Road Abandoned Objects(RAOs)pose significant threats to traffic safety,particularly due to their small size,irregular shapes,and unpredictable distribution in complex road environments.The primary objective of this st...Road Abandoned Objects(RAOs)pose significant threats to traffic safety,particularly due to their small size,irregular shapes,and unpredictable distribution in complex road environments.The primary objective of this study is to develop an accurate and real-time detection framework for RAOs while maintaining low computational cost for practical deployment.To achieve this,we propose RAO-YOLO,a lightweight vision-based detection framework built upon an enhanced YOLO architecture.Specifically,a Mixed Aggregation Network(MANet)is introduced to improve multi-scale feature representation,and a Lightweight Shared Detail-Enhanced Detection(LSDD)head is designed to enhance localization accuracy for small and irregular objects.Furthermore,a Focal-MPDIoU loss function is proposed to address sample imbalance and geometric irregularity during training.Extensive experiments conducted on the RAOD dataset demonstrate that the proposed method achieves superior performance compared to state-of-the-art detectors,achieving a mAP@0.5:0.95 of 56.1%while maintaining real-time inference speed.These results validate the effectiveness of the proposed framework for practical intelligent transportation applications.展开更多
Chinese automobile safety regulations are considering the introduction of thorax impactor subsystem tests to evaluate vehicle safety performance concerning thorax protection for Vulnerable Road Users(VRUs).However,the...Chinese automobile safety regulations are considering the introduction of thorax impactor subsystem tests to evaluate vehicle safety performance concerning thorax protection for Vulnerable Road Users(VRUs).However,there is currently an insufficient amount of data regarding VRU thorax-vehicle contact boundary conditions,which is essential for establishing the thorax impactor test procedure.Consequently,the obj ective of this study is to examine the characteristics of VRU thorax-vehicle contact boundary conditions,utilizing multi-body crash simulations that are informed by the distribution of accident scenarios.The simulation data suggest that the boundary conditions for thorax-vehicle contact in VRUs are predominantly influenced by the relative height of the VRU's pelvis in relation to the vehicle's bonnet leading edge,which in turn affects upper body kinematics.This results in variations across different vehicle and VRU types involved in collisions.The analysis of these contact boundary conditions indicates that thorax impactor subsystem test procedures should differentiate between vehicle types.The results suggest that:thorax impactor subsystem tests should concentrate on the Wrap Around Distance(WAD) range of 900-1800 mm;for testing at the bonnet-windscreen area,the thorax impactor could be launched at speeds of 16.5 km/h(with a vector angle of 24° and an initial inclination angle of 17°) for sedans,and 23.5 km/h(with a vector angle of 25° and an initial inclination angle of 22°) for SUVs/MPVs.Additionally,a horizontally directional velocity of 35.5 km/h(with an initial inclination angle of 30°) could be specified for thorax impactor tests at the bonnet leading edge area of SUVs/MPVs.The above data provides foundational data for future thorax impactor subsystem tests in China.展开更多
Due to low reflectance(5%10%)of black asphalt pavement,most of the incident solar radiation(2952500 nm)is absorbed and stored.This results in the high temperature(even exceeding 70 C in summer)of the pavement surface,...Due to low reflectance(5%10%)of black asphalt pavement,most of the incident solar radiation(2952500 nm)is absorbed and stored.This results in the high temperature(even exceeding 70 C in summer)of the pavement surface,which leads to pavement diseases,exacerbates the heat island effect,and reduces human thermal comfort.Reflective pavement coating with high reflectance ranging from 20%to 80%is an effective way to solve the above problems.However,excessively improving the visible reflectance and ignoring the mixed reflection behavior(including specular and diffuse reflection properties)may cause glare problems and negatively affect road light environment safety.Therefore,precise control of reflectance is very significant.In this study,an automated test platform of reflection behavior was developed to investigate the mixed light reflection distribution pattern of reflective coating.Additionally,the impact of reflective coating on the light environment was explored.It was found that there was obvious specular reflection under conditions of a low incidence angle(less than 10°).Moreover,reflective coating could change the lightness index and specular reflection coefficient of traditional pavement.Finally,considering glare during the daytime and the nighttime illumination safety,the control indexes of reflective pavement coating were proposed.The visible reflectance and specular reflection coefficient should be lower than 22%and 1.5,respectively.The results will provide a theoretical basis for the precise and safe design of reflective pavement coatings.The coatings aim to improve the thermal and light environments,thereby enhancing driving safety,while also providing better illumination during emergency repair and maintenance of road infrastructure.展开更多
Global climate change is intensifying the impact of slope hazards,particularly rainfall-induced landslide hazards(RILH),on mountain road networks(MRNs).However,effective quantitative models for dynamically assessing M...Global climate change is intensifying the impact of slope hazards,particularly rainfall-induced landslide hazards(RILH),on mountain road networks(MRNs).However,effective quantitative models for dynamically assessing MRNs vulnerability under RILH disturbances are still lacking.To bridge this gap,this study develops a Cascading Failure Model for Rainfall-Induced Landslide Hazard(CFM-RILH).Validation via a case study of the GarzêTibetan Autonomous Prefecture Road Network(GTPRNs)reveals key characteristics of MRNs system vulnerability under RILH disturbances:(1)Under the disturbance effects of RILH,the vulnerability of the MRNs system follows a nonlinear phase transition law that intensifies with increasing disturbance intensity,exhibiting a distinct critical threshold.When the disturbance intensity exceeds this threshold,the system undergoes a global cascading failure phenomenon analogous to an“avalanche.”(2)Under RILH disturbances,the robustness of the MRNs system possesses a distinct safety boundary.Exceeding this boundary not only fails to improve hazard resistance but instead substantially elevates the risk of large-scale cascading failure.(3)Increasing network redundancy may be considered one of the primary engineering measures for enhancing MRNs resilience against such disturbances.Based on these findings,we propose a“Two-Stage Emergency Response and Hierarchical Fortification”strategy specifically to improve the resilience of GTPRNs impacted by RILH.The CFM-RILH model provides an effective tool for assessing road network vulnerability under such hazards.Furthermore,its modeling framework can also inform vulnerability assessment and resilience strategy development for road networks affected by other types of slope hazards.展开更多
At present,environmental problems are becoming increasingly severe,and sustainable development concerns the common destiny of all mankind around the world.Leveraging ecological footprint and ecological carrying capaci...At present,environmental problems are becoming increasingly severe,and sustainable development concerns the common destiny of all mankind around the world.Leveraging ecological footprint and ecological carrying capacity data for Eurasia from 2000 to 2022,this study employs a three-dimensional ecological footprint model to conduct a multi-scale sustainability assessment.Further applying a difference-in-differences model,we analyze the impact mechanisms of the Belt and Road Initiative on Eurasia's ecological footprint.Quantile regression and heterogeneity analysis reveal Belt and Road Initiative's differential effects across countries.Key findings indicate that:(1)Eurasia's unsustainable development intensified from 2000 to 2022,with ecological footprint depth rising from 1.966 to 2.513 ha/cap,while per capita ecological footprint size declined slightly from 1.092 to 1.023 ha/cap.(2)Classifying 83 countries into 9 sustainability types based on ecological footprint depth and size,Asia showed weak sustainability(low size-medium depth and low size-low depth types),while Europe was primarily low size-medium depth with relatively stronger sustainability.Six countries experienced weakened sustainability and six improved.(3)The Belt and Road Initiative significantly increased ecological footprint in Eurasian countries,mediated by industrial structure,technological innovation,and foreign direct investment.Quantile regression indicates Belt and Road Initiative's effect is stronger in nations with lower initial ecological footprint.Heterogeneity analysis further shows Belt and Road Initiative disproportionately impacts countries with lower ecological footprint depth,smaller per capita ecological footprint size,and weaker sustainability.These insights provide critical guidance for implementing the UN 2030 Agenda and formulating Belt and Road Initiative policies to enhance long-term sustainability.展开更多
