Map-matching technology is a key and difficult technology in the development of vehicle navigation systems. Only by correctly identifying the road segment on which the vehicle is traveling can the navigation system make the right decision. At the same time, the complexity of the road network structure and a variety of error factors have introduced great challenges to map matching and have attracted the attention of many researchers as well. This paper analyzes various map-matching algorithms, determines that the key to the matching performance is the junction matching, performs an in-depth study on the junction-matching problem, and puts forward the junction decision domain model. The model mainly involves information regarding the width of the road segment, the angle between two road segments, the accuracy of GPS and the accuracy of the road network. In this paper, we use this model to improve the map-matching algorithm based on a hidden Markov model (HMM). The experimental results show that the improved matching algorithm can effectively reduce the error rate of junction matching and improve the matching performance of a navigation system.

Comparisons of results between different map-matching algorithms.

Map Matching Software Market Outlook

According to our latest research, the global map matching software market size reached USD 1.82 billion in 2024, demonstrating robust expansion across key sectors. The market is expected to grow at a CAGR of 11.7% from 2025 to 2033, projecting a value of USD 5.13 billion by 2033. This remarkable growth is primarily driven by the increasing integration of real-time location intelligence in transportation, logistics, automotive, and public sector applications, coupled with the rapid advancements in connected and autonomous vehicle technologies.

One of the primary growth factors for the map matching software market is the exponential rise in demand for accurate geospatial data to support navigation and route optimization. With the proliferation of IoT devices, smart mobility solutions, and telematics, organizations are increasingly relying on map matching algorithms to align raw GPS data with digital map data, thereby enhancing the precision of location-based services. The surge in fleet management solutions across logistics and transportation industries, where real-time vehicle tracking and route optimization are critical, has further accelerated the adoption of map matching software. Additionally, the growth in urbanization and the need for efficient traffic management systems in metropolitan areas are driving governments and public sector agencies to invest in advanced map matching solutions.

Another significant driver of market growth is the evolution of autonomous vehicles and the broader automotive sector. As automotive manufacturers and technology companies race to develop self-driving cars, the necessity for high-precision mapping and real-time road network data has become paramount. Map matching software plays a crucial role in enabling autonomous vehicles to interpret their position relative to roadways, intersections, and traffic conditions, thereby ensuring safe and reliable navigation. This technological shift is not only fueling investments in map matching algorithms but also fostering collaborations between automotive OEMs, software vendors, and mapping service providers. The ongoing digital transformation in automotive and transportation is expected to sustain high demand for map matching solutions throughout the forecast period.

The market is also witnessing significant traction due to the increasing adoption of location-based services (LBS) across diverse industries such as retail, utilities, and public safety. Businesses are leveraging map matching software to enhance customer experiences through personalized offers, optimized delivery routes, and improved service reliability. In the utilities sector, map matching enables precise asset tracking and maintenance scheduling, contributing to operational efficiency. The integration of artificial intelligence and machine learning with map matching algorithms is further amplifying the capabilities of these solutions, enabling predictive analytics and real-time decision-making. These technological advancements, combined with the growing ecosystem of smart cities and connected infrastructure, are expected to provide sustained impetus to market growth.

From a regional perspective, North America currently dominates the global map matching software market, owing to the early adoption of advanced transportation systems, a strong presence of leading automotive and technology firms, and significant investments in smart infrastructure. Europe follows closely, driven by stringent regulations on road safety and environmental sustainability, as well as widespread deployment of intelligent transport systems. Asia Pacific is poised for the fastest growth during the forecast period, fueled by rapid urbanization, expanding logistics networks, and government initiatives to modernize transportation infrastructure. Emerging markets in Latin America and Middle East & Africa are also showing increasing interest in map matching solutions, particularly in sectors such as logistics, utilities, and public safety, as they seek to address urban mobility challenges and improve service delivery.

Component Analysis

The component segment of the map matching software market is bifurcated into software and services, each playing a pivotal role in the ecosystem. The software segment includes standalone map matching applications, embedded mapping modules, an

Test result of DS 2.

Test result of DS 1.

