Road Environment Research Articles

FCOSH: A novel single-head FCOS for faster object detection in autonomous-driving systems

In autonomous driving systems, object detection plays a pivotal role by facilitating their ability to perceive the surrounding road environment effectively. Object detection's foremost challenge pertains to its real-time operational capabilities. Achieving this necessitates reducing the detectors' computational complexity while preserving their accuracy. Nevertheless, most of the approach in object detection involves dividing image processing over multiple heads, each tasked with detecting objects at particular scales. Even though this approach improves detection accuracy, it adds an extra computational burden. In this study, our objective is to assess the feasibility of employing a single head within the originally multi-headed architecture of the FCOS detector. In response to the challenges posed by this significant modification, we propose a set of straightforward solutions, resulting in the development of a novel Fully Convolutional One-Stage with a Single Head (FCOSH) detector. Through experiments on the BDD100K benchmark, our FCOSH detector exhibits substantial improvements in computational efficiency relative to the original FCOS while concurrently achieving a superior detection 0.5% accuracy. Specifically, FCOSH achieves an 18% reduction in inference time, a 24% reduction in required FLOPs, and a 10% decrease in the number of model parameters compared to FCOS.

Roadside Radar Network Deployment and Parameter Optimization in Road Environments

Roadside Radar Network Deployment and Parameter Optimization in Road Environments

Construction of a digital library of vocal music resources based on second-order data decomposition algorithm

Abstract In this paper, in order to solve the modal aliasing problem of the EMD decomposition algorithm and EEMD decomposition algorithm and optimize the vocal audio data decomposition on the basis of the adaptive VMD algorithm, the EEMD-VMD second-order data decomposition algorithm is proposed to decompose the digitized time series of vocal music resources, and to update the construction of the digital library of vocal music resources. Combined with the decomposition steps of the second-order data decomposition algorithm in the vocal resources digitized library, the overall framework of the vocal resources digitized library is designed and constructed with the main line of vocal resource types and the secondary line of content categories. Design the experimental environment, preprocess the vocal audio signal features, explore the modal number K value size of the EEMD-VMD second-order data decomposition algorithm, analyze the vocal audio denoising performance of the algorithm, and compare the correlation coefficients of the IMF components of the decomposition algorithms with the original audio signals. Explore the second-order data decomposition algorithm’s emotional classification of vocal resources and the performance of vocal signal enhancement, add noise sources, and use subjective and objective evaluation methods to assess the quality of vocal PESQ and STOI after decomposition processing. The EEMD-VMD second-order data decomposition algorithm performs the most prominently in street noise environments. The enhancement results in the case of signal-to-noise ratios of -5, -10, and -15 are 3.59, respectively, 4.36, 4.29, and the mean value of the enhancement performance reaches 4.08. The second-order data decomposition algorithm’s precise processing of vocal resources provides better quality digital resources for the construction of a digital library of vocal resources.

Статистичний аналіз дорожньо-транспортних пригод у Тернопільській області та заходи щодо зниження аварійності

The aim of this study is to analyze the dynamics, causes, and consequences of road traffic accidents (RTAs) in the Ternopil region over the past five years. This analysis seeks to identify the primary types of RTAs, determine the most frequent causes, and propose effective measures to reduce the number of accidents and their severity. By understanding these factors, we aim to enhance road safety and minimize the socio-economic impacts associated with RTAs in this region. In this study, a comprehensive statistical analysis of RTAs in the Ternopil region was conducted. This analysis revealed a significant increase in the number of accidents, which reached 2547 cases in 2023, an 11% rise compared to 2022. The primary types of accidents identified include collisions (50%), hitting obstacles (19%), hitting stationary vehicles (16%), and pedestrian accidents (8%). The study found that the highest mortality rates occur in pedestrian accidents (34%) and vehicle collisions (33%). Key causes of RTAs were identified as violations of maneuvering rules (40%), speeding (23%), failure to maintain a safe distance (10%), driving under the influence of alcohol (7%), and violations at intersections (5%). Based on these findings, several recommendations were made to enhance road safety. These include the implementation of artificial road bumps, installation of traffic lights with adjustable timers, additional road signs, high-visibility and illuminated pedestrian crossings, and the use of surveillance cameras to monitor compliance with traffic rules and identify violators. Moreover, the study emphasizes the importance of developing and implementing methodologies for predicting accident rates using statistical methods and conflict zone analysis, as well as calculating accident-related economic and environmental losses to evaluate the effectiveness of proposed measures. This study underscores the urgent need for improved road safety measures in the Ternopil region. Implementing the recommended strategies and methodologies will significantly reduce the number of RTAs, enhance overall road safety, decrease the risks of injuries and fatalities, and lower the economic costs associated with road traffic accidents. These findings provide a clear roadmap for policymakers and road safety authorities to take actionable steps towards a safer road environment.