Urban traffic generates massive and diverse data,yet most systems remain fragmented.Current approaches to congestion management suffer from weak data consistency and poor scalability.This study addresses this gap by p...Urban traffic generates massive and diverse data,yet most systems remain fragmented.Current approaches to congestion management suffer from weak data consistency and poor scalability.This study addresses this gap by proposing the Urban Traffic Congestion Unified Metadata Model(UTC-UMM).The goal is to provide a standardized and extensible framework for describing,extracting,and storing multisource traffic data in smart cities.The model defines a two-tier specification that organizes nine core traffic resource classes.It employs an eXtensible Markup Language(XML)Schema that connects general elements with resource-specific elements.This design ensures both syntactic and semantic interoperability across siloed datasets.Extension principles allow new elements or constraints to be introducedwithout breaking backward compatibility.Adistributed pipeline is implemented usingHadoop Distributed File System(HDFS)and HBase.It integrates computer vision for video and natural language processing for text to automate metadata extraction.Optimized row-key designs enable low-latency queries.Performance is tested with the Yahoo!Cloud Serving Benchmark(YCSB),which shows linear scalability and high throughput.The results demonstrate that UTC-UMM can unify heterogeneous traffic data while supporting real-time analytics.The discussion highlights its potential to improve data reuse,portability,and scalability in urban congestion studies.Future research will explore integration with association rulemining and advanced knowledge representation to capture richer spatiotemporal traffic patterns.展开更多
The deterioration of road performance in asphalt mixtures due to aging can significantly affect the service period of asphalt pavement.Therefore,it is particularly important to find a suitable method to resist the agi...The deterioration of road performance in asphalt mixtures due to aging can significantly affect the service period of asphalt pavement.Therefore,it is particularly important to find a suitable method to resist the aging of asphalt mixture.In this study,various red mud-compounded styrene-butadiene-styrene(SBS)-modified asphalt mixtures were prepared using acid-treated and surface-modified raw red mud(RM)as a modifier for SBS-modified asphalt.First,SBS-modified asphalt mixture specimens were prepared at the optimal oil-rock ratio.Subsequently,both unaged and aged mixtures were subjected to Marshall stability,low-temperature splitting,freeze-thaw splitting,and indirect tensile fatigue tests to evaluate the effect of different red muds on the road performance of SBSmodified asphalt mixtures.The experimental results showed that the addition of raw red mud(RM)improved the high-temperature performance,moisture susceptibility,and fatigue performance of SBS-modified asphalt mixtures,but adversely affected their low-temperature performance.The high-temperature stability,moisture susceptibility,and fatigue performance were further enhanced with the incorporation of organic red mud.Additionally,raw red mud effectively delayed the thermal-oxidative aging of the mixture.After surface modification,red mud can significantly enhance the thermal-oxidative aging resistance of the SBS-modified asphalt mixture.Among the tested samples,the mixture incorporating red mud treated with oxalic acid and titanate coupling agent exhibited the highest durability against aging.展开更多
The development of road materials as alternatives to mineral aggregates has become an important research direction.This paper proposes cold-bonded lightweight aggregates(R-CBLA)as substitutes for conventional aggregat...The development of road materials as alternatives to mineral aggregates has become an important research direction.This paper proposes cold-bonded lightweight aggregates(R-CBLA)as substitutes for conventional aggregates and prepares lightweight aggregate-modified soil(LA-Soil)and lightweight aggregate-hydraulic bound mixtures(LA-HBM)for subgrade and base applications.By adjusting the rotation speed of the extrusion granulator,feeding rate,and raw material moisture,R-CBLA can be produced with a granulation rate higher than 90%.Its water absorption shows a significant negative correlation with strength,while bulk density exhibits a significant positive correlation,thus providing a theoretical basis for optimizing performance.In LA-Soil,incorporating 40%–50%R-CBLA with natural coarse grains develops a skeleton-dense structure,which enhances dry density,CBR,and resilient modulus,while still maintaining durability under freeze-thaw cycles.In LA-HBM,two critical replacement thresholds are identified,performance changes are limited below 25%,performance decreases moderately but remains technically feasible between 25%and 75%,the skeleton structure becomes unstable and performance declines sharply beyond 75%.Cost analysis further shows that R-CBLA offers advantages in materials,transportation,and construction,with maximum cost reductions reaching 87%.This economic benefit is especially pronounced in resource-scarce regions.In conclusion,the study verifies the feasibility of R-CBLA in road engineering,proposes a long-life pavement design concept,and emphasizes largescale production,systematic performance optimization,and long-term durability as priorities for future research.展开更多
Ground-penetrating radar(GPR)imaging is widely used for detecting hidden defects in urban roads.However,the complex noise environment,large-scale variations in defect features,and the sensitivity of slender defects to...Ground-penetrating radar(GPR)imaging is widely used for detecting hidden defects in urban roads.However,the complex noise environment,large-scale variations in defect features,and the sensitivity of slender defects to annotation errors pose significant challenges to accurate detection.To address these issues,this study proposes an improved object detection framework,termed DFF-MoCA-YOLO,based on YOLOv11 for identifying void and loose defects in GPR images.First,a multi-strategy gated feature fusion module(MSGFF-C3k2)is designed to enhance feature robustness against complex noise and scale variations.Then,aMonte Carlo Attention(MoCAttention)module is introduced to improve defect-feature representation via stochastic sampling and channel recalibration.Subsequently,an adaptive aspect-ratio penalty CIoU loss(CIoU-ARP)is developed to improve bounding box regression accuracy for slender defects.A labeled dataset containing void and loose defects is constructed using multi-source GPR data collected from eight urban roads.Finally,a series of ablation experiments is conducted on the proposed modules.Experimental results demonstrate that the proposed method achieves consistent performance improvements over the baseline YOLOv11 and other mainstream YOLO variants,while maintaining relatively low computational complexity.The results indicate that the proposed framework offers an effective and practical solution for detecting hidden defects in urban roads using GPR images.Moreover,the model’s robustness to noise and ability to accurately detect defects at varying scales make it a promising tool for urban infrastructure maintenance.Its efficient performance with minimal computational overhead makes it suitable for real-time defect detection.展开更多