Abstract

The Ghana Millennium Development Authority's (MiDA) Agriculture Project within the Government of Ghana's Compact with the Millennium Challenge Corporation is design to improve farming in a number of areas. Under the Agricultural Project being implemented by (MiDA) some feeder roads are to be rehabilitated or reconstructed to promote development in the sector. In the first phase, about 336 km of feeder roads in eight (8) districts in two intervention zones are to be rehabilitated to reduce transportation costs and time, and increase access to major domestic and international markets. The feeder roads activity will also facilitate transportation linkages from rural areas to social service networks (including hospitals, clinics and schools).

The purpose of this project is to conduct an impact evaluation of the MiDA's Feeder Roads Activity. As stated in the Terms of Reference of the request for proposals, "the primary data for the impact evaluation will be a series of surveys similar in scope to the Consumer Price Index (CPI) survey, examining changes in prices over time Findings from the market surveys will contribute to the overall impact evaluation conducted by the Institute of Statistical, Social and Economic Research (ISSER). The Ghana Living Standards Survey (GLSS) 5+ is the primary instrument used in the overall evaluation, and 'Difference in Difference' is the proposed method of evaluation of data."

Thus, this study focuses on how prices of goods sold at local markets (that are transported on improved roads) change over time. It is also to document the changes in goods transport tariffs and passenger fares to market places served by the feeder roads.

The sample design uses a carefully tailored algorithm employed to match 154 localities that will benefit from the road improvements with an identical number of control localities that are comparatively far from the improvements. The sample size is sufficient to provide robust estimates of price effects associated with the road improvements. The minimum population for a locality to be included in the sample is 1,000, a condition imposed to help ensure that most designated items could be found in most localities.

Beginning in August 2009 interviewers visited the sample localities to obtain three price observations for each item in the defined "basket" of goods and transportation services. The final "basket" contains 39 fresh food items, 24 packaged food items, 19 non food items and 6 transportation tariffs-3 for the locality's residents' most frequent passenger destinations and 3 for the most frequent freight destinations.

Geographic coverage

308 localities in Ghana - 154 localities that will benefit from the road improvements with an identical number of control localities that are comparatively far from the improvements.

Analysis unit

The main unit of analysis is a market. Within each market, we priced the following items at up to three different vendors: 39 fresh food items, 24 packaged food items, 19 non food items and 6 transportation tariffs-3 for the locality's residents' most frequent passenger destinations and 3 for the most frequent freight destinations.

Universe

The data is only meant to represent the 308 localities surveyed. The results cannot be generalized to a larger population. The objective was not to produce estimates of national means and totals, but to estimate the parameters of an analytical model of program impact.

Kind of data

Sample survey data [ssd]

Sampling procedure

In the present application, the approach that is being used, in lieu of randomization, to select a control sample is statistical matching. A matched-pairs design was used, matching 174 (154 plus 20 replacements) treatment localities to 174 control localities using nearest-neighbor matching. Sampling was restricted, as mentioned earlier, to localities having population 1,000 or more (according to the 2000 Census) and to the 20 largest localities in each district.

The treatment population included all localities within 120 minutes estimated travel time of the nearest MiDA program road, and the control population included all localities located more than 120 minutes estimated travel time from the nearest MiDA program road. (The estimated travel times were calculated using a GIS model of the Ghana road network (documented separately).) This resulted in resulted in population sizes of 675 treatment units and 848 control units. Sampling was restricted to all of the country except Western Region.

Matching was based on a number of variables, including population, travel time to Accra, travel time to the nearest MiDA feeder road, and physiographic data.

The sample localities occur at all distances from the program roads, since it was desired to have substantial variation in the travel time to the program roads.

Because of the sample design process, the sample has reasonable spread, balance and orthogonality for a large number of design variables. Also, the sample includes a control sample for which the units are individually matched to units in the treatment sample. The sample will be a very good one for use in estimating an analytical model showing the relationship of program impact (price changes) to the Ghana MiDA feeder-road improvements, and for estimating a double-difference estimate of program impact.

Sampling deviation

Of the 308 sampled localities only one locality was removed from the sample because we were unable to locate it. This locality, Choo #0155, was not located and was removed along with its matching pair, Sabiye #0159. These localities were replaced with Suame #0812 and Ogbodzo #1264. All other localities were located and surveyed.

