<rss version="2.0" xmlns:atom="https://www.w3.org/2005/Atom">
  <channel>
    <title>Research in Progress (RIP)</title>
    <link>https://rip.trb.org/</link>
    <atom:link href="https://rip.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>Research in Progress (RIP)</title>
      <url>https://rip.trb.org/Images/PageHeader-wTitle-RIP.jpg</url>
      <link>https://rip.trb.org/</link>
    </image>
    <item>
      <title>AI-Enabled Vision System for Intersection Analytics </title>
      <link>https://rip.trb.org/View/2673053</link>
      <description><![CDATA[Phase I of this project revealed limitations of using a single camera per intersection to automatically extract key traffic performance and safety information from video feeds. To overcome these limitations and enhance data accuracy, the Phase II approach will deploy a second camera at selected high-impact intersections. By fusing the views from two different camera angles, the system can establish a true spatial relationship of objects in the intersection, essentially achieving a more complete 3D understanding of vehicle and pedestrian trajectories.]]></description>
      <pubDate>Tue, 24 Feb 2026 15:00:25 GMT</pubDate>
      <guid>https://rip.trb.org/View/2673053</guid>
    </item>
    <item>
      <title>Observational Intersection Traffic Safety Analysis</title>
      <link>https://rip.trb.org/View/2655705</link>
      <description><![CDATA[While planners and engineers design intersections with safety in mind, the intended use and actual use of facilities do not always align. This misalignment can lead to increased safety risks for all intersection participants, particularly non-motorized users including pedestrians and cyclists. Although facility utilization mismatches can be detected through observation, typical monitoring occurs only during limited peak hours, failing to fully capture comprehensive usage patterns and emerging safety concerns.

This research proposes long-term intersection monitoring to uncover emerging facility utilization patterns and assess inherent intersection safety. The approach leverages existing traffic camera infrastructure combined with modern deep learning techniques for accurate detection and tracking of vehicles, bicycles, and pedestrians. As an explicit use case, the study examines unprotected left-turns to characterize both vehicle-vehicle conflicts through time gap analysis and trajectory conflicts involving other road users. The project develops a computer vision system capable of processing trajectories to quantify left-turns with insufficient gaps, instances where vehicles fail to yield appropriately, and average time gaps, collectively providing metrics to characterize intersection safety.

This interdisciplinary project combines computer vision algorithm development expertise from the University of Nevada, Las Vegas (UNLV) with programming support from Howard University. System evaluation will occur at intersections in both the Washington, DC area and the Las Vegas metropolitan area, utilizing purpose-built high-resolution monitoring equipment for short-term deployment as well as existing lower-resolution traffic cameras for long-term analysis. The project leverages intersection equipment acquired through NSF Award Number 2216489.

Expected outcomes include research contributions in computer vision and machine learning for trajectory analysis, workforce development through student training across both institutions, and technology transfer through publications on intersection safety scoring and practitioner engagement for field deployment.]]></description>
      <pubDate>Mon, 19 Jan 2026 16:30:17 GMT</pubDate>
      <guid>https://rip.trb.org/View/2655705</guid>
    </item>
    <item>
      <title>Use of Advanced Data Capture Tools on Measurements of Crack Lengths and Potholes for Estimates and Final Quantities</title>
      <link>https://rip.trb.org/View/2652613</link>
      <description><![CDATA[According to the Pavement Management Information System, the Kansas Department of Transportation (KSDOT) maintains 11,357 miles of pavement (counting miles in both directions of divided highways).  About 90% of this mileage is asphalt pavement. KSDOT’s contract maintenance work related to crack sealing, pot-hole patching, etc., is common for these pavements. 

The current measurement techniques use a measuring wheel, distance measuring instrument (DMI), etc. These techniques are highly susceptible to human errors and utilize considerable time and manpower. They also obstruct the traffic flow while conducting roadway measurements and putting the personnel at risk. The KSDOT idea submitted cites data collection via high-accuracy drone surveys but drone operations are restricted on KSDOT right of ways to prevent traveler distraction.   

Recent developments in camera technology and high-speed, high-resolution image capture at an affordable cost offer the opportunity for automation of measurements of crack lengths and potholes/patches for estimates and final quantities.  Example camera models include Vantrue S1 Pro 2.7K Front and Rear 5G WiFi Dash Cam, VIOFO Dash Cam Front and Rear 2K 1440P 60fps, Dash Cam Front and Rear - POFOTO 2.5K 1440P 60fps and 1080P 30fps Dash Camera, VIOFO A129 Plus Dash Cam 2K 1440P 60FPS GPS Wi-Fi Car Dash Camera with HDR and equivalent. These cameras all cost less than $250. 