The article outlines the main characteristics of the operation of the Hungarian road network during the Soviet bloc era and the three and a half decades after its abandonment,together with its social-economic environm...The article outlines the main characteristics of the operation of the Hungarian road network during the Soviet bloc era and the three and a half decades after its abandonment,together with its social-economic environment and its development efforts and its adaptation to the Western models.After a brief presentation of the decades preceding the democratic turnaround in Europe,it summarises the main trends from the start of market operations to the present days,divided into three stages of development.It refers to professional successes and problems,to social expectations and to the limited possibilities of the country’s economic performance and external conditions,to changes in financial financing and the organisation system of development management.展开更多
This study focuses on the protection and revitalization utilization of linear cultural heritage,selecting the Qi’ao Ancient Road in Southern China as a typical case study,a cultural route with both historical depth a...This study focuses on the protection and revitalization utilization of linear cultural heritage,selecting the Qi’ao Ancient Road in Southern China as a typical case study,a cultural route with both historical depth and practical significance.The paper first systematically reviews four theoretical foundations:“cultural route”,“cultural heritageelics”,“structural functionality and space”,and“e-commerce new media marketing”,constructing an integrated“function-culture-space”analytical framework.Guided by this framework,the research establishes the investigation path with the Ming and Qing Dynasties as the temporal scope and the Southern and Eastern Main Routes of the Qi’ao Ancient Road as the spatial scope.It comprehensively employs literature research,field surveys,and Geographic Information System(GIS)analysis methods to systematically screen and analyze the value of tangible and intangible cultural relics along the ancient road.The study shows that the Qi’ao Ancient Road was not only a vital land transportation artery between Guangdong and Macao during the Ming and Qing Dynasties and an important overland link for the Maritime Silk Road,but also a witness to the integration of Chinese and Western cultures,the spread of ideas,and social transformations.In response to the current state of its protection and utilization,this paper innovatively proposes an integrated e-commerce new media marketing strategy centered on the“Online Three-in-One”(cross-border e-commerce platforms,independent websites,overseas social media)and“Offline Six-in-One”(museums/cultural centers,culturalourism bureaus,scenic areas,universitiesesearch institutions,enterprises,and intangible cultural heritage experience shops).This strategy aims to transform and disseminate the value of the ancient road’s cultural relics through modernized,marketized,and experiential means,thereby providing a path reference with both theoretical foresight and practical operability for achieving holistic protection,sustainable utilization,and methodological innovation in linear cultural heritage.展开更多
Digital economy(DE)is on the verge of becoming a pivotal facilitator of the energy transition(ET).However,it remains to be seen to what extent China's outward foreign direct investment(OFDI)can stimulate the devel...Digital economy(DE)is on the verge of becoming a pivotal facilitator of the energy transition(ET).However,it remains to be seen to what extent China's outward foreign direct investment(OFDI)can stimulate the development of the DE and promote ET under the Belt and Road Initiative(BRI).Employing a nonparametric additive model,this study examines this issue by using panel data from 84 BRI countries spanning 2007–2022.The connections between China's OFDI and the DE and ET of BRI nations vary across different regions.China's OFDI has considerably fostered the ET of nations along its route to Central Asia,Europe,North Africa,and the Middle East.Conversely,in the Pacific and East Asian regions,China's OFDI has a constructive effect on the advancement of DE in participating nations.However,the effect of China's OFDI on the ET of nations in the Pacific Islands and East Asia and South Asia is statistically insignificant.Moreover,China's OFDI impairs the DE of nations in Central Asia and Europe,the Caribbean and Latin America,as well as North Africa and the Middle East.Notably,the net effect of China's OFDI on ET is positive;however,the mediating effect of facilitating ET through DE is not pronounced.展开更多
Matias Jere is at a hardware shop in Malawi’s capital city,Lilongwe.He is waiting for it to open so that he can buy ball joints for his vehicle,his third set in as many months.“Our roads are so bad that ball joints ...Matias Jere is at a hardware shop in Malawi’s capital city,Lilongwe.He is waiting for it to open so that he can buy ball joints for his vehicle,his third set in as many months.“Our roads are so bad that ball joints don’t last long,and it’s costing me a small fortune,”he said.Businessman Rafik Mwamadi is also worried.He needs to travel more than 300 km to the Northern Region city of Mzuzu to deliver merchandise,but the road is riddled with potholes.In the past,the road trip took about five hours,but in its current poor condition,it takes about nine hours.展开更多
Against the backdrop of the concurrent advancement of China's expressway network development and large-scale reconstruction and expansion projects,the reconstruction and expansion of a single road section can trig...Against the backdrop of the concurrent advancement of China's expressway network development and large-scale reconstruction and expansion projects,the reconstruction and expansion of a single road section can trigger a redistribution of the overall traffic flow within the regional road network,with significant characteristics of traffic volume transfer across routes,corridors,and regions.Traditional traffic volume analysis methods,which focus on individual road sections,struggle to meet the practical demands of regional road network linkage,multipath competition,and dynamic traffic organization.To scientifically grasp the traffic transfer patterns within the road network during reconstruction and expansion and ensure the safety and efficiency of road network operations during construction,this paper adopts a perspective of regional road network linkage to systematically analyze the internal mechanisms and spatiotemporal distribution characteristics of traffic volume transfer during expressway reconstruction and expansion.Furthermore,it proposes a traffic volume transfer forecasting and analysis system suitable for reconstruction and expansion scenarios.Through this analysis,the paper aims to provide theoretical support and practical references for formulating traffic assurance plans for expressway reconstruction and expansion projects,optimizing the allocation of regional road network resources,and preventing and controlling traffic operation risks.This research holds significant importance for enhancing the service level of the road network during expressway reconstruction and expansion.展开更多
The effects of climate change,such as increasing temperatures and changing precipitation patterns,significantly affect road infrastructure's structural integrity and longevity,requiring a reevaluation of maintenan...The effects of climate change,such as increasing temperatures and changing precipitation patterns,significantly affect road infrastructure's structural integrity and longevity,requiring a reevaluation of maintenance standards.Previous research on pavement performance did not incorporate climate adaptation into maintenance standards.This study develops a scenario-based road infrastructure maintenance cost prediction approach integrating climate and traffic scenarios.Using high-resolution data on pavement depth and materials,it evaluates future impacts on maintenance costs in Western Australia,and advances sustainable spatial planning under climate change through geospatial,decision-oriented analysis.The results show that without intervention,traffic and climate change could significantly increase road maintenance costs by 2050.Under an equivalent service-improvement target of a 1.0-point reduction in network-average International Roughness Index,adopting climate-adaptive pavement standards reduces life-cycle maintenance costs by 16.1%relative to the baseline scenario,while trafficmanagement-based redistribution reduces costs by 17.0%relative to the same baseline scenario.Integrating climate adaptation into road maintenance standards provides more accurate,actionable recommendations for policymakers and engineers to enhance infrastructure resilience,reduce long-term costs,and safeguard against the adverse climate change impacts on transportation networks.展开更多
