3D Road Network Modeling and Road Structure Recognition in Internet of Vehicles

Internet of Vehicles (IoV) is a new system that enables individual vehicles to connect with nearby vehicles,people, transportation infrastructure, and networks, thereby realizing amore intelligent and efficient transportationsystem. The movement of vehicles and the three-dimensional (3D) nature of the road network cause the topologicalstructure of IoV to have the high space and time complexity.Network modeling and structure recognition for 3Droads can benefit the description of topological changes for IoV. This paper proposes a 3Dgeneral roadmodel basedon discrete points of roads obtained from GIS. First, the constraints imposed by 3D roads on moving vehicles areanalyzed. Then the effects of road curvature radius (Ra), longitudinal slope (Slo), and length (Len) on speed andacceleration are studied. Finally, a general 3D road network model based on road section features is established.This paper also presents intersection and road section recognition methods based on the structural features ofthe 3D road network model and the road features. Real GIS data from a specific region of Beijing is adopted tocreate the simulation scenario, and the simulation results validate the general 3D road network model and therecognitionmethod. Therefore, thiswork makes contributions to the field of intelligent transportation by providinga comprehensive approach tomodeling the 3Droad network and its topological changes in achieving efficient trafficflowand improved road safety.

ConvNeXt-UperNet-Based Deep Learning Model for Road Extraction from High-Resolution Remote Sensing Images

When existing deep learning models are used for road extraction tasks from high-resolution images,they are easily affected by noise factors such as tree and building occlusion and complex backgrounds,resulting in incomplete road extraction and low accuracy.We propose the introduction of spatial and channel attention modules to the convolutional neural network ConvNeXt.Then,ConvNeXt is used as the backbone network,which cooperates with the perceptual analysis network UPerNet,retains the detection head of the semantic segmentation,and builds a new model ConvNeXt-UPerNet to suppress noise interference.Training on the open-source DeepGlobe and CHN6-CUG datasets and introducing the DiceLoss on the basis of CrossEntropyLoss solves the problem of positive and negative sample imbalance.Experimental results show that the new network model can achieve the following performance on the DeepGlobe dataset:79.40%for precision(Pre),97.93% for accuracy(Acc),69.28% for intersection over union(IoU),and 83.56% for mean intersection over union(MIoU).On the CHN6-CUG dataset,the model achieves the respective values of 78.17%for Pre,97.63%for Acc,65.4% for IoU,and 81.46% for MIoU.Compared with other network models,the fused ConvNeXt-UPerNet model can extract road information better when faced with the influence of noise contained in high-resolution remote sensing images.It also achieves multiscale image feature information with unified perception,ultimately improving the generalization ability of deep learning technology in extracting complex roads from high-resolution remote sensing images.

Resilience assessment and optimization method of city road network in the post-earthquake emergency period

The post-earthquake emergency period,which is a sensitive time segment just after an event,mainly focuses on saving life and restoring social order.To improve the seismic resilience of city road networks,a resilience evaluation method used in the post-earthquake emergency period is proposed.The road seismic damage index of a city road network can consider the influence of roads,bridges and buildings along the roads,etc.on road capacity after an earthquake.A function index for a city road network is developed,which reflects the connectivity,redundancy,traffic demand and traffic function of the network.An optimization model for improving the road repair order in the post-earthquake emergency period is also developed according to the resilience evaluation,to enable decision support for city emergency management and achieve the best seismic resilience of the city road network.The optimization model is applied to a city road network and the results illustrate the feasibility of the resilience evaluation and optimization method for a city road network in the post-earthquake emergency period.

