scholarly journals AUTOMATIC DETECTION AND RECOGNITION OF ROAD INTERSECTIONS FOR ROAD EXTRACTION FROM IMAGERY

2020 ◽  
Vol XLIII-B3-2020 ◽  
pp. 113-117
Author(s):  
P. Li ◽  
Y. Li ◽  
J. Feng ◽  
Z. Ma ◽  
X. Li
Keyword(s):  
Urban Areas ◽  
Road Network ◽  
Feature Vector ◽  
Region Of Interest ◽  
Road Extraction ◽  
Geometric Information ◽  
The Road ◽  
Contour Shape ◽  
Intersection Area ◽  
Road Intersections

Abstract. Automatic road extraction from remote sensing imagery is very useful for many applications involved with geographic information. For road extraction of urban areas, road intersections offer stable and reliable information for extraction of road network, with higher completeness and accuracy. In this paper, a segmentation-shape analysis based method is proposed to detect road intersections and their branch directions from an image. In the region of interest, it uses the contour shape of the segmented-intersection area to form a feature vector representing its geometric information. The extracted feature vector is then matched with some template vectors in order to find the best matched intersection pattern, obtain the type of intersection and the direction of connected roads. The experimental analysis are carried out with ISPRS Vaihingen and Toronto images. The experimental results show that the proposed method can extract most of the road intersections correctly. For the Vaihingen image, the the completeness and correctness are 81% and 87%, respectfully, while for the Toronto image, the the completeness and correctness are 78% and 85%, respectfully. It can help to build more correct and complete road network.

scholarly journals AUTOMATIC EXTRACTION OF ROAD CENTERLINES AND EDGE LINES FROM AERIAL IMAGES VIA CNN-BASED REGRESSION

2020 ◽  
Vol V-2-2020 ◽  
pp. 925-932
Author(s):  
Y. Wei ◽  
X. Hu ◽  
M. Zhang ◽  
Y. Xu
Keyword(s):  
Road Network ◽  
Aerial Images ◽  
Automatic Extraction ◽  
Tensor Voting ◽  
Road Extraction ◽  
The Road ◽  
Road Width ◽  
Road Intersections ◽  
On The Road ◽  
Segmentation Problem

Abstract. Extracting roads from aerial images is a challenging task in the field of remote sensing. Most approaches formulate road extraction as a segmentation problem and use thinning and edge detection to obtain road centerlines and edge lines, which could produce spurs around the extracted centerlines/edge lines. In this study, a novel regression-based method is proposed to extract road centerlines and edge lines directly from aerial images. The method consists of three major steps. First, an end-to-end regression network based on CNN is trained to predict confidence maps for road centerlines and estimate road width. Then, after the CNN predicts the confidence map, non-maximum suppression and road tracking are applied to extract accurate road centerlines and construct road topology. Meanwhile, Road edge lines are generated based on the road width estimated by the CNN. Finally, in order to improve the connectivity of extracted road network, tensor voting is applied to detect road intersections and the detected intersections are used as guidance for the overcome of discontinuities. The experiments conducted on the SpaceNet and DeepGlobe datasets show that our approach achieves better performance than other methods.

scholarly journals Optimization of Evacuation and Walking-Home Routes from Osaka City After a Nankai Megathrust Earthquake Using Road Network Big Data

2021 ◽  
pp. 369-389
Author(s):  
Atsushi Takizawa ◽  
Yutaka Kawagishi
Keyword(s):  
Big Data ◽  
Public Transportation ◽  
Urban Areas ◽  
Road Network ◽  
Large Earthquake ◽  
The Road ◽  
Return Home ◽  
Flooded Area ◽  
Network Big Data ◽  
Surrounding Areas

AbstractWhen a disaster such as a large earthquake occurs, the resulting breakdown in public transportation leaves urban areas with many people who are struggling to return home. With people from various surrounding areas gathered in the city, unusually heavy congestion may occur on the roads when the commuters start to return home all at once on foot. In this chapter, it is assumed that a large earthquake caused by the Nankai Trough occurs at 2 p.m. on a weekday in Osaka City, where there are many commuters. We then assume a scenario in which evacuation from a resulting tsunami is carried out in the flooded area and people return home on foot in the other areas. At this time, evacuation and returning-home routes with the shortest possible travel times are obtained by solving the evacuation planning problem. However, the road network big data for Osaka City make such optimization difficult. Therefore, we propose methods for simplifying the large network while keeping those properties necessary for solving the optimization problem and then recovering the network. The obtained routes are then verified by large-scale pedestrian simulation, and the effect of the optimization is verified.