The challenge lies in processing the images. However, with recent developments in artificial intelligence and machine learning, this problem can be resolved relatively quickly. One such algorithm for spatial pattern analysis is Convolutional Neural Networks (CNN), which have developed rapidly and have been applied in computer vision, natural language processing, and other fields. The convolutional neural network mimics the biological visual perception mechanism and can carry out supervised and unsupervised learning. However, traditional CNN has some drawbacks, like as the number of layers increases, the quality of the model decreases, ultimately leading to a decline in supervised learning accuracy. Thus, newer algorithms based on CNN have been developed that will be deployed in this study.]]></description>
      <pubDate>Tue, 13 Jan 2026 16:08:53 GMT</pubDate>
      <guid>https://rip.trb.org/View/2652613</guid>
    </item>
    <item>
      <title>Evaluating the I-25 Greenland Wildlife Overpass using network camera monitoring</title>
      <link>https://rip.trb.org/View/2643441</link>
      <description><![CDATA[This project will examine the effectiveness the largest wildlife overpasses in the U.S. and will explore the application of cameras with networked and high-quality imaging and other other methodologies. The study should inform future wildlife mitigation design decisions and advance the ability to study and monitor wildlife structures with increased safety and accuracy and reduced staff time and cost.]]></description>
      <pubDate>Tue, 23 Dec 2025 13:59:51 GMT</pubDate>
      <guid>https://rip.trb.org/View/2643441</guid>
    </item>
    <item>
      <title>Traffic Signal Non-Intrusive Detection Technology Assessment and Comparison</title>
      <link>https://rip.trb.org/View/2601431</link>
      <description><![CDATA[North Carolina Department of Transportation (NCDOT) has been using in-pavement (in-ground) magnetic induction loops to detect vehicles and operate traffic signals for decades as have many other state DOTs. Given the high number of signals in NC there are hundreds of thousands of loops that must be maintained for efficient signal operation and coordination. Many non-intrusive (above-ground or out-of-pavement) vehicle detection systems are compatible with NCDOT's signal controllers and can provide the same operation-critical inputs to the controllers as can magnetic induction loops. Yet they have numerous benefits enumerated herein.

The motivation for this study is to assess the costs of non-intrusive vehicle detection systems so that NCDOT can compare their costs and the value of the benefits they provide to the cost and benefits of magnetic induction loops. The goal is to determine how to quantify the various benefits and costs. The ITS and Traffic Signals Section has identified radar and cameras as the most promising non-intrusive detection technologies. The Signals Management Program Plan update now identifies the need to make a dedicated study of the costs, benefits, and return on investment of these technologies. Their goal is to identify specific technologies that meet specifications and to determine whether a targeted or blanket shift to those technologies is the optimal use of Department financial and time resources.

The purpose of this research is to assess NCDOT traffic signal detection technology to determine if it should evolve from the current magnetic induction loops to a technology based on radar or cameras (so that signal system performance is maintained or enhanced) and determine the cost of transitioning partially or fully. This study to answer the following questions: (1) “what technology is most well suited to NCDOT's needs?" (2) “what is the cost of the transition?" (3) “what is the return on investment? (4) “how would the transition occur?" This study will explore whether or not used by any division within NC and be realistically and efficiently implemented.

The lessons learned from the assessment and analysis will be combined with the experiences of other NC divisions and with knowledge gained from the literature to formulate one or more potential strategies to meet NCDOT needs. In doing so, NCDOT may improve both its overall financial decision making and the management of this critical roadway asset, resulting in overall cost savings and safety enhancement.

The proposal articulated below first introduces the context of the research need statement by providing a background. The background describes the nature of the NC traffic signal system. It then provides quantification data. The introduction also addresses the technology of vehicle detection systems and describes those that are most prominent. For each detection technology a table provides examples of manufactured products followed by a brief assessment of each technology.

The research needs and objectives are stated next and are followed by a literature review. This introductory literature review illustrates a number of important references that aid in understanding what others have done to address the questions mentioned above. The research tasks are then enumerated in significant detail. The significance of the proposed work (and the execution of the enumerated tasks) is stated. The research products are articulated next and a detailed discussion of the implementation plan is presented. That is followed by a cost benefit analysis which is a major part of the proposed work.