Weakly Supervised Network with Scribble-Supervised and Edge-Mask for Road Extraction from High-Resolution Remote Sensing Images

Significant advancements have been achieved in road surface extraction based on high-resolution remote sensingimage processing. Most current methods rely on fully supervised learning, which necessitates enormous humaneffort to label the image. Within this field, other research endeavors utilize weakly supervised methods. Theseapproaches aim to reduce the expenses associated with annotation by leveraging sparsely annotated data, such asscribbles. This paper presents a novel technique called a weakly supervised network using scribble-supervised andedge-mask (WSSE-net). This network is a three-branch network architecture, whereby each branch is equippedwith a distinct decoder module dedicated to road extraction tasks. One of the branches is dedicated to generatingedge masks using edge detection algorithms and optimizing road edge details. The other two branches supervise themodel’s training by employing scribble labels and spreading scribble information throughout the image. To addressthe historical flaw that created pseudo-labels that are not updated with network training, we use mixup to blendprediction results dynamically and continually update new pseudo-labels to steer network training. Our solutiondemonstrates efficient operation by simultaneously considering both edge-mask aid and dynamic pseudo-labelsupport. The studies are conducted on three separate road datasets, which consist primarily of high-resolutionremote-sensing satellite photos and drone images. The experimental findings suggest that our methodologyperforms better than advanced scribble-supervised approaches and specific traditional fully supervised methods.

Autonomous Vehicle Platoons In Urban Road Networks:A Joint Distributed Reinforcement Learning and Model Predictive Control Approach

In this paper, platoons of autonomous vehicles operating in urban road networks are considered. From a methodological point of view, the problem of interest consists of formally characterizing vehicle state trajectory tubes by means of routing decisions complying with traffic congestion criteria. To this end, a novel distributed control architecture is conceived by taking advantage of two methodologies: deep reinforcement learning and model predictive control. On one hand, the routing decisions are obtained by using a distributed reinforcement learning algorithm that exploits available traffic data at each road junction. On the other hand, a bank of model predictive controllers is in charge of computing the more adequate control action for each involved vehicle. Such tasks are here combined into a single framework:the deep reinforcement learning output(action) is translated into a set-point to be tracked by the model predictive controller;conversely, the current vehicle position, resulting from the application of the control move, is exploited by the deep reinforcement learning unit for improving its reliability. The main novelty of the proposed solution lies in its hybrid nature: on one hand it fully exploits deep reinforcement learning capabilities for decisionmaking purposes;on the other hand, time-varying hard constraints are always satisfied during the dynamical platoon evolution imposed by the computed routing decisions. To efficiently evaluate the performance of the proposed control architecture, a co-design procedure, involving the SUMO and MATLAB platforms, is implemented so that complex operating environments can be used, and the information coming from road maps(links,junctions, obstacles, semaphores, etc.) and vehicle state trajectories can be shared and exchanged. Finally by considering as operating scenario a real entire city block and a platoon of eleven vehicles described by double-integrator models, several simulations have been performed with the aim to put in light the main f eatures of the proposed approach. Moreover, it is important to underline that in different operating scenarios the proposed reinforcement learning scheme is capable of significantly reducing traffic congestion phenomena when compared with well-reputed competitors.

Optimized Binary Neural Networks for Road Anomaly Detection:A TinyML Approach on Edge Devices

Integrating Tiny Machine Learning(TinyML)with edge computing in remotely sensed images enhances the capabilities of road anomaly detection on a broader level.Constrained devices efficiently implement a Binary Neural Network(BNN)for road feature extraction,utilizing quantization and compression through a pruning strategy.The modifications resulted in a 28-fold decrease in memory usage and a 25%enhancement in inference speed while only experiencing a 2.5%decrease in accuracy.It showcases its superiority over conventional detection algorithms in different road image scenarios.Although constrained by computer resources and training datasets,our results indicate opportunities for future research,demonstrating that quantization and focused optimization can significantly improve machine learning models’accuracy and operational efficiency.ARM Cortex-M0 gives practical feasibility and substantial benefits while deploying our optimized BNN model on this low-power device:Advanced machine learning in edge computing.The analysis work delves into the educational significance of TinyML and its essential function in analyzing road networks using remote sensing,suggesting ways to improve smart city frameworks in road network assessment,traffic management,and autonomous vehicle navigation systems by emphasizing the importance of new technologies for maintaining and safeguarding road networks.

