WO2022047958A1 - 一种基于人工智能的城市道路网络自动生成方法 - Google Patents

一种基于人工智能的城市道路网络自动生成方法 Download PDF

Info

Publication number
WO2022047958A1
WO2022047958A1 PCT/CN2020/124318 CN2020124318W WO2022047958A1 WO 2022047958 A1 WO2022047958 A1 WO 2022047958A1 CN 2020124318 W CN2020124318 W CN 2020124318W WO 2022047958 A1 WO2022047958 A1 WO 2022047958A1
Authority
WO
WIPO (PCT)
Prior art keywords
road
scheme
network
urban
anchor point
Prior art date
Application number
PCT/CN2020/124318
Other languages
English (en)
French (fr)
Inventor
杨俊宴
夏歌阳
朱骁
史北祥
张政承
杨晓方
Original Assignee
东南大学
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 东南大学 filed Critical 东南大学
Priority to US17/616,293 priority Critical patent/US20220309203A1/en
Publication of WO2022047958A1 publication Critical patent/WO2022047958A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/10—Geometric CAD
    • G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/10—Geometric CAD
    • G06F30/18—Network design, e.g. design based on topological or interconnect aspects of utility systems, piping, heating ventilation air conditioning [HVAC] or cabling
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29—Geographical information databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0475—Generative networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/088—Non-supervised learning, e.g. competitive learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/094—Adversarial learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/17—Terrestrial scenes taken from planes or by drones
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/182—Network patterns, e.g. roads or rivers
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/02—Knowledge representation; Symbolic representation
    • G06N5/022—Knowledge engineering; Knowledge acquisition

Definitions

  • the invention relates to an automatic generation method of an urban road network, in particular to an automatic generation method of an urban road network based on artificial intelligence.
  • the purpose of the present invention is to provide a method for automatically generating an urban road network based on artificial intelligence, and the process of the method for automatically generating an urban road network of the present invention is highly efficient: this method can set the feasible range of the urban road network scheme, and simultaneously in a short time Generate multiple schemes to reduce labor costs and improve design efficiency; system simulation: This method applies an interpretable generative adversarial network (infoGAN) to build a road network rule library based on urban planning road-related specifications, and automatically generates roads on this basis.
  • infoGAN interpretable generative adversarial network
  • the network scheme set improves the degree of fitting between the scheme set and the real road network, and ensures the quality of the automatically generated scheme set; the results are intuitive: the results generated by this method are simulated and displayed through a two-dimensional interactive device, which is convenient for urban planning professionals and managers. communication.
  • a method for automatic generation of urban road network based on artificial intelligence includes the following steps:
  • S1 Data acquisition and input module, which is used to collect the two-dimensional vector data of the planning range by means of drone collection and urban open source data platform, and input it into the geographic information platform.
  • Machine learning module which is used to collect branch road network data through an open source data platform and build an urban branch road network sample library; then use the rectangular centroid of branch road division as an anchor point to generate a corresponding anchor point distribution library; distribute the anchor points
  • the vector image of the sample library is converted into a bitmap image, and a unified dimensional anchor point distribution machine learning sample library is constructed; based on the generative adversarial network, the anchor point distribution model is adversarially trained.
  • the rule base building module is used to input the urban branch spacing range specification, urban road red line specification, and urban road chamfering specification in the "Urban Road Traffic Planning and Design Specification" into the geographic information platform through the geographic information platform, and build rules library.
  • scheme set generation module which is used to generate and distribute anchor points within the planning range from the anchor point distribution model obtained by the machine learning module, and generate an anchor point distribution scheme set; and then generate corresponding anchor points according to the anchor points of each scheme in the anchor point distribution scheme set.
  • the set of Thiessen polygon distribution schemes of the The new anchor point in the distribution scheme set is centered, and the corresponding road centerline layout scheme set is generated through the rectangular expansion method; the feasible road centerline network scheme set is screened out through the "Code for Urban Road Traffic Planning and Design" rule base, and the feasible road centerline layout is The schemes in the scheme set generate road network scheme output and generate road network scheme set according to the "Code for Urban Road Traffic Planning and Design" rule base.