Percutaneous coronary intervention(PCI)via the transradial route is now standard practice,particularly in elderly patients,owing to its lower bleeding risk and early ambulation.However,agerelated vascular changes such...Percutaneous coronary intervention(PCI)via the transradial route is now standard practice,particularly in elderly patients,owing to its lower bleeding risk and early ambulation.However,agerelated vascular changes such as radial and subclavian tortuosity,elongation,and reduced arterial compliance can pose unique procedural challenges.One such challenge is catheter kinking,which can impede the smooth delivery of stents.展开更多
Based on CMIP6 model simulations,this study investigates the impacts and mechanisms of soil moisture–atmosphere coupling(SA)on the Silk Road Pattern(SRP)in the Northern Hemisphere summer.A comparison between LS3MIP(u...Based on CMIP6 model simulations,this study investigates the impacts and mechanisms of soil moisture–atmosphere coupling(SA)on the Silk Road Pattern(SRP)in the Northern Hemisphere summer.A comparison between LS3MIP(uncoupled)and AMIP(coupled)experiments reveals that weakened SA alters both the position and intensity of the SRP wave train centers,showing a positive–negative–positive–negative anomalous distribution around 40°N(in meridional wind pattern).The results indicate that the SA in the Tibetan Plateau(TP)region plays an important role in the distribution of the SRP.Furthermore,SA significantly influences the SRP wave train characteristics in midlatitude regions by regulating surface heat fluxes and atmospheric heat sources(),with notable geopotential height anomalies over the Caspian Sea,the TP and Northeast Asia.Specifically,due to the weakening of the SA,the cooling effect over the TP induces subsidence,while the regions surrounding the Caspian Sea and Northeast Asia exhibit heat source anomalies accompanied by ascending motion.This results in a corresponding positive–negative–positive geopotential height anomaly pattern associated with the SRP,ultimately influencing the wave train distribution of the SRP.Thus,SA is an important factor driving the variability of the SRP wave train.展开更多
Road-surface identification is important for transportation monitoring and maintenance.However,this task is challenging due to the complexity of vibration signals,feature overlap among different surface types,and vari...Road-surface identification is important for transportation monitoring and maintenance.However,this task is challenging due to the complexity of vibration signals,feature overlap among different surface types,and variations in real-world operating conditions.These challenges become more significant in time-series classification,where models must achieve high accuracy while remaining computationally efficient and suitable for low-cost hardware.This study investigates the design and evaluation of an automatic road-surface classification system using motion data collected from inertial sensors mounted on a vehicle,including accelerometers and gyroscopes.The system segments synchronized IMU signals into fixed-length windows and assigns each window to a predefined road-surface category.To address this problem,this study proposes CGB-Net,a lightweight and efficient deep learning architecture for road-surface classification.In this architecture,the integration of modules is designed to capture hierarchical features:one-dimensional convolutional neural networks(1D-CNN)are used to extract local temporal features from accelerometer and gyroscope signals,Gated Recurrent Units(GRU)model short-term temporal dependencies,and Bidirectional Long Short-Term Memory(Bi-LSTM)networks capture global long-term temporal context in both directions.The model is trained to distinguish among three types of road surfaces representing different material properties and degradation states:Asphalt_10(new asphalt,less than 10 years old),Asphalt_15(aged asphalt,more than 15 years old),and Concrete.Experimental results show that the proposed system achieves high classification performance,with both accuracy and F1-score exceeding 95%.These results indicate strong potential for practical applications in automated road monitoring and maintenance systems.展开更多
Automated road damage detection is a critical component of intelligent transportation systems,enabling efficient infrastructure maintenance and improved traffic safety.However,existing approaches often suffer from lim...Automated road damage detection is a critical component of intelligent transportation systems,enabling efficient infrastructure maintenance and improved traffic safety.However,existing approaches often suffer from limited contextual understanding,insufficient segmentation accuracy,and suboptimal real-time performance.This study presents TCR-RoadNet,a transformer-enhanced multi-task deep learning architecture designed for simultaneous road damage detection and segmentation in real-world driving environments.The proposed framework integrates a multi-scale convolutional backbone with a Transformer Context Refinement(TCR)module to capture both fine-grained structural details and long-range spatial dependencies across feature scales.To further enhance performance,a Decoupled Detection Head(DDH)is employed to stabilize localization and classification learning,while a Classification Refinement Module(CRM)improves inter-class discrimination using region-based feature enhancement.In addition,a Boundary-Aware Segmentation Head is introduced to generate precise damage contours by incorporating edge-sensitive learning mechanisms.The model is evaluated on the RDD2022 dataset,complemented by an extended dataset containing additional road images collected from Kazakhstan to increase environmental diversity and robustness.Experimental results demonstrate that the proposed method achieves 0.9416 precision,0.9235 recall,and 0.8718 mAP@50,along with a segmentation performance of 0.8129 mean Intersection over Union(mIoU),while maintaining real-time inference at 57 FPS.Comparative analysis and ablation studies confirm that each architectural component contributes to consistent performance gains in both detection and segmentation tasks.Qualitative results further illustrate the robustness of the proposed framework under varying lighting,weather,and road conditions.The proposed approach offers a scalable and efficient solution for real-time road condition monitoring and intelligent infrastructure management systems.展开更多
Based on an earthquake-damage-based road traffic capacity assessment model,this paper innovatively introduces the spatial aggregation density of geological hazards as a correction factor to construct a multi-factor we...Based on an earthquake-damage-based road traffic capacity assessment model,this paper innovatively introduces the spatial aggregation density of geological hazards as a correction factor to construct a multi-factor weighted traffi c capacity assessment model.The study systematically investigates the variation patterns of road traffi c capacity in Pingshan County under diff erent seismic intensities.The results show that the impact of earthquakes on road traffi c capacity in Pingshan County exhibits signifi cant spatial heterogeneity,with the western mountainous area being signifi cantly more aff ected than the eastern plain area.As seismic intensity increases,road traffic capacity decreases in a stepwise manner;the higher the intensity,the more pronounced the east-west diff erence.County roads and roads in the western mountainous area are the weak links in earthquake relief eff orts.This study provides a scientifi c basis for post-earthquake emergency route optimization and regional disaster prevention planning.展开更多
基金partially supported by the Natural Science Foundation of China(Grant Number:52308457)China Postdoctoral Science Foundation(Grant Number:2024M761811)Natural Science Foundation of Shandong Province(Grant Number:ZR2023QE220).
