Road Classification Research Articles

Desain lapisan Perkerasan Jalan Pada Ruas Jalan Desa Mbangga – Woloboa Kecamatan Wolowaru Kabupaten Ende

The Mbangga-Woloboa road section, Rindiwawo Village, Wolowaru District is included in the local road type with rigid pavement and a road width of 3 meters. Every year the condition of the Mbangga-Woloboa road section experiences damage, where several parts of the road have many holes and when it rains there are lots of puddles of water, which is very disturbing for road users. Even though the Ministry of Public Works, with the available funds, has repaired the existing damage by overlaying it repeatedly, it has not been able to solve the existing problem completely because the road condition has deteriorated again before it reaches its design life. Therefore, it needs to be redesigned by repairing the subgrade layer and replacing the road surface layer with new rigid pavement according to the load of vehicles passing through the road. So by using the AASHTO method, the traffic growth rate (i) of the planned road is 5.23% per year with collector road class. The effective Resilient Modulus (MR) value on the road section is 2770 psi with a CBR value of 1.87%, and DDT 2.70 kg/cm2. The thickness of the pavement layer is found to be D1 = 13 cm, D2 = 20 cm, and D3 = 41 cm.

A novel framework for road vectorization and classification from historical maps based on deep learning and symbol painting

Road networks in the past are imperative for understanding evolution of transportation infrastructure, urban sprawl, and route planning, etc. Various approaches have been developed for road extraction from historical maps, among which deep learning techniques stand out as the most effective ones. However, little attention has been paid to investigating road vectorization and classification from historical maps. Moreover, road classification via machine learning methods usually requires large amounts of dedicated training data. To address these issues, this paper proposes a novel and comprehensive framework for road vectorization and classification on the basis of road segmentation from historical maps. First, deep learning is used to get pixel-wise raster road segmentation results, which are further skeletonized using morphological operations. Then, considering that each road class is represented with a certain symbol, a painting function is defined for each class able to paint the corresponding symbol. These painting functions are then used to draw road segments along the skeletons. Since the start and end points in each painting function are used to vectorise the segment, this method achieves vectorization and classification at the same time. Our method is validated on four Siegfried map sheets in Switzerland, and evaluated via both visual and quantitative assessments. The results indicate that the method is capable of classifying roads accurately. In particular, two evaluation metrics completeness and correctness achieve 90.69% and 72.71% respectively for road class 2 which accounts for the highest portion in the map. Moreover, the results of this method avoid the saw-toothed issue of vectorised road lines. This research is beneficial for creating complete vector road network datasets with class information to support decision-making in urban planning and transportation.

УСТАНОВЛЕННЯ НАЦІОНАЛЬНИХ ВИМОГ ДО ЗЕРНОВОГО СКЛАДУ АСФАЛЬТОБЕТОННИХ СУМІШЕЙ ЗГІДНО З ДСТУ EN 13108-1

Introduction. DSTU EN 13108-1 establishes requirements for asphalt mixtures used for the arrangement of pavement layers of roads, airfields, etc. These asphalt mixtures are used for arranging the base layer, binding layer, and a surface layer. Problem statement. A special feature of DSTU EN 13108-1 is that it establishes general requirements for all indicators, in particular for grading. That is there are no specific requirements for the grading of asphalt mixtures depending on the road category, traffic loading and the location of the asphalt concrete layer in the road pavement structure. Therefore, it is advisable to consider in detail the requirements for the grading of asphalt mixtures, compare them with the requirements of national standards and propose appropriate national requirements. Purpose. Establishment of national requirements for the grading of asphalt mixtures according to DSTU EN 13108-1.

ПРОЄКТУВАННЯ АВТОМАГІСТРАЛЕЙ КОНТИНЕНТАЛЬНОГО, СУБКОНТИНЕНТАЛЬНОГО ТА ТРАНСРЕГІОНАЛЬНОГО СПОЛУЧЕННЯ В РОЗРІЗІ ПОЛОЖЕНЬ ЗАКОНОДАВЧИХ АКТІВ ЄС

Introduction. The introduction to the paper highlights the importance of the design and construction of highways of various link functions levels as a key factor in modern integration processes and also emphasizes the role of highways for substantial increasing of the road network safety. Problem statement. The issues of the paper concern aspects of highways design based on the experience of European colleagues in the context of the provisions of the relevant legislative acts of EU. Purpose. The goal of the paper is to analyze the main provisions for the design of continental, subcontinental and transregional highways considering, within the format of the publication, the design features of the highways elements which are universal for various design systems. Results. The highways categorization regarding their link functions levels and with this categorization linked classification by design classes were reviewed which accept the highways jurisdiction and the build-up areas related location and also the corresponding restrictions on vehicle speed limits. The highways characteristics were defined allowing the determination of highways as a separate category of motor roads in the world-wide practice of the road building industry.