  • S5 Human-computer interaction display module, which is used to output the road network scheme to the two-dimensional interactive display device, which specifically includes scheme drawing generation, scheme effect simulation and scheme index display.
  • the boundary line of the planning range is a secondary trunk road, and only a branch road network is generated within the planning range;
  • the collected two-dimensional vector data of the planning range is a polygonal plot with a closed outline, including the shape and size of the polygon. information.
  • the specific operation steps are to collect the branch road network data of Chinese cities through the open source data platform, and input the geographic information platform; the sample planning scope boundary is the secondary road, and the planning scope is Branch network, the sample size is 10000.
  • the concrete operation steps of constructing a unified dimension anchor point distribution machine learning sample library are to convert the vector image of the anchor point distribution sample library into a bitmap with a scale of 1:2000, a resolution of 100dpi, and a size of 300mm*300mm. image, thereby generating an anchor distribution machine learning sample library, and the number of samples is 10,000.
  • the anchor point distribution model is confronted and trained, and the specific operation steps are to use Gaussian white noise as the input data, and use the anchor point automatic distribution image as the output data to construct a generative network;
  • the automatic point distribution image and the anchor point distribution machine learning sample image are the input data, the loss function is designed, and the discriminant network is constructed;
  • the generating network and the discriminant network are convolutional neural networks;
  • the point automatic distribution image gradually approximates the anchor point distribution machine learning sample image.
  • a rule base is constructed in the step S3: the index control is organized and constructed according to the rule base of the "Urban Road Traffic Planning and Design Specification” and the "Road Chamfering Radius Specification”;
  • the road centerline layout scheme is based on the new anchor point to generate the corresponding road centerline layout scheme through the rectangular expansion method.
  • the anchor point is the center, and the square expands in four orthogonal directions at the same rate at the same time.
  • the bar will be expanded. Edges stop expanding, other edges continue to expand, until finally all boundaries stop expanding, generating a rectangle with the same number of anchor points. Integrate the sides of the rectangle to form the road centerline layout, delete the rectangular sides outside the planning area and overlapping the planning area, and integrate the rectangular sides within the planning area into a unique non-overlapping line segment.
  • screening the feasible set of road center network solutions, and its specific operation steps are to judge whether all the road center line segment lengths of the road center line layout plan generated by the rectangular expansion method are within 150-250m, if not, then Discard the scheme; if so, export the scheme to the feasible road centerline layout scheme set.
  • the specific steps of generating the road network plan set are to expand the feasible road centerline layout plan respectively from the centerline to both sides by 6-7.5m to form a road red line with a width of 12-15m, and then connect the inner branch road to the road red line.
  • the road red line chamfer of 10-15m is generated at the intersection of the branch road, and the road red line chamfer of 20-25m is generated at the intersection of the boundary branch road and the secondary trunk road; the road network scheme collection after the red line and the chamfer are generated, Generate a set of road network scenarios.
  • the scheme effect simulation and display means that the examiner can select the required road network scheme in the road network scheme library through the operation lever and display the scheme drawings and scheme effect simulation on a display device with a resolution of 1920 ⁇ 1080 or more than 55 inches.
  • Figures and various indicators of the scheme refers to mapping the roadway and sidewalk with modeling software based on the road plan of the planning scope, wherein the roadway is the asphalt texture map, and the sidewalk is the brick map ; Render the road network model, and use the image editing software to combine the model rendering with the real scene of the drone aerial photography to form a plan effect simulation map for display;
  • the indicators of the plan include the grade of each road, The width of the red line of the road, the chamfering of the red line of the road, the side length and area of the street divided by the road, the density of the branch road network in the planning scope, and the proportion of the "cross" intersection nodes to all the intersection nodes.