Mode of data collection

Face-to-face [f2f]

Research instrument

During the initial visit the NORC FM identified a subset of items on the GLSS surveys to identify and price in the market. This initial pricing and observation allowed for a detailed understanding of the impediments interviewers may encounter during data collection. After observing local conditions the NORC FM met with his counterparts on the local subcontractor team (Pentax Management and Consulting) to carry out an item by item review of the GLSS survey. Through this review NORC and Pentax were able to refine the GLSS survey to meet the needs of the current study. Standard weights and product types were identified for the majority of products, non important items were deleted in order to reduce the time of the survey, and possible fielding issues were discussed with resolutions identified.

The three questionnaires are attached to this document - one for the pricing of goods, one for the pricing of tariff and passenger costs, and one for collecting information on the locality.

Cleaning operations

Data editing was done in the field by supervisors, and double data entry was carried out by Pentax. After receiving data from Pentax, NORC assisted with reconciliation between the first and second entries. After reconciling the data, NORC carried out significant data cleaning, including some imputation of values for missing observations. For a detailed explanation of data editing and cleaning, please refer to the attached “Phase 1, Baseline Findings” report. For the raw dataset receioved by NORC from Pentax, see the attached "Raw Data". For SPSS scripts detailing cleaning done on the dataset, see "SPSS Scripts".

Cloud Map Matching for Fleets Market Outlook

According to our latest research, the global Cloud Map Matching for Fleets market size reached USD 1.82 billion in 2024, with a robust compound annual growth rate (CAGR) of 13.8% projected through the forecast period. By 2033, the market is expected to reach USD 5.17 billion, driven by the increasing adoption of advanced navigation technologies, the proliferation of connected vehicles, and the growing need for real-time fleet optimization. The market’s expansion is further fueled by the rising demand for cloud-based solutions, which offer scalability, flexibility, and cost efficiency for fleet operators worldwide.

A critical growth factor for the Cloud Map Matching for Fleets market is the rapid digital transformation within the transportation and logistics sectors. As organizations strive to optimize their fleet operations, there is a significant emphasis on leveraging cloud-based platforms for real-time data processing and analytics. The integration of artificial intelligence and machine learning algorithms into map matching solutions enables fleets to achieve higher accuracy in route planning, reduce operational costs, and improve fuel efficiency. Additionally, the surge in e-commerce and on-demand delivery services has heightened the need for efficient fleet management, further accelerating the adoption of cloud map matching technologies.

Another pivotal driver is the increasing regulatory pressure on fleet operators to enhance safety, reduce emissions, and comply with stringent government mandates. Cloud map matching solutions facilitate compliance by providing precise vehicle tracking, route optimization, and timely reporting capabilities. These platforms enable transportation companies to monitor driver behavior, ensure adherence to legal requirements, and mitigate risks associated with non-compliance. Moreover, the growing trend of urbanization and smart city initiatives is creating new opportunities for cloud map matching providers, as municipalities and public transport agencies seek innovative tools to manage traffic congestion and improve public mobility.

The evolution of telematics and the emergence of the Internet of Things (IoT) have also played a crucial role in propelling the Cloud Map Matching for Fleets market. Modern fleets are increasingly equipped with IoT sensors and connected devices that generate vast volumes of location and operational data. Cloud-based map matching platforms are uniquely positioned to harness this data, transforming it into actionable insights for fleet managers. The ability to seamlessly integrate with other enterprise systems, such as fleet management software and ERP solutions, further enhances the value proposition of cloud map matching, driving widespread adoption across diverse industry verticals.

From a regional perspective, North America continues to lead the Cloud Map Matching for Fleets market, accounting for the largest revenue share in 2024, followed closely by Europe and Asia Pacific. The strong presence of established technology providers, high penetration of connected vehicles, and early adoption of advanced fleet management solutions are key factors contributing to North America’s dominance. However, the Asia Pacific region is witnessing the fastest growth, fueled by expanding logistics networks, government investments in smart transportation infrastructure, and the rapid digitalization of fleet operations in emerging economies such as China and India. This dynamic regional landscape underscores the global nature of the market and the diverse opportunities for stakeholders across different geographies.