Automatic road extraction framework based on codec network

Road extraction based on deep learning is one of hot spots of semantic segmentation in the past decade.In this work,we proposed a framework based on codec network for automatic road extraction from remote sensing images.Firstly,a pre-trained ResNet34 was migrated to U-Net and its encoding structure was replaced to deepen the number of network layers,which reduces the error rate of road segmentation and the loss of details.Secondly,dilated convolution was used to connect the encoder and the decoder of network to expand the receptive field and retain more low-dimensional information of the image.Afterwards,the channel attention mechanism was used to select the information of the feature image obtained by up-sampling of the encoder,the weights of target features were optimized to enhance the features of target region and suppress the features of background and noise regions,and thus the feature extraction effect of the remote sensing image with complex background was optimized.Finally,an adaptive sigmoid loss function was proposed,which optimizes the imbalance between the road and the background,and makes the model reach the optimal solution.Experimental results show that compared with several semantic segmentation networks,the proposed method can greatly reduce the error rate of road segmentation and effectively improve the accuracy of road extraction from remote sensing images.

DFNet:高效的无解码语义分割方法

针对编解码语义分割网络计算量大、解码结构复杂的问题,提出一种高效无解码的二值语义分割模型DFNet。该模型首先去除主流分割网络中复杂的解码结构和跳跃连接,采用卷积重塑上采样方法重塑特征编码直接得到分割结果,简化网络模型结构;其次在编码器中融合轻量双重注意力机制EC&SA,提高特征编码的通道及空间信息交互,增强网络的编码能力;最后使用PolyCE损失替代常规分割损失,解决正负样本不均衡问题,提高模型的分割精度。在Deep‑Globe道路分割和CrackForest缺陷检测等二值分割数据集上的实验结果表明,本文模型的分割精度F1均值和IoU均值分别达到84.69%和73.95%,且分割速度高达94 FPS,远超主流语义分割模型,极大地提高了分割任务效率。

基于改进U-Net模型的遥感影像道路提取方法研究

针对高分辨率遥感影像背景信息复杂,道路提取难度大,自动化程度低等问题,论文提出了一种改进的U-Net的道路提取方法。首先,编码器使用VGG16网络结构替代原始U-Net编码器结构;然后,在每个编码器和解码器块后加入特征压缩激活模块(SENet)增强网络特征学习能力;最后,使用Dice损失函数和二分类交叉熵损失函数复合的损失函数进行训练,减轻了道路提取任务中的样本不平衡问题。在Massachusetts Road数据集上的结果表明,改进后的算法对道路提取结果得到了有效的提升。所提方法在测试集上的精确度、召回率、F1-score和mIoU评价指标分别达到82.5%、77.8%、80.0%及82.1%,在测试影像中对错综交叉的道路具有更好的识别效果。

Adapted Speed System in a Road Bend Situation in VANET Environment

Today,road safety remains a serious concern for governments around the world.In fact,approximately 1.35 million people die and 2–50 million are injured on public roads worldwide each year.Straight bends in road traffic are the main cause of many road accidents,and excessive and inappropriate speed in this very critical area can cause drivers to lose their vehicle stability.For these reasons,new solutions must be considered to stop this disaster and save lives.Therefore,it is necessary to study this topic very carefully and use new technologies such as Vehicle Ad Hoc Networks(VANET),Internet of Things(IoT),Multi-Agent Systems(MAS)and Embedded Systems to create a new system to serve the purpose.Therefore,the efficient and intelligent operation of the VANET network can avoid such problems as it provides drivers with the necessary real-time traffic data.Thus,drivers are able to drive their vehicles under correct and realistic conditions.In this document,we propose a speed adaptation scheme for winding road situations.Our proposed scheme is based on MAS technology,the main goal of which is to provide drivers with the information they need to calculate the speed limit they must not exceed in order to maintain balance in dangerous areas,especially in curves.The proposed scheme provides flexibility,adaptability,and maintainability for traffic information,taking into account the state of infrastructure and metering conditions of the road,as well as the characteristics and behavior of vehicles.