  • the process efficiency of the method for automatically generating the urban road network of the present invention can generate multiple schemes simultaneously in a short time by setting the feasible range of the urban road network scheme, reducing labor costs and improving design efficiency;
  • the system simulation of the method for automatically generating the urban road network of the present invention applies an interpretable generative adversarial network (infoGAN), constructs a road network rule base based on the relevant specifications of urban planning roads, and automatically generates a road network scheme set on this basis. , which improves the fitting degree between the scheme set and the real road network, and ensures the quality of the automatically generated scheme set;
  • infoGAN interpretable generative adversarial network
  • results of the method for automatically generating the urban road network of the present invention are intuitive: the results generated by the method are simulated and displayed through a two-dimensional interactive device, which is convenient for communication between urban planning professionals and managers.
  • Fig. 1 is the flow chart of the generation method of the present invention
  • Fig. 2 is the schematic diagram of road automatic generation planning scope of the present invention.
  • Fig. 3 is the schematic diagram of screening of road centerline layout scheme of the present invention.
  • FIG. 4 is a schematic diagram of an automatic road generation scheme of the present invention.
  • An automatic generation method of urban road network based on artificial intelligence includes the following steps:
  • S1 Data acquisition and input module, which is used to collect the two-dimensional vector data of the planning range by means of the UAV aerial photography equipment with 1920*1080 resolution lens and the method obtained from the urban open source data platform, and input it into the geographic information platform;
  • the boundary line of the planning scope is the secondary trunk road, as shown in Figure 2, only the branch road network is generated within the planning scope.
  • the collected two-dimensional vector data of the planning area are polygonal plots with closed contours, including the geographic coordinates, shape and size information of the polygons.
  • the machine learning module is used to collect the branch road network data through the open source data platform and construct the urban branch road network sample library; then use the rectangular centroid divided by the branch road as the anchor point to generate the corresponding anchor point distribution library; distribute the anchor points
  • the vector images of the sample library are converted into bitmap images, and a unified dimensional anchor point distribution machine learning sample library is constructed; based on the interpretable generative adversarial network (infoGAN), the anchor point distribution model is adversarially trained.
  • infoGAN interpretable generative adversarial network
  • the specific operation steps are to collect the branch road network data of Chinese cities through the open source data platform and input it into the geographic information platform.
  • the boundary of the sample planning range is the secondary trunk road, and the planned range is the branch road network, and the number of samples is 10,000.
  • Construct a unified dimension anchor point distribution machine learning sample library Construct a unified dimension anchor point distribution machine learning sample library.
  • the specific operation steps are to convert the vector image of the anchor point distribution sample library into a bitmap image of 1:2000 scale, 100dpi resolution, and 300mm*300mm size, so as to generate anchor points.
  • Point distribution machine learning sample library the number of samples is 10,000.
  • the specific operation steps are to use Gaussian white noise as the input data, and the automatic distribution image of anchor points as the output data to construct a generative network; use the automatic distribution of anchor points as the output data.
  • Image and anchor point distribution The machine learning sample image is used as input data, the loss function is designed, and the discriminant network is constructed.
  • the generation network and the discriminant network are convolutional neural networks (CNN).
  • the rule base building module is used to input the urban branch spacing range specification, urban road red line specification, and urban road chamfering specification in the "Urban Road Traffic Planning and Design Specification" into the geographic information platform through the geographic information platform, and build rules library;
  • the index control is organized and constructed according to the rule base of "Urban Road Traffic Planning and Design Specification” and "Road Chamfering Radius Specification”.
  • a scheme set generation module which is used to generate and distribute anchor points within the planning range from the anchor point distribution model obtained by the machine learning module, and generate an anchor point distribution scheme set; and then generate corresponding anchor points according to the anchor points of each scheme in the anchor point distribution scheme set.
  • the set of Thiessen polygon distribution schemes of the The new anchor point in the distribution scheme set is the center, and the corresponding road centerline layout scheme set is generated by the rectangular expansion method; the feasible road centerline layout scheme set is screened out through the "Code for Urban Road Traffic Planning and Design" rule base, and the feasible road centerline
  • the schemes in the layout scheme set will generate the road network scheme output according to the "Code for Urban Road Traffic Planning and Design" rule base and generate the road network scheme set;
  • the corresponding road centerline layout scheme is generated by the rectangular expansion method.