Концепція оцінки ергономічної стійкості транспортного потоку великих міст з урахуванням динамічності зміни впливових факторів

The methodological approach of forecasting the congestion of the streets of large cities, taking into account the fluctuations in the density of traffic flows and the speed of movement of cars in the flow, received further development. The methodical approach takes into account fluctuations in the dynamics of the traffic flow in the form of changes in the acceleration of the movement of cars in the flow and fluctuations in changes in the infrastructure of the road environment, which is associated with the number of traffic lights, pedestrian crossings and the number of lanes for the movement of vehicles. Through modeling, it was found that increasing the acceleration values of cars in the stream significantly increases the range of robustness. At low values of acceleration of cars, the reserve of resistance to the formation of traffic jams decreases, which negatively affects the traffic flow, there is a probability of the formation of traffic jams. The presence of fluctuations in the density of the traffic flow and the speed of movement of cars in the flow, due to changes in the acceleration of cars, allows making adjustments to the value of the robustness criterion. Adjustments can be made for different clusters of the road network, for different times of the day, and take into account the period of fluctuations. The dependences of the change in the robustness range of the traffic flow upon changing the infrastructure of the road network are given. It has been established that increasing the number of lanes and simultaneously reducing the number of traffic lights and pedestrian crossings on the controlled cluster significantly increases the stability of the movement of vehicles in the flow. Conversely, reducing the number of lanes, increasing the number of traffic lights and pedestrian crossings on the controlled cluster significantly reduces the stability of the movement of vehicles in the flow. Adjustment of density and movement speed can be performed taking into account the amplitude of oscillations. The concept of modeling and forecasting the stability of traffic flows of large cities to the formation of traffic jams is formulated. The main components of the concept, according to which such an assessment is performed step by step, taking into account the dynamics of changes in influencing factors, are substantiated. The proposed concept differs from the known ones in that it takes into account fluctuations in traffic flow parameters - the density and speed of movement of vehicles over time. Such changes are characteristic of the city's road network during "peak hours".

Model Predictive Control Based Path Planner Design for On-road Autonomous Tractor Trailer Vehicles

Efficient path planning for on-road autonomous tractor trailer vehicles (ATTVs) is a complex task due to the intricate kinematics introduced by the articulated trailer. This technical paper introduces a novel Model Predictive Control (MPC) based lateral path planner designed to address the unique challenges of maneuvering ATTVs, particularly in environments that require navigation through narrow spaces and around multiple obstacles on well-structured roads. The authors have expertly developed a Cartesian kinematic model tailored for ATTVs and have innovatively applied the Frenet frame to better apply constraints in structured road environments. The efficacy of the proposed path planner is confirmed through real-time testing on actual roadways, showcasing its practical application and the advantages it offers over existing methods.

Editorial Special Section on Coordination, Cooperation, and Control of Autonomous Vehicles in Smart Connected Road Environments

Editorial Special Section on Coordination, Cooperation, and Control of Autonomous Vehicles in Smart Connected Road Environments

Analyzing the role of climatic factors in the driver—vehicle—road—environment system

Climate peculiarities affect road performance and, consequently, vehicle operating conditions. The autumn-winterspring period is characterized by sharp air temperature fluctuations within 0...± 4 °C, large amounts of precipitation, high air humidity, thaws, icing, which are a concomitant factor of accidents on the roads. The analysis of road accident statistics showed that in the transitional periods of fall-winter and winter-spring there are localized spikes in the number of accidents. During the analysis it was revealed that the increase in the number of accidents in the transition period falls on the so-called "critical" month, characterized by air temperature spikes in the range of 0...±4 °C and heavy precipitation. Keywords WADS system; climatic zones of the Russian Federation; factors of the subsystem "environment"; accident statistics; winter road maintenance

Unraveling The Effects of Micro-Level Street Environment on Dockless Bikeshare in Ithaca