Finally, the project schedule is presented in two parts. The first part focuses on major milestones. These are a point in time. In one sense, they act as deadlines. The second schedule articulates the research tasks as activities. These span a longer duration over time.​]]></description>
      <pubDate>Thu, 18 Sep 2025 00:48:46 GMT</pubDate>
      <guid>https://rip.trb.org/View/2601431</guid>
    </item>
    <item>
      <title>Assessing the Value of LiDAR in Detecting Conflicts at Intersections to Enhance Safety</title>
      <link>https://rip.trb.org/View/2596528</link>
      <description><![CDATA[The goal of this research is to evaluate and compare the effectiveness of camera-based and LiDAR-based systems for detecting traffic conflicts. AI-based methods will be developed and applied separately  to datasets collected from each sensing platform. The study will assess the performance of each system in terms of conflict detection accuracy at three sites representing varied environmental and traffic conditions. In addition to technical performance, a cost-benefit assessment will be conducted to evaluate the practicality and scalability of each sensing approach. ]]></description>
      <pubDate>Tue, 09 Sep 2025 08:19:50 GMT</pubDate>
      <guid>https://rip.trb.org/View/2596528</guid>
    </item>
    <item>
      <title>SPR-5005: Evaluation of Asset Identification Technology</title>
      <link>https://rip.trb.org/View/2582580</link>
      <description><![CDATA[The Indiana Department of Transportation (INDOT)'s asset management databases are constructed using a variety of techniques ranging from as-built take-offs, visually driving the network, “camcordering” the network, and contracting automated systems such as Pathways. Commercial dashcams now provide extensive coverage of the INDOT network. This study will explore and evaluate of a variety of methods to use these dashcam images for asset management purposes.]]></description>
      <pubDate>Thu, 31 Jul 2025 11:05:23 GMT</pubDate>
      <guid>https://rip.trb.org/View/2582580</guid>
    </item>
    <item>
      <title>Effects of Automated Speed Enforcement on Crashes Involving Pedestrians and Bicyclists






</title>
      <link>https://rip.trb.org/View/2570609</link>
      <description><![CDATA[Speed is a crucial factor in the probability of crashes occurring and crash severity. Automated speed enforcement (ASE) has been shown to reduce speeding and speed-related motor vehicle crashes. The National Highway Traffic Safety Administration (NHTSA) has identified automated enforcement as a speed management countermeasure in their Highway Safety Countermeasure Guide for State Highway Safety Offices (SHSOs). The Federal Highway Administration (FHWA) also lists speed cameras as part of their collection of proven safety countermeasures. ASE is a valuable tool that can help SHSOs and local agencies reduce speeding, speed-related crashes, and crash severity.

Many states and local jurisdictions are considering the use of speed cameras to reduce the frequency and severity of vulnerable road user crashes. However, the effects of ASE on crashes involving pedestrians and bicyclists is a gap in the research literature. Research is needed to quantify safety impacts and inform implementation strategies, and develop a better understanding of the influence of roadway context.

The objective of this research is to develop a guide for SHSOs and other stakeholders that:
(1) Quantifies the effects of ASE on crashes involving pedestrians, bicyclists, and other nonmotorized users; (2) Examines how roadway context and related factors influence the safety impacts of ASE; and (3) Identifies key considerations for planning and implementing ASE programs to improve safety for vulnerable road users.
]]></description>
      <pubDate>Tue, 01 Jul 2025 14:37:48 GMT</pubDate>
      <guid>https://rip.trb.org/View/2570609</guid>
    </item>
    <item>
      <title>Investigation of Emerging Sensing and AI/ML Technologies to Enhance the Safety of Vulnerable Roadway Users at Signalized Intersection</title>
      <link>https://rip.trb.org/View/2553153</link>
      <description><![CDATA[Accurately identifying and analyzing vulnerable roadway users (VRUs) such as pedestrians, bicyclists, and other non-vehicle occupants, are a crucial yet difficult undertaking. VRUs’ behavior is influenced by localized factors such as land use, and their movements are not confined to predefined paths. This study will investigate the use of emerging technologies such as LiDAR, network cameras, and artificial intelligence/machine learning (AI/ML) algorithms to capture the movements and behaviors of vulnerable road users (VRUs). By evaluating pedestrian demand, including the volume and characteristics of pedestrian traffic, this research aims to assess and improve the safety of intersections.
This project will start with a comprehensive study of the state-of-the-art methods of VRU data collection, image- and LiDAR-based VRU object detection and classification, and dynamic VRU trajectory estimation methods. Next, a candidate study intersection will be reviewed and selected for the sensor installation and data collection. The LiDARs and Cameras will be synchronized with the field processing unit and the retrieved data will be transferred and saved to be further analyzed. 
In the model development process, three traffic data collection framework will be designed: a roadside LiDAR-based VRU data collection, video-based VRU data collection, and an integrated framework.
]]></description>
      <pubDate>Tue, 13 May 2025 19:09:57 GMT</pubDate>
      <guid>https://rip.trb.org/View/2553153</guid>
    </item>
    <item>
      <title>CCTV Pole Solar Panel Wrap</title>
      <link>https://rip.trb.org/View/2483293</link>
      <description><![CDATA[The major objectives of the project are as follows: (1) research if flexible solar panels can be bent to wrap around a CCTV pole; (2) investigate if the panels can withstand impacts from lowering the suspended camera on windy days; (3) determine how often the panels need to be cleaned to maintain effectiveness and to develop some sight characteristic guidance for deployment consideration (shade tolerance); and (4) explore feasibility studies on the cost to benefit ratio the additional maintenance will require versus existing operating costs, also to discover a break point of frequency of deployment, pole height, site spacing, economies of scale, etc. 

