<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>Detection and Susceptibility Mapping of Landslide Using Multi-Temporal Lidar Digital Elevation Models: Case Study of Prince George’s County, Maryland</title>
      <link>https://trid.trb.org/View/2697858</link>
      <description><![CDATA[Landslides are among the most destructive natural hazards, particularly in regions with varied terrain, geomorphologic, and climatic characteristics. This study is focused on Prince George’s County, Maryland, one of the most landslide-prone areas in the state, with the highest number of recorded landslides in Maryland’s inventory. A remote sensing-based approach using high-resolution lidar digital elevation models (DEMs) is presented for detecting and mapping landslide-prone areas. Datasets were acquired for the years 2014, 2018, and 2020, to help study temporal changes in elevation. The methodology integrates DEM preprocessing, geomorphometric analysis, and spatial overlay within a geographic information system (GIS) environment. Key terrain factors, including slope, aspect, curvature, and DEM of difference (DoD) were derived to characterize topographic instability. Raster-based classification was used in ArcGIS Pro to identify historical and potential landslide zones. Buffer and overlay operations along critical highway corridors were included. Detected zones were categorized as stable, upward, or downward displacements caused by various factors and based on the relative vertical movement of the land surface. Validation was conducted through comparison with historical landslide inventories, overlaid on all causative geomorphometric factors, as well as using reclassification methods proposed in previous work. The resulting landslide susceptibility map provides a detailed spatial representation of terrain deformation across the study area over the years, offering valuable insights for land-use planning, infrastructure development, and hazard mitigation. This research demonstrates the effectiveness of lidar-integrated geospatial analysis for regional-scale landslide detection and risk mapping.]]></description>
      <pubDate>Sat, 02 May 2026 15:47:05 GMT</pubDate>
      <guid>https://trid.trb.org/View/2697858</guid>
    </item>
    <item>
      <title>Federal-Industry Waterway Governance Mapping</title>
      <link>https://trid.trb.org/View/2698370</link>
      <description><![CDATA[This project will produce the first comprehensive governance map of the U.S. inland waterway system, documenting how federal agencies, waterway commissions, port authorities, operators, industry associations, and advisory bodies exercise authority, coordinate responsibilities, and influence decisions across planning, operations, maintenance, and emergency response. While the inland waterway system depends on a complex interplay of federal ownership, federally authorized navigation channels, industry-operated vessels, federally maintained locks and dams, state commissions, port authorities, cooperative working groups, and advisory committees, there is currently no resource that synthesizes this institutional architecture into a clear, accessible structure. The research will analyze agency documentation, statutory authorities, standing committee structures, and operational guidance, complemented by targeted interviews with practitioners, to clarify how decisions flow through the system and how organizations interact across routine and non-routine conditions. The final product will provide a governance map and a narrative analysis that identifies gaps, redundancies, and friction points in the institutional landscape. This work will support planners, policymakers, and operators and offer a foundational understanding of how governance arrangements shape reliability, resilience, and system performance.]]></description>
      <pubDate>Fri, 01 May 2026 19:58:47 GMT</pubDate>
      <guid>https://trid.trb.org/View/2698370</guid>
    </item>
    <item>
      <title>MS-SLAM: Multiple Input Multiple Output Synthetic Aperture Radar Simultaneous Localization and Mapping</title>
      <link>https://trid.trb.org/View/2659149</link>
