Road Elements Research Articles

Analysis of the behaviour for a steering rack under the influence of the road elements

The automotive industry is dealing with rapid innovation and competition, which calls for either changing current products or replacing them with more modern materials. Automobile manufacturers are currently focusing on reducing the weight in order to conserve natural resources and energy. As luxury and safety equipment is added, the weight of the vehicle increases, which reduces overall performance and fuel efficiency. As a result, modern car industry leaders prioritize vehicle armoring. The use of composite materials based on plastic fibers in automobile manufacture has a number of financial and practical benefits for both the buyer and the manufacturer. Benefits are attributed to a decrease in weight, improved production standards, stylistic advancements, corrosion and abrasion resistance. Studying how various composite material types used to build directional cases behave under impact with a potentially hazardous object while moving at a speed of 100 km/h is the proposal of this article.

Driving Risk Field and Control Strategies for Autonomous Vehicles at a Signalized Intersection

Driving pattern has been increasingly researched to improve driving safety and develop autonomous vehicles. Oriented towards the complex infrastructures at signalized intersections, this research digs into the risk sources brought by different kinds of road elements, including road lane markings, road curbs, median separators, signal timing, and neighboring vehicles around the ego car. Referring to vehicle speed both in the longitudinal and latitudinal dimensions, risk scope and distribution are quantified with the vehicle position of a torus with a Gaussian cross-section. Then, the risk is summed over all the road elements across all the points involved by the ego car, the level of which should be controlled within the threshold value when the ego vehicle explores to minimize trip delay. Thus, autonomous driving strategies are developed with respect to vehicle speed and steering angle. The proposed model is validated with NGSIM data, where a signalized intersection on Peachtree Street is selected and vehicles moving in different directions are analyzed. It is found that the proposed model manages to control vehicles with risk at the accepted level and to enhance the speed level as well as reduce acceleration fluctuations. This research contributes to improving autonomous driving against complex driving conditions for driving safety and efficiency.

THE IMPLEMENTATION OF SEMI-AUTOMATED ROAD SURFACE MARKINGS EXTRACTION SCHEMES UTILIZING MOBILE LASER SCANNED POINT CLOUDS FOR HD MAPS PRODUCTION

Abstract. As research on autonomous driving deepens, High-definition Maps (HD Maps) have gradually become an auxiliary information for the new generation of autonomous driving technology. Compared to traditional electronic navigation maps, HD Maps have higher accuracy requirements and more information. Multi-road environment information and road elements are included. In the production of HD Maps, the on-board Mobile Laser Scanning (MLS) system has the ability to quickly collect environmental information, with high precision, thus making the system a widely used data collection method today. However, subsequent map building, digitization, and other mapping work still rely on manual operation, which is time-consuming and laborious. Therefore, this research is dedicated to developing a semi-automatic algorithm to generate HD Maps from the acquired point cloud data. This research focuses on the extraction of road surface markings, using the Cloth Simulation Filter (CSF) to obtain the road surface point cloud to improve the extraction efficiency. The road markings are extracted using the characteristic of high intensity values, and the commonly used Otsu threshold filter in image processing is used to extract point clouds with high reflectance intensity, eliminating the need for manual setting of point clouds. And based on geometric conditions, the objects are classified, such as arrow lines, pedestrian crossings, stop lines, and lane lines, which are convenient for further mapping HD Maps.

Performance analysis of rule-based classification and deep learning method for automatic road extraction

The need for accurate and up-to-date spatial data by decision-makers in public and private administrations is increasing gradually. In recent decades, in the management of disasters and smart cities, fast and accurate extraction of roads, especially in emergencies, is quite important in terms of transportation, logistics planning, and route determination. In this study, automatic road extraction analyses were carried out using the Unmanned Aerial Vehicle (UAV) data set, belonging to the Yildiz Technical University Davutpasa Campus road route. For this purpose, this paper presents a comparison between performance analysis of rule-based classification and U-Net deep learning method for solving automatic road extraction problems. Objects belonging to the road and road network were obtained with the rule-based classification method with overall accuracy of 95%, and with the deep learning method with an overall accuracy of 86%. On the other hand, the performance metrics including accuracy, recall, precision, and F1 score were utilized to evaluate the performance analysis of the two methods. These values were obtained from confusion matrices for 4 target classes consisting of road and road elements namely road, road line, sidewalk, and bicycle road. Finally, integration of classified image objects with ontology was realized. Ontology was developed by defining four target class results obtained as a result of the rule-based classification method, conceptual class definition and properties, rules, and axioms.

