From the viewpoint of Graph Theory this paper builds a town road network graph of regional scale, and proposes numerical vertex degree (Di), rank vertex degree (Dr) and population size vertex degree (Dp) on the base o...From the viewpoint of Graph Theory this paper builds a town road network graph of regional scale, and proposes numerical vertex degree (Di), rank vertex degree (Dr) and population size vertex degree (Dp) on the base of vertex degree (D). Then the indicators of Di, Dr, Dp and mathematical statistics methods are applied to investigating scale-free structure of town road networks in the southern Jiangsu Province. The results show that the distribution of Di does not exhibit scale-free properties, but Dr and Dp do. Additionally the correlation coefficient between Dp and Di is only 0.569, but the spatial correlation between Dp and Dr is very evident on the base of correlation analysis and spatial analysis of GIS. The mutual mechanism between Dp and Dr spatially represents a "Core-Belt" model of town development of regional scale. The town development model is open and clustered, and beneficial to both economic development and ecological protection. And then we suggest that Suzhou City, Wuxi City, Changzhou City and Wujin City control towns' high-density pattern by conducting centralization and consolidation policies, and properly controlling and planning higher rank roads; whereas Nanjing City, Zhenjiang City, Jintan City and Liyang City must strengthen the development of towns along higher rank roads.展开更多
优化城市道路中的交通信号灯控制是低成本地提升城市交通路网性能的方法之一。该研究提出了一种利用策略梯度(Policy Gradient, PG)强化调优的交通灯控制算法。该算法引入了道路压力项、旅程时间项和黑名单机制项,利用统计方式预测汽车...优化城市道路中的交通信号灯控制是低成本地提升城市交通路网性能的方法之一。该研究提出了一种利用策略梯度(Policy Gradient, PG)强化调优的交通灯控制算法。该算法引入了道路压力项、旅程时间项和黑名单机制项,利用统计方式预测汽车行程轨迹,并采用策略梯度估计的优化算法调整算法中的参数。在数据挖掘国际会议Knowledge Discovery and Data Mining (KDD)组织的算法竞赛KDD Cup 2021城市大脑挑战赛中,获得了冠军的成绩。在该挑战赛提供的城市路网规模复杂车流仿真平台上的实验结果表明,算法具有应用于实际场景的价值。展开更多
为了解决遥感道路提取中边缘细节特征利用不充分,以及复杂背景遮挡区域的道路难以实现准确分割等问题,提出一种基于边缘引导和多尺度感知的遥感道路提取模型(Edge-guidance and Multi-scale perception U-Net,EMUNet)。以U-Net为基础,...为了解决遥感道路提取中边缘细节特征利用不充分,以及复杂背景遮挡区域的道路难以实现准确分割等问题,提出一种基于边缘引导和多尺度感知的遥感道路提取模型(Edge-guidance and Multi-scale perception U-Net,EMUNet)。以U-Net为基础,增加遥感图像的Canny边缘检测结果作为输入,并通过设计结合注意力的边缘引导融合模块对各层编码器进行特征引导,以此充分利用边缘信息提高最终的道路提取质量;其次,针对图像中存在的背景遮挡问题,通过构建多尺度并行空洞卷积模块增强网络的多尺度感知能力,从而捕获更多的上下文信息,对一些受到背景遮挡的区域实现准确提取。在Massachusetts道路数据集上进行实验验证,与U-Net相比,EMUNet能实现对细小道路和受遮挡区域更准确的分割,并且召回率、F1分数和交并比均优于其他对比算法,能够实现更为完整和准确的道路信息提取。展开更多
The ride comfort experimental assessment of crawler off-road vehicle is relatively overlooked, and is expensive and difficult to execute with higher and higher ride comfort performance requirements. To trade off betwe...The ride comfort experimental assessment of crawler off-road vehicle is relatively overlooked, and is expensive and difficult to execute with higher and higher ride comfort performance requirements. To trade off between precise and cost, an experimental method based on the similitude theory is proposed. Under the guidance of the similitude theory, a 1：5 crawler power chassis scale model equipped with a kind of variable stiffness suspension system is used. The power spectrum density（PSD）, the root mean square（RMS） of weighed acceleration, peak factor, average absorbed power（AAP） and vibration dose value（VDV） are selected as ride comfort evaluation indexes, and tests results are transformed via similarity indexes to predict the performance of full-scale power chassis. PSD shows that the low-order natural frequency of the vertical natural frequency（z axis） is 1.1 Hz, and the RMS, AAP and VDV values indicate the ride comfort performance of this kind of power chassis is between the ＂A little uncomfortable＂ and ＂Rather uncomfortable＂. From the results, low-order vertical natural frequency, obtained by PSD, validates that the similarity relationship between two models is satisfied, and 1：5 scale model used in experiment meets the similarity relationship with the full-scale model; consequently, the ride comfort prophase evaluation with the 1：5 scale model is feasible. The attempt of applying the similitude theory to crawler vehicle ride comfort test study decreases the cost and improves the test feasibility with sufficient test precise.展开更多
