collision risks in multi-vehicle car-following scenarios under adverse weather conditions by proposing an integrated framework. The integrated framework is applied to a case study of three-vehicle car-following scenario in Norway without loss of generality. For identifying car-following groups with extreme collision risks, the collision risk of each group in the raw dataset is evaluated using an extended probabilistic driving risk field. Quantitative collision risks are analyzed to fit the Generalized Pareto distribution, and high-risk scenarios screened via mean residual life plots and threshold stability plots. To determine risk-contributing factors, Generalized Pareto Regression Trees (GPRT) are constructed to pinpoint significant influences on rear-end collision risks. By integrating the classification and regression trees with extreme value theory, the GPRT discards data assumptions and covariate continuity requirements of most extreme value analysis (e.g., extreme quantile regression). Moreover, the GPRT not only identifies the hierarchical structure of variables affecting rear-end collision risks but also determines risk-impact thresholds for covariates, offering superior interpretability and engineering applicability. The results show that revealed risks conform well to the Generalized Pareto distribution, allowing for the formulating Generalized Pareto regression trees. Compared to the Generalized Additive Model (GAM) and Negative Binomial Regression (NBR) methods, the GPRT approach demonstrates superior performance in balancing risk fitting accuracy and model complexity. Vehicle speeds, weights, and headways emerge as critical factors for collision risks under clear, rainy, and snowy conditions. As weather conditions deteriorate from clear to rainy or snowy, the influence of vehicle speed and weight diminishes, while the influence of headway and road surface conditions becomes more pronounced. Collision risks are high on sunny days, regardless of whether the middle vehicles of three-vehicle groups are light or heavy vehicles. The integrated evaluation framework developed in this study provides a tool for car-following safety assessment under extreme weather conditions.]]></description>
      <pubDate>Wed, 15 Apr 2026 10:29:29 GMT</pubDate>
      <guid>https://trid.trb.org/View/2686646</guid>
    </item>
    <item>
      <title>Assessment of Truck Parking Demand and Safety During Normal and Severe Weather Conditions in Nebraska</title>
      <link>https://trid.trb.org/View/2690988</link>
      <description><![CDATA[This project examined truck parking capacity, demand, and utilization patterns along I-80 in Nebraska. The objectives were to (1) document the capacity of public and private truck parking facilities along I-80, (2) analyze spatial and temporal trends in parking demand, (3) develop models to predict occupancy at parking facilities, (4) identify clusters of undesignated parking during inclement weather, and (5) assess whether truck parking shortages contribute to truck-involved crashes. Within a one-mile buffer of I-80, 21 public facilities and 49 private facilities were identified. The spatiotemporal analysis of these public and private truck parking facilities using the National Agriculture Imagery Program and Google Earth Imagery data between 2010 and 2022 showed a higher parking occupancy rate at private facilities, with several private facilities experiencing 100% occupancy or higher. Public facilities near Omaha had a consistently high occupancy rate. To enable the Nebraska Department of Transportation (NDOT) to estimate the occupancy rate of a facility, public or private, expansion factors were first developed using the 2022 American Transportation Research Institute (ATRI) Global Positioning System (GPS) data. The number of trucks parked at public and private facilities was then estimated by multiplying the number of GPS-identified trucks that remained stationary for more than 60 minutes by the corresponding expansion factor. Building on these estimates, a hybrid Bayesian modeling framework was developed to predict occupancy. Parking facilities were clustered based on their inter-facility distances, resulting in groups containing either single or multiple facilities. Accordingly, a dynamic time series model was developed for individual facilities, while a panel model with time fixed effects and distance-based spatial lags was developed for multi-facility clusters. Results indicate that lagged occupancy is the strongest predictor, with spatial effects also significant in the panel model. Both models achieved strong predictive performance. During inclement weather, trucks were found to park in four locations: facility entry and exit areas, off-road sites, ramps, and shoulders. Lastly, statistical analysis showed no significant relationship between truck-involved crashes and parking shortages.]]></description>
      <pubDate>Wed, 15 Apr 2026 10:28:13 GMT</pubDate>
      <guid>https://trid.trb.org/View/2690988</guid>
    </item>
    <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>A Study on the Relationship between Impact Conditions and Head Injury Criterion (HIC) in Powered-Two-Wheeler to Car Crashes</title>