Object Detection-Based System for Traffic Signs on Drone-Captured Images

The construction industry is on the path to digital transformation. One of the main challenges in this process is inspecting, assessing, and maintaining civil infrastructures and construction elements. However, Artificial Intelligence (AI) and Unmanned Aerial Vehicles (UAVs) can support the tedious and time-consuming work inspection processes. This article presents an innovative object detection-based system which enables the detection and geo-referencing of different traffic signs from RGB images captured by a drone’s onboard camera, thus improving the realization of road element inventories in civil infrastructures. The computer vision component follows the typical methodology for a deep-learning-based SW: dataset creation, election and training of the most accurate object detection model, and testing. The result is the creation of a new dataset with a wider variety of traffic signs and an object detection-based system using Faster R-CNN to enable the detection and geo-location of traffic signs from drone-captured images. Despite some significant challenges, such as the lack of drone-captured images with labeled traffic signs and the imbalance in the number of images for traffic signal detection, the computer vision component allows for the accurate detection of traffic signs from UAV images.

Developing new hybrid grey wolf optimization-based artificial neural network for predicting road crash severity

With more cars on the road and an increasing travel rate, one of the main issues in transportation engineering is how to make roads safe. The evaluation of the level of road crash severity is a significant component of the road safety assessment in terms of financial and personal losses. One of the most advanced ways to control and manage traffic information in modern traffic management systems is through intelligent transportation systems (ITS). ITS plays a big part in improving road safety. On the other hand, machine learning techniques play an important role in increasing the level of ITS performance. Hence, this study aims to predict the level of crash severity through a classification approach. In this study, two machine learning techniques namely artificial neural network (ANN) and Grey Wolf optimization algorithm (GWO)–ANN were developed to predict the level of road crash severity, and several performance metrics were used to assess the predictive algorithms' predictive capability. For this purpose, some factors that affect the level of severity were considered, including light condition (LC), weekday (W), horizontal alignment (HA), road element (RE), type of crash (TC), vehicle type (VT), driver gender (DG), average speed (AS) and annual average daily traffic (AADT). 202 case studies were recorded from urban roads in Calabria in southern Italy. When comparing the proposed GWO–ANN model to the ANN model, the findings clearly demonstrated the superiority of the proposed GWO–ANN model.

Exploring road safety of pedestrians in proximity to public transit access points (bus stops and metro stations), a case study of Montreal, Canada

Public transit plays a significant role in the sustainability of an urban region which requires high pedestrian safety at the interchange points. This research studies the magnitude of pedestrian collisions in the proximity of Public Transit Access Points (PTAPs) and address how Traffic Calming strategies and road elements improve pedestrian safety at PTAPs. Getis-Ord Hotspot Analysis and the Negative Binomial models are applied to address research questions. Pedestrian collisions occur more frequently at intersections with the presence of a PTAP and with a higher volume and number of bus routes. Traffic calming strategies such as road width reduction, sidewalk width increase, median refugees, pedestrian crossing phase, and vehicle stop signs could improve pedestrian safety of PTAP. Besides, pedestrians are at more risk in PTAP at locations where high road gradients and in proximity to intersections with a higher number of directions of vehicle traffic flow.

A visual reasoning-based approach for driving experience improvement in the AR-assisted head-up displays

Enabled by advanced data analytics and intelligent computing, augmented reality head-up displays (AR-HUDs) are appraised with a certain degree of intelligence towards an in-car assistance system providing more convenience for drivers and ensuring safer traffic. Nevertheless, current AR-HUDs systems fail to analyze perceptual results with recommended driving strategies as the cognitive intelligence, while solely rely on driver’s own decision-makings. To pave the way, this work stepwise proposes a visual reasoning-based approach for presenting drivers with perceptual, predictive, and reasoning information onto AR-HUDs toward cognitive intelligence. Firstly, a Driving Scenario Knowledge Graph comprising many road elements and empirical knowledge is established appropriately. Then, by analyzing the video streams and images collected by an in-car visual camera, the driving scene can be perceived comprehensively, including 1) identifying road elements and 2) moving elements’ intention recognition. Afterwards, a graph-based driving scenario reasoning model, driving scenario-adaptive KAGNET, is built for achieving driving strategy recommendations. Moreover, the analyzed information is shown on the HUDs via pre-defined AR graphics to support drivers intuitively. A case study is given lastly to prove its feasibility. As an explorative study, some limitations and future work are emphasized to attract further study and open discussion in this area for pursuing the better implementation of AR-HUDs.