This case study examines how the Hampton Roads Sea Level Rise Preparedness and Resilience Intergovernmental Planning Pilot Project, a whole-of-government and whole-of-community approach to planning for and adapting to...This case study examines how the Hampton Roads Sea Level Rise Preparedness and Resilience Intergovernmental Planning Pilot Project, a whole-of-government and whole-of-community approach to planning for and adapting to sea level rise, addressed coastal resilience in a southeastern Virginia watershed that spans multiple jurisdictions. Meeting the challenge of sea level rise requires that actors across multiple sectors—citizens, community organizations, industry and government—understand the risks and work together to make critical decisions regarding adaptation strategies and actions. The case study area includes Little Creek Amphibious Base, which is bordered by the cities of Norfolk and Virginia Beach. Adaptation responses to sea level rise by the military base and the local governments will impact each other and the residents of the area, but no cooperative agreements are in place for a joint or collaborative response. This case study examines public and private infrastructure at risk, the infrastructure interdependencies, and mechanisms for providing collaborative solutions. Engagement of area residents and other stakeholders is also integral to the process of adaptation, which includes educating about sea level rise risk and provides a mechanism for social learning that enables stakeholders to participate in critical adaptation decisions. The case study demonstrates a method to improve resiliency in the case study area and inform a regional, multi-sectoral response to sea level rise adaptation strategies.展开更多
基金Under the auspices of National Natural Science Foundation of China (No. 40435013, No. 40535026)
文摘From the viewpoint of Graph Theory this paper builds a town road network graph of regional scale, and proposes numerical vertex degree (Di), rank vertex degree (Dr) and population size vertex degree (Dp) on the base of vertex degree (D). Then the indicators of Di, Dr, Dp and mathematical statistics methods are applied to investigating scale-free structure of town road networks in the southern Jiangsu Province. The results show that the distribution of Di does not exhibit scale-free properties, but Dr and Dp do. Additionally the correlation coefficient between Dp and Di is only 0.569, but the spatial correlation between Dp and Dr is very evident on the base of correlation analysis and spatial analysis of GIS. The mutual mechanism between Dp and Dr spatially represents a "Core-Belt" model of town development of regional scale. The town development model is open and clustered, and beneficial to both economic development and ecological protection. And then we suggest that Suzhou City, Wuxi City, Changzhou City and Wujin City control towns' high-density pattern by conducting centralization and consolidation policies, and properly controlling and planning higher rank roads; whereas Nanjing City, Zhenjiang City, Jintan City and Liyang City must strengthen the development of towns along higher rank roads.