  • the expansion of the square is carried out in two orthogonal directions.
  • the specific operation steps are to judge whether all road centerline layout schemes generated by the rectangular expansion method are within 150-250m in length, and if not, discard the scheme; If yes, output the scheme to the feasible road centerline layout scheme set, as shown in Figure 3
  • the specific steps for generating the road network scheme set are to expand the feasible road centerline layout scheme from the centerline to both sides by 6-7.5m respectively to form a road red line with a width of 12-15m, and then cross the internal branch road with the branch road.
  • the road red line chamfer of 10-15m is generated at the entrance, and the road red line chamfer of 20-25m is generated at the intersection of the boundary branch road and the secondary trunk road.
  • the road network scheme set after the red line and chamfering will be generated to generate the road network scheme set.
  • S5 Human-computer interaction display module, used to output the road network scheme to a two-dimensional interactive display device with a resolution of 1920 ⁇ 1080 or more than 55 inches, which specifically includes scheme drawing generation, scheme effect simulation and scheme index display, as shown in Figure 4 shown.
  • Scheme effect simulation and display means that the examiner can select the required road network scheme in the road network scheme library through the operation lever and display the scheme drawings, scheme effect simulation diagrams and scheme items on a display device with a resolution of 1920 ⁇ 1080 or more than 55 inches. index.
  • the effect simulation diagram of the scheme refers to mapping the roadway and sidewalk with modeling software based on the road plan of the planning range, wherein the roadway is the asphalt texture map, and the sidewalk is the brick map; and then the road network model is mapped. Rendering, and use the image editing software to combine the model rendering with the real scene of the drone aerial photography to form a scheme effect simulation diagram for display.