      <link>https://trid.trb.org/View/2692113</link>
      <description><![CDATA[Road Traffic crash statistics highlight the importance of reducing fatalities among Powered-Two-Wheeler (PTW) riders, and suggest the necessity of a robust method to evaluate PTW crashworthiness performance. The objective of this study is to clarify the relationship between impact conditions and the Head Injury Criterion (HIC) to establish a fundamental basis for determining representative crash configurations for safety.A total of 1,272 PTW-front to car-side impact simulations were conducted by using production car and PTW models. HIC was used as a metric indicating likelihood of head injury. Velocities, impact angle, and impact locations were varied to create response surfaces. The surfaces were evaluated in terms of their accuracy in identifying the representative impact conditions. In addition, head trajectories were analyzed to clarify the kinematics until head impact.The Finite Element (FE) simulations produced the following findings.These findings establish a fundamental basis for determining the representative crash scenario through an analysis of the relationship between crash conditions and the HIC.]]></description>
      <pubDate>Tue, 14 Apr 2026 15:11:24 GMT</pubDate>
      <guid>https://trid.trb.org/View/2692113</guid>
    </item>
    <item>
      <title>Safety-Centered Scenario Generation for Autonomous Vehicles</title>
      <link>https://trid.trb.org/View/2692101</link>
      <description><![CDATA[This paper presents a scenario generation framework that creates diverse, parametrized, and safety-critical driving situations to validate the safety features of autonomous vehicles in simulation [1]. By modeling factors such as road geometry, traffic participants, environmental conditions, and perception uncertainties, the framework enables repeatable and scalable testing of safety mechanisms, including emergency braking, evasive maneuvers, and vulnerable road user protection. The framework supports both regulatory and edge case scenarios, mapped to hazards and safety goals derived from Hazard Analysis and Risk Assessment (HARA), ensuring traceability to ISO 26262 functional safety requirements and performance limitations. The output from these simulations provides quantitative safety metrics such as time-to-collision, minimum distance, braking and steering performance, and residual collision severity. These metrics enable the systematic evaluation of evasive maneuvering as a safety feature, while highlighting system limitations and edgecase vulnerabilities. Integration of scenario-based simulation with safety engineering principles offers accelerated validation cycles, improved test coverage at reduced cost, and stronger evidence for regulatory and stakeholder confidence.]]></description>
      <pubDate>Tue, 14 Apr 2026 15:11:24 GMT</pubDate>
      <guid>https://trid.trb.org/View/2692101</guid>
    </item>
    <item>
      <title>A Cloud-Vehicle Integrated Closed-Loop Testing Framework for Intelligent Chassis</title>
      <link>https://trid.trb.org/View/2691841</link>
      <description><![CDATA[Vehicle system testing serves as a critical phase in obtaining road certification for prototype vehicles. While direct road testing with physical vehicles yields the most authentic data, this approach entails significant costs, challenges in reproducing extreme scenarios, and inherent safety risks. In contrast, virtual vehicle-based testing technologies represent advanced simulation methodologies for enhancing development efficiency and quality, effectively mitigating risks associated with complex real-world operating conditions and hazardous physical testing. However, virtual vehicle models often rely on idealized parameters, limiting their ability to reflect real-world dynamics and resulting in lower credibility of test outcomes. Furthermore, as evidenced in current mainstream virtual testing software, environmental simulations predominantly remain confined to the visual domain, with limited direct interaction between dynamic environmental changes and virtual vehicle responses. To address these limitations, this study proposes a novel testing framework leveraging vehicle-cloud integration technology, which combines the authenticity of physical testing with the flexibility of virtual simulation. The proposed system is validated through an AEB (Automatic Emergency Braking) function activation test. Experimental results demonstrate real-time data interoperability between physical and virtual vehicles, achieving a 89% accuracy rate in synchronizing virtual scenario velocities with real-world speeds. This approach enables safe and efficient preliminary testing, providing robust data support for subsequent physical validation and significantly lowers the overall testing cycle.]]></description>
      <pubDate>Tue, 14 Apr 2026 15:11:21 GMT</pubDate>
      <guid>https://trid.trb.org/View/2691841</guid>
    </item>
    <item>
      <title>Section-Based Crash Risk Analysis Integrating the Effect of Traffic States and Road Geometry</title>