Road friction estimation based on vision for safe autonomous driving

Road peak friction is a significant parameter determining vehicle driving safety. This paper focuses on road friction monitoring based on vision for autonomous vehicles. A deep learning classification model combined with training strategies adapted to the real-scenario road friction image dataset is proposed. The road peak friction coefficient is initially derived based on the classification probability and an empirical inference model. To enhance the usability and reliability of the estimated friction coefficient, a filter that concerns the classification model uncertainty and the variation of estimation output is then performed. The top-1 and top-2 classification accuracy on five road friction classes reach 94.84% and 99.22%, respectively. The developed friction preview scheme is further deployed and validated in real-vehicle scenarios. The results indicate that the proposed methods are robust to road environment change. It has potential in practical applications that provide crucial road information for safer autonomous driving.

Spatial Analysis of Risk Exposure of Urban Trees: A Case Study from Bologna (Italy)

In Europe, more than two-thirds of the population live in urban areas. The management of urban green areas and trees is becoming increasingly relevant involving different players and stakeholders, as well for keeping a focus on the Sustainable Development Goals. Society and policy makers are often unaware of the disservices that neglecting these areas can cause. Appropriate monitoring interventions can protect both citizens and trees themselves. The aim of the study was to assess the risk potential in urban trees in Bologna suburbs (Italy). For each tree in the city of Bologna, three target variables identifying the number and categories of streets, buildings, and walking and cycle paths near the tree were considered and used as covariates. A multiple regression model assessing the relationship between a dependent synthetic spatial variable (digital number, DN), proxy of the likelihood of tree failure, and the three independent covariates was estimated. Both the number of streets and walking and cycle paths in the area surrounding a tree are shown to be significantly associated with the DN value. The use of open data can assist in monitoring and maintaining urban green areas. The tool supports a virtuous circle between stakeholders in urban systems through sustainability and efficiency.

LAND COVERAGE ANALYSIS OF PAKISTAN USING SATELLITE IMAGERY

Abstract. Pakistan has a unique landscape geographically due to its strategic geo-political importance. It has played a vital role in global climate and politics. There are various semantic segmentation studies performed on remote sensing high-resolution imagery of various urban and rural areas into major classes of buildings, vegetation, water, and roads. These analyses have supported the land coverage study, which can facilitate urban infrastructure management, forestry, disaster management, and climate challenges. Recent climate reports have confirmed the importance of these studies, especially for Pakistan. It’s a critical location for the global south to observe the climate catastrophe. This research will focus on three major cities of Islamabad, Karachi, and Quetta and semantically segment the satellite imagery to study the land coverage. Our research contributes the dataset from major cities of Pakistan and compare the performance of state-of-the-art semantic segmentation networks to evaluate the dataset. Benchmark can help in selecting a highly effective deep learning network and generalizing those networks on our prepared dataset. Dataset can be downloaded from here: https://github.com/Abdullah-Sabir/Pakistan-Land-Coverage-Analysis-Dataset

Road Damage Detection and Classification

Abstract: This is a road damage detection desktop application. In the subject of transportation engineering, identifying road damage early on is essential because it can save maintenance costs and avoid accidents. Deep learning methods have demonstrated encouraging performance in a number of computer vision tasks recently, including the detection of road damage. In this study, we suggest a region-based convolutional neural network (R-CNN)-based method for detecting road degradation. Using a publicly accessible dataset of road photos with different kinds of damage, such as cracks, potholes, and patches, we trained our R-CNN. Our approach outperformed cutting-edge techniques with an accuracy of 85% in identifying road damage.

Where is it complex to reallocate road space?

Road space distribution has traditionally been based on the hierarchical classification of streets. In arterials, the majority of space is dedicated to traffic lanes, whereas local streets typically have fewer traffic lanes and more space for parking or sidewalks. Within urban areas, road space is contested between two main types of spaces: corridors of movement, and places for access and standing/stillness/staying. Given the limited availability of urban space, particularly in central areas, deciding how to allocate space for these functions poses a dilemma and requires tradeoffs. Nonetheless, certain areas experience underutilization and inefficiencies in space utilization over time. In this context, we propose a site selection methodology to identify complex zones within a city where different types of users and demands compete for space. These zones present the potential for dynamically allocating road space based on fluctuating demands and policy objectives. This methodology serves as an initial guide for planners to identify zones that require a thorough evaluation of activities and diverse temporal-spatial demands when reallocating road space. We use network centrality, land use indicators, traffic, and public transport dynamics indicators to detect complex zones and apply them to a Lisbon case study.