摘要Road Abandoned Objects(RAOs)pose significant threats to traffic safety,particularly due to their small size,irregular shapes,and unpredictable distribution in complex road environments.The primary objective of this study is to develop an accurate and real-time detection framework for RAOs while maintaining low computational cost for practical deployment.To achieve this,we propose RAO-YOLO,a lightweight vision-based detection framework built upon an enhanced YOLO architecture.Specifically,a Mixed Aggregation Network(MANet)is introduced to improve multi-scale feature representation,and a Lightweight Shared Detail-Enhanced Detection(LSDD)head is designed to enhance localization accuracy for small and irregular objects.Furthermore,a Focal-MPDIoU loss function is proposed to address sample imbalance and geometric irregularity during training.Extensive experiments conducted on the RAOD dataset demonstrate that the proposed method achieves superior performance compared to state-of-the-art detectors,achieving a mAP@0.5:0.95 of 56.1%while maintaining real-time inference speed.These results validate the effectiveness of the proposed framework for practical intelligent transportation applications.
基金Supported by National Natural Science Foundation of China (Grant No.52275286)Hunan Outstanding Youth Fund (Grant No.2023JJ10010)+2 种基金Hunan Provincial Natural Science Foundation (Grant No.2023JJ30246)Scientific Research Fund of Hunan Provincial Education Department (Grant No.24A0329)Shenzhen Science and Technology Program (Grant No.JCYJ20230807122004009)。
摘要Chinese automobile safety regulations are considering the introduction of thorax impactor subsystem tests to evaluate vehicle safety performance concerning thorax protection for Vulnerable Road Users(VRUs).However,there is currently an insufficient amount of data regarding VRU thorax-vehicle contact boundary conditions,which is essential for establishing the thorax impactor test procedure.Consequently,the obj ective of this study is to examine the characteristics of VRU thorax-vehicle contact boundary conditions,utilizing multi-body crash simulations that are informed by the distribution of accident scenarios.The simulation data suggest that the boundary conditions for thorax-vehicle contact in VRUs are predominantly influenced by the relative height of the VRU's pelvis in relation to the vehicle's bonnet leading edge,which in turn affects upper body kinematics.This results in variations across different vehicle and VRU types involved in collisions.The analysis of these contact boundary conditions indicates that thorax impactor subsystem test procedures should differentiate between vehicle types.The results suggest that:thorax impactor subsystem tests should concentrate on the Wrap Around Distance(WAD) range of 900-1800 mm;for testing at the bonnet-windscreen area,the thorax impactor could be launched at speeds of 16.5 km/h(with a vector angle of 24° and an initial inclination angle of 17°) for sedans,and 23.5 km/h(with a vector angle of 25° and an initial inclination angle of 22°) for SUVs/MPVs.Additionally,a horizontally directional velocity of 35.5 km/h(with an initial inclination angle of 30°) could be specified for thorax impactor tests at the bonnet leading edge area of SUVs/MPVs.The above data provides foundational data for future thorax impactor subsystem tests in China.
基金the National Key Research and Development Program of the Ministry of Science and Technology of the People’s Republic of China(2023YFB2604000)the Science and Technology Commission of Shanghai Municipality of China(23210711400)+1 种基金the Transportation Science and Technology Program of Henan Province(2023-4-2)the Key Research and Development Program of Ningxia Science and Technology Department(2022BEG02008)。
摘要Due to low reflectance(5%10%)of black asphalt pavement,most of the incident solar radiation(2952500 nm)is absorbed and stored.This results in the high temperature(even exceeding 70 C in summer)of the pavement surface,which leads to pavement diseases,exacerbates the heat island effect,and reduces human thermal comfort.Reflective pavement coating with high reflectance ranging from 20%to 80%is an effective way to solve the above problems.However,excessively improving the visible reflectance and ignoring the mixed reflection behavior(including specular and diffuse reflection properties)may cause glare problems and negatively affect road light environment safety.Therefore,precise control of reflectance is very significant.In this study,an automated test platform of reflection behavior was developed to investigate the mixed light reflection distribution pattern of reflective coating.Additionally,the impact of reflective coating on the light environment was explored.It was found that there was obvious specular reflection under conditions of a low incidence angle(less than 10°).Moreover,reflective coating could change the lightness index and specular reflection coefficient of traditional pavement.Finally,considering glare during the daytime and the nighttime illumination safety,the control indexes of reflective pavement coating were proposed.The visible reflectance and specular reflection coefficient should be lower than 22%and 1.5,respectively.The results will provide a theoretical basis for the precise and safe design of reflective pavement coatings.The coatings aim to improve the thermal and light environments,thereby enhancing driving safety,while also providing better illumination during emergency repair and maintenance of road infrastructure.
基金financially supported by the National Key R&D Program of China(2024YFE0111900)The National Natural Science Foundation of China(U2468214,52378370,52278372)+1 种基金The National Ten Thousand Talent Program for Young Top-notch Talents(2022QB04978)The Science and Technology Program of Hebei Province(2023HBQZYCSB004)。
摘要Global climate change is intensifying the impact of slope hazards,particularly rainfall-induced landslide hazards(RILH),on mountain road networks(MRNs).However,effective quantitative models for dynamically assessing MRNs vulnerability under RILH disturbances are still lacking.To bridge this gap,this study develops a Cascading Failure Model for Rainfall-Induced Landslide Hazard(CFM-RILH).Validation via a case study of the GarzêTibetan Autonomous Prefecture Road Network(GTPRNs)reveals key characteristics of MRNs system vulnerability under RILH disturbances:(1)Under the disturbance effects of RILH,the vulnerability of the MRNs system follows a nonlinear phase transition law that intensifies with increasing disturbance intensity,exhibiting a distinct critical threshold.When the disturbance intensity exceeds this threshold,the system undergoes a global cascading failure phenomenon analogous to an“avalanche.”(2)Under RILH disturbances,the robustness of the MRNs system possesses a distinct safety boundary.Exceeding this boundary not only fails to improve hazard resistance but instead substantially elevates the risk of large-scale cascading failure.(3)Increasing network redundancy may be considered one of the primary engineering measures for enhancing MRNs resilience against such disturbances.Based on these findings,we propose a“Two-Stage Emergency Response and Hierarchical Fortification”strategy specifically to improve the resilience of GTPRNs impacted by RILH.The CFM-RILH model provides an effective tool for assessing road network vulnerability under such hazards.Furthermore,its modeling framework can also inform vulnerability assessment and resilience strategy development for road networks affected by other types of slope hazards.
基金supported by the National Natural Science Foundation of China(Nos.72273151 and 22021004)Science Foundation of China University of Petroleum,Beijing(No.2462025SZBH001).