The innovative part of this project is the use of flexible solar panels. This feature will help to minimize structural wind load on existing poles. Rigid solar panels have been in use but require ground mounting, additional real estate, enhanced crash protections, and if pole is mounted, it requires a structurally upgraded pole to withstand the wind resistance.]]></description>
      <pubDate>Thu, 26 Dec 2024 16:07:01 GMT</pubDate>
      <guid>https://rip.trb.org/View/2483293</guid>
    </item>
    <item>
      <title>Estimating Daytime Population for Data-Driven Urban Planning</title>
      <link>https://rip.trb.org/View/2458991</link>
      <description><![CDATA[The COVID-19 pandemic and the subsequent increase in remote work have changed how people move around cities and where people spend their time during the day, shifting the daytime population to different streets and neighborhoods. Accurately estimating this daytime population is essential for data-informed urban planning, as it impacts infrastructure, transportation service needs, and land use decisions. Partnering with the New York City Department of City Planning, (NYC DCP), this project aims to leverage Artificial Intelligence (AI) and computer vision to analyze video data from over 900 traffic cameras across NYC to estimate daytime population. The primary objectives include classifying cameras by street hierarchy, extracting vehicle and vulnerable road user (e.g., pedestrian) information (e.g., density) on both street level and community level, and using spatial analysis to explore the collective impact of various factors on traffic congestion and urban dynamics. This will provide timely insights for improving urban infrastructure, land use planning, and decision-making, enhancing accessibility, and reducing traffic congestion.]]></description>
      <pubDate>Thu, 21 Nov 2024 17:20:10 GMT</pubDate>
      <guid>https://rip.trb.org/View/2458991</guid>
    </item>
    <item>
      <title>A Cost-Efficient Digital Twin Approach Using Pan-Tilt-Zoom Cameras to Enhance Urban Mobility Situational Awareness</title>
      <link>https://rip.trb.org/View/2459070</link>
      <description><![CDATA[Pan-tilt-zoom (PTZ) cameras are widely deployed across U.S. cities to support Traffic Management Centers (TMCs) in real-time traffic monitoring and rapid response to incidents. Since 2009, the New York State Department of Transportation (NYSDOT)'s 511NY program has utilized over 1,700 PTZ cameras statewide, mainly at key intersections, for 360-degree coverage. This research leverages the extensive PTZ network in a three-stage approach to enhance urban mobility situational awareness. First, the project will employ cooperative control and spatio-temporal prediction methods to enable real-time, network-wide traffic monitoring. Next, it will integrate these controls with the SUMO traffic simulator to create an Urban Mobility Digital Twin (UMDT) for improved situational awareness. Finally, the project will validate the PTZ control scheme and UMDT using AIWaysion-provided data and devices. The UMDT will synthesize driver-centric information, detect safety and mobility risks, and support proactive decision-making in transportation management. Expected outcomes include enhanced insights and capabilities for states and communities using PTZ cameras.]]></description>
      <pubDate>Thu, 21 Nov 2024 17:02:04 GMT</pubDate>
      <guid>https://rip.trb.org/View/2459070</guid>
    </item>
    <item>
      <title>Red Light Camera Expansion in New York City: Spillover Effect, Behavioral Insights and Strategic Allocation</title>
      <link>https://rip.trb.org/View/2459059</link>
      <description><![CDATA[Red Light Cameras (RLCs) are being deployed across various cities in the U.S. as tools to combat red-light running behavior at intersections on arterial roads which can lead to severe crashes and fatalities. Launched in 1994, New York City (NYC)'s Red Light Camera Program has played a vital role in enhancing traffic safety over the past three decades. The current deployment consists of 150 locations (1% of city intersections), each issuing a $50 fine for red light violations. According to the NYC Department of Transportation (NYC DOT), red light running has been reduced by 73% at locations with cameras, T-bone collisions have dropped by 65%, and rear-end collisions have fallen by 49%. In June 2024, New York State passed a renewal and expansion of the Red Light Camera Program to cover 5% of intersections (~600 locations). This provides an opportunity to evaluate the expansion’s impact and determine if it could further improve traffic safety and compliance, potentially leading to other benefits such as reduced congestion due to fewer incidents from red light running. This research project, in partnership with NYC DOT, aims to provide timely analytical support