      <link>https://trid.trb.org/View/2686148</link>
      <description><![CDATA[Highway collisions are influenced by a variety of factors, including dynamic traffic conditions and road geometry. A comprehensive understanding of how these factors specifically affect crash risk is essential for enhancing traffic safety. While previous studies have examined the relationship between traffic conditions and collision risk, as well as the influence of road geometry, limited attention has been given to analyses that consider both dimensions simultaneously. The configuration of road sections plays a critical role in vehicle behaviour and, consequently, in collision risk. This study introduces a section-based crash risk analysis framework to investigate the interplay between traffic states and crash likelihood, with a particular focus on merging and diverging areas. Traffic states were classified using upstream and downstream detector speeds. Specifically, we analyse the impact of speed differences between upstream and downstream traffic, along with the influence of ramp flow on collision risk across various geometric configurations. Crash risk was quantified using crash occurrence (CR) and the potential crash occurrence rate (PCR). The relationships between traffic states and crash risk were modelled using polynomial and segmented regression. The results reveal that diverging sections exhibit the highest collision risk, especially under conditions of pronounced speed disparity, regardless of whether traffic is free-flowing or congested. Moreover, the findings indicate a sharp increase in crash risk when the ramp-to-mainline flow ratio exceeds a critical threshold. These insights underscore the necessity of targeted traffic management strategies and optimized road design to mitigate high-risk scenarios. They also emphasize the importance of future research that integrates both geometric and dynamic traffic characteristics in modelling collision risk.]]></description>
      <pubDate>Tue, 14 Apr 2026 14:31:58 GMT</pubDate>
      <guid>https://trid.trb.org/View/2686148</guid>
    </item>
    <item>
      <title>Exploring the Safety Impacts of Pavement Friction Using Continuous Pavement Friction Measurement Data with Correlated Random Parameters Negative Binomial Models</title>
      <link>https://trid.trb.org/View/2658046</link>
      <description><![CDATA[Maintaining adequate pavement friction is critical for reducing skidding-related crash risks and ensuring roadway safety for all users. Continuous pavement friction measurement (CPFM) has become a proven approach to enhancing the understanding of roadway safety performance. This study investigated the impacts of pavement friction profiles and related pavement features on crash frequency, using CPFM data collected in 2023 across more than 3,447 lane-kilometers (2,142 lane-miles) of state roads in the Tampa Bay region of Florida. The surveyed roadways were divided into 0.16 km (0.1 mile) segments, each matched with corresponding pavement conditions, roadway geometry, traffic characteristics, and crash data from 2018 to 2020. Random parameter negative binomial (RPNB) and correlated RPNB models were employed to develop safety performance functions (SPFs) across 12 population groups, accounting for variations in crash, area, and pavement types. Crash modification functions (CMFs) were subsequently derived to quantify the effects of pavement friction, macrotexture, and other pavement characteristics on crash occurrences. The results indicate that higher levels of pavement friction and macrotexture are generally associated with reduced crash frequencies. However, substantial spatial variability in friction and macrotexture tends to increase crash frequencies in specific scenarios. Additional pavement features such as roughness, rutting, and surface cracking were also found to significantly affect crash outcomes. Based on the modeling results, investigatory levels (ILs) were proposed to define friction demand thresholds and trigger safety review. The findings, including the developed SPFs, CMFs, and ILs, offer valuable insights for data-driven pavement safety management and proactive roadway maintenance planning.]]></description>
      <pubDate>Mon, 13 Apr 2026 09:40:12 GMT</pubDate>
      <guid>https://trid.trb.org/View/2658046</guid>
    </item>
    <item>
      <title>Enabling Next-Generation Safe, Efficient and Reliable Traffic Signal Management via Advanced Sensing and Foundation Models</title>
      <link>https://trid.trb.org/View/2691670</link>
      <description><![CDATA[Urban traffic signal management systems often rely on outdated techniques and strategies that fail to adapt to dynamic roadway conditions, leading to safety concerns, congestion, and access issues for road users. In addition, current signal optimization approaches rarely consider energy efficiency as the main objective. This research proposes a next-generation safe, efficient and reliable traffic signal control framework powered by advanced roadside sensing and foundation models, specifically Visual Language Models (VLMs) and Multi-Modal Large Language Models (MMLLMs). By integrating high-definition cameras, LiDAR, and real-time data analytics, the system will accurately detect multimodal traffic flows, predict future traffic conditions, and optimize signal phase and timings to enhance mobility while minimizing energy consumption. The framework will be validated through a case study at the Riverside Smart Intersection testbed, leveraging real-world data and co-simulation environments.]]></description>