摘要At present,environmental problems are becoming increasingly severe,and sustainable development concerns the common destiny of all mankind around the world.Leveraging ecological footprint and ecological carrying capacity data for Eurasia from 2000 to 2022,this study employs a three-dimensional ecological footprint model to conduct a multi-scale sustainability assessment.Further applying a difference-in-differences model,we analyze the impact mechanisms of the Belt and Road Initiative on Eurasia's ecological footprint.Quantile regression and heterogeneity analysis reveal Belt and Road Initiative's differential effects across countries.Key findings indicate that:(1)Eurasia's unsustainable development intensified from 2000 to 2022,with ecological footprint depth rising from 1.966 to 2.513 ha/cap,while per capita ecological footprint size declined slightly from 1.092 to 1.023 ha/cap.(2)Classifying 83 countries into 9 sustainability types based on ecological footprint depth and size,Asia showed weak sustainability(low size-medium depth and low size-low depth types),while Europe was primarily low size-medium depth with relatively stronger sustainability.Six countries experienced weakened sustainability and six improved.(3)The Belt and Road Initiative significantly increased ecological footprint in Eurasian countries,mediated by industrial structure,technological innovation,and foreign direct investment.Quantile regression indicates Belt and Road Initiative's effect is stronger in nations with lower initial ecological footprint.Heterogeneity analysis further shows Belt and Road Initiative disproportionately impacts countries with lower ecological footprint depth,smaller per capita ecological footprint size,and weaker sustainability.These insights provide critical guidance for implementing the UN 2030 Agenda and formulating Belt and Road Initiative policies to enhance long-term sustainability.
基金supported by the National Natural Science Foundation of China(Grant No.62172033).
摘要Urban traffic generates massive and diverse data,yet most systems remain fragmented.Current approaches to congestion management suffer from weak data consistency and poor scalability.This study addresses this gap by proposing the Urban Traffic Congestion Unified Metadata Model(UTC-UMM).The goal is to provide a standardized and extensible framework for describing,extracting,and storing multisource traffic data in smart cities.The model defines a two-tier specification that organizes nine core traffic resource classes.It employs an eXtensible Markup Language(XML)Schema that connects general elements with resource-specific elements.This design ensures both syntactic and semantic interoperability across siloed datasets.Extension principles allow new elements or constraints to be introducedwithout breaking backward compatibility.Adistributed pipeline is implemented usingHadoop Distributed File System(HDFS)and HBase.It integrates computer vision for video and natural language processing for text to automate metadata extraction.Optimized row-key designs enable low-latency queries.Performance is tested with the Yahoo!Cloud Serving Benchmark(YCSB),which shows linear scalability and high throughput.The results demonstrate that UTC-UMM can unify heterogeneous traffic data while supporting real-time analytics.The discussion highlights its potential to improve data reuse,portability,and scalability in urban congestion studies.Future research will explore integration with association rulemining and advanced knowledge representation to capture richer spatiotemporal traffic patterns.
基金supported by National Natural Science Foundation of China(grant number 52378449)Hunan Provincial Natural Science Foundation of China(grant number 2024JJ2019)+1 种基金Project of Yuelushan Center for Industrial Innovation(grant number 2025YCII0218)the Science and Technology Program of Hunan Provincial Department of Transportation(grant number 202612).
摘要The deterioration of road performance in asphalt mixtures due to aging can significantly affect the service period of asphalt pavement.Therefore,it is particularly important to find a suitable method to resist the aging of asphalt mixture.In this study,various red mud-compounded styrene-butadiene-styrene(SBS)-modified asphalt mixtures were prepared using acid-treated and surface-modified raw red mud(RM)as a modifier for SBS-modified asphalt.First,SBS-modified asphalt mixture specimens were prepared at the optimal oil-rock ratio.Subsequently,both unaged and aged mixtures were subjected to Marshall stability,low-temperature splitting,freeze-thaw splitting,and indirect tensile fatigue tests to evaluate the effect of different red muds on the road performance of SBSmodified asphalt mixtures.The experimental results showed that the addition of raw red mud(RM)improved the high-temperature performance,moisture susceptibility,and fatigue performance of SBS-modified asphalt mixtures,but adversely affected their low-temperature performance.The high-temperature stability,moisture susceptibility,and fatigue performance were further enhanced with the incorporation of organic red mud.Additionally,raw red mud effectively delayed the thermal-oxidative aging of the mixture.After surface modification,red mud can significantly enhance the thermal-oxidative aging resistance of the SBS-modified asphalt mixture.Among the tested samples,the mixture incorporating red mud treated with oxalic acid and titanate coupling agent exhibited the highest durability against aging.
基金supported by the Shaanxi Provincial Department of Education(Grant No.24JE007)the National Natural Science Foundation of China(Grant No.52478436)the Natural Science Foundation of Shaanxi Province(Grant No.2020JM-249).
摘要The development of road materials as alternatives to mineral aggregates has become an important research direction.This paper proposes cold-bonded lightweight aggregates(R-CBLA)as substitutes for conventional aggregates and prepares lightweight aggregate-modified soil(LA-Soil)and lightweight aggregate-hydraulic bound mixtures(LA-HBM)for subgrade and base applications.By adjusting the rotation speed of the extrusion granulator,feeding rate,and raw material moisture,R-CBLA can be produced with a granulation rate higher than 90%.Its water absorption shows a significant negative correlation with strength,while bulk density exhibits a significant positive correlation,thus providing a theoretical basis for optimizing performance.In LA-Soil,incorporating 40%–50%R-CBLA with natural coarse grains develops a skeleton-dense structure,which enhances dry density,CBR,and resilient modulus,while still maintaining durability under freeze-thaw cycles.In LA-HBM,two critical replacement thresholds are identified,performance changes are limited below 25%,performance decreases moderately but remains technically feasible between 25%and 75%,the skeleton structure becomes unstable and performance declines sharply beyond 75%.Cost analysis further shows that R-CBLA offers advantages in materials,transportation,and construction,with maximum cost reductions reaching 87%.This economic benefit is especially pronounced in resource-scarce regions.In conclusion,the study verifies the feasibility of R-CBLA in road engineering,proposes a long-life pavement design concept,and emphasizes largescale production,systematic performance optimization,and long-term durability as priorities for future research.