Numerical Simulation of the Effect of Variation in Subgrade CBR Values on Rigid Pavement

This study presents the results of research on the stress behavior of rigid pavement concrete slabs by varying CBR subgrade values. It aims to know the effect of changing the rigid pavement strss. Data used in this study are geometric data and material properties of the pavement structure. The load vehicle considered is National Road class standard. Rigid pavement is very sensitive with un-uniformity of underlaying supposrt. In this research, the effect of un-uniform support of subgrade was modeled numerically using Abaqus software. The friction coefficient of each layer was also considered in the model. Model simulation of existing rigid pavement calculated 13 variations of CBR values. Result shown that there is a stress increment by 26.27% in the longitudinal direction of the rigid pavement between models with uniform variations of CBR and models with non-uniform variations of CBR. This result show the sensitivity of rigid pavement to un-uniformity of subgrade.

Optimal planning of safety improvements on road sites belonging to different categories within large networks: An integrated multi-layer framework

Planning road safety interventions on large road networks implies several layers of complexity in the decision-making process. In fact, the following simultaneous problems should be addressed: estimating safety performances on the different road elements of the network, identifying sites showing high potential for improvement with respect to reference values, defining the possible types of safety measures to be implemented and their anticipated effect on traffic safety, limiting the number of interventions given fixed budget constraints.This study proposes an integrated multi-layer framework which takes into account the above-defined problems into a single optimization procedure which provides the number and type of safety interventions to be implemented over a wide road network composed of different categories of road elements. The proposed framework is based on the following peculiar aspects: the potential for safety improvement is quantitatively assessed based on the estimation of safety performances for each road category, a bi-level thresholding process integrated in the optimization process is used to highlight sites for interventions, the anticipated outcome of safety measures is quantitatively assessed as well through available crash reduction factors.The proposed methodology is applied to a case study which analyzes a sample of real roads belonging to a province-wide road network composed of various road elements (i.e., different categories of segments and intersections), under different budget constraints. Results demonstrate the applicability and flexibility of the proposed approach, which could be used for planning purposes, independently of the particular geographic location. Clearly, the approach is valid at the planning stage, given that several details of the different layers of analysis are necessarily simplified, while they should be studied in detail at the single intervention project stage.

Road Pattern Classification Using Deep Learning for Noise Data for Autonomous Driving Vehicle

Tire-pavement Interaction Noise (TPIN) is noise caused by interactions between rolling tires and road surfaces. After measuring the TPIN using a microphone, transform TPIN to images using continuous wavelet transform (CWT). The transformed images are used to classify the driving road and tire using convolutional neural network (CNN). The road and tire classification network using CNN is required for braking systems in autonomous vehicle. The CNN in this paper can classify snow road, asphalt road, and two types of tires with over 97% accuracy.

Characterization of road surfaces using three near-infrared diode lasers

Rapid road network expansion has heightened the importance of surface condition information for traffic accident prevention and route optimization. This article introduces a laser diode-based sensor that identifies seven surface conditions and accurately measure ice, water, and snow film thicknesses on roads. An optical module was developed to detect weak optical signals based on the characteristic absorption spectrum of the target surface. The module used three laser diodes (1310, 1440, and 1550 nm wavelengths) as light sources. Additionally, a road classification algorithm that is adaptable to foggy weather was developed using a multi-wavelength processing protocol. The sensor was subjected to numerous calibration and performance verification experiments. During thick foggy measurements, the processed spectra displayed a maximum variation of 2.372% across a 600 to 25,000 m visibility range with a relative standard deviation of only 0.328%. This demonstrated effective weakening of the effects of visibility variations. During winter field testing, the sensor classified road conditions effectively and accurately measured ice, snow, and water film thicknesses, with a correlation coefficient of 0.97444. The accuracy of the measurements was less than 0.5 mm. The sensor’s effectiveness for long-term field-based road testing has been verified.