Unraveling The Effects of Micro-Level Street Environment on Dockless Bikeshare in Ithaca

야간 시간대 보행자의 범죄 두려움 감소를 위한 CPTED 적용 방안

Fear of crime is a deeply rooted source of anxiety in modern society, making it essential to reduce this fear to improve the quality of life for residents. Previous studies have indicated that pedestrians, especially during nighttime hours, often experience a significant level of fear of crime. Therefore, this study focuses on identifying vulnerable points for fear of crime during nighttime pedestrian activity in Jangyang 2-dong, Gwangjin-gu, Seoul. It also proposes crime prevention strategies based on Crime Prevention Through Environmental Design (CPTED) principles, considering road environments and inter-individual spacing metrics.
 Firstly, using K-means Clustering on reported crime data for Jangyang 2-dong, nighttime hours were defined as 21:00 to 01:00. Subsequently, social network analysis were applied to identify areas with low centrality, categorizing them into Cluster 1 (Jangyangbyeong-ro 6, Dukseom-ro 44, Dukseom-ro 50) and Cluster 2 (Jayang-ro 3, Dukseom-ro 58) as locations vulnerable to fear of crime. Finally, tailored crime prevention designs were proposed for each cluster. This study is significant for its use of social network analysis on safety data to identify fear of crime vulnerable areas and for suggesting crime prevention measures tailored to the characteristics of the region from a CPTED perspective.

Augmented Reality (AR) as a New Educational Medium for Children: Using Road Safety Content

Road accidents, often involving one or more vehicles, can result in property damage, injuries, or even fatalities. These incidents can occur due to a range of factors, including human errors, adverse weather conditions, or mechanical failures, despite precautions taken by road users. Consequently, early education on road safety is crucial, especially for children. This research focuses on assessing children's knowledge of road accidents in Malaysia and evaluating the impact of augmented reality (AR) experiences on their understanding. To support this project, we developed an AR application using the Pendidikan Keselamatan Jalan Raya (PKJR) Year 2 Guidebook as a medium for students to learn about road safety. Selected pages in the book serve as markers, enabling students to engage with AR content while using the book. The study aims to determine the effectiveness of the AR application as an educational tool for children. A group of school children participated in testing this AR application, and their experiences were assessed using an adapted Game Experience Questionnaire (GEQ) model. The results indicate that after using the AR application, the group of 8-year-old children exhibited improved awareness of the road environment. This paper also explores the emotional aspects of participant experiences as emphasized by the GEQ. These findings highlight the potential of AR as an innovative tool for educating children about road safety, challenging traditional approaches, and promoting safer road behaviors among young individuals. Furthermore, this project aligns with the strategies outlined in the Malaysian Road Safety Plan 2020-2030, particularly in reducing risks to pedestrians. In a broader context, this study contributes to the evolving landscape of technology-driven safety initiatives, underscoring the importance of adapting contemporary educational mediums to address complex societal issues like road accidents. In conclusion, we discuss the potential for future studies involving road safety education and interactive technology.

Simulation-based Accident Threshold Verification Study by Road Environment Factors for Traffic Crashes

Simulation-based Accident Threshold Verification Study by Road Environment Factors for Traffic Crashes

The Role of Road Safety Units in the Prevention of Child Traffic Injuries

This article describes a number of issues devoted to the role of units responsible for ensuring road safety in the prevention of child road traffic injuries. The author examines the issue of the importance and effectiveness of the activities of units responsible for ensuring road safety in the context of preventing child road traffic injuries. The author analyzes in detail the key aspects of the role of these units in carrying out preventive measures aimed at reducing the risk of injury to children on the roads. A wide range of methods and technologies are discussed, including video surveillance systems, smart traffic lights and automated means of recording traffic violations, which are seen as integral tools for improving safety. Automated means of recording violations of traffic rules further strengthen control over compliance with the rules, recording violations with high accuracy. Together, these technologies form a comprehensive approach to security, based on the use of advanced tools and techniques. Such consideration contributes to the creation of a more effective system for preventing child road traffic injuries. The author highlights the importance of collaboration between safety departments and community organizations in the development and implementation of effective strategies to combat childhood road traffic injuries. The result highlights the need for concerted efforts to create a safe road environment and reduce the risk of injury to children in road situations. In conclusion, the author emphasizes that only through an integrated approach and the introduction of advanced technologies can the safety of children on the roads be ensured, emphasizing the importance of cooperation with the public to achieve this important goal.