摘要Ground-penetrating radar(GPR)imaging is widely used for detecting hidden defects in urban roads.However,the complex noise environment,large-scale variations in defect features,and the sensitivity of slender defects to annotation errors pose significant challenges to accurate detection.To address these issues,this study proposes an improved object detection framework,termed DFF-MoCA-YOLO,based on YOLOv11 for identifying void and loose defects in GPR images.First,a multi-strategy gated feature fusion module(MSGFF-C3k2)is designed to enhance feature robustness against complex noise and scale variations.Then,aMonte Carlo Attention(MoCAttention)module is introduced to improve defect-feature representation via stochastic sampling and channel recalibration.Subsequently,an adaptive aspect-ratio penalty CIoU loss(CIoU-ARP)is developed to improve bounding box regression accuracy for slender defects.A labeled dataset containing void and loose defects is constructed using multi-source GPR data collected from eight urban roads.Finally,a series of ablation experiments is conducted on the proposed modules.Experimental results demonstrate that the proposed method achieves consistent performance improvements over the baseline YOLOv11 and other mainstream YOLO variants,while maintaining relatively low computational complexity.The results indicate that the proposed framework offers an effective and practical solution for detecting hidden defects in urban roads using GPR images.Moreover,the model’s robustness to noise and ability to accurately detect defects at varying scales make it a promising tool for urban infrastructure maintenance.Its efficient performance with minimal computational overhead makes it suitable for real-time defect detection.
摘要The article outlines the main characteristics of the operation of the Hungarian road network during the Soviet bloc era and the three and a half decades after its abandonment,together with its social-economic environment and its development efforts and its adaptation to the Western models.After a brief presentation of the decades preceding the democratic turnaround in Europe,it summarises the main trends from the start of market operations to the present days,divided into three stages of development.It refers to professional successes and problems,to social expectations and to the limited possibilities of the country’s economic performance and external conditions,to changes in financial financing and the organisation system of development management.
基金supported by the Foundation for Distinguished Young Talents in Higher Education of Guangdong,China(Grant No.2023WQNCX280,“Research on the Cultural Route Relics of the Qi’ao Ancient Road in Southern China from the Perspective of E-commerce New Media Marketing”)the Scientific Research Fund Project of the Yunnan Provincial Department of Education,titled“A Study of Cultural Commonalities between Yunnan and Southeast Asia from an Anthropological Perspective”(Project No.2024J0904).
摘要This study focuses on the protection and revitalization utilization of linear cultural heritage,selecting the Qi’ao Ancient Road in Southern China as a typical case study,a cultural route with both historical depth and practical significance.The paper first systematically reviews four theoretical foundations:“cultural route”,“cultural heritageelics”,“structural functionality and space”,and“e-commerce new media marketing”,constructing an integrated“function-culture-space”analytical framework.Guided by this framework,the research establishes the investigation path with the Ming and Qing Dynasties as the temporal scope and the Southern and Eastern Main Routes of the Qi’ao Ancient Road as the spatial scope.It comprehensively employs literature research,field surveys,and Geographic Information System(GIS)analysis methods to systematically screen and analyze the value of tangible and intangible cultural relics along the ancient road.The study shows that the Qi’ao Ancient Road was not only a vital land transportation artery between Guangdong and Macao during the Ming and Qing Dynasties and an important overland link for the Maritime Silk Road,but also a witness to the integration of Chinese and Western cultures,the spread of ideas,and social transformations.In response to the current state of its protection and utilization,this paper innovatively proposes an integrated e-commerce new media marketing strategy centered on the“Online Three-in-One”(cross-border e-commerce platforms,independent websites,overseas social media)and“Offline Six-in-One”(museums/cultural centers,culturalourism bureaus,scenic areas,universitiesesearch institutions,enterprises,and intangible cultural heritage experience shops).This strategy aims to transform and disseminate the value of the ancient road’s cultural relics through modernized,marketized,and experiential means,thereby providing a path reference with both theoretical foresight and practical operability for achieving holistic protection,sustainable utilization,and methodological innovation in linear cultural heritage.
基金support provided by the National Social Science Foundation of China(Grant No.20BJY076).
摘要Digital economy(DE)is on the verge of becoming a pivotal facilitator of the energy transition(ET).However,it remains to be seen to what extent China's outward foreign direct investment(OFDI)can stimulate the development of the DE and promote ET under the Belt and Road Initiative(BRI).Employing a nonparametric additive model,this study examines this issue by using panel data from 84 BRI countries spanning 2007–2022.The connections between China's OFDI and the DE and ET of BRI nations vary across different regions.China's OFDI has considerably fostered the ET of nations along its route to Central Asia,Europe,North Africa,and the Middle East.Conversely,in the Pacific and East Asian regions,China's OFDI has a constructive effect on the advancement of DE in participating nations.However,the effect of China's OFDI on the ET of nations in the Pacific Islands and East Asia and South Asia is statistically insignificant.Moreover,China's OFDI impairs the DE of nations in Central Asia and Europe,the Caribbean and Latin America,as well as North Africa and the Middle East.Notably,the net effect of China's OFDI on ET is positive;however,the mediating effect of facilitating ET through DE is not pronounced.
摘要Matias Jere is at a hardware shop in Malawi’s capital city,Lilongwe.He is waiting for it to open so that he can buy ball joints for his vehicle,his third set in as many months.“Our roads are so bad that ball joints don’t last long,and it’s costing me a small fortune,”he said.Businessman Rafik Mwamadi is also worried.He needs to travel more than 300 km to the Northern Region city of Mzuzu to deliver merchandise,but the road is riddled with potholes.In the past,the road trip took about five hours,but in its current poor condition,it takes about nine hours.
摘要Against the backdrop of the concurrent advancement of China's expressway network development and large-scale reconstruction and expansion projects,the reconstruction and expansion of a single road section can trigger a redistribution of the overall traffic flow within the regional road network,with significant characteristics of traffic volume transfer across routes,corridors,and regions.Traditional traffic volume analysis methods,which focus on individual road sections,struggle to meet the practical demands of regional road network linkage,multipath competition,and dynamic traffic organization.To scientifically grasp the traffic transfer patterns within the road network during reconstruction and expansion and ensure the safety and efficiency of road network operations during construction,this paper adopts a perspective of regional road network linkage to systematically analyze the internal mechanisms and spatiotemporal distribution characteristics of traffic volume transfer during expressway reconstruction and expansion.Furthermore,it proposes a traffic volume transfer forecasting and analysis system suitable for reconstruction and expansion scenarios.Through this analysis,the paper aims to provide theoretical support and practical references for formulating traffic assurance plans for expressway reconstruction and expansion projects,optimizing the allocation of regional road network resources,and preventing and controlling traffic operation risks.This research holds significant importance for enhancing the service level of the road network during expressway reconstruction and expansion.
