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 imag...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.展开更多
Landscape characters in estuarine regions generally controlled by tidal regimes and human activities like road construction.In this work,tidal channels and road construction in the Yellow River Delta(YRD)were extracte...Landscape characters in estuarine regions generally controlled by tidal regimes and human activities like road construction.In this work,tidal channels and road construction in the Yellow River Delta(YRD)were extracted by visual interpretation methods so as to decipher impacts of tidal channel development and road construction on landscape patch change during 1989–2016.Spatial distribution history of three wetlands,which covered by Phragmites australis(freshwater marsh,FM),Suaeda salsa(salt marsh,SM),and mudflats(MD)were also established.Results indicated that tidal channel,number,frequency,and fractal dimension were all the maximum in 2003,and the minimum in 1998,respectively.Road length,number,and density showed increasing trend during 1989–2016.MD were the predominant landscape type,followed by FM and SM during 1989-2016.Principal component analysis implied two extracted factors,F1 and F2,which could represent 91.93% of the total variations.F1 mainly proxied tidal channel development,while F2 represented road construction.A multiple linear regression analysis showed positive effects of both F1 and F2 on FM patch numbers and negative impacts on SM patch areaes with R^2 values of 0.416 and 0.599,respectively.Tidal channels were negatively related to MD patch numbers,while roads were positively related to that.In any case,road construction showed larger impacts on landscape type shifting than that of tidal channel development in the YRD.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
随着信息技术的快速发展,建筑信息模型(Building Information Modeling,BIM)在建筑行业中的应用日益广泛。本论文针对路桥项目的特殊性,以解决实际问题为目标,探讨了BIM在路桥项目管理与协调中的应用[1]。通过对实际项目的案例研究,提...随着信息技术的快速发展,建筑信息模型(Building Information Modeling,BIM)在建筑行业中的应用日益广泛。本论文针对路桥项目的特殊性,以解决实际问题为目标,探讨了BIM在路桥项目管理与协调中的应用[1]。通过对实际项目的案例研究,提出了一套基于BIM的路桥项目管理与协调的方法和工具,以优化项目的生命周期管理和提高项目的整体效率。本研究为路桥项目的实际应用提供了有益的参考和指导。展开更多
以2030年“碳达峰”为研究时点,通过IPCC(Intergovernmental Panel on Climate Change,联合国政府间气候变化专门委员会)“自下而上”法和社会网络分析法,探究不同通道情境下区际城市群公路物流碳排放及其减排潜力的网络格局,分析渤海...以2030年“碳达峰”为研究时点,通过IPCC(Intergovernmental Panel on Climate Change,联合国政府间气候变化专门委员会)“自下而上”法和社会网络分析法,探究不同通道情境下区际城市群公路物流碳排放及其减排潜力的网络格局,分析渤海通道对其产生的影响。研究表明:①2030年不同通道情境的区际城市群公路物流碳排放网络差异:陆上通道情境下,区际城市群碳交流向经济、交通发达轴带和渤海海峡端点城市集中;陆海通道情境下,区际碳交流向邻近陆上通道的城市集聚;渤海通道改善了区际城市群“渤海海峡端点城市”指向的高耗能局面。②2030年区际城市群公路物流减排潜力网络格局:以大连为减排枢纽,以渤海海峡为中心,强减排城市组对南多北少,并存在零减排城市组对;渤海通道主要通过端点城市向其他城市施以碳减排影响,对距其较远且处在公路物流边缘的部分城市的碳减排影响较为有限。展开更多
基金supported by National Natural Science Foundation of China(No.61864025)2021 Longyuan Youth Innovation and Entrepreneurship Talent(Team),Young Doctoral Fund of Higher Education Institutions of Gansu Province(No.2021QB-49)+4 种基金Employment and Entrepreneurship Improvement Project of University Students of Gansu Province(No.2021-C-123)Intelligent Tunnel Supervision Robot Research Project(China Railway Scientific Research Institute(Scientific Research)(No.2020-KJ016-Z016-A2)Lanzhou Jiaotong University Youth Foundation(No.2015005)Gansu Higher Education Research Project(No.2016A-018)Gansu Dunhuang Cultural Relics Protection Research Center Open Project(No.GDW2021YB15).
文摘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.
基金Under the auspices of National Key Research and Development Project(No.2017YFC0505901)
文摘Landscape characters in estuarine regions generally controlled by tidal regimes and human activities like road construction.In this work,tidal channels and road construction in the Yellow River Delta(YRD)were extracted by visual interpretation methods so as to decipher impacts of tidal channel development and road construction on landscape patch change during 1989–2016.Spatial distribution history of three wetlands,which covered by Phragmites australis(freshwater marsh,FM),Suaeda salsa(salt marsh,SM),and mudflats(MD)were also established.Results indicated that tidal channel,number,frequency,and fractal dimension were all the maximum in 2003,and the minimum in 1998,respectively.Road length,number,and density showed increasing trend during 1989–2016.MD were the predominant landscape type,followed by FM and SM during 1989-2016.Principal component analysis implied two extracted factors,F1 and F2,which could represent 91.93% of the total variations.F1 mainly proxied tidal channel development,while F2 represented road construction.A multiple linear regression analysis showed positive effects of both F1 and F2 on FM patch numbers and negative impacts on SM patch areaes with R^2 values of 0.416 and 0.599,respectively.Tidal channels were negatively related to MD patch numbers,while roads were positively related to that.In any case,road construction showed larger impacts on landscape type shifting than that of tidal channel development in the YRD.
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。
文摘随着信息技术的快速发展,建筑信息模型(Building Information Modeling,BIM)在建筑行业中的应用日益广泛。本论文针对路桥项目的特殊性,以解决实际问题为目标,探讨了BIM在路桥项目管理与协调中的应用[1]。通过对实际项目的案例研究,提出了一套基于BIM的路桥项目管理与协调的方法和工具,以优化项目的生命周期管理和提高项目的整体效率。本研究为路桥项目的实际应用提供了有益的参考和指导。
文摘以2030年“碳达峰”为研究时点,通过IPCC(Intergovernmental Panel on Climate Change,联合国政府间气候变化专门委员会)“自下而上”法和社会网络分析法,探究不同通道情境下区际城市群公路物流碳排放及其减排潜力的网络格局,分析渤海通道对其产生的影响。研究表明:①2030年不同通道情境的区际城市群公路物流碳排放网络差异:陆上通道情境下,区际城市群碳交流向经济、交通发达轴带和渤海海峡端点城市集中;陆海通道情境下,区际碳交流向邻近陆上通道的城市集聚;渤海通道改善了区际城市群“渤海海峡端点城市”指向的高耗能局面。②2030年区际城市群公路物流减排潜力网络格局:以大连为减排枢纽,以渤海海峡为中心,强减排城市组对南多北少,并存在零减排城市组对;渤海通道主要通过端点城市向其他城市施以碳减排影响,对距其较远且处在公路物流边缘的部分城市的碳减排影响较为有限。