scholarly journals Broadening Understanding on Managing the Communication Infrastructure in Vehicular Networks: Customizing the Coverage Using the Delta Network

2018 ◽  
Vol 11 (1) ◽  
pp. 1 ◽  
Author(s):  
Cristiano Silva ◽  
Lucas Silva ◽  
Leonardo Santos ◽  
João Sarubbi ◽  
Andreas Pitsillides
Keyword(s):  
Urban Areas ◽  
Road Network ◽  
Vehicular Networks ◽  
Urban Environments ◽  
Urban Mobility ◽  
Circle Pattern ◽  
The Road ◽  
The Past ◽  
Communication Devices ◽  
Definition Of

Over the past few decades, the growth of the urban population has been remarkable. Nowadays, 50% of the population lives in urban areas, and forecasts point that by 2050 this number will reach 70%. Today, 64% of all travel made is within urban environments and the total amount of urban kilometers traveled is expected to triple by 2050. Thus, seeking novel solutions for urban mobility becomes paramount for 21st century society. In this work, we discuss the performance of vehicular networks. We consider the metric Delta Network. The Delta Network characterizes the connectivity of the vehicular network through the percentage of travel time in which vehicles are connected to roadside units. This article reviews the concept of the Delta Network and extends its study through the presentation of a general heuristic based on the definition of scores to identify the areas of the road network that should receive coverage. After defining the general heuristic, we show how small changes in the score computation can generate very distinct (and interesting) patterns of coverage, each one suited to a given scenario. In order to exemplify such behavior, we propose three deployment strategies based on simply changing the computation of scores. We compare the proposed strategies to the intuitive strategy of allocating communication units at the most popular zones of the road network. Experiments show that the strategies derived from the general heuristic provide higher coverage than the intuitive strategy when using the same number of communication devices. Moreover, the resulting pattern of coverage is very interesting, with roadside units deployed a circle pattern around the traffic epicenter.

Coupling Natural Hazard Estimates with Road Network Analysis to Assess Vulnerability and Risk: Case Study of Freetown (Sierra Leone)

2019 ◽  
Vol 2673 (8) ◽  
pp. 11-24
Author(s):  
Andrew Nelson ◽  
Sarah Lindbergh ◽  
Lucy Stephenson ◽  
Jeremy Halpern ◽  
Fatima Arroyo Arroyo ◽  
...  
Keyword(s):  
Climate Change ◽  
Decision Making ◽  
Sierra Leone ◽  
Road Network ◽  
Natural Hazard ◽  
Transportation Infrastructure ◽  
The Road ◽  
Public Data ◽  
Road Intersections ◽  
Flooding Events

Many of the world’s most disaster-prone cities are also the most difficult to model and plan. Their high vulnerability to natural hazards is often defined by low levels of economic resources, data scarcity, and limited professional expertise. As the frequency and severity of natural disasters threaten to increase with climate change, and as cities sprawl and densify in hazardous areas, better decision-making tools are needed to mitigate the effects of near- and long-term extreme events. We use mostly public data from landslide and flooding events in 2017 in Freetown, Sierra Leone to simulate the events’ impact on transportation infrastructure and continue to simulate alternative high-risk disasters. From this, we propose a replicable framework that combines natural hazard estimates with road network vulnerability analysis for data-scarce environments. Freetown’s most central road intersections and transects are identified, particularly those that are both prone to serviceability loss due to natural hazard and whose disruption would cause the most severe immediate consequences on the entire road supply in terms of connectivity. Variations in possible road use are also tested in areas with potential road improvements, pointing to opportunities to harden infrastructure or reinforce redundancy in strategic transects of the road network. This method furthers network science’s contributions to transportation resilience under hydrometeorological hazard and climate change threats with the goal of informing investments and improving decision-making on transportation infrastructure in data-scarce environments.