Effects of Volumetric Augmented Reality Displays on Human Depth Judgments

Many driving scenarios involve correctly perceiving road elements in depth and manually responding as appropriate. Of late, augmented reality (AR) head-up displays (HUDs) have been explored to assist drivers in identifying road elements, by using a myriad of AR interface designs that include world-fixed graphics perceptually placed in the forward driving scene. Volumetric AR HUDs purportedly offer increased accuracy of distance perception through natural presentation of oculomotor cues as compared to traditional HUDs. In this article, the authors quantify participant performance matching virtual objects to real-world counterparts at egocentric distances of 7-12 meters while using both volumetric and fixed-focal plane AR HUDs. The authors found the volumetric HUD to be associated with faster and more accurate depth judgements at far distance, and that participants performed depth judgements more quickly as the experiment progressed. The authors observed no differences between the two displays in terms of reported simulator sickness or eye strain.

Representativity and univocity of traffic signs and their effect of trajectory movement in a tracking task: informative signs

The importance of how cognitive processes (Reasoning) influence on the understanding and the mental representation of road-side elements in form of the movement effects on the path driving must be studied in-depth. Literature shows that the key point to explain the influence of attention on movement is the meaning of the object being processed; literature also shows that the Reasoning with those cues we pay attention to has an effect on driving. By using a driving-simulation task, traffic signs have been tested on their effect on movement. Results show that the least-representative-of-their-meaning signs deviate participants´ movement path more intensively than the most-representative-of-their-meaning signs. Conclusions: Traffic accidents are well-known for their. The results here reported help to improve the cognitive Ergonomics of every road element, specially, traffic signs.

Sustainability of thin layer road markings based on their service life

Road markings are road elements that require frequent periodic renewals (not replacement) to maintain their key properties. To evaluate the impact of materials selection on sustainability of road markings, several representative products were tested in the field. The results revealed that the main impactor for their service life was selection of paint, followed by the choice of glass beads. The measured length of service life was used to calculate the consumption of resources for a series of renewals until end-of-life. The outcome clearly demonstrated that lowest carbon footprint was achieved with road marking materials that afforded longest service life, even if their composition was not environmentally friendly. The methodology described in this article may be used by road administrators and by scientists as a tool for quick assessment of sustainability of road markings based on their service life during homologation testing and composition of the utilised materials.

Overfitting Prevention in Accident Prediction Models: Bayesian Regularization of Artificial Neural Networks

In the present paper, we implemented the Bayesian regularization (BR) backpropagation algorithm for calibrating an artificial neural network (ANN) as an accident prediction model (APM) to be used on Italian four-lane divided roads. We chose the BR-ANN since it efficiently allows for dealing with small sample size and avoiding overfitting issues by adding a regularization term in the objective function to be minimized during training. Moreover, BR-ANNs are sparsely employed in road safety analyses, and their peculiarities deserve to be emphasized. In our work, the BR-ANN aims to predict the number of fatal and injury (FI) crashes across 236 road elements, for a total length of 78 km. The input features are road element length, horizontal and vertical alignment, cross-section geometry, operating speed, traffic flow, sight distance, and road area type (i.e., a categorical predictor accounting for the potential influence of merge and diverge influence areas). Training and test phases of the BR-ANN have been evaluated by determination coefficient ( R2), root mean square error (RMSE), overfitting ratio (OR), scatterplots, residuals analysis, and by the same ANN architecture trained with the gradient descent (GD) with momentum and adaptive learning rate backpropagation algorithm (GD-ANN). Results demonstrate that the BR-ANN markedly outperforms the GD-ANN, which suffers severe overfitting issues. Furthermore, BR-ANN does not overfit data (OR close to the unity), reports a satisfactory R2 (0.726), and shows a Gaussian residual distribution with zero mean. Therefore, road authorities could consider regularized ANNs for performing appropriate safety analyses, especially when dealing with small road sample sizes.