Component Analysis

The Component segment in the Cloud Map Matching for Fleets market is broadly categorized into Software, Hardware, and Services. The Software sub-segment dominates the market, owing to the increasing reliance on sophisticated algorithms and cloud platforms that deliver real-time map matching, route optimization, and analytics. Fleet operators are increasingly investing in software solutions that offer seamless integration with existing fleet management systems, enhanced user interfaces, and customizable features tailored to specific operational requirements. The demand for software is further propelled by the growing need for scalable and flexible solutions that can adapt to evolving business needs and technological advancements.

Basic information of testing routes.

A trajectory restoration algorithm for low-sampling-rate floating car data and complex urban road networks

When planning road construction measures, it is essential to have up-to-date information on road conditions. If this information is not to be obtained manually, it is currently obtained using laser scanners mounted on mobile mapping vehicles, which can measure the 3D road profile. However, a large number of mobile mapping vehicles would be necessary to record an entire road network on a regular basis. Since 2D road damages can be found automatically on monocular camera images, the idea was born to use a stereo camera system to capture the 3D profile of roads. With stereo camera systems, it would be possible to equip a large number of vehicles and regularly collect data from large road networks. In this thesis, the potential applications of a stereo camera system for measuring road profiles, which is mounted behind the windshield of a vehicle, are investigated. Since this requires a calibration of the stereo camera system, but the effort for the user should be kept low, the camera self-calibration for this application is also examined. 3D reconstruction from stereoscopic images is a well-studied topic, but its application on road surfaces with little and repetitive textures requires special algorithms. For this reason, a new stereo method was developed. It is based on the plane-sweep approach in combination with semi-global matching. It was tested with different measures for pixel comparison. Furthermore, the plane-sweep approach was implemented in a neural network that solves the stereo correspondence problem in a single step. It uses the stereoscopic images as input and provides an elevation image as output. A completely new approach was developed for the self-calibration of mono cameras and stereo camera systems. Previous methods search for feature points in several images of the same scene. The points are matched between the images and used for the calibration. In contrast to these methods, the proposed method uses feature maps instead of feature points to compare multiple views of one and the same plane. To estimate the unknown parameters, the backpropagation algorithm is used together with the gradient descent method. The measurements obtained by stereoscopic image processing were compared with those obtained by industrial laser scanners. They show that both measurements are very close to each other and that a stereoscopic camera system is in principle suitable for capturing the surface profile of a road. Experiments show that the proposed self-calibration method is capable of estimating all parameters of a complex camera model, including lens distortion, with high precision.

The rapid growth of traffic trajectory data and the development of positioning technology have driven the demand for its analysis. However, in the current application scenarios, there are some problems such as the deviation between positioning data and real roads and low accuracy of existing trajectory data traffic prediction models. Therefore, a map matching algorithm based on hidden Markov models is proposed in this study. The algorithm starts from the global route, selects K nearest candidate paths, and identifies candidate points through the candidate paths. It uses changes in speed, angle, and other information to generate a state transition matrix that match trajectory points to the actual route. When processing trajectory data in the experiment, K = 5 is selected as the optimal value, the algorithm takes 51 ms and the accuracy is 95.3%. The algorithm performed well in a variety of road conditions, especially in parallel and mixed road sections, with an accuracy rate of more than 96%. Although the time loss of this algorithm is slightly increased compared with the traditional algorithm, its accuracy is stable. Under different road conditions, the accuracy of the algorithm is 98.3%, 97.5%, 94.8% and 96%, respectively. The accuracy of the algorithm based on traditional hidden Markov models is 95.9%, 95.7%, 95.4% and 94.6%, respectively. It can be seen that the accuracy of the algorithm designed has higher precision. The experiment proves that the map matching algorithms based on hidden Markov models is superior to other algorithms in terms of matching accuracy. This study makes the processing of traffic trajectory data more accurate.