  • the indicators of the plan include the grade of each road, the width of the road red line, the chamfering of the road red line, the side length and area of the road divided by the road, the density of the branch road network within the planning scope, and the “ten” intersection nodes account for all intersection nodes. point ratio.
  • description with reference to the terms “one embodiment,” “example,” “specific example,” etc. means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one aspect of the present invention. in one embodiment or example.
  • schematic representations of the above terms do not necessarily refer to the same embodiment or example.
  • the particular features, structures, materials or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Business, Economics & Management (AREA)
  • General Engineering & Computer Science (AREA)
  • Geometry (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Hardware Design (AREA)
  • Tourism & Hospitality (AREA)
  • Biomedical Technology (AREA)
  • Mathematical Physics (AREA)
  • Computing Systems (AREA)
  • Molecular Biology (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Remote Sensing (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Analysis (AREA)
  • Pure & Applied Mathematics (AREA)
  • Educational Administration (AREA)
  • Development Economics (AREA)
  • Computational Mathematics (AREA)
  • Marketing (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Medical Informatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Databases & Information Systems (AREA)

Abstract

一种基于人工智能的城市道路网络自动生成方法，包括数据获取与输入模块、机器学习模块、规则库构建模块、方案集生成模块、人机交互展示模块，通过机器学习构建锚点分布模型，在次干路为边界的规划范围内分布锚点，通过矩形扩张法生成道路中心线布局方案集，并基于城市规划道路相关规范转译形成的规则库，筛选出可行方案集，进一步自动生成道路网络方案集，最后将方案输出至二维交互展示设备进行模拟展示。以机器学习和城市规划领域的规则共同驱动实现道路网络设计，提供了一种简洁高效的城市道路网络的自动生成方法，能够短时间内生成多方案，为人工智能城市规划设计实践提供高效率、直观化的参考。

Description

一种基于人工智能的城市道路网络自动生成方法 技术领域
本发明涉及一种城市道路网络自动生成方法，具体是一种基于人工智能的城市道路网络自动生成方法。
背景技术