基于改进的GoogleNet-ResNet算法的路基病害智能分类方法

针对路基病害分类算法存在的复杂病害辨识难度大、多视图雷达图像特征利用不充分等问题,提出一种基于改进的GoogleNet-ResNet算法的路基病害智能分类方法;首先,引入坐标注意力和改进的Inception模块对GoogleNet网络结构进行优化;然后,利用改进的GoogleNet学习c-scan数据特征剔除非目标病害,实现病害目标的粗分类;最后,将分类成病害的b-scan数据输入基于迁移学习的ResNet50,实现病害的细分类;实验表明,改进的GoogleNet进行病害粗分类的准确率可达到98.2%,检测速度可达90.9 fps;基于迁移学习的ResNet50进行病害细分类的准确率可达90.5%,检测速度可达52.6 fps;该算法的准确率比单独的改进的GoogleNet网络高10.1%,比单独的ResNet50网络高7.4%,有效地提高了道路路基病害的识别精度与效率。

Risk assessment of oil and gas investment environment in countries along the Belt and Road Initiative

With the implementation of the Belt and Road Initiative, China is deepening its cooperation in oil and gas resources with countries along the Initiative. In order to better mitigate risks and enhance the safety of investments, it is of significant importance to research the oil and gas investment environment in these countries for China's overseas investment macro-layout. This paper proposes an indicator system including 27 indicators from 6 dimensions. On this basis, game theory models combined with global entropy method and analytic hierarchy process are applied to determine the combined weights, and the TOPSIS-GRA model is utilized to assess the risks of oil and gas investment in 76 countries along the Initiative from 2014 to 2021. Finally, the GM(1,1) model is employed to predict risk values for 2022-2025. In conclusion, oil and gas resources and political factors have the greatest impact on investment environment risk, and 12 countries with greater investment potential are selected through cluster analysis in conjunction with the predicted results. The research findings may provide scientific decisionmaking recommendations for the Chinese government and oil enterprises to strengthen oil and gas investment cooperation with countries along the Belt and Road Initiative.

基于ROAD的租车订购系统业务流程建模

基于业务架构为中心的企业架构开发思路,采用开放组架构框架(TOGAF)业务架构ACF元模型的划分,提出了一种ROAD架构迭代建模方法。针对目前ROAD元架构中业务活动模型采用IDEF0的活动模型导致的面向场景业务能力的不足,文中通过使用BPMN模型来覆盖IDEF0的活动建模,避免在描述复杂的业务过程时可能存在的局限性,并且更好地捕捉和表示所有的细节和关系,不会使得模型过于抽象。从而实现面向场景的系统建模和管理,提高业务架构设计的效率和精度。最后,文章中以旅游出行租车订购系统为例的方法,采用ROAD元架构方法建立场景化业务架构模型组,并对其进行讨论和改进,为现有架构体系提供一种面向场景的扩展思路。

A Brief Discussion on the Development of the Silk-Weaving Industry Along the “Southern Silk Road” in Yunnan

Ancient Yunnan was one of the most significant regions along China’s ancient“Southern Silk Road.”During the Nanzhao period(738–902)of the late Tang Dynasty,Yunnan’s silk-weaving industry underwent a qualitative leap as skilled silk craftsmen from the Bashu area migrated to Yunnan and introduced mulberry planting,silkworm breeding,and advanced silk-weaving techniques from Sichuan to the region.Consequently,people in Yunnan gradually acquired expertise in brocade weaving and embroidery.Many even mastered complex silk-weaving techniques.The development and progress of the silk-weaving industry in the ancient Yunnan region were intricately linked to the economic function and value of silk as both a commodity and currency along the“Southern Silk Road.”The local government in ancient Yunnan was greatly motivated by the economic interests brought by the development of silk-related industries and recognized the significance of developing the local silk industry.They even initiated a campaign to capture skilled silk craftsmen from Sichuan,aiming to foster the growth of the silk-weaving industry in Yunnan.After years of dedicated efforts from the local government in ancient Yunnan,the region emerged as a significant hub for silk production along China’s ancient“Southern Silk Road.”Despite the devastation caused by the wars in other parts of the country,Yunnan’s silk industry continued to thrive and provide ample silk products to sustain trade along this renowned route.In the contemporary era,amidst the decline of the silk-weaving industry in eastern China,Yunnan has proposed an industrial development strategy known as“relocating the silk-weaving industry from east to west.”This involves introducing advanced silk production techniques from the eastern regions into Yunnan to enhance and enrich its local silk industry,thereby establishing it as a traditional national sector and securing a competitive position within the global silk market.The historical experience of Yunnan’s silk industry demonstrated that economic development opportunities can only be seized through proactive endeavors rather than passive anticipation.The modern Yunnan silk industry,which upholds its historical traditions,continues to actively engage in international high-end technical cooperation,thus ensuring the enduring vitality of the ancient“Southern Silk Road.”