This thesis deals with problems from the theory of finite directed graphs. A directed graph (digraph for short) is a binary relation whose domain has finite size. With that digraphs can be seen as a very general way of representing (possibly asymmetric) relations between pairs from a finite set of objects. Undoubtedly, such a generality allows to encode many structures by digraphs. This works particularly well if important properties of the structure at hand can be expressed as relations or connections between objects. To give some selected examples, let us mention road networks, electricity networks, radio networks, the world wide web, circuits in electronic devices, or neural networks. A main focus of the thesis at hand is the investigation of properties of one of the most fundamental objects all over graph theory, the so-called cycle (sometimes also called circuit). A cycle in a graph is determined by a closed alternating sequence of cyclically connected vertices and edges. In a graph of finite size one will typically see loads of distinct cycles of various types. Therefore cycles constitute an important and recurring motive in almost all branches of graph theory, for instance, they play important roles in structural graph theory, in the theory of flows on directed networks, in theoretical characterizations of graph classes, as well as in the theory of graph colorings. Additionally, cycles play a decisive role in numerous algorithmic problems and their solutions, such as in the Traveling Salesman Problem, algorithms for finding a largest matching in a given graph, in the max-flow problem, and also in subprocedures such as Kruskal's algorithm for finding a minimum weight spanning tree. For those reasons, a substantial amount of research in graph theory has specialised on the structure of cycles in graphs. In the first major part of this thesis we deal with cycles which occur in directed graphs, and prove several necessary and sufficient theoretical conditions for the existence of cycles of certain types. Additionally, we deal with algorithmic problems related to cycles in directed graphs. In the second part we deal with the problem of acyclic colorings of directed graphs, which also relates to the (non-)existence of certain cycles. The dichromatic number represents an optimization problem in which we seek to color the vertices of a given digraph with the fewest number of colors while avoiding monochromatic directed cycles. This topic was introduced 40 years ago by Paul Erdős and Victor Neumann-Lara and since then, particularly in the last two decades, has been considered by many researchers. In this thesis we contribute new results that on the one hand establish new theoretical bounds on the dichromatic number and on the other hand shed more light on the computational complexity of this problem. The third and last major part of this thesis carries on with the topic of digraph colorings and presents new results for various further notions of digraph coloring and ways of decomposing a given digraph into the fewest number of simpler subdigraphs.

The rapid growth of traffic trajectory data and the development of positioning technology have driven the demand for its analysis. However, in the current application scenarios, there are some problems such as the deviation between positioning data and real roads and low accuracy of existing trajectory data traffic prediction models. Therefore, a map matching algorithm based on hidden Markov models is proposed in this study. The algorithm starts from the global route, selects K nearest candidate paths, and identifies candidate points through the candidate paths. It uses changes in speed, angle, and other information to generate a state transition matrix that match trajectory points to the actual route. When processing trajectory data in the experiment, K = 5 is selected as the optimal value, the algorithm takes 51 ms and the accuracy is 95.3%. The algorithm performed well in a variety of road conditions, especially in parallel and mixed road sections, with an accuracy rate of more than 96%. Although the time loss of this algorithm is slightly increased compared with the traditional algorithm, its accuracy is stable. Under different road conditions, the accuracy of the algorithm is 98.3%, 97.5%, 94.8% and 96%, respectively. The accuracy of the algorithm based on traditional hidden Markov models is 95.9%, 95.7%, 95.4% and 94.6%, respectively. It can be seen that the accuracy of the algorithm designed has higher precision. The experiment proves that the map matching algorithms based on hidden Markov models is superior to other algorithms in terms of matching accuracy. This study makes the processing of traffic trajectory data more accurate.

The rapid growth of traffic trajectory data and the development of positioning technology have driven the demand for its analysis. However, in the current application scenarios, there are some problems such as the deviation between positioning data and real roads and low accuracy of existing trajectory data traffic prediction models. Therefore, a map matching algorithm based on hidden Markov models is proposed in this study. The algorithm starts from the global route, selects K nearest candidate paths, and identifies candidate points through the candidate paths. It uses changes in speed, angle, and other information to generate a state transition matrix that match trajectory points to the actual route. When processing trajectory data in the experiment, K = 5 is selected as the optimal value, the algorithm takes 51 ms and the accuracy is 95.3%. The algorithm performed well in a variety of road conditions, especially in parallel and mixed road sections, with an accuracy rate of more than 96%. Although the time loss of this algorithm is slightly increased compared with the traditional algorithm, its accuracy is stable. Under different road conditions, the accuracy of the algorithm is 98.3%, 97.5%, 94.8% and 96%, respectively. The accuracy of the algorithm based on traditional hidden Markov models is 95.9%, 95.7%, 95.4% and 94.6%, respectively. It can be seen that the accuracy of the algorithm designed has higher precision. The experiment proves that the map matching algorithms based on hidden Markov models is superior to other algorithms in terms of matching accuracy. This study makes the processing of traffic trajectory data more accurate.