Effects of Sensor Errors on the Performance of Map Matching

2005 ◽  
Vol 58 (2) ◽  
pp. 273-282 ◽  
Author(s):  
Wu Chen ◽  
Zhilin Li ◽  
Meng Yu ◽  
Yongqi Chen
Keyword(s):  
Hong Kong ◽  
Efficient Method ◽  
Urban Areas ◽  
Road Network ◽  
Dead Reckoning ◽  
Navigation Systems ◽  
Map Matching ◽  
The Road ◽  
Sensor Errors

Map matching has been widely applied in car navigation systems as an efficient method to display the location of vehicles on maps. Various map-matching algorithms have been proposed. Inevitably, the correctness of the map matching is closely related to the accuracy of positioning sensors, such as GPS or Dead Reckoning (DR), and the complexity of the road network and map, especially in urban areas where the GPS signal may be constantly blocked by buildings and the road network is complicated. The existing map matching algorithms cannot resolve the positioning problems under all circumstances. They sometimes give the wrong position estimates of the car on road; the result is called mismatching. In order to improve the quality of map matching, a deep understand of the accuracy of sensor errors on mismatching is important. This paper analyses various factors that may affect the quality of map matching based on extensive tests in Hong Kong. Suggestions to improve the success rate of map matching are also provided.

scholarly journals SPATIAL CLASSIFICATION OF TRANSPORT NETWORKS AND ITS CONNECTION WITH THE TYPOLOGY OF TRANSIT-ORIENTED DEVELOPMENT FOR THE CITIES OF NAJAF AND KUFA OF THE PROVINCE OF NAJAF

2020 ◽  
Vol 5 (9) ◽  
pp. 57-66
Author(s):  
A. Al-jaberi
Keyword(s):  
Land Use ◽  
Urban Areas ◽  
Road Network ◽  
Structural Features ◽  
Transit Oriented Development ◽  
Spatial Classification ◽  
The Road ◽  
Different Types ◽  
Gis Environment

Transport is a link between territories with different types of land use in urban areas. At the same time, the improved accessibility associated with the transport network can lead to increased segregation and a change in land use. The article analyzes the road network of the Najaf and Kufa cities, Najaf province, Iraq, in order to identify the spatial classification of roads and streets. Based on the analysis, three main types of roads and streets are identified with respect to their structural features and characteristics: regional, city and district. The dependence of the typology and location of transit-oriented zones on the classification of the road network is indicated. In the process of analyzing the study area, the most optimal points for the practice of transit-oriented development (TOD) are identified, the territories most favorable for the location of transit-oriented zones of regional, city and district significance are introduced, the main characteristics of these zones are given. In order to reach goals, this article includes the collection of data and the creation of a database for land use applying a geographic information systems (GIS) environment. The result of the spatial analysis are five regional nodes, six urban nodes and seven district nodes

Smart Cities: Study and Comparison of Traffic Light Optimization in Modern Urban Areas Using Artificial Intelligence

2018 ◽  
Vol 8 (2) ◽  
pp. 10
Author(s):  
Mustapha Kabrane ◽  
Salah-ddine Krit ◽  
Lahoucine El Maimouni
Keyword(s):  
Traffic Congestion ◽  
Urban Areas ◽  
Road Network ◽  
Smart Cities ◽  
Optimization Techniques ◽  
Traffic Light ◽  
Large Cities ◽  
Traffic Lights ◽  
The Road ◽  
Road Signs

In large cities, the increasing number of vehicles private, society, merchandise, and public transport, has led to traffic congestion. Users spend much of their time in endless traffic congestion. To solve this problem, several solutions can be envisaged. The interest is focused on the  system of road signs: The use of a road infrastructure is controlled by a traffic light controller, so it is a matter of knowing how to make the best use of the controls of this system (traffic lights) so as to make traffic more fluid. The values of the commands computed by the controller are determined by an algorithm which is ultimately, only solves a mathematical model representing the problem to be solved. The objective is to make a study and then the comparison on the optimization techniques based on artificial intelligence1 to intelligently route vehicle traffic. These techniques make it possible to minimize a certain function expressing the congestion of the road network. It can be a function, the length of the queue at intersections, the average waiting time, also the total number of vehicles waiting at the intersection

PEAK HOUR FACTOR AT URBAN ROAD NETWORK SYSTEM WITH FIXED HOURLY INTERVAL AND MOVING HOURLY INTERVAL (A CASE STUDY AT URBAN ROAD IN CIMAHI CITY)