人工智能技术不断发展，对城市规划设计领域带来前所未有的冲击。应用人工智能辅助城市规划的调研分析、设计研究、管理监测等全过程工作，成为当前和未来城市规划研究的重点方向。在设计阶段，城市道路网络的设计是首要环节，是街坊设计和建筑设计的基础。由于城市空间具有复杂多元的特征，道路网络形态与自然山水、用地功能等城市要素间相互影响相互制约，因此城市道路网络设计面临一系列不确定性因素，仍具有一定的挑战性。
目前已有的城市道路网络自动生成方法，一种是基于航拍遥感图像或车行轨迹，在计算机生成已有的道路、街道，这种方法只是对真实道路网络的重现，对于缺失现有道路的新城区的作用有限。另一种是基于图像学习，通过学习海量道路网络样本的规律，训练对抗生成网络模型，在严格规定大小地块内生成道路网络，但这种方式存在着模型训练速度较慢，生成结果与真实道路网络间的拟合不足，人工筛选可行道路网络的成本较高等问题。
发明内容
本发明的目的在于提供一种基于人工智能的城市道路网络自动生成方法，本发明城市道路网络自动生成方法过程高效性：本方法通过设定城市道路网络方案的可行范围，能够在短时间内同时生成多个方案，减少人力成本，提高设 计效率；系统仿真性：本方法应用可解释的生成式对抗网络(infoGAN)，基于城市规划道路相关规范构建道路网络规则库，在此基础上自动生成道路网络方案集，提高了方案集与真实道路网络的拟合程度，保证自动生成方案集的质量；成果直观性：本方法生成成果通过二维交互设备进行模拟展示，便于城市规划专业人员和管理者的沟通。
本发明的目的可以通过以下技术方案实现：
一种基于人工智能的城市道路网络自动生成方法，生成方法包括以下步骤：
S1：数据获取与输入模块，用于通过无人机采集和城市开源数据平台中获取的方式采集规划范围的二维矢量数据，并输入至地理信息平台中。
S2：机器学习模块，用于通过开源数据平台采集支路网络数据，构建城市支路网络样本库；再以支路划分的矩形质心为锚点，生成对应的锚点分布库；将锚点分布样本库的矢量图像转化为位图图像，构建统一量纲的锚点分布机器学习样本库；基于生成式对抗网络，对抗训练锚点分布模型。
S3：规则库构建模块，用于通过地理信息平台，将《城市道路交通规划设计规范》中的城市支路间距范围规范、城市道路红线规范、城市道路倒角规范输入地理信息平台，并构建规则库。
S4：方案集生成模块，用于通过机器学习模块得到的锚点分布模型在规划范围内生成并分布锚点，生成锚点分布方案集；再根据锚点分布方案集中各方案的锚点生成对应的泰森多边形分布方案集；并将各泰森多边形分布方案中的泰森多边形的质心替换该多边形内的锚点作为新锚点，生成新的锚点分布方案集；再以新的锚点分布方案集中的新锚点为中心通过矩形扩张法生成对应道路中心线布局方案集；通过《城市道路交通规划设计规范》规则库筛选出可行的道路中心网络方案集，将可行的道路中心线布局方案集中的方案根据《城市道 路交通规划设计规范》规则库生成道路网络方案输出并生成道路网络方案集。
S5：人机交互展示模块，用于将道路网络方案输出至二维交互展示设备，其具体包括方案图纸生成、方案效果模拟和方案各项指标展示。
进一步的，所述步骤S1中，规划范围边界线为次干路，规划范围内只生成支路网；收集的规划范围的二维矢量数据为轮廓闭合的多边形地块，包含多边形的形状和大小信息。
进一步的，所述构建城市支路网络样本库，其具体操作步骤为通过开源数据平台采集中国城市的支路道路网络数据，输入地理信息平台；样本规划范围边界为次干路，规划范围内为支路网，样本数量为10000。
进一步的，所述构建统一量纲的锚点分布机器学习样本库，其具体操作步骤为将锚点分布样本库的矢量图像转化为1:2000比例尺，100dpi分辨率，300mm*300mm尺寸的位图图像，从而生成锚点分布机器学习样本库，样本数量为10000。
进一步的，所述步骤S2中，基于生成式对抗网络对抗训练锚点分布模型，其具体操作步骤为以高斯白噪声为输入数据，以锚点自动分布图像为输出数据，构建生成网络；以锚点自动分布图像与锚点分布机器学习样本图像为输入数据，设计损失函数，构建判别网络；所述生成网络与判别网络为卷积神经网络；通过对生成网络与判别网络进行迭代训练，使锚点自动分布图像逐渐逼近锚点分布机器学习样本图像。
进一步的，所述步骤S3中构建规则库：指标控制根据《城市道路交通规划设计规范》和《道路倒角半径规范》的规则库整理构建；
表1：不同支路网规则指标控制
控制项 控制参数范围
支路网间距 150-250m
道路红线宽度 12-15m
支路网内部倒角 10-15m
支路与外部次干路倒角 20-25m
进一步的，所述步骤S4中道路中心线布局方案是以新锚点为中心通过矩形扩张法生成对应道路中心线布局方案，其具体操作步骤为控制新的锚点分布方案以自身的每一个新锚点为中心，以相同的速率同时朝自己的四个正交方向进行正方形的扩张，当两个相邻的锚点的扩张边触碰时，或者扩张边全部超出规划范围时，则该条边停止扩张，其他边继续扩张，直到最终所有边界停止扩张，生成与锚点数量一致的矩形。整合矩形各边形成道路中心线布局，将规划范围外及与规划范围重叠的矩形边删除，将规划范围内的矩形边整合为唯一的不重叠线段。