The rapid growth of traffic trajectory data and the development of positioning technology have driven the demand for its analysis. However, in the current application scenarios, there are some problems such as the deviation between positioning data and real roads and low accuracy of existing trajectory data traffic prediction models. Therefore, a map matching algorithm based on hidden Markov models is proposed in this study. The algorithm starts from the global route, selects K nearest candidate paths, and identifies candidate points through the candidate paths. It uses changes in speed, angle, and other information to generate a state transition matrix that match trajectory points to the actual route. When processing trajectory data in the experiment, K = 5 is selected as the optimal value, the algorithm takes 51 ms and the accuracy is 95.3%. The algorithm performed well in a variety of road conditions, especially in parallel and mixed road sections, with an accuracy rate of more than 96%. Although the time loss of this algorithm is slightly increased compared with the traditional algorithm, its accuracy is stable. Under different road conditions, the accuracy of the algorithm is 98.3%, 97.5%, 94.8% and 96%, respectively. The accuracy of the algorithm based on traditional hidden Markov models is 95.9%, 95.7%, 95.4% and 94.6%, respectively. It can be seen that the accuracy of the algorithm designed has higher precision. The experiment proves that the map matching algorithms based on hidden Markov models is superior to other algorithms in terms of matching accuracy. This study makes the processing of traffic trajectory data more accurate.

The rapid growth of traffic trajectory data and the development of positioning technology have driven the demand for its analysis. However, in the current application scenarios, there are some problems such as the deviation between positioning data and real roads and low accuracy of existing trajectory data traffic prediction models. Therefore, a map matching algorithm based on hidden Markov models is proposed in this study. The algorithm starts from the global route, selects K nearest candidate paths, and identifies candidate points through the candidate paths. It uses changes in speed, angle, and other information to generate a state transition matrix that match trajectory points to the actual route. When processing trajectory data in the experiment, K = 5 is selected as the optimal value, the algorithm takes 51 ms and the accuracy is 95.3%. The algorithm performed well in a variety of road conditions, especially in parallel and mixed road sections, with an accuracy rate of more than 96%. Although the time loss of this algorithm is slightly increased compared with the traditional algorithm, its accuracy is stable. Under different road conditions, the accuracy of the algorithm is 98.3%, 97.5%, 94.8% and 96%, respectively. The accuracy of the algorithm based on traditional hidden Markov models is 95.9%, 95.7%, 95.4% and 94.6%, respectively. It can be seen that the accuracy of the algorithm designed has higher precision. The experiment proves that the map matching algorithms based on hidden Markov models is superior to other algorithms in terms of matching accuracy. This study makes the processing of traffic trajectory data more accurate.

The data are composed by the coordinates of the intersection (NODES) of the road map (LINKS) of the downtown of Shenzhen, China. In the file SPEEDS there are the estimation of the space-mean links speed every 5 mins computed after a map matching algorithm of available of about 20,000 taxis' GPS points with the road map. The day taken in consideration are the 7th, 8th and 9th September 2011.