      <description><![CDATA[In this paper we propose a radar-only simultaneous localization and mapping algorithm based on multiple input multiple output synthetic aperture radar images. The algorithm distinguishes itself from others by depending only on radar data for generating synthetic aperture radar images for estimating traversed trajectory and building a visual representation. In our algorithm, ego-velocity (estimated using only radar data) is used for generating synthetic aperture radar images. The generated radar images are used for rotation estimation in the odometry step as well as for place recognition by exploiting the Fourier-Radon image registration approach. After the trajectory is optimized, we combine coherent and incoherent processing over the radar data for generating a map of the traversed area. The proposed concept was evaluated over multiple sequences comprising heterogeneous and dynamic environments. The results show high performance of the algorithm in terms of place recognition, attaining a balanced f-score in the range of 0.86–0.96. Moreover, the algorithm also achieves good results in terms of simultaneous localization and mapping. For example, it achieves an absolute trajectory error of 0.11 m for a trajectory of length 340 m, and 0.43 m for a trajectory of length 1092 m. Finally, we also include a case study in which we show the capability of the radar-only localization and mapping solution in operating under scenarios that are challenging for global navigation satellite systems.]]></description>
      <pubDate>Wed, 29 Apr 2026 09:10:07 GMT</pubDate>
      <guid>https://trid.trb.org/View/2659149</guid>
    </item>
    <item>
      <title>Systematic identification and analysis of map-matching anomalies in road network models for urban cycling</title>
      <link>https://trid.trb.org/View/2647043</link>
      <description><![CDATA[OpenStreetMap (OSM) is now an important data source for many mobility services. In particular, the OSM road network model is often used by cycling applications and studies. A very common operation with cycling data is map-matching, where the GPS traces of cycling trips are matched against the road network model. However, cyclists can take many unconventional paths that do not always match the official road network model. This fuzziness can severely compromise the ability of map-matching algorithms to produce valuable results. In this work, we introduce the concept of map-matching anomaly as a systematic mismatch between cycling traces and the road network data model to which the traces are expected to be matched. Contrary to sporadic map-matching errors, anomalies will recurrently occur for similar traces and will therefore accumulate at specific locations. This paper proposes a methodology to support the systematic and large-scale identification of map-matching anomalies in urban environments and discusses how knowledge about these anomalies can help cities uncover novel and actionable insights about cycling behaviour. The proposed methodology achieved 84% precision in identifying locations prone to map-matching anomalies. We identified several cases where the OSM road network was incorrect or incomplete. We also identified several locations where a deeper intervention is needed to improve the road network infrastructure.]]></description>
      <pubDate>Wed, 22 Apr 2026 16:15:31 GMT</pubDate>
      <guid>https://trid.trb.org/View/2647043</guid>
    </item>
    <item>
      <title>A bivariate Wurman Dot approach to mapping job density and commuting inflows</title>
      <link>https://trid.trb.org/View/2643800</link>
      <description><![CDATA[Commuting to work is a key form of everyday mobility. This study introduces a bivariate Wurman Dot method to visualise the relationship between commuting inflows and the Job Density Index (JDI) in Slovakia. Using 2021 Population and Housing Census data and a hexagonal grid, both indicators are visualised through a combination of symbol size and a bivariate colour scheme. The method reduces biases typical of choropleth and proportional-symbol maps by minimising shape heterogeneity, preventing symbol overlap, and enabling joint interpretation of absolute and relative labour-market indicators. The resulting visualisation reveals the hierarchy of employment centres, peripheral labour markets, and spatial mismatches between labour demand and commuting intensity, demonstrating the analytical value of the approach.]]></description>
      <pubDate>Wed, 22 Apr 2026 16:15:30 GMT</pubDate>
      <guid>https://trid.trb.org/View/2643800</guid>
    </item>
    <item>
      <title>The city of ‘minutes’: mapping trends and focus areas across the globe</title>
      <link>https://trid.trb.org/View/2652336</link>