for the expansion of NYC's Red Light Camera Program. Through spatiotemporal analysis of historical RLC data combined with transportation and demographic data, the project will provide insights on the longitudinal effectiveness of the current program. Moreover, predictive analysis based on machine learning and spatial models will be developed to estimate the RLC network spillover effect and recommend strategic allocation of cameras to achieve the desired impact. This will help NYC DOT make data-driven decisions to maximize the program's benefits throughout the expansion. The expanded RLC network is expected to reduce intersection incidents, improve traffic flow, and decrease congestion, contributing to overall mobility and safety. The findings will also provide valuable insights for other states and communities with red light safety camera programs.]]></description>
      <pubDate>Thu, 21 Nov 2024 16:54:25 GMT</pubDate>
      <guid>https://rip.trb.org/View/2459059</guid>
    </item>
    <item>
      <title>Digital Twin for Driving as Planning Support Tool</title>
      <link>https://rip.trb.org/View/2440022</link>
      <description><![CDATA[Digital tools for mapping are now an integral tool for navigation. Waze, Google maps have leveraged Satellite and Google Street imagery which allow us to have an accurate representation of any set of Global Positioning System (GPS) coordinates. This technology evolved just a couple of months ago with the release in May 2023 of dynamic models of the Earth. Companies like Cesium, a Google backed up startup based in Philadelphia is offering Unity and Unreal models of the Earth, with an Application Programming Interface (API) that can be leveraged for any dynamic Geospatial application. While a number of drone applications have been developed, no solid test has been developed for a driving application.
This proposal continues a project with Jitsik LLC, a small startup in Mixed Reality, testing the Unity and Unreal API of the Earth to create Virtual Reality models and extends the work for application as a planning support tool. The research team proposes to continue to focus on Roosevelt Blvd in Philadelphia, which has already been the subject of academic research (Dr.Guerra) and is at the center of ongoing advocacy work by Dr. Guerra’s PhD student Jay Arzu to redesign the Boulevard to improve safety and accommodate high-capacity transit infrastructure. The main idea is to develop drivable virtual models of existing conditions, as well as proposed infrastructural changes, such as lane removals, an elevated train, and exclusive bus only lanes. This environment will support the Environmental Impact Review process as state agencies develop locally preferred investment priorities and design alternatives to share with the public.
The research team will also work with the City of Philadelphia to identify and install cameras on roadway segments that will receive speed camera enforcement based on new legislation. The team will develop digital twins for selected roadway corridors and control segments. The team will also collect camera data from before and after camera enforcement to examine how speed cameras affect driver behavior and use these data to simulate driver behavior for their digital twin simulator.
By developing and interactive model, the team hopes to help residents better understand the implications of public policies, such as speed cameras and roadway redesigns, and democratize the review process, which currently often requires a basic understanding of plan views, sections, and other technical drawings for full citizen interaction.

Please note that this project is a continuation of a year one project and includes the same partners.
]]></description>
      <pubDate>Sun, 13 Oct 2024 09:30:31 GMT</pubDate>
      <guid>https://rip.trb.org/View/2440022</guid>
    </item>
    <item>
      <title>SPR-4930:  Further Refinement and Integrated Platform for INDOT Traffic Management and Safety Toolset</title>
      <link>https://rip.trb.org/View/2401904</link>
      <description><![CDATA[This project addresses INDOT's need to use highway surveillance cameras to gather traffic information, such as flow rate, weaving data, and traffic anomaly detection.  TASI and INDOT will work on two objectives: (1) the expansion and refinement of the anomaly detection method being developed, (2) the development of a user-friendly system that integrates the software developed for lane-based flowrate detection, weaving analysis, and anomaly detection in the past and present, and other TASI and INDOT jointly developed traffic management tools in the near future. The final system will be deployed
to INDOT for daily operations.
]]></description>
      <pubDate>Tue, 09 Jul 2024 14:48:00 GMT</pubDate>
      <guid>https://rip.trb.org/View/2401904</guid>
    </item>
  </channel>
</rss>