文摘优化城市道路中的交通信号灯控制是低成本地提升城市交通路网性能的方法之一。该研究提出了一种利用策略梯度(Policy Gradient, PG)强化调优的交通灯控制算法。该算法引入了道路压力项、旅程时间项和黑名单机制项,利用统计方式预测汽车行程轨迹,并采用策略梯度估计的优化算法调整算法中的参数。在数据挖掘国际会议Knowledge Discovery and Data Mining (KDD)组织的算法竞赛KDD Cup 2021城市大脑挑战赛中,获得了冠军的成绩。在该挑战赛提供的城市路网规模复杂车流仿真平台上的实验结果表明,算法具有应用于实际场景的价值。
文摘为了解决遥感道路提取中边缘细节特征利用不充分,以及复杂背景遮挡区域的道路难以实现准确分割等问题,提出一种基于边缘引导和多尺度感知的遥感道路提取模型(Edge-guidance and Multi-scale perception U-Net,EMUNet)。以U-Net为基础,增加遥感图像的Canny边缘检测结果作为输入,并通过设计结合注意力的边缘引导融合模块对各层编码器进行特征引导,以此充分利用边缘信息提高最终的道路提取质量;其次,针对图像中存在的背景遮挡问题,通过构建多尺度并行空洞卷积模块增强网络的多尺度感知能力,从而捕获更多的上下文信息,对一些受到背景遮挡的区域实现准确提取。在Massachusetts道路数据集上进行实验验证,与U-Net相比,EMUNet能实现对细小道路和受遮挡区域更准确的分割,并且召回率、F1分数和交并比均优于其他对比算法,能够实现更为完整和准确的道路信息提取。
基金Supported by Special Fund for Argo-scientific Research in the Public Interest,China(Grant No.201203024)National Natural Science Foundation of China(Grant No.51175498)
文摘The ride comfort experimental assessment of crawler off-road vehicle is relatively overlooked, and is expensive and difficult to execute with higher and higher ride comfort performance requirements. To trade off between precise and cost, an experimental method based on the similitude theory is proposed. Under the guidance of the similitude theory, a 1：5 crawler power chassis scale model equipped with a kind of variable stiffness suspension system is used. The power spectrum density（PSD）, the root mean square（RMS） of weighed acceleration, peak factor, average absorbed power（AAP） and vibration dose value（VDV） are selected as ride comfort evaluation indexes, and tests results are transformed via similarity indexes to predict the performance of full-scale power chassis. PSD shows that the low-order natural frequency of the vertical natural frequency（z axis） is 1.1 Hz, and the RMS, AAP and VDV values indicate the ride comfort performance of this kind of power chassis is between the ＂A little uncomfortable＂ and ＂Rather uncomfortable＂. From the results, low-order vertical natural frequency, obtained by PSD, validates that the similarity relationship between two models is satisfied, and 1：5 scale model used in experiment meets the similarity relationship with the full-scale model; consequently, the ride comfort prophase evaluation with the 1：5 scale model is feasible. The attempt of applying the similitude theory to crawler vehicle ride comfort test study decreases the cost and improves the test feasibility with sufficient test precise.
文摘This case study examines how the Hampton Roads Sea Level Rise Preparedness and Resilience Intergovernmental Planning Pilot Project, a whole-of-government and whole-of-community approach to planning for and adapting to sea level rise, addressed coastal resilience in a southeastern Virginia watershed that spans multiple jurisdictions. Meeting the challenge of sea level rise requires that actors across multiple sectors—citizens, community organizations, industry and government—understand the risks and work together to make critical decisions regarding adaptation strategies and actions. The case study area includes Little Creek Amphibious Base, which is bordered by the cities of Norfolk and Virginia Beach. Adaptation responses to sea level rise by the military base and the local governments will impact each other and the residents of the area, but no cooperative agreements are in place for a joint or collaborative response. This case study examines public and private infrastructure at risk, the infrastructure interdependencies, and mechanisms for providing collaborative solutions. Engagement of area residents and other stakeholders is also integral to the process of adaptation, which includes educating about sea level rise risk and provides a mechanism for social learning that enables stakeholders to participate in critical adaptation decisions. The case study demonstrates a method to improve resiliency in the case study area and inform a regional, multi-sectoral response to sea level rise adaptation strategies.
文摘为了提高多尺度道路目标的检测性能,本文针对目标检测算法在非极大值抑制阶段的检测质量表征不合理问题,提出了一种优化定位置信度改进算法.首先基于RepPoints构建研究框架,研究定位置信度对多尺度道路目标的敏感性.在敏感性研究结果的基础上,本文提出了混合定位置信度.然后针对IoU定位置信度无法区分重叠程度相同的包围框的缺陷,提出了CIoU定位置信度.最后将这两种定位置信度结合得到优化定位置信度改进算法,解决了检测质量表征不合理问题.在道路场景数据集Cityscapes上的实验结果表明,混合定位置信度和CIoU定位置信度单一作用时均有效,共同作用时精度提高2.4%,多尺度目标检测精度均有显著提升,且实时性没有下降.相较于主流道路场景检测算法如Cascade-RCNN、FCOS等,本文算法取得了最高的mAP、AP M和AP L.