      <description><![CDATA[Debates about (post)pandemic cities and neighbourhoods, and the growing interest in sustainable mobility encouraged academics to develop the proximity-based planning (PBP) concept under the recent label of the 15-Minute City (FMC). To better understand the rise and nature of the concept, a total of 287 studies were identified in Web of Science and Scopus using 21 relevant keywords. The corpus was quantitatively examined based on performance analysis and science mapping in bibliometric analysis, as well as using Exploratory Factor Analysis. The results were then visualized using VOSviewer and Gephi. The results revealed that proximity-based studies have evolved across three distinct periods, gaining traction as a consequence of COVID-19 pandemic, while new directions have also emerged. Most of the conceptual work is published by researchers from Western Europe, and such research is also more influential, as citation figures show. Besides the large number of publications on the core concepts of proximity-based planning, ‘transport’ and ‘built environment-design’ are the most popular themes, particularly in North America and Western Europe. Interestingly, publications emphasizing ‘spatial equity’ more often centre on Latin America, East Asia, and South Asia as study areas, while those with a ‘people and health’ focus tend to concentrate on Oceania. Despite the diversity in research priorities and the growing number of publications, the FMC label tends to create a common research ground that connects various domains and geographical regions. Finally, the findings not only reveal the model’s latent structure but also highlight understudied dimensions of PBP and related concepts—such as digitalization, the ‘quality’ of facilities (as opposed to their more commonly studied ‘quantity’), and public perception—offering opportunities for further refinement.]]></description>
      <pubDate>Wed, 22 Apr 2026 16:15:28 GMT</pubDate>
      <guid>https://trid.trb.org/View/2652336</guid>
    </item>
    <item>
      <title>CrossViewSeg: A Cross-View Consistency-Based Semi-Supervised Framework for Road Segmentation</title>
      <link>https://trid.trb.org/View/2658002</link>
      <description><![CDATA[In urban planning, intelligent traffic management, and emergency response, accurate road information is of great importance. However, pixel-level annotation is costly, data are imbalanced, and road shapes vary widely. These issues lead to poor pseudo-label quality and insufficient detail representation in deep-learning-based road segmentation. To address these problems, we propose CrossViewSeg, a cross-view semi-supervised learning framework. First, a dual-network processes the same image under weak and strong augmentations, with perturbations introduced at both the image and feature levels. Then, through a cross-view consistency mechanism, pseudo-labels generated by the weak augmentation branch supervise the strongly augmented branch without thresholding. Next, a cross-attention feature enhancement module is introduced to maximize feature differences between the two paths and avoid homogenization. Finally, higher weights are assigned to regions of disagreement between the two views in the cross-entropy loss, so that learning focuses on hard-to-segment road networks and complex areas. Experiments on the DeepGlobe and Massachusetts datasets demonstrate that CrossViewSeg outperforms mainstream methods across multiple metrics, particularly showing stronger structural coherence and road boundary delineation in complex traffic scenarios.]]></description>
      <pubDate>Tue, 21 Apr 2026 14:30:17 GMT</pubDate>
      <guid>https://trid.trb.org/View/2658002</guid>
    </item>
    <item>
      <title>Global Navigation Satellite System-Aided Post-Simultaneous Localization and Mapping Correction of Lidar Maps: Modular Pipeline for Enhanced Global Accuracy</title>
      <link>https://trid.trb.org/View/2691030</link>
      <description><![CDATA[Lidar-based simultaneous localization and mapping (SLAM) enables the generation of detailed 3D maps for such applications as autonomous navigation and infrastructure monitoring. However, SLAM systems are prone to drift accumulation, especially in the absence of a tightly integrated global navigation satellite system (GNSS) or inertial measurement unit, leading to degraded global accuracy. This paper presents a modular, post-processing correction pipeline that leverages high-accuracy GNSS real-time kinematic (RTK) data to correct lidar SLAM outputs in high-drift scenarios. The pipeline operates in three stages: (1) segment-based SLAM trajectory correction through alignment with time-synchronized GNSS RTK points using a singular value decomposition and Iterative Closest Point (SVD-ICP) method; (2) propagation of these corrections to the aggregated point cloud through timestamp-aligned delta application, generating a non-rigid intermediate reference map; and (3) conditional map refinement using either the SVD-ICP method for globally rigid alignment in low-drift scenarios or a Random Sample Consensus (RANSAC)-progressive Iterative Closest Point (ICP) method for robust registration in cases with significant residual drift, outliers, or local inconsistencies. The final output is a globally corrected high-fidelity point cloud in LAS file format. Experimental results demonstrate sub-meter global accuracy and strong visual consistency with satellite basemaps and GNSS control points, confirming the pipeline’s effectiveness for post-SLAM correction in environments with limited sensor integration.]]></description>