      <pubDate>Sun, 12 Apr 2026 23:42:56 GMT</pubDate>
      <guid>https://trid.trb.org/View/2691670</guid>
    </item>
    <item>
      <title>Optimizing External Human-Machine Interfaces (eHMIs) Designs in Autonomous Vehicles to Improve Communication with Drivers and Bicyclists</title>
      <link>https://trid.trb.org/View/2691668</link>
      <description><![CDATA[Autonomous Vehicles (AVs) will transform road safety and efficiency in the years to come, but achieving this requires large-scale deployment, trust, and understanding from all human road users, including drivers and bicyclists. External Human-Machine Interfaces (eHMIs) are becoming a crucial part of the process, enabling intuitive communication between AVs and other road users. This project aims to develop, assess, and optimize the concept of eHMIs to foster positive perceptions, build trust, and ensure safe interactions in mixed traffic scenarios. This study will involve a test of about 40 participants who will interact with AVs fitted with various eHMI prototypes under controlled conditions using driving and bicycle simulators. Behavioral metrics like the perception-reaction time (PRT), the perceived level of comfort, and the perceived level of trust, as well as transportation metrics like travel time, intersection clearance time, and near-miss incidents, will be assessed for different designs for the eHMI, including visual-based (LED Displays, Symbolic Messages, Color-coded Signals, Animated Indicators, etc.) and multimodal designs. Longitudinal experiments will measure the impact of acclimatization and determine the best eHMI setups, followed by field tests under realistic conditions for verification. User-focused optimization tools will also be designed to adapt enhanced eHMI setups to various demands and scenarios. Expected outcomes will include best-in-class eHMI designs for increased road safety, operational efficiency, and user confidence, providing valuable guidance for city planners, policymakers, and AV manufacturers.]]></description>
      <pubDate>Sun, 12 Apr 2026 23:39:01 GMT</pubDate>
      <guid>https://trid.trb.org/View/2691668</guid>
    </item>
    <item>
      <title>Machine Vision Toolkit for Automated Fleet Composition Assessment and Reporting</title>
      <link>https://trid.trb.org/View/2691665</link>
      <description><![CDATA[State Departments of Transportation (DOTs) and Metropolitan Planning Organizations (MPOs) employ fleet composition data (e.g., passenger vehicles, single-unit trucks, and combination trucks) in a variety of planning, economic, roadway performance, and safety applications. Accurate fleet composition data is essential for pavement management, safety analysis, and fuel consumption modeling. However, traditional methods are labor-intensive, costly, and often lack the temporal or spatial resolution required to capture variations between freeways, arterials, and managed lanes vs. general-purpose lanes. Using machine vision tools to quickly, efficiently, and accurately capture on-road percentages of light-duty vehicle, light-duty truck, medium-duty truck, and a variety of heavy-duty truck classifications will enhance analytical and modeling accuracy and reduce state DOT data management costs. Building upon prior National Center for Sustainable Transportation (NCST) research that developed machine vision algorithms for vehicle identification, this project will package those research findings into a deployable, open-source Automated Fleet Classification Toolkit for practitioners and researchers. The research team will develop and release comprehensive Standard Operating Procedures (SOPs) and software tools allowing agencies to convert standard roadside or overpass video feeds into high-resolution fleet composition data. The toolkit will utilize advanced object detection (e.g., YOLO architectures) to automate the identification of vehicle classes (aligning with FHWA 13-category schemes where possible) and propulsion types based on visual vehicle features. The system is designed to distinguish traffic conditions on complex roadway geometries, allowing users to generate separate classification profiles for managed lanes vs. general-purpose lanes, and separating freeway mainlines from adjacent arterial service roads. The project focuses on technology transfer: providing the "how-to" manuals, open-source code, and data processing protocols so that State DOTs, consultants, university partners and research institutes can replicate the data collection and extraction without relying on proprietary "black box" services.]]></description>
      <pubDate>Sun, 12 Apr 2026 23:29:28 GMT</pubDate>
      <guid>https://trid.trb.org/View/2691665</guid>
    </item>
  </channel>
</rss>