1. OverviewRoad intersections are crucial nodes in urban networks, where transportation lanes converge and socioeconomic activity is concentrated. While methods to identify road intersections using raster maps, satellite images, and trace data have been explored, challenges in accuracy and consistency remain.This paper proposes a method for identifying intersections based on OpenStreetMap data, which records networks at the lane level. Unlike geometric line intersections in OpenStreetMap, the identified intersections “summarize” parallel lanes and incorporate branch information, such as counts and orientations. The proposed method uses a vector-raster fusion approach to initially locate intersections, followed by hierarchical geometric configuration to improve accuracy and extract branch data.Experimental results show that the method effectively handles complex road networks in various cities, accurately identifying intersections and their branches. Experiments conducted on OpenStreetMap data from 7 cities yielded over 98% precision and 97% recall, outperforming the popular OSMnx tool. Additionally, lane synthesis at intersections achieved 99.43% precision and 98.34% recall. Urban characteristics can be quantitatively analyzed based on the identified road intersections. For instance, the proportion of four-way road intersections in New York is 52.6%, whereas in London, it is 9.6%, which may be attributed to the differing urban histories of these cities.2. Instructions for dataThis dataset contains road intersection data of seven cities (Berlin, Beijing, London, Nanjing, New York City, Rome, Shanghai) identified by our proposed method.The data of each city are stored in the folder named by its abbreviation.In each folder, there will be five *.shp files:(1) Roadnetwork (roads.shp)This layer stores the OSM road network with tag attributes.(2) Intersection points (cross-res.shp)This layer stores the location of the intersection point and the general characteristics of the road layout, including the number of intersecting roads and layout type. This provides the necessary location information for mapping and spatial analyses.(3) Related road lines (fullLine-res.shp/fail-fullLine.shp)The original road lines related to intersections extracted from the road networks were stored in this layer, preserving the inherent attributes of the original dataset. In addition, matching information, indicating whether the lines represent the same road, was stored as an attribute.(4) Synthesized road lines (simpleLine-res.shp)The geometries of this layer store synthesized road lines representing road orientations, whereas the attributes store acquired characteristics, including roadway configurations and match indices, which allow the synthesized road lines to be connected to the original roads from which they were derived. This connection is achieved through “pt_id” linked with cross-res.shp and “match_id” linked with fullLine-res.shp.3. Instructions for codesThis code repository is organized into eight folders and two files:(1) Folder: candidateIdentifyThis folder contains code related to the identification of candidate junctions or intersections from the input data. Each script plays a specific role in the overall process:bufferThin.py: Implements a thinning algorithm to generate a skeleton of buffered road geometry.candidateIdentify.py: The core script for identifying candidate points for road intersections in a spatial dataset.fastJunction.py: Provides an optimized method for detecting junctions quickly in large datasets by leveraging a fast hit-or-miss operation.junctionGeo.py: Handles the geometric processing of junction points, focusing on transforming raster cells into geographical positions.(2) Folder: compareEvaluationclipByregion.py: Clips spatial data to a specific region, which is useful for limiting analysis to a predefined geographic area. This is typically used to obtain intersections identified within the randomly selected regions.(3) Folder: geometricConfigurationTemplateMatchThis folder includes tools for matching geometric templates of road intersections:templateMatcher.py: The main module that matches geometric configurations of road intersections to the determined templates.utils_g.py: Provides utility functions that assist in geometric operations and template matching processes.(4) Folder: maxRadiusBufferThis folder focuses on the code of a greedy algorithm that produces the largest nonoverlapping buffers for a given collection of points.:maxRadBuffer.py: Core script for this algorithm.(5) Folder: intersectionDistanceAnalysisThis folder contains scripts for analyzing distances between intersection points for parameter determination:distanceAnalysis.py: Calculates the distances between identified intersections and analyze their distribution.(6) Folder: proportionDrawerThis folder contains scripts using R to produce pie charts in Figure 14.(7) Folder: refineCandidateThis folder contains a script that refines the previously identified intersection candidates.refineCandidate.py: This core script refines the set of candidate intersections by applying further geometric or statistical methods.(8) Folder: resultAnalysisThis folder is used for analyzing the identified results for insights of urban characteristics:angleAnalysis.py: Compute and analyze angles between road branches at intersections.4. Instructions on how to reproduce each reported findingsThe file 'instructions_on_how_to_reproduce_each_reported_findings.md' details the steps to reproduce the figures and the tables shown in the paper.

VIS-MM: A vehicle-borne image semantic fusion-based map-matching algorithm for parallel road scenes

This dataset provides the core data supporting the manuscript entitled "Commuter Carpooling Matching Model Based on Saving-Genetic Algorithm", enabling the implementation and validation of the proposed carpool matching model.The data comprises two key files:1.Commuter Location Coordinates: Contains the geographic coordinates (latitude and longitude) of commuter origins and destinations (drivers and passengers) in Changchun City.2.Travel Distance Matrix: Provides the real-road-network travel distances between all location pairs. This matrix serves as the direct input for calculating the distance "Saving" and driving the Genetic Algorithm optimization.This dataset allows other researchers to reproduce the paper's findings and can be reused for broader transportation optimization and vehicle routing problem studies.