      <pubDate>Mon, 13 Apr 2026 08:41:21 GMT</pubDate>
      <guid>https://trid.trb.org/View/2691030</guid>
    </item>
    <item>
      <title>Multi-session perception-aware coverage path planning for active semantic SLAM and automatic change detection</title>
      <link>https://trid.trb.org/View/2688291</link>
      <description><![CDATA[This paper introduces a novel framework for multi-session, perception-aware coverage path planning integrated with active semantic Simultaneous Localization and Mapping (SLAM) and automatic change detection. The goal is to enhance autonomous robotic exploration in dynamic environments by combining semantic understanding with adaptive path planning for long-term monitoring. The proposed approach consists of three tightly integrated components. First, a semantic-informed inspection planner uses Kernel Density Estimation (KDE) to prioritize exploration of semantically significant regions. Second, an active semantic SLAM module builds a semantic map incrementally, providing real-time feedback to refine the inspection path. Third, a multi-session change detection strategy compares current and previous semantic data to identify and localize environmental changes. Together, these components allow the robot to intelligently adapt its exploration strategy over time, focusing on areas of interest and reacting to environmental dynamics. The framework is validated through both simulation and real-world experiments, demonstrating improved coverage efficiency, mapping accuracy, and change detection robustness compared to traditional methods. While applied to buoy detection, the system is broadly applicable to long-term robotic tasks such as environmental monitoring, infrastructure inspection, mine counter-measure operations, and disaster response, or other scenarios that demand adaptability and semantic awareness in complex, evolving environments.]]></description>
      <pubDate>Tue, 07 Apr 2026 15:37:01 GMT</pubDate>
      <guid>https://trid.trb.org/View/2688291</guid>
    </item>
    <item>
      <title>Airborne sound power levels and third octave band spectra of passenger ships across operational phases in the Port of Split</title>
      <link>https://trid.trb.org/View/2652587</link>
      <description><![CDATA[Mapping airborne environmental noise in passenger ports is increasingly important due to their proximity to residential areas and associated health risks. Predictive models have been limited by the scarcity of reliable airborne sound power data for ships under real operating conditions. This study addresses that gap through a short-term campaign at the Port of Split (Croatia). A-weighted sound power levels and third-octave spectra were derived for ferries, cruise ships, and catamarans during key operational phases: hotelling (at berth), loading/unloading, arrival, and departure. Measurements were conducted by qualified personnel with Class-1 instrumentation under favorable meteorological conditions and processed following established procedures. Results show marked differences among ship types and phases. Small catamarans are generally quiet except for auxiliary ventilation near departure; large catamarans exhibit higher levels at departure due to engine activation. Ferries separate into two behaviors: large units emit continuously during hotelling from ventilation and auxiliary machinery, whereas small ferries can be silent at berth or operate low-mounted engines intermittently. Cruise ships produced significant airborne noise mainly during hotelling, with elevated source heights that may enhance propagation toward urban receivers. The resulting dataset, based on repeated operations in a regular port schedule, offers directly model-ready inputs for noise mapping.]]></description>
      <pubDate>Fri, 03 Apr 2026 12:12:45 GMT</pubDate>
      <guid>https://trid.trb.org/View/2652587</guid>
    </item>
    <item>
      <title>An Online Map Matching Algorithm for Path-Free Trajectories by Integrating Path-Constrained Trajectories</title>
      <link>https://trid.trb.org/View/2591331</link>