DEVELOPMENT OF A METHODICAL APPROACH TO THE MAINTENANCE OF HIGHWAYS IN THE WINTER PERIOD TAKING INTO ACCOUNT WORLDWIDE EXPERIENCE

The article examines models and proposes a methodical approach to highway maintenance in the winter period, taking into account world experience. It was determined that the assessment of winter road maintenance measures performed in different countries takes different forms according to: quality indicator or standard; cost accounting and analysis; organized management system; standards for inspection and monitoring of works; measurement of conformity of service provision; analysis of complaints from users of the road network; methods of forecasting and prevention of certain winter phenomena. It is proposed to use the WSI (FHWA) index, which is calculated on the basis of the average value of daily snowfall and the recorded minimum and maximum temperature on average for the season, to assess the severity of the impact of weather on winter maintenance. It is recommended that the results of precipitation forecasting and the level of the WSI index be used as a basis for determining the operational level of service, which forms a set of potential measures for winter road maintenance. It is proposed to justify the level of service based on models of winter maintenance and forecasting measures that allow to form a methodical approach to highway maintenance. A methodological approach has been developed, which is based on the use of a mathematical model of road maintenance in the winter period, which is a function of minimizing the accumulated indicators of the quality of winter maintenance of road elements depending on their weight for maintenance.

Multiobjective Emergency Resource Allocation under the Natural Disaster Chain with Path Planning.

Public safety and health cannot be secured without the comprehensive recognition of characteristics and reliable emergency response schemes under the disaster chain. Distinct from emergency resource allocation that focuses primarily on a single disaster, dynamic response, periodic supply, and assisted decision-making are necessary. Therefore, we propose a multiobjective emergency resource allocation model considering uncertainty under the natural disaster chain. Resource allocation was creatively combined with path planning through the proposed multiobjective cellular genetic algorithm (MOCGA) and the improved A* algorithm with avoidance of unexpected road elements. Furthermore, timeliness, efficiency, and fairness in actual rescue were optimized by MOCGA. The visualization of emergency trips and intelligent avoidance of risk areas were achieved by the improved A* algorithm. The effects of logistics performance, coupling of disaster factors, and government regulation on emergency resource allocation were discussed based on different disaster chain scenarios. The results show that disruption in infrastructure support, cascading effect of disasters, and time urgency are additional environmental challenges. The proposed model and algorithm work in obtaining the optimal solution for potential regional coordination and resilient supply, with a 22.2% increase in the total supply rate. Cooperative allocation complemented by political regulation can be a positive action for successfully responding to disaster chains.

Construction of a simulation model for substantiating the parameters of long-term road maintenance contracts

This paper reports a study into the main parameters of long-term contracts for the maintenance of roads. Weaknesses in existing methods and models of substantiation of the initial characteristics of contracts have been identified. It is established that the main reason for the transition to long-term contacts in the road sector is the need to improve the efficiency and effectiveness of road asset management. This determines the main goal to maintain the operational condition of all components of roads at a level that ensures the satisfaction of user requirements and contributes to the preservation of assets. A simulation model for substantiating the parameters of long-term contracts for road maintenance has been built, which makes it possible to simulate forecast assessments of the characteristics of contracts. Underlying this study is the Monte Carlo method, as well as the triangular law of distribution, models of deterioration and restoration of the condition of road elements. Taking into consideration these models, it was established that the error in justifying the parameters of long-term contracts according to the devised method is up to 10 %. The devised model was tested by applying the developed original LTCsimula program using an example of the section of a motorway with a length of 87.3 km with an average level of requirements. According to the results of the test, the assessment of the laws of distribution of value, as well as the amount of deductions and profits of a long-term contract, was carried out. The calculation results demonstrated the model’s capability to determine the strategies for the maintenance of roads, taking into consideration the risk of implementing a contract with an error of up to 3.9 %. The practical use of the devised simulation model makes it possible to improve the efficiency of operational maintenance of roads, as well as to save from 10 % to 40 % of the cost of road maintenance

Traffic Load Estimation from Structural Health Monitoring sensors using supervised learning

Traffic Load Estimation (TLE) is increasingly adopted in public road infrastructures to regulate the access and limit heavy vehicles circulation. Standard approaches to TLE are based either on installing dedicated sensors such as intelligent cameras or infrared sensors or using existing smartphone sensors. However, both approaches have severe limitations, as often dedicated sensors are power-hungry and expensive to install and maintain, whereas smartphone-based approaches critically rely massively on users collaboration. More recently, researchers have started investigating TLE approaches using networks of accelerometers that are often already installed on critical road elements such as viaducts and bridges for Structural Health Monitoring (SHM) purposes. Specifically, in previous solutions, the detection and counting of vehicles was based on unsupervised anomaly detection and did not use any labeled data. While this simplifies the system’s setup, it also makes full validation impossible. In this work, we investigate the TLE problem using a supervised learning approach for SHM-sensor-based TLE for the first time. In particular, we use a relatively short recording session from a smart camera to label acceleration data with the corresponding number (and type) of passing vehicles. Labeled data are then fed to a Machine Learning (ML) model trained as a regressor to estimate the vehicle count corresponding to each input sample. We perform an extensive comparison among different types of ML models, both classic and deep. Our experiments find that the highest accuracy is achieved by a Support Vector Regressor (SVR) combined with simple feature extraction, which can reach a Mean Absolute Error (MAE) of 0.47 light vehicles and 0.21 heavy vehicles. This corresponds to a 9.8× and 8.1× error reduction compared to previous unsupervised solutions, respectively. Lastly, we show that our approach lends itself to an energy-efficient implementation on a real SHM gateway.

