<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>Three-Dimensional Highway Alignment Design System Using Stereoscopy of Aerial Photographs and Computer Graphics</title>
      <link>https://trid.trb.org/View/2159485</link>
      <description><![CDATA[A three-dimensional alignment design system in the virtual space recreated by stereoscopy of aerial photographs is developed. In order to define the three-dimensional alignment in the virtual space, B-spline curves are applied. Definition of a highway alignment as a three-dimensional alignment enables the direct acquisition of digital three-dimensional model and the real-time assessment of the design.]]></description>
      <pubDate>Sat, 07 Mar 2026 16:05:43 GMT</pubDate>
      <guid>https://trid.trb.org/View/2159485</guid>
    </item>
    <item>
      <title>Data Augmentation for Environment Perception With Unmanned Aerial Vehicles</title>
      <link>https://trid.trb.org/View/2598821</link>
      <description><![CDATA[Large and high-quality training datasets are of critical importance for deep learning. In the context of the semantic segmentation challenge for UAV aerial images, we propose a strategy for data augmentation that can significantly reduce the effort of manually annotating a large number of images. The result is a set of semantic, depth and RGB images that can be used to improve the performance of neural networks. The main focus of the method is the generation of semantic images, with depth and texture images also being generated through the process. The proposed method for semantic image generation relies on a 3D semantic mesh representation of the real-world environment. First, we propagate the existing semantic information from a reduced set of manually labeled images into the mesh representation. To deal with errors in the manually labeled images, we propose a specific weighted voting mechanism for the propagation process. Second, we use the semantic mesh to create new images. Both steps use the perspective projection mechanism and the Depth Buffer algorithm. The images can be generated using different camera orientations, allowing novel view perspectives. Our approach is conceptually general and can be used to improve various existing datasets. Experiments with existing datasets (UAVid and WildUAV), augmented with the proposed method, are performed on HRNet. An overall performance improvement of the inference results by up to 5.5% (mIoU) is obtained.]]></description>
      <pubDate>Mon, 08 Dec 2025 17:05:43 GMT</pubDate>
      <guid>https://trid.trb.org/View/2598821</guid>
    </item>
    <item>
      <title>Coaxial Tilt-Rotor UAV: Fixed-Time Control, Mixer, and Flight Test</title>
      <link>https://trid.trb.org/View/2598792</link>
      <description><![CDATA[The coaxial tilt-rotor (CTR) unmanned aerial vehicle (UAV) is a distinctive multirotor aircraft which incorporates two coaxial tilt-rotor (CTR) modules and a rear rotor, enabling it to execute diverse maneuvers and achieve high-speed forward flight. In this work, according to the specific configuration of the CTRUAV, a cascaded fixed-time (FT) control strategy and a nonlinear state-varying mixer are proposed to improve the CTRUAV's stability, transient performance, and robustness. The FT convergent property of the designed control strategy is validated and discussed by simulations. Finally, real-time experiments are implemented on a self-built CTRUAV experimental platform. The simulations and experimental results with different controllers demonstrate the effectiveness and superiority of the designed control method.]]></description>
      <pubDate>Mon, 08 Dec 2025 17:05:42 GMT</pubDate>
      <guid>https://trid.trb.org/View/2598792</guid>
    </item>
    <item>
      <title>Generating Pixel Enhancement for Road Extraction in High-Resolution Aerial Images</title>
      <link>https://trid.trb.org/View/2591659</link>
      <description><![CDATA[Road extraction is a powerful technique support to autonomous driving as it provides routable road information for motion planning algorithms. High-resolution aerial images offer comprehensive road information, facilitating the establishment of efficient and accurate road networks to monitor road changes in a timely manner. However, widespread occlusions and abundant local details pose challenges to highly accurate and continuous extraction, especially in areas with road bifurcations. To simultaneously improve both accuracy and connectivity of road extraction, in this paper, the authors propose a novel approach TPEGAN to integrate pixel-level segmentation and graph inference based on road pixel enhancement. By generating road pixels enhanced images, the generative adversarial network exploits the consistency among road pixels to embed pixel-level accuracy into the segmentation module. The multi-scale dual-branch segmentation module employs graph convolution reasoning to capture dependencies across different spatial regions, maintaining the connectivity of road networks. Extensive experiments on three public datasets demonstrate that TPEGAN outperforms SOTA methods with a considerable performance gap. As the complexity of road networks increases, the performance of TPEGAN degrades more slowly than SOTA method. Even in challenging urban scenes where the proportion of road pixels is more than 15%, TPEGAN retains its high performance and achieves a rIoU of 0.664 with an APLS of 72.81%, amounting to improvements of 4.1% and 2.62% over SOTA method, respectively.]]></description>