A Novel Network Screening Methodology for Rural Low-Volume Roads

Low-volume roads (LVRs) are an integral part of the rural transportation network providing access to remote rural areas and facilitating the movement of goods from farms to markets. These roads pose unique challenges for highway agencies including those related to safety management on the highway network. Specifically, traditional network screening methods using crash history can be effective in screening rural highways with higher traffic volumes and more frequent crashes. However, these traditional methods are often ineffective in screening LVR networks due to low traffic volumes and the sporadic nature of crash occurrence. Further, many of the LVRs are owned and operated by local agencies that may lack access to detailed crash, traffic and roadway data and the technical expertise within their staff. Therefore, there is a need for more efficient and practical network screening approaches to facilitate safety management programs on these roads. This study proposes one such approach which utilizes a heuristic scoring scheme in assessing the level of risk/safety for the purpose of network screening. The proposed scheme is developed based on the principles of US Highway Safety Manual (HSM) analysis procedures for rural highways and the fundamentals in safety science. The primary application of the proposed scheme is for ranking sites in network screening applications or for comparing multiple improvement alternatives at a specific site. The proposed approach does not require access to detailed databases, technical expertise, or exact information, making it an invaluable tool for small agencies and local governments (e.g. counties, townships, tribal governments, etc.).

The Third Silk Road NGO Cooperation Network Forum Was Held

The Third Silk Road NGO Cooperation Network Forum was held in Zhengzhou,Henan Province from October 19 to 21 with the theme of Building on a Decade of Glory and Forging Ahead towards a Brighter Future.This Forum saw the presence of Ji Bingxuan,Vice-Chairperson of the Standing Committee of the 13th National People's Congress of China and President of the Chinese Association for International Understanding.

基于级联U-Net的遥感影像道路分割和轮廓提取方法

针对基于深度学习的遥感图像道路信息提取模型往往只能输出单任务结果且多任务之间相关性利用不充分的问题,提出了一种基于级联U-Net的道路语义分割和轮廓联合检测方法,将道路语义分割后的特征图与原始图像融合后进行道路轮廓的提取,实现道路语义分割和边界轮廓的联合训练。首先使用U-Net网络结构提取光学遥感图像丰富的层次化特征,通过级联结构将特征串联融合,分别用于提取道路的语义类别和边界轮廓。其次在每级U-Net结构中引入注意力机制模块,进行空间上下文信息和深层次特征提取,改善网络提取过程中出现的细节模糊现象。最后,使用骰子系数和交叉熵误差组成的联合损失函数进行多任务整体训练,实现深度学习模型对遥感图像中道路语义类别和边界轮廓的同时提取。通过在加拿大渥太华城市地区的光学遥感数据集上进行实验,基于级联U-Net的道路信息联合提取方法在分割指标上分别获得了42%的精确度、58%的召回率、48.2%的F1分数以及71.6%的平均交并比,在道路检测指标上取得了0.896的全局最佳阈值(ODS)。结果表明,该模型在满足联合提取道路多任务信息的同时具有更优的检测精度。