      <description><![CDATA[Online map matching (MM) aligns real-time GPS trajectories with digital road networks, playing a vital role in vehicle navigation, route planning, and traffic analysis. Hidden Markov Models (HMMs) are widely used for their interpretability and ability to handle low GPS sampling rates. However, in urban scenarios characterized by complex road networks, significant GPS localization error, and dynamic traffic conditions, existing HMM-based methods face challenges such as large road search spaces due to uniform GPS localization error distributions (GLED) and inaccurate route accessibility estimates stemming from inadequate consideration of real-time traffic conditions. This paper proposes an improved HMM-based MM method, recognizing that urban vehicle trajectories can be categorized into two types: path-free (e.g., taxis, private cars) and path-constrained (e.g., buses). Analyzing path-constrained trajectories helps estimate fine-grained GLED and real-time traffic states of path-free vehicles more precisely. The novelty of our approach lies in two aspects: i) Using a hierarchical spectral clustering algorithm based on GPS localization errors of path-constrained bus trajectories, a city is divided into fine-grained sub-regions with consistent GLED. This enables the HMM an adaptive road search scopes, improving online MM efficiency. ii) Gradient boosting trees, known for their interpretability, estimate free-flow speeds by integrating path-constrained trajectories with the factors like road attributes and time, optimizing HMM state transition probabilities for path-free trajectory MM. Experiments on real-world data demonstrate that the optimized HMM methods, leveraging different trajectory types, significantly enhance MM efficiency and accuracy compared to baseline models.The codebase of our methods and datasets are available at https://github.com/jacklee018/onlineMM-IPCT.]]></description>
      <pubDate>Tue, 31 Mar 2026 16:34:41 GMT</pubDate>
      <guid>https://trid.trb.org/View/2591331</guid>
    </item>
    <item>
      <title>Tiny Machine Learning Approach for Grid-Based Monitoring of UAV Tracking and Cyber-Physical Systems in Hydraulic Surveying</title>
      <link>https://trid.trb.org/View/2610705</link>
      <description><![CDATA[With the advancement in Tiny Machine Learning (ML) technologies, their application in enhancing unmanned aerial vehicles (UAVs) for hydraulic engineering surveying and mapping has become increasingly significant. TinyML’s integration offers a leap in processing efficiency and capabilities, particularly in addressing challenges such as UAV search and monitoring due to loss of contact or forced landings. The usage of medical cyber-physical systems in healthcare can revolutionize existing service delivery methods. The study focuses into the spatial grid mapping technique for three-dimensional information, the PTZ camera spatial grid target locking algorithm, and the UAV detection and image correction algorithm. The UAV target is processed using the surveying UAV target tracking method. TinyML techniques are essential for processing and analyzing these photos quickly. Precise UAV identification and tracking are made possible by the combination of image recognition and radar data, which are then processed using TinyML algorithms. This study explores the complexities of algorithms designed specifically for TinyML, such as tracking, UAV detection, grid mapping, and 3D grid space division. Experimental results validate the enhanced capability of this. The results show how well the proposed technique maps and surveys water conservation regions while promptly catching, locking onto, and tracking drones. The algorithm in this study betters than the YOLO, SSD, and RetinaNet algorithms in the recognition and detection of image-oriented surveying and mapping drones.]]></description>
      <pubDate>Mon, 30 Mar 2026 17:10:22 GMT</pubDate>
      <guid>https://trid.trb.org/View/2610705</guid>
    </item>
    <item>
      <title>Feasibility of GNSS independent harbour geo-localization via LiDAR SLAM and prior maps</title>
      <link>https://trid.trb.org/View/2685331</link>