      <pubDate>Fri, 24 Oct 2025 16:53:57 GMT</pubDate>
      <guid>https://trid.trb.org/View/2591659</guid>
    </item>
    <item>
      <title>Comparison of Two Techniques of Aerial Photography for Application in Freeway Traffic Operations Studies</title>
      <link>https://trid.trb.org/View/2543331</link>
      <description><![CDATA[Aerial surveys were made of the traffic flow on a six-mile section of the Gulf Freeway in Houston, Texas. Two types of aerial photography were investigated: (1) strip photography where two continuous pictures are taken simultaneously from the beginning to the end of the study section; and (2) time-lapse photography where individual pictures are taken at short intervals of time. The objectives of this study were: (1) To determine the operational characteristics of the freeway and those factors that affect the level of service offered to the motorist; and (2) To evaluate the two techniques of aerial photography and their application to traffic studies. The results of the study of operational characteristics will be reported in another paper. The purpose of this report is to compare the two types of aerial photography used in this study for their application to traffic studies.]]></description>
      <pubDate>Wed, 21 May 2025 14:12:17 GMT</pubDate>
      <guid>https://trid.trb.org/View/2543331</guid>
    </item>
    <item>
      <title>Disabled Parking CV: Scalable Methods to Analyze Disability Parking using Computer Vision and High-Resolution Aerial and Streetscape Images</title>
      <link>https://trid.trb.org/View/2553158</link>
      <description><![CDATA[People with disabilities disproportionately rely on public transportation to access employment, education, and healthcare services; however, public transit is not always available or equally distributed, which excludes social and community participation. Car transit is thus the only viable alternative. Since the Americans with Disability Act (ADA) of 1990, 4-8% of public parking spaces need to be reserved for drivers/passengers with disabilities, providing wide, accessible spaces close to destinations. And yet, there has been no systematic, large-scale study of the allocation and sizes of disability parking spaces across the US. The limited prior work that does exist has employed questionnaire methods to survey disabled drivers or examines the appropriate design of the disabled parking spot itself (e.g., its dimensions).

In this project, the research team proposes building and evaluating state-of-the-art computer vision (CV) methods applied to emerging high resolution aerial photography—such as the open 0.08 meter/pixel orthoimagery of Washington DC (DC Orthophoto, 2021)—to semi-automatically (1) track the allocation of disability parking in public and commercial lots; (2) examine characteristics of said parking (e.g., size, access area, % of allotment to normal parking) as well as public transportation ridership usage; (3) and create new analytic metrics enabled by this approach such as such as the proximity of disabled spaces to POIs (e.g., the distance to an entrance). 

The overarching goal of this work is to create open datasets and analytics for ADA-accessible parking as well as to infuse this information into modern mapping tools (e.g., OpenStreetMaps).
]]></description>
      <pubDate>Tue, 13 May 2025 19:30:49 GMT</pubDate>
      <guid>https://trid.trb.org/View/2553158</guid>
    </item>
    <item>
      <title>Artificial Intelligence (AI) Frameworks for Detecting Roadway Features Along Arterial Roadways from Planimetric Satellites Imagery Data </title>
      <link>https://trid.trb.org/View/2522024</link>
      <description><![CDATA[Departments of Transportation (DOTs) at the state level play a vital role in collecting and maintaining highway inventory data to support informed decision-making across various operational levels. Traditionally, these efforts have relied on labor-intensive and expensive processes, presenting challenges in updating and expanding inventory coverage. However, advancements in Artificial Intelligence (AI), particularly in computer vision and deep learning, offer a transformative solution to these limitations.

The overall goal of this proposed research is to develop an AI-driven framework that enables automated extraction of roadway geometric features (i.e., pedestrian crosswalks and turn lanes) from aerial imagery, advancing Ohio Department of Transportation's (ODOT's) efficiency in data collection. The associated objectives include: (1) Collect and pre-process georeferenced aerial images for detecting pedestrian crosswalks and turn lanes, annotating them to train AI algorithms effectively. (2) Design and train a deep learning model to detect specific roadway features from satellite images. (3) Develop a Geographic Information System (GIS) database to organize and store the extracted features for easy accessibility and integration with existing ODOT datasets. (4) Build a flexible framework to support future expansion, enabling the detection of additional roadway features as needed.