进一步的，筛选可行的所述道路中心网络方案集，其具体操作步骤为判断通过矩形扩张法生成的道路中心线布局方案是否所有的道路中心线线段长度都在150-250m内，如果否，则废弃该方案；如果是，则将该方案输出至可行道路中心线布局方案集中。
进一步的，所述生成道路网络方案集，其具体步骤为将可行道路中心线布局方案自中心线往两侧分别扩张6-7.5m，形成12-15m宽度的道路红线，再在内部支路与支路交叉口处生成10-15m的道路红线倒角，在边界支路与次干路的交叉口处生成20-25m的道路红线倒角；将生成红线和倒角之后的道路网络方案集合，生成道路网络方案集。
进一步的，所述方案效果模拟与展示是指审查员可以通过操作杆在道路网络方案库中选择需要的道路网络方案在1920×1080分辨率55寸以上的显示设备进行展示方案图纸、方案效果模拟图和方案各项指标；所述方案效果模拟图，指以规划范围道路平面图为基础，利用建模软件对车行道和人行道进行贴图， 其中车行道为沥青纹理贴图，人行道为砖块贴图；再对道路网模型进行渲染，并利用图像编辑软件将模型渲染图与无人机航拍的真实场景进行结合，形成方案效果模拟图进行展示；所述方案各项指标包括各条道路的等级、道路红线宽度、道路红线倒角，以及道路划分的街坊边长和面积、规划范围支路网密度、“十”字路口结点占全部路口结点的比例。
本发明的有益效果：
1、本发明城市道路网络自动生成方法过程高效性：本方法通过设定城市道路网络方案的可行范围，能够在短时间内同时生成多个方案，减少人力成本，提高设计效率；
2、本发明城市道路网络自动生成方法系统仿真性：本方法应用可解释的生成式对抗网络(infoGAN)，基于城市规划道路相关规范构建道路网络规则库，在此基础上自动生成道路网络方案集，提高了方案集与真实道路网络的拟合程度，保证自动生成方案集的质量；
3、本发明城市道路网络自动生成方法成果直观性：本方法生成成果通过二维交互设备进行模拟展示，便于城市规划专业人员和管理者的沟通。
附图说明
下面结合附图对本发明作进一步的说明。
图1是本发明生成方法流程图；
图2是本发明道路自动生成规划范围示意图；
图3是本发明道路中心线布局方案筛选示意图；
图4是本发明道路自动生成方案图。
具体实施方式
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清 楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其它实施例，都属于本发明保护的范围。
一种基于人工智能的城市道路网络自动生成方法,如图1所示,自动生成方法包括以下步骤：
S1:数据获取与输入模块，用于通过搭载1920*1080分辨率镜头无人机航拍设备采集和城市开源数据平台中获取的方式采集规划范围的二维矢量数据，并输入至地理信息平台中；
规划范围边界线为次干路，如图2所示，规划范围内只生成支路网。收集的规划范围的二维矢量数据为轮廓闭合的多边形地块，包含多边形的地理坐标、形状和大小信息。
S2:机器学习模块，用于通过开源数据平台采集支路网络数据，构建城市支路网络样本库；再以支路划分的矩形质心为锚点，生成对应的锚点分布库；将锚点分布样本库的矢量图像转化为位图图像，构建统一量纲的锚点分布机器学习样本库；基于可解释的生成式对抗网络(infoGAN)，对抗训练锚点分布模型。
构建城市支路网络样本库，其具体操作步骤为通过开源数据平台采集中国城市的支路道路网络数据，输入地理信息平台。样本规划范围边界为次干路，规划范围内为支路网，样本数量为10000。
构建统一量纲的锚点分布机器学习样本库，其具体操作步骤为将锚点分布样本库的矢量图像转化为1:2000比例尺，100dpi分辨率，300mm*300mm尺寸的位图图像，从而生成锚点分布机器学习样本库，样本数量为10000。
基于可解释的生成式对抗网络(infoGAN)对抗训练锚点分布模型，其具体操作步骤为以高斯白噪声为输入数据，以锚点自动分布图像为输出数据，构建 生成网络；以锚点自动分布图像与锚点分布机器学习样本图像为输入数据，设计损失函数，构建判别网络。所述生成网络与判别网络为卷积神经网络(CNN)。通过对生成网络与判别网络进行迭代训练，使锚点自动分布图像逐渐逼近锚点分布机器学习样本图像。
S3:规则库构建模块，用于通过地理信息平台，将《城市道路交通规划设计规范》中的城市支路间距范围规范、城市道路红线规范、城市道路倒角规范输入地理信息平台，并构建规则库；
指标控制根据《城市道路交通规划设计规范》和《道路倒角半径规范》的规则库整理构建。
表1：不同支路网规则指标控制
控制项 控制参数范围
支路网间距 150-250m
道路红线宽度 12-15m
支路网内部倒角 10-15m
支路与外部次干路倒角 20-25m