Polarization adaptation to improve cell border area bitrates and system capacity in small cells

The target of this paper is to show the impact of polarization adaptation on the received signal quality in an outdoor small-cell deployment scenario. The signal-to-interference ratio (SIR) is the key factor in defining the achievable data rate, and the capacity of the cell. At the cell border area, the SIR value is typically low and causes a significant decrease in the system capacity and achievable data rates. These bad SIR areas at the cell border can be improved by using orthogonal polarizations in the neighboring cells rather than using all polarizations over the whole cell coverage area. For the research work of this paper, a series of measurements were carried out to measure a received signal power and a cross polarization discrimination (XPD) ratio while the signal is transmitted and received with a different set of polarizations. In the measurements, we have considered horizontal, vertical, +/− 45° slanted polarizations, and two different environments, urban street and open space, and three frequency bands, 970−1030 MHz, 2000−2030 MHz and 3364−3400 MHz. The measurement results revealed that at a different distance from the transmitter, for horizontal/vertical polarization, the average XPD is around 24.7 dB and 31.7 dB in the urban street and open area environments, respectively. For +/− 45° slanted polarization, the average XPD is around 11.5 dB and 12.1 dB in the urban street and open area environments, respectively. This paper goes on to propose polarization adaptation in each cell, where the primary polarization is valid for the whole service area of the cell, and secondary polarization is only used in close proximity of the base station antenna. Considering the results, it is emphasized that system capacity can be significantly improved by having only one channel with good SIR values compared to multiple channels with bad SIR values. However, MIMO channels with orthogonal polarizations or with spatial multiplexing can be utilized in the closed vicinity of the base station, i.e., in an area with good SIR values. It is shown that the overall cell capacity can be increased by almost 35% by utilizing polarization adaptation compared to MIMO 2 × 2.

Using meta-learning to establish a highly transferable driving speed prediction model from the visual road environment

Driving speed prediction is of great significance for the realization of autonomous driving and intelligent transportation systems. The effectiveness of the existing driving speed prediction models often relies on a large number of training data, and their performance will drop sharply with the change in the usage environment. To solve these problems, this study adopted a Meta-learning algorithm to propose a highly transferable driving speed prediction model based on the visual road environment. The data used in this study were the visual road environment pictures and corresponding driving speed from three different types of scenarios (i.e., rural roads, urban roads, and highways) in a naturalistic driving experiment and a public KITTI dataset. The analysis of a Random forest model showed that the influence degree of visual road environment elements on driving speed was quite distinct in different scenarios. Then, a Meta-learning-based driving speed prediction model was presented to address two issues, including the small sample size and transferability. To examine the performance of this new model, a driving speed prediction model based on a convolutional neural network (CNN) was also used for comparison. The results showed that the prediction accuracy of Meta-learning was significantly improved compared to CNN in the face of the small sample size problem and when transferred to new scenarios. The findings in this study can contribute to the optimization of the driving speed prediction model and the improvement of the visual road environment design.

Development of a 470-Horsepower Fuel Cell–Battery Hybrid Xcient Dynamic Model Using SimscapeTM

Polymer electrolyte membrane fuel cells (PEMFCs) are employed in trucks and large commercial vehicles utilizing hydrogen as fuel due to their rapid start-up characteristics and responsiveness. However, addressing the requirement for high power output in the low-current section presents a challenge. To solve this issue, a multi-stack can be applied using two stacks. Furthermore, thermal management, which significantly affects the performance of the stacks, is essential. Therefore, in this study, a hydrogen electric truck system model was developed based on a Hyundai Xcient hydrogen electric truck model using MATLAB/SimscapeTM 2022b. In addition, the system’s performance and thermal characteristics were evaluated and analyzed under different road environments and wind conditions while driving in Korea.