           ]]></description>
      <pubDate>Fri, 14 Mar 2025 13:41:09 GMT</pubDate>
      <guid>https://trid.trb.org/View/2522024</guid>
    </item>
    <item>
      <title>A Deep Learning Model for Automatic Data Collection of Road Characteristics</title>
      <link>https://trid.trb.org/View/2492904</link>
      <description><![CDATA[Road inventory data is collected manually to identify the road environment near crash locations. In this study, the authors automatically detect median on roads and presence of intersections from aerial images. Data is manually as well as automatically collected from two different cities (Chennai and Trichy) in the state of Tamil Nadu in India using Google Application Programming Interface (API). An image recognition model is built using Convolutional Neural Networks (CNN). Multiple models were built using ResNet architecture comprising training dataset from same city as of test set and mixed dataset of both the cities to test the model's generalizability. F1 scores are used to rate the model performance. The results reveal that the model's F1 scores increase when training data comprises images from both cities. This work makes two contributions. Firstly, it describes how CNN can be utilized for road safety research and secondly, the proposed dataset can be used in future to build the model for other cities so that manual data collection can be minimized. Lastly, recommendations are made for more such work in future.]]></description>
      <pubDate>Thu, 20 Feb 2025 08:46:09 GMT</pubDate>
      <guid>https://trid.trb.org/View/2492904</guid>
    </item>
    <item>
      <title>YOLC: You Only Look Clusters for Tiny Object Detection in Aerial Images</title>
      <link>https://trid.trb.org/View/2441910</link>
      <description><![CDATA[Detecting objects from aerial images poses significant challenges due to the following factors: 1) Aerial images typically have very large sizes, generally with millions or even hundreds of millions of pixels, while computational resources are limited. 2) Small object size leads to insufficient information for effective detection. 3) Non-uniform object distribution leads to computational resource wastage. To address these issues, the authors propose YOLC (You Only Look Clusters), an efficient and effective framework that builds on an anchor-free object detector, CenterNet. To overcome the challenges posed by large-scale images and non-uniform object distribution, they introduce a Local Scale Module (LSM) that adaptively searches cluster regions for zooming in for accurate detection. Additionally, they modify the regression loss using Gaussian Wasserstein distance (GWD) to obtain high-quality bounding boxes. Deformable convolution and refinement methods are employed in the detection head to enhance the detection of small objects. The authors perform extensive experiments on two aerial image datasets, including Visdrone2019 and UAVDT, to demonstrate the effectiveness and superiority of the proposed approach.]]></description>
      <pubDate>Mon, 13 Jan 2025 10:24:42 GMT</pubDate>
      <guid>https://trid.trb.org/View/2441910</guid>
    </item>
    <item>
      <title>Vehicle Trajectory Deviation Data Collection Method Based on Unmanned Aerial Vehicle Aerial Imagery</title>
      <link>https://trid.trb.org/View/2475544</link>
      <description><![CDATA[Traffic risk is higher on curved road sections compared to regular sections. Understanding vehicle trajectory deviation is crucial for analyzing road safety. The conventional method for collecting vehicle trajectory is limited to measuring the deviation of a single vehicle or vehicles on a single lane. To overcome this limitation, this study proposes a novel method that utilizes drone aerial imagery to gather data on vehicle trajectory deviation. By leveraging the bird’s-eye view and high-resolution images provided by drones, detailed trajectory information and deviation analysis of multiple vehicles in multiple lanes can be obtained. The effectiveness and accuracy of this method were confirmed through testing on real road scenarios. The trajectory analysis results reveal significant deviations from the lane lines in tight radius curves for both large and small vehicles. These analysis results provide valuable data for road design, traffic safety assessment, and the development of driving assistance systems.]]></description>
      <pubDate>Thu, 19 Dec 2024 16:58:19 GMT</pubDate>
      <guid>https://trid.trb.org/View/2475544</guid>
    </item>
    <item>
      <title>Automated Geographic-Information-System-Based Framework for Detecting Crosswalk Changes from Bi-Temporal High-Resolution Aerial Images</title>
      <link>https://trid.trb.org/View/2452818</link>