Attention-Enhanced One-Stage Algorithm for Traffic Sign Detection and Recognition

Detection and recognition of traffic signs are the keys to creating advanced driving assistance systems. Making highly precise maps also requires the identification and extraction of such road elements as traffic signs. Traditional detection and recognition methods no longer meet today’s needs, and object recognition algorithms based on deep learning have become the mainstream solution. However, current algorithms have limitations. The recognition speed of one-stage strategy algorithms is fast, but recognition accuracy is not satisfactory especially for small objects. The accuracy of two-stage algorithms is higher, but the recognition speed is extremely slow. This paper solves these problems with a proposed parallel attention convolution module, a channel attention pyramid network, and a loss function diagonal and center point IoU based on the YOLOv3 algorithm. The improved models in this paper are compared with SSD, YOLOv3, and Faster RCNN. Experimental results show that the proposed models have some improvement over the above models: the mAP of the models with PACM, CAFPN, and DCPIoU was 76.02%, compared with SSD300, SSD500, Faster RCNN, and YOLOv3, which had improvements of 9.27%, 6.93%, 2.94, and 5.3%, respectively. And the FPS of the improved model is basically the same as the original YOLOv3, without reducing the real-time performance.

Testing of Railway Prestressed Concrete Sleepers Using Acoustic Emission

The article describes the tests of prestressed concrete sleepers made according to the method specified in the requirements of the European standards (EN 13230-2:2009 Railway applications – Track – Concrete sleepers and bearers – Part 2: Prestressed monoblock sleepers) and WTWiO regulations, and an additional measurement method was used – acoustic emission (AE). The purpose of the tests using the acoustic emission method was to verify the results obtained using other test methods de-scribed in the European standard. The use of this method in sleeper tests enables obtaining precise data from the sleeper load test and determination of the characteristic parameters based on the recorded AE signals. Due to the variety of existing sleepers and the development of products in this area: wooden sleepers, composite sleepers, steel sleepers (type Y), the use of the acoustic emission method in research will be a good support and will enable proper assessment of these elements of the railway road.

Roads of the Russian-Belarusian Borderland in the 15th — 17th Centuries: the Experience of European Travelers

The trans-regional road network served as a territorial framework, determined the level of mobility of people and influenced the development of territories. In the course of our study, nine roads of Russian-Belarussian borderland of the 15th — 17th centuries were reconstructed. The state of road structural elements was analyzed, presence and quality of the existing artificial road structures and infrastructural elements were determined, the actual length of the road sections between the settlements was established. Conclusions about travel speed and comfort along the borderlands of the Grand Duchy of Lithuania and the Russian state were made. Twenty diary entries, messages and reports of foreign travelers were selected as the source for communication quality study. The main criteria for the data selection were the route fixation by the author and personal traveler experience description. For every informant, the Russian-Belarussian borderland was a transit region on a long journey from the starting point to that of destination.

Cryogenic Process Optimization for Medium Carbon Spring Steels

Spring steels are extensively used in load bearing elements of road and railway vehicles. The basic microstructure of these parts, which are subjected to high cycle fatigue, is tempered martensite. The improvement of the mechanical properties of these steels can only be achieved by modifying the material microstructure. In the microstructure of steel parts produced in different diameters, the formation of retained austenite and residual stresses is inevitable. For spring steels operating under heavy load, it is very important to remove the residual austenite form. Although the cryogenic treatment process is applied as a standard process for high alloyed and high carbon steels, it is not optimized for low alloy and medium carbon steels. In this study, different types of cryogenic treatment (Deep Cryogenic Treatment (DCT) / Shallow Cryogenic Treatment (SCT)) and tempering applications were carried out on spring steels with different alloying levels. With the outputs obtained from these experiments, optimization of cryogenic process parameters for medium carbon spring steels is aimed.