Automation in road distress detection,diagnosis and treatment

Road transportation plays a crucial role in society and daily life,as the functioning and durability of roads can significantly impact a nation's economic development.In the whole life cycle of the road,the emergence of disease is unavoidable,so it is necessary to adopt relevant technical means to deal with the disease.This study comprehensively reviews the advancements in computer vision,artificial intelligence,and mobile robotics in the road domain and examines their progress and applications in road detection,diagnosis,and treatment,especially asphalt roads.Specifically,it analyzes the research progress in detecting and diagnosing surface and internal road distress and related techniques and algorithms are compared.In addition,also introduces various road gover-nance technologies,including automated repairs,intelligent construction,and path planning for crack sealing.Despite their proven effectiveness in detecting road distress,analyzing diagnoses,and planning maintenance,these technologies still confront challenges in data collection,parameter optimization,model portability,system accuracy,robustness,and real-time performance.Consequently,the integration of multidisciplinary technologies is imperative to enable the development of an integrated approach that includes road detection,diagnosis,and treatment.This paper addresses the challenges of precise defect detection,condition assessment,and unmanned construction.At the same time,the efficiency of labor liberation and road maintenance is achieved,and the automation level of the road engineering industry is improved.

Local failure mechanism of sand-blocking fence in latticed dune along desert roads

The latticed dunes in the Tengger Desert are widely distributed,and the sand-blocking fence placed here are highly susceptible to local failure due to complex wind-sand activities,posing a serious threat to the safe operation of the highway.To explore the local failure mechanism of sand-blocking fence in the latticed dune area,the local failure of sand-blocking fence in the latticed dune areas along the Wuhai-Maqin Highway in China was observed.Taking the first main ridge of the latticed dune as the placement location,the structure of the wind-sand flow field of sand-blocking fence placed at top,the bottom and the middle of windward slope was analyzed by Computational Fluid Dynamics(CFD).The results show that when placed at top of the first main ridge,the wind speed near the sand-blocking fence is the highest,up to 15.23 m/s.Therefore,the wind load strength on the sand barrier is correspondingly larger,up to 232.61 N∙m-2.As the strength of material continues to decrease,the nylon net is prone to breakage.The roots of the angle steel posts are susceptible to hollowing by vortex action,which can cause sand-blocking fence to fall over in strong wind conditions.When placed at the bottom of windward slope,wind speed drop near sand-blocking fence is greatest,with the decrease of 12.48-14.32 m/s compared to the original wind speed.This is highly likely to lead to large-scale deposition of sand particles and burial of the sand-blocking fence.When placed in the middle of windward slope,sand-blocking fence is subjected to less wind load strength(168.61N∙m-2)and sand particles are mostly deposited at the bottom of windward slope,with only a small amount of sand accumulating at the root of sand-blocking fence.Based on field observations and numerical modelling results,when the sand-blocking fence is placed in latticed dune area,it should be placed in the middle of the windward slope of the first main ridge as a matter of priority.Besides the sand-blocking fence should be placed at the top of the first main ridge,and sand fixing measures should be added.

Toxicity Evaluation of Different Exposure Scenarios of Road Dust Using Daphnia magna and Artemia salina as Aquatic Organisms, and Prosopis cineraria and Vachellia tortilis as Native Plant Species

Particulate matter (PM10) deposited as road dust is considered an important source of contamination from atmosphere. However, there are limited studies on the toxicity of road dust as such on different organisms. This study evaluates the toxicity of road dust using different extraction scenarios on Daphnia magna and Artemia salina as aquatic organisms and also on Prosopis cineraria and Vachellia tortilis as local plant species. Chemical analysis of different extracts shows considerable amount of trace metals, however the trace metals in the dust extract associated with suspended sediment were not absorbed by the receptors. On the other hand, the concentration of trace metals in the artificial mixture was found bioavailable and absorbed causing a high percentage of mortality. In the plant assay, significant difference was obtained in the germination percentage between the control and three different extraction exposures in both plant species. The mean root length of P. cineraria and V. tortilis were higher in 20% and 50% extracts than the control probably due to the availability of nutrients from the dust extract. Interestingly however, the seedling vigor index was the opposite with higher index in the control and lower in dust extracts that contain heavy metals.