      <description><![CDATA[Identifying changes in pavement markings has become crucial for infrastructure monitoring, maintenance, development, traffic management, and safety. Automated extraction of the roadway geometry is critical in helping with this, given the increasing availability of high-resolution images and advancements in computer vision and object detection. Specifically, because of the substantial volume of satellite and high-resolution aerial images captured at different time instances, change detection has become a viable solution. In this study, an automated framework is developed to detect changes in crosswalks in Orange, Osceola, and Seminole counties in Florida, utilizing data extracted from high-resolution images obtained at various time intervals. Specifically, for Orange County, crosswalk changes between 2019 and 2021 were manually extracted, verified, and categorized as either new or modified crosswalks. For Seminole County, the developed model was used to automatically extract crosswalk changes between 2018 and 2021, while for Osceola County, changes between 2019 and 2020 were extracted. Findings indicate that Orange County witnessed approximately 2,094 crosswalk changes, with 314 occurring on state roads. In Seminole and Osceola counties, on the other hand, 1,040 and 1,402 crosswalk changes were observed on both local and state roads, respectively. Among these, 340 and 344 were identified on state roads in Seminole and Osceola, respectively. Spatiotemporal changes observed in crosswalks can be utilized to regularly update the existing crosswalk inventories, which is essential for agencies engaged in traffic and safety studies. Data extracted from these crosswalk changes can be combined with traffic and crash data to provide valuable insights to policymakers.]]></description>
      <pubDate>Wed, 20 Nov 2024 10:58:06 GMT</pubDate>
      <guid>https://trid.trb.org/View/2452818</guid>
    </item>
    <item>
      <title>Retargeting HR Aerial Photos Under Contaminated Labels With Application in Smart Navigation</title>
      <link>https://trid.trb.org/View/2325297</link>
      <description><![CDATA[Retargeting aims to shrink a photo wherein the perceptually prominent regions are appropriately kept. In practice, optimally shrinking a high resolution (HR) aerial photo is a useful tool for smart navigation. Nowadays, vehicle drivers’ path planning is generally guided by an HR aerial photo recommended by a navigation App like Google Maps. Owing to the limited and various resolution of vehicle displays, the authors have to retarget each original HR aerial photo accordingly, wherein the navigation-aware regions can be well preserved. In practice, HR aerial photo retargeting is non-trivial due to three challenges: 1) the rich number of internal objects and their complex spatial layouts, 2) deriving the region-level semantics from potentially contaminated image labels, and 3) the inefficiency of retargeting each HR aerial photo with millions of pixels. To handle these problems, they propose a novel HR aerial photo retargeting pipeline that can intelligently avoid the negative effects from incorrect image labels. The key is a noise-tolerant hashing algorithm that converts image-level semantics into the hash codes corresponding to different regions, which guides the HR aerial photo shrinking. More specifically, for each HR aerial photo, they extract visually/semantically salient object patches inside it. To explicitly encode their spatial layout, they construct a graphlet by linking the spatially adjacent object patches into a small graph. Subsequently, a binary matrix factorization (MF) is designed to exploit the underlying semantics of these graphlets, wherein three attributes: i) binary hash codes learning, ii) noisy labels refinement, iii) deep image-level semantics, are collaboratively encoded. Such binary MF can be solved iteratively and each graphlet is subsequently converted into the binary hash codes. Finally, the hash codes corresponding to graphlets within each HR aerial photo are utilized to learn a Gaussian mixture model (GMM) that optimizes the HR aerial photo retargeting. During the experimental validation, the authors compiled a smart navigation dataset including 132743 planned paths annotated from 10132 HR aerial photos, based on which comparative study has demonstrated the superiority of their method.]]></description>
      <pubDate>Tue, 28 May 2024 10:44:32 GMT</pubDate>
      <guid>https://trid.trb.org/View/2325297</guid>
    </item>
    <item>
      <title>How to detect occluded crosswalks in overview images? Comparing three methods in a heavily occluded area</title>
      <link>https://trid.trb.org/View/2366933</link>