      <description><![CDATA[This paper presents a feasibility study of a LiDAR SLAM based prior map fitting pipeline that yields map-referenced position estimates in known harbour environments, independent of GNSS. To address the challenge of precise positioning in unstructured and dynamic environments, a LiDAR sensor provides accurate measurements of the surroundings, which are fitted to a prior map using rotational initial alignment and G-ICP detail registration. The initial alignment process improves the accuracy of subsequent registration by leveraging corner features of the environment to address the limitations associated with large transformations in ICP registration. The resulting position estimates enable redundant positioning estimated by an Unscented Kalman Filter sensor fusion algorithm together with GNSS positioning. Results demonstrate map-referenced positioning accuracy of 3-6 m and end-to-end system latencies of approximately 1.8 s, indicating the method’s practical feasibility for coastal and port operations and its potential role in improving the navigation safety and autonomy of maritime platforms. While likely not generalizable for all land structures, we argue the potential usefulness of the system for redundant positioning in pre-vetted, well structured harbour environments.]]></description>
      <pubDate>Fri, 27 Mar 2026 10:14:49 GMT</pubDate>
      <guid>https://trid.trb.org/View/2685331</guid>
    </item>
    <item>
      <title>HGG-Net: Hierarchical Geometry Generation Network for Point Cloud Completion</title>
      <link>https://trid.trb.org/View/2610633</link>
      <description><![CDATA[Point cloud completion concerns the inference of the completed geometries for real-scanned point clouds that are sparse and incomplete due to occlusion, noise, and viewpoint. Previous methods usually learn a one-shot partial-to-complete mapping, which is incapable of generating fine structure details for the complex point cloud distributions. In this paper, a Hierarchical Geometry Generation point completion Network (HGG-Net) is proposed to hierarchically generate the fine-grained completed point cloud with a skeleton-to-details strategy, which consists of three fundamental modules, namely Transformer-enhanced Feature Encoder (TFE), Multi-level Geometry Representation Decoder (MGRD), and Hierarchical Dynamic Geometry Generator (HDG). Specifically, TFE first extracts geometry features of the incomplete input and obtains a coarse prediction via self-attention mechanism and edge convolution. Second, MGRD obtains the multi-level decoded geometry representations by Geometric Interactive Transformer (GIT) and Channel-Attention-based Geometry Features Fusion (CAGF), where GIT is proposed to decode the complete prompt by capturing the semantic relationship between geometry features of the incomplete and the decoded complete objects, and CAGF aims to fuse them for the high-quality representation. Third, HDG generates the complete points hierarchically from skeleton to details based on the Dynamic Graph Attention mechanism. Qualitative and quantitative experiments demonstrate that the proposed HGG-Net outperforms state-of-the-art methods on several point cloud completion datasets. Our code is available at https://github.com/haalexx/HGGNet.]]></description>
      <pubDate>Wed, 25 Mar 2026 17:11:08 GMT</pubDate>
      <guid>https://trid.trb.org/View/2610633</guid>
    </item>
    <item>
      <title>SSCNet: Synchronous Stratification and Cross-Level Feature Fusion for Road Extraction</title>
      <link>https://trid.trb.org/View/2610625</link>
      <description><![CDATA[Deep learning-based road extraction technologies can swiftly identify road information in complex environments, playing a crucial role in advancing urban intelligence and achieving sustainable development goals. However, the current road extraction models exhibit significant omissions when confronted with scenarios involving occluded roads and densely distributed road networks. To address the issue of partial road extraction, this paper introduces a novel method named SSCNet. This approach addresses potential causes of road extraction failures by leveraging synchronous stratification learning and cross-level feature fusion to fully utilize information across various layers. The model incorporates a Dynamic Road Detail Matcher to extract a wealth of road detail information from shallow feature maps, a Cross Contextual Adaptive Attention to capture multi-scale contextual information and interact with shallow feature maps, and a Multi-Scale Global Information Integrator to consolidate global information from different levels of feature maps, enhancing the model’s understanding of road integrity. The model has been extensively tested on the public datasets DeepGlobe, Massachusetts, SpaceNet, and RoadTracer, showing significant improvements in F1 score and IoU compared to current state-of-the-art models.]]></description>
      <pubDate>Wed, 25 Mar 2026 17:11:07 GMT</pubDate>
      <guid>https://trid.trb.org/View/2610625</guid>
    </item>
  </channel>
</rss>