2020 ◽  
Vol 6 (01) ◽  
pp. 29
Author(s):  
Hendra Hendrawan
Keyword(s):  
Urban Areas ◽  
Road Network ◽  
Resource Constraints ◽  
Important Variable ◽  
Network System ◽  
Urban Road Network ◽  
Hourly Interval ◽  
Urban Road ◽  
The Road

The Peak Hour Factor (PHF) is an important variable for determining road capacity. The value of PHF will vary greatly depending on location characteristics and classification of road functions. This study aims to obtain the estimated value of PHF in the urban road network system with variations in the classification of functions and types of roads. In addition this study also aims to obtain a method of approaching the PHF value near to fluctuations in traffic flow which has limited resources for surveys based on the duration specified in the traffic survey guidelines in Indonesia. The method used is descriptive statistical analysis and parametric test using Independent T sample test. The PHF is calculated based on Fixed Hourly Interval and Moving Hourly Interval and their inverse. The results of the study show the value of PHF in the road network system in urban areas for variations function and type of road that is in the range of 0.79 to 0.98 with an average of 0.91. Other findings show that the inverse method of Moving Hourly Interval can be used as an approach to obtain the PHF value under conditions of resource constraints

scholarly journals Road Extraction from High-Resolution Remote Sensing Imagery Using Deep Learning

2018 ◽  
Vol 10 (9) ◽  
pp. 1461 ◽  
Author(s):  
Yongyang Xu ◽  
Zhong Xie ◽  
Yaxing Feng ◽  
Zhanlong Chen
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Deep Learning ◽  
High Resolution ◽  
Convolutional Neural Network ◽  
Road Network ◽  
Deep Convolutional Neural Network ◽  
Road Extraction ◽  
Remote Sensing Imagery ◽  
The Road

The road network plays an important role in the modern traffic system; as development occurs, the road structure changes frequently. Owing to the advancements in the field of high-resolution remote sensing, and the success of semantic segmentation success using deep learning in computer version, extracting the road network from high-resolution remote sensing imagery is becoming increasingly popular, and has become a new tool to update the geospatial database. Considering that the training dataset of the deep convolutional neural network will be clipped to a fixed size, which lead to the roads run through each sample, and that different kinds of road types have different widths, this work provides a segmentation model that was designed based on densely connected convolutional networks (DenseNet) and introduces the local and global attention units. The aim of this work is to propose a novel road extraction method that can efficiently extract the road network from remote sensing imagery with local and global information. A dataset from Google Earth was used to validate the method, and experiments showed that the proposed deep convolutional neural network can extract the road network accurately and effectively. This method also achieves a harmonic mean of precision and recall higher than other machine learning and deep learning methods.

scholarly journals Road Topology Refinement via a Multi-Conditional Generative Adversarial Network

Sensors ◽  
2019 ◽  
Vol 19 (5) ◽  
pp. 1162
Author(s):  
Yang Zhang ◽  
Xiang Li ◽  
Qianyu Zhang
Keyword(s):  
Road Network ◽  
Rapid Development ◽  
Road Networks ◽  
Extraction Methods ◽  
Road Extraction ◽  
Generative Adversarial Network ◽  
Topological Information ◽  
The Road ◽  
Adversarial Network ◽  
Spectral Performance

With the rapid development of intelligent transportation, there comes huge demands for high-precision road network maps. However, due to the complex road spectral performance, it is very challenging to extract road networks with complete topologies. Based on the topological networks produced by previous road extraction methods, in this paper, we propose a Multi-conditional Generative Adversarial Network (McGAN) to obtain complete road networks by refining the imperfect road topology. The proposed McGAN, which is composed of two discriminators and a generator, takes both original remote sensing image and the initial road network produced by existing road extraction methods as input. The first discriminator employs the original spectral information to instruct the reconstruction, and the other discriminator aims to refine the road network topology. Such a structure makes the generator capable of receiving both spectral and topological information of the road region, thus producing more complete road networks compared with the initial road network. Three different datasets were used to compare McGan with several recent approaches, which showed that the proposed method significantly improved the precision and recall of the road networks, and also worked well for those road regions where previous methods could hardly obtain complete structures.

Sign in / Sign up

Export Citation Format

Share Document