      <description><![CDATA[Crosswalk presence data is crucial for pedestrian safety and urban planning. However, obtaining such data at a large scale is often challenging due to the high cost associated with traditional collection methods. While automated methods based on computer vision have been explored to detect crosswalks from aerial images, a major obstacle to their application is the handling of candidate crosswalks occluded by objects or shadows in the aerial imagery. To address this challenge, this study explores different deep learning-based solutions, including the aerial-view and street-view methods, which are commonly used, and a combination of the two − dual-perspective method. Deep learning models based on Convolutional Neural Networks with VGG16 architecture were trained using 16,815 images to automatically detect crosswalks from both aerial and street view images. To compare the performance of these methods in handling occlusions, 1,378 images from a heavily occluded area were processed separately by the three methods. The results showed that the aerial-view method suffered the most when dealing with images from a heavily occluded area, resulting in the lowest accuracy, precision, recall, and F1 score among the three methods. On the other hand, the street-view method outperformed the aerial-view method significantly. The dual-perspective method demonstrated the highest accuracy and precision values, indicating its superiority in accurately predicting the location of a crosswalk. However, the street-view method exhibited the highest recall value, highlighting its superior ability to recover an occluded crosswalk among all methods.]]></description>
      <pubDate>Thu, 23 May 2024 09:41:01 GMT</pubDate>
      <guid>https://trid.trb.org/View/2366933</guid>
    </item>
    <item>
      <title>An Investigation on Accurate Road User Location Estimation in Aerial Images Collected by Drones</title>
      <link>https://trid.trb.org/View/2353268</link>
      <description><![CDATA[Unmanned aerial vehicles (UAVs) have recently become popular in collecting positional data of road users. In comparison to other tools at ground level, UAVs have the advantages of low cost, wider view coverage, and significantly less occlusion. However, the depth relief of road users and the perspective distortion of the onboard camera induce nonnegligible error while applying UAVs for localization of road users. This study proposed a method for accurate road user localization in aerial images. First, the localization error induced by the depth relief and perspective distortion was examined and modeled. Then, a deep-learning-based method was applied for automatic road user detection and localization in the aerial images by leveraging oriented bounding boxes to achieve higher localization accuracy compared to applying horizontal bounding boxes. Finally, an error compensation strategy was proposed to eliminate the perspective- and depth-relief-induced localization error by rectifying the oriented bounding boxes obtained from the previous step. Field experiments were conducted to evaluate the method’s performance. The results demonstrated its promising accuracy for road user location estimation and its potential to improve the reliability of UAVs in traffic applications.]]></description>
      <pubDate>Wed, 17 Apr 2024 11:29:44 GMT</pubDate>
      <guid>https://trid.trb.org/View/2353268</guid>
    </item>
    <item>
      <title>Fine-grained crack segmentation for high-resolution images via a multiscale cascaded network</title>
      <link>https://trid.trb.org/View/2339943</link>
      <description><![CDATA[High-resolution (HR) crack images offer more detailed information for assessing structural conditions compared to low-resolution (LR) images. This wealth of detail proves indispensable in bolstering the safety of unmanned aerial vehicle (UAV)-based inspection procedures and elevating the precision of small crack segmentation. Nonetheless, achieving a balance between segmentation accuracy and GPU memory consumption poses a substantial challenge for deep learning models when processing HR crack images. To overcome this challenge, a novel “HR crack segmentation framework” (HRCSF) is proposed, specifically designed to meticulously segment crack images with resolutions exceeding 4K. First, a multiscale crack feature extraction network (MsCFEN) was proposed with the embedment of the strip pooling operation to enhance the representation of the transverse and longitudinal crack pixels from the complex backgrounds. Subsequently, two cascaded operations were tailored to MsCFEN, enabling a comprehensive refinement process that incorporates both global and local aspects. Furthermore, to fully leverage the potential of each proposed component in the refinement process, the complete architecture was trained using a loss function with embedded boundary optimization. Conclusively, a UAV-based case study was conducted on a real bridge in Changsha, demonstrating HRCSF's practicability in segmenting HR crack images. The implementation of HRCSF allows the UAV to perform crack inspection effectively from a distance of 3 m away from the girder, resulting in a significant 50% reduction in inspection time compared to LR segmentation methods while maintaining high detection accuracy.]]></description>
      <pubDate>Mon, 18 Mar 2024 17:19:35 GMT</pubDate>
      <guid>https://trid.trb.org/View/2339943</guid>
    </item>
  </channel>
</rss>