Research on Street Color Environment Perception Based on CEP-KASS Framework

The color of urban streets plays a crucial role in shaping a city’s image, enhancing street appeal, and optimizing the experience of citizens. Nevertheless, the relationship between street color environment and residents’ perceptions has rarely been deeply discussed, and most of the existing studies adopt qualitative methods. To accurately and effectively assess the connection between street color environment and residents’ emotional perceptions, this paper introduces a quantitative research framework based on multi-source data called “Color Emotion Perception with K-Means, Adversarial Strategy, SegNet, and SVM (CEP-KASS)”. By combining K-Means unsupervised machine learning and SegNet computer vision techniques, it captures and analyzes visual elements and color data from Baidu Street View Images (BSVI). It then employs a human–machine adversarial scoring model to quantify residents’ perceptions of BSVI and uses the support vector machine regression model to predict the final perception scores. Based on these data, a Pearson correlation analysis and visual analysis were conducted on the elements and color in the urban environment. Subsequently, the streets were classified based on perception frequency and perception scores by integrating multi-source data, and areas within the third ring of Xuzhou City were selected for validating the research framework. The results demonstrate that utilizing street-view images and the CEP-KASS framework can quantitatively analyze urban color perception and establish a connection with residents’ emotions. In terms of color perception, red, orange, and blue all have a strong positive correlation with the interesting score, whereas black is positively correlated with a sense of safety. Regarding color attributes, low-saturation bright colors result in higher fun perception scores in urban spaces; too low saturation and brightness can affect their attractiveness to residents; brightness has an inverse relationship with the perception of safety, and adjusting brightness inversely can improve the perceived safety experience in certain urban external spaces. The street classification criteria based on perception frequency and perception scores proposed herein can provide references for planners to prioritize color transformation decisions, with a priority on emulating HSHF streets and transforming LSHF streets. When formulating color planning, suggestions for color adjustment can be given based on the correlation study of color with visual elements and perception scores, optimizing urban residents’ spatial perception and their emotional experiences. These findings provide robust theoretical support for further enhancing the visual quality of streets and refining urban color planning.

Application of Clay–rubber Mixtures for the Transportation Geotechnics—the Numerical Analysis

Abstract The use of waste materials (including rubber) in industry is one of the most important issues in terms of environmental protection. One of such applications is the use of soil–rubber mixtures in backfills or lower layers of embankments or road structures. The numerical analyses of the behavior of a clay–rubber mixture layer built into a road embankment are presented in this article. An elastic-perfectly plastic model with a Coulomb–Mohr yield surface was used in the finite element analysis. The parameters of soil–rubber mixtures adopted for the analysis were estimated on the basis of triaxial tests: monotonic (UU—unconsolidated undrained, and CU—consolidated undrained) and cyclic (CU) performed with low frequency (f = 0,001 Hz). The triaxial tests were carried out on mixtures of kaolin (K) and red clay (RC) with the addition of 1–5 mm rubber granulate (G) in the amount of 5–25% by weight. Numerical analyses included a static plate load test (VSS) of a layer made of a rubber–soil mixture built into the embankment and testing the stability of embankments using the c–ϕ strength reduction procedure. The results of laboratory tests confirm the necessity of testing soil–rubber mixtures each time before their use in embankments. The observed overall decrease in shear strength and stiffness of the tested material is variable and depends on the type of soil and the content of rubber waste. Satisfactory results of the analysis were obtained, both in terms of the values of layer stiffness modules and slope safety factors, which allows for the conclusion of the possibility of using soil–rubber mixtures (with the recommended granulate addition up to 30% by weight) in the layers of road embankments and (depending on the road class) in the lower layers of the pavement structure.

Research on road damage recognition and classification based on improved VGG-19

In recent years, methods of road damage detection, recognition and classification have achieved remarkable results, but there are still problems of efficient and accurate damage detection, recognition and classification. In order to solve this problem, this paper proposes a road damage VGG-19 model construction method that can be used for road damage detection. The road damage image is processed by digital image processing technology (DIP), and then combined with the improved VGG-19 network model to study the method of improving the recognition speed and accuracy of VGG-19 road damage model. Based on the performance evaluation index of neural network model, the feasibility of the improved VGG-19 method is verified. The results show that compared with the traditional VGG-19 model, the road damage VGG-19 road damage recognition model proposed in this paper shortens the training time by 79 % and the average test time by 68 %. In the performance evaluation of the neural network model, the comprehensive performance index is improved by 2.4 % compared with the traditional VGG-19 network model. The research is helpful to improve the model performance of VGG-19 road damage identification network model and its fit to road damages.

Evaluating the Performance of Low-Cost PM2.5 Sensors in Mobile Settings.