基金supported by the National Natural Science Foundation of China(Grants No.72201229 and 72361137006)Centre for Infrastructure Delivery Research Funding(Grant No.P0055981)。
摘要The effects of climate change,such as increasing temperatures and changing precipitation patterns,significantly affect road infrastructure's structural integrity and longevity,requiring a reevaluation of maintenance standards.Previous research on pavement performance did not incorporate climate adaptation into maintenance standards.This study develops a scenario-based road infrastructure maintenance cost prediction approach integrating climate and traffic scenarios.Using high-resolution data on pavement depth and materials,it evaluates future impacts on maintenance costs in Western Australia,and advances sustainable spatial planning under climate change through geospatial,decision-oriented analysis.The results show that without intervention,traffic and climate change could significantly increase road maintenance costs by 2050.Under an equivalent service-improvement target of a 1.0-point reduction in network-average International Roughness Index,adopting climate-adaptive pavement standards reduces life-cycle maintenance costs by 16.1%relative to the baseline scenario,while trafficmanagement-based redistribution reduces costs by 17.0%relative to the same baseline scenario.Integrating climate adaptation into road maintenance standards provides more accurate,actionable recommendations for policymakers and engineers to enhance infrastructure resilience,reduce long-term costs,and safeguard against the adverse climate change impacts on transportation networks.
摘要Percutaneous coronary intervention(PCI)via the transradial route is now standard practice,particularly in elderly patients,owing to its lower bleeding risk and early ambulation.However,agerelated vascular changes such as radial and subclavian tortuosity,elongation,and reduced arterial compliance can pose unique procedural challenges.One such challenge is catheter kinking,which can impede the smooth delivery of stents.
基金supported by theNational Natural Science Foundation of China(Grant Nos.42088101 and 42275172)。
摘要Based on CMIP6 model simulations,this study investigates the impacts and mechanisms of soil moisture–atmosphere coupling(SA)on the Silk Road Pattern(SRP)in the Northern Hemisphere summer.A comparison between LS3MIP(uncoupled)and AMIP(coupled)experiments reveals that weakened SA alters both the position and intensity of the SRP wave train centers,showing a positive–negative–positive–negative anomalous distribution around 40°N(in meridional wind pattern).The results indicate that the SA in the Tibetan Plateau(TP)region plays an important role in the distribution of the SRP.Furthermore,SA significantly influences the SRP wave train characteristics in midlatitude regions by regulating surface heat fluxes and atmospheric heat sources(),with notable geopotential height anomalies over the Caspian Sea,the TP and Northeast Asia.Specifically,due to the weakening of the SA,the cooling effect over the TP induces subsidence,while the regions surrounding the Caspian Sea and Northeast Asia exhibit heat source anomalies accompanied by ascending motion.This results in a corresponding positive–negative–positive geopotential height anomaly pattern associated with the SRP,ultimately influencing the wave train distribution of the SRP.Thus,SA is an important factor driving the variability of the SRP wave train.
基金funded by Institute of Information Technology(VAST)grant number NVKN02.01/26-27The APC was funded by Academy of Policy and Development(Duong DoThe).
摘要Road-surface identification is important for transportation monitoring and maintenance.However,this task is challenging due to the complexity of vibration signals,feature overlap among different surface types,and variations in real-world operating conditions.These challenges become more significant in time-series classification,where models must achieve high accuracy while remaining computationally efficient and suitable for low-cost hardware.This study investigates the design and evaluation of an automatic road-surface classification system using motion data collected from inertial sensors mounted on a vehicle,including accelerometers and gyroscopes.The system segments synchronized IMU signals into fixed-length windows and assigns each window to a predefined road-surface category.To address this problem,this study proposes CGB-Net,a lightweight and efficient deep learning architecture for road-surface classification.In this architecture,the integration of modules is designed to capture hierarchical features:one-dimensional convolutional neural networks(1D-CNN)are used to extract local temporal features from accelerometer and gyroscope signals,Gated Recurrent Units(GRU)model short-term temporal dependencies,and Bidirectional Long Short-Term Memory(Bi-LSTM)networks capture global long-term temporal context in both directions.The model is trained to distinguish among three types of road surfaces representing different material properties and degradation states:Asphalt_10(new asphalt,less than 10 years old),Asphalt_15(aged asphalt,more than 15 years old),and Concrete.Experimental results show that the proposed system achieves high classification performance,with both accuracy and F1-score exceeding 95%.These results indicate strong potential for practical applications in automated road monitoring and maintenance systems.
基金This study was prepared for the AP23487192 project,titled“Development of a real-time road damage detection systemwith using computer vision and artificial intelligence”financial support theMinistry of Science and Higher Education of the Republic of Kazakhstan provides through Grant Funding for Scientific and(or)Scientific and Technical Projects for Young Researchers for 2025-2027.
摘要Automated road damage detection is a critical component of intelligent transportation systems,enabling efficient infrastructure maintenance and improved traffic safety.However,existing approaches often suffer from limited contextual understanding,insufficient segmentation accuracy,and suboptimal real-time performance.This study presents TCR-RoadNet,a transformer-enhanced multi-task deep learning architecture designed for simultaneous road damage detection and segmentation in real-world driving environments.The proposed framework integrates a multi-scale convolutional backbone with a Transformer Context Refinement(TCR)module to capture both fine-grained structural details and long-range spatial dependencies across feature scales.To further enhance performance,a Decoupled Detection Head(DDH)is employed to stabilize localization and classification learning,while a Classification Refinement Module(CRM)improves inter-class discrimination using region-based feature enhancement.In addition,a Boundary-Aware Segmentation Head is introduced to generate precise damage contours by incorporating edge-sensitive learning mechanisms.The model is evaluated on the RDD2022 dataset,complemented by an extended dataset containing additional road images collected from Kazakhstan to increase environmental diversity and robustness.Experimental results demonstrate that the proposed method achieves 0.9416 precision,0.9235 recall,and 0.8718 mAP@50,along with a segmentation performance of 0.8129 mean Intersection over Union(mIoU),while maintaining real-time inference at 57 FPS.Comparative analysis and ablation studies confirm that each architectural component contributes to consistent performance gains in both detection and segmentation tasks.Qualitative results further illustrate the robustness of the proposed framework under varying lighting,weather,and road conditions.The proposed approach offers a scalable and efficient solution for real-time road condition monitoring and intelligent infrastructure management systems.
基金Fund Projects:National Key Research and Development Program of China,Science and Technology Innovation Special Project for Xiong'an New Area(2023XAGG0067)Hebei Province Earthquake Technology Spark Program(DZ2025081900031,DZ2025092800001,DZ2021121500007)。
摘要Based on an earthquake-damage-based road traffic capacity assessment model,this paper innovatively introduces the spatial aggregation density of geological hazards as a correction factor to construct a multi-factor weighted traffi c capacity assessment model.The study systematically investigates the variation patterns of road traffi c capacity in Pingshan County under diff erent seismic intensities.The results show that the impact of earthquakes on road traffi c capacity in Pingshan County exhibits signifi cant spatial heterogeneity,with the western mountainous area being signifi cantly more aff ected than the eastern plain area.As seismic intensity increases,road traffic capacity decreases in a stepwise manner;the higher the intensity,the more pronounced the east-west diff erence.County roads and roads in the western mountainous area are the weak links in earthquake relief eff orts.This study provides a scientifi c basis for post-earthquake emergency route optimization and regional disaster prevention planning.