AN APPROACH OF HIGH DEFINITION MAP INFORMATION INTERACTION

Abstract. High definition (HD) maps play a very important role in the realization of autonomous driving technology. It assists self-driving vehicles to efficiently and safely complete a series of driving decisions and route planning by virtue of having most of the accurate and reliable prior information in the road environment. With the continuous change of technology, there are higher requirements for the accuracy, richness and freshness of the information stored in the HD map, so as to assist the practical application of automatic driving technology. However, current research related to HD maps mainly focuses on static information in the road environment. Since there is a large amount of complex, variable and uncertain dynamic information in the road environment, it can be used as prior knowledge for self-driving to make better decisions. Therefore, the research focus of this paper is on the dynamic information. We propose to use HD map as an information system - high definition map information system (HDMIS) - to assist autonomous driving vehicles. We design the specific content of dynamic information in the HDMIS, and develop an information interaction approach based on the vehicle end of the self-driving car and the HDMIS cloud as the interactive subject of dynamic information. In the experiment, we design and build three types of specific traffic scenarios on the simulation platform, and verify the effectiveness of the interaction approach by using the database to perform information interaction between different ports. The results show that our interaction approach can meet the storage and release of dynamic information by HDMIS to a certain extent, and can provide a large amount of dynamic information for autonomous vehicles to help them complete subsequent driving decisions and planning.

LIDAR MATCHING STRATEGIES FOR HD POINT CLOUD MAP GENERATION IN URBAN AREA

Abstract. Autonomous driving relies on high accuracy point vector map, which was generated by the point cloud map, and pre-provides the vehicle preliminary road environment information. Lidar Odometry and Mapping (LOAM) has always been a promising research topic in the field of robotics, environment sensing, and currently autonomous driving. However, in certain urban environments like basement parking lot, tunnels, highways, or other similar settings, the geometric features are not clearly discernible. As a result, algorithms resembling the LOAM framework may encounter difficulties in accurately mapping these areas. The paper utilized relative low-cost LiDAR expecting to propose a state-of-the-art point cloud mapping/update scheme. We compared the GNSS-challenge area with straight line and loop area separately, simultaneously considered the DG, ICP, NDT matching algorithm for the low-cost mapping/update strategy. With the realistic experiment conduction, our result evaluated by point to point corresponding mean error and standard error. For the straight line environment, ICP has the fastest convergence in empirical cumulative distribution under 0.4 meters. For the loop scenario, point-to-point ICP still has the fastest convergence in empirical cumulative distribution under 0.22 meters. Yet both of them still suffer from the fault matching.

How do children move and behave on streets? Vision-based movement behavior analysis using children's trajectories in urban surveillance systems

Understanding how children use streets will allow urban planners to create streets that are livelier and more child-friendly. However, it is still challenging to investigate detailed information on children's movement behaviors on individual streets due to labor-intensive observations, the difficulty of integrating qualitative data, and privacy concerns. With the wide application of vision-based technologies, Researchers can analyze the movements and behaviors of large groups of children on streets automatically and continuously. This study aims to analyze children's movement behaviors on streets utilizing computer vision techniques in urban surveillance systems. The proposed methods automatically extract children's trajectories, calculate movement behavioral features, and classify the movement behavioral characteristics of children. Our results identify five movement behaviors of children on streets: walking, staying, running, accelerating, and decelerating, demonstrating their use of streets. In addition, the results showed the feasibility of computer vision techniques to identify differences in children's movement behaviors under varying conditions, such as day and time, and the potential of street environments to positively influence children's use of streets from the daily street lives of children. Utilizing vision-based analysis of children's movement behaviors provides meaningful information for improving streets for children toward a better understanding of the use of streets.

What Drives the Spatial Heterogeneity of Urban Leisure Activity Participation? A Multisource Big Data-Based Metrics in Nanjing, China

With the rapid pace of urbanization, enhancing the quality of life has become an urgent demand for the general public in both developed and developing countries. This study addresses the pressing need to understand the spatial distribution and underlying mechanisms of urban leisure activity participation. To achieve this, we propose a novel methodological framework that integrates diverse big data sources, including mobile phone signaling data, urban geospatial data, and web-crawled data. By applying this framework to the urban area of Nanjing, our study reveals both the temporal and spatial patterns of urban leisure activity participation in the city. Notably, leisure activity participation is significantly higher on weekends, with distinctive daily peaks. Moreover, we identify spatial heterogeneity in leisure activity participation across the study area. Leveraging the OLS regression model, we design and quantify a comprehensive set of 12 internal and external indicators to explore the formation mechanisms of leisure participation for different leisure activity types. Our findings offer valuable guidance for urban planners and policymakers to optimize the allocation of resources, enhance urban street environments, and develop leisure resources in a rational and inclusive manner. Ultimately, this study contributes to the ongoing efforts to improve the quality of urban life and foster vibrant and sustainable cities.