Low-cost sensors (LCSs) for measuring air pollution are increasingly being deployed in mobile applications, but questions concerning the quality of the measurements remain unanswered. For example, what is the best way to correct LCS data in a mobile setting? Which factors most significantly contribute to differences between mobile LCS data and those of higher-quality instruments? Can data from LCSs be used to identify hotspots and generate generalizable pollutant concentration maps? To help address these questions, we deployed low-cost PM2.5 sensors (Alphasense OPC-N3) and a research-grade instrument (TSI DustTrak) in a mobile laboratory in Boston, MA, USA. We first collocated these instruments with stationary PM2.5 reference monitors (Teledyne T640) at nearby regulatory sites. Next, using the reference measurements, we developed different models to correct the OPC-N3 and DustTrak measurements and then transferred the corrections to the mobile setting. We observed that more complex correction models appeared to perform better than simpler models in the stationary setting; however, when transferred to the mobile setting, corrected OPC-N3 measurements agreed less well with the corrected DustTrak data. In general, corrections developed by using minute-level collocation measurements transferred better to the mobile setting than corrections developed using hourly-averaged data. Mobile laboratory speed, OPC-N3 orientation relative to the direction of travel, date, hour-of-the-day, and road class together explain a small but significant amount of variation between corrected OPC-N3 and DustTrak measurements during the mobile deployment. Persistent hotspots identified by the OPC-N3s agreed with those identified by the DustTrak. Similarly, maps of PM2.5 distribution produced from the mobile corrected OPC-N3 and DustTrak measurements agreed well. These results suggest that identifying hotspots and developing generalizable maps of PM2.5 are appropriate use-cases for mobile LCS data.

Quantifying the Variability of Ground Light Sources and Their Relationships with Spaceborne Observations of Night Lights Using Multidirectional and Multispectral Measurements.

With the transition to LED lighting technology, multispectral night-time sensors are needed to quantify the changing nightscapes, given the limitations of the panchromatic sensors. Our objective was to quantify the contribution of lighting sources as measured on the ground and examine their correspondence with night-time brightness and color as measured from space. We conducted ground-based measurements of night-time brightness using the multidirectional (top, rear, right, front, left) and multispectral LANcube v2, which was mounted on the roof of a car, over 458 km of roads in central Israel and in Brisbane, Australia. For spaceborne measurements, we used the SDGSAT-1 multispectral Glimmer sensor. We found that spaceborne measurements of apparent radiance were best explained when including all ground-based directional measurements, with greater explanatory power for highways (R2 = 0.725) than for urban roads (R2 = 0.556). Incoming light in the five directions varied between road classes and land use. In most cases, the variability in night-time brightness and color was greater for urban road sections than for highways. We conclude that due to the spectral mixture of lighting sources, at a medium spatial resolution, the impact of the transition to LED lighting may be more easily recognized from space over highways than in dense urban settings.

A multilevel decision-making approach for road infrastructure management

ABSTRACT The design of effective road safety countermeasures requires a network diagnosis supported by data. Moreover, infrastructures need to be ready for the introduction of vehicle-to-infrastructure communications to support technologies, as truck platooning. Ascendi, a motorway concessionaire, developed an action plan to decrease crash frequency and casualties that rests in data recorded by automatic vehicle counting devices. To have a good network representation, new equipment will provide more data, thus enhancing the selection of countermeasures. We developed a multilevel decision-support approach to define equipment location. The process stages correspond to three levels of analysis: (1) clustering for road segment classification (network level); (2) quantification of the devices to install ensuring similar coverage (concession level); (3) device allocation according to geographical and cost criteria (segment level). An iterative and participatory process involving Ascendi resulted in a proposal for adding 43 devices to the existing 72, increasing the network coverage to 39%.

A Machine Learning Approach for Detection and Suppression of Shadow or Wet Road Surfaces

In advanced driver assistance system detection of road surfaces is an important task. Few algorithms have been proposed in past to detect the road surfaces based on intensities. However, problem arises in detection process is due to the presence of shadows or wet road surfaces. Here we have proposed a novel algorithm for detection of shadows with the help of machine learning approaches. Initially shadow is being detected with the help of a threshold-based approach followed by windowing-based method. The detected shadow region gets confirmed with the help of a set of features and classifier. The detected shadow or wet pixels are in painted to obtain set of pixels without shadow for road classification problems. The simplicity and accuracy of the algorithm makes it robust and can be used as a part of road surface detection algorithm.