S4:方案集生成模块，用于通过机器学习模块得到的锚点分布模型在规划范围内生成并分布锚点，生成锚点分布方案集；再根据锚点分布方案集中各方案的锚点生成对应的泰森多边形分布方案集；并将各泰森多边形分布方案中的泰森多边形的质心替换该多边形内的锚点作为新锚点，生成新的锚点分布方案集；再以新的锚点分布方案集中的新锚点为中心通过矩形扩张法生成对应道路中心线布局方案集；通过《城市道路交通规划设计规范》规则库筛选出可行的道路中心线布局方案集，将可行的道路中心线布局方案集中的方案根据《城市道路交通规划设计规范》规则库生成道路网络方案输出并生成道路网络方案集；
以新锚点为中心通过矩形扩张法生成对应道路中心线布局方案，其具体操作步骤为控制新的锚点分布方案以自身的每一个新锚点为中心，以相同的速率 同时朝自己的四个正交方向进行正方形的扩张，当两个相邻的锚点的扩张边触碰时，或者扩张边全部超出规划范围时，则该条边停止扩张，其他边继续扩张，直到最终所有边界停止扩张，生成与锚点数量一致的矩形。整合矩形各边形成道路中心线布局，将规划范围外及与规划范围重叠的矩形边删除，将规划范围内的矩形边整合为唯一的不重叠线段。
筛选可行的道路中心线布局方案集，其具体操作步骤为判断通过矩形扩张法生成的道路中心线布局方案是否所有的道路中心线线段长度都在150-250m内，如果否，则废弃该方案；如果是，则将该方案输出至可行道路中心线布局方案集中，如图3所示
所述生成道路网络方案集，其具体步骤为将可行道路中心线布局方案自中心线往两侧分别扩张6-7.5m，形成12-15m宽度的道路红线，再在内部支路与支路交叉口处生成10-15m的道路红线倒角，在边界支路与次干路的交叉口处生成20-25m的道路红线倒角。将生成红线和倒角之后的道路网络方案集合，生成道路网络方案集。
S5:人机交互展示模块，用于将道路网络方案输出至1920×1080分辨率55寸以上二维交互展示设备，其具体包括方案图纸生成、方案效果模拟和方案各项指标展示，如图4所示。
方案效果模拟与展示是指审查员可以通过操作杆在道路网络方案库中选择需要的道路网络方案在1920×1080分辨率55寸以上的显示设备进行展示方案图纸、方案效果模拟图和方案各项指标。所述方案效果模拟图，指以规划范围道路平面图为基础，利用建模软件对车行道和人行道进行贴图，其中车行道为沥青纹理贴图，人行道为砖块贴图；再对道路网模型进行渲染，并利用图像编辑软件将模型渲染图与无人机航拍的真实场景进行结合，形成方案效果模拟图 进行展示。所述方案各项指标包括各条道路的等级、道路红线宽度、道路红线倒角，以及道路划分的街坊边长和面积、规划范围支路网密度、“十”字路口结点占全部路口结点的比例。
在本说明书的描述中，参考术语“一个实施例”、“示例”、“具体示例”等的描述意指结合该实施例或示例描述的具体特征、结构、材料或者特点包含于本发明的至少一个实施例或示例中。在本说明书中，对上述术语的示意性表述不一定指的是相同的实施例或示例。而且，描述的具体特征、结构、材料或者特点可以在任何的一个或多个实施例或示例中以合适的方式结合。
以上显示和描述了本发明的基本原理、主要特征和本发明的优点。本行业的技术人员应该了解，本发明不受上述实施例的限制，上述实施例和说明书中描述的只是说明本发明的原理，在不脱离本发明精神和范围的前提下，本发明还会有各种变化和改进，这些变化和改进都落入要求保护的本发明范围内。

Claims (10)

  1. 一种基于人工智能的城市道路网络自动生成方法，其特征在于，生成方法包括以下步骤：
    S1：数据获取与输入模块，用于通过无人机采集和城市开源数据平台中获取的方式采集规划范围的二维矢量数据，并输入至地理信息平台中；
    S2：机器学习模块，用于通过开源数据平台采集支路网络数据，构建城市支路网络样本库；再以支路划分的矩形质心为锚点，生成对应的锚点分布库；将锚点分布样本库的矢量图像转化为位图图像，构建统一量纲的锚点分布机器学习样本库；基于生成式对抗网络，对抗训练锚点分布模型；
    S3：规则库构建模块，用于通过地理信息平台，将《城市道路交通规划设计规范》中的城市支路间距范围规范、城市道路红线规范、城市道路倒角规范输入地理信息平台，并构建规则库；
    S4：方案集生成模块，用于通过机器学习模块得到的锚点分布模型在规划范围内生成并分布锚点，生成锚点分布方案集；再根据锚点分布方案集中各方案的锚点生成对应的泰森多边形分布方案集；并将各泰森多边形分布方案中的泰森多边形的质心替换该多边形内的锚点作为新锚点，生成新的锚点分布方案集；再以新的锚点分布方案集中的新锚点为中心通过矩形扩张法生成对应道路中心线布局方案集；通过《城市道路交通规划设计规范》规则库筛选出可行的道路中心网络方案集，将可行的道路中心线布局方案集中的方案根据《城市道路交通规划设计规范》规则库生成道路网络方案输出并生成道路网络方案集；
    S5：人机交互展示模块，用于将道路网络方案输出至二维交互展示设备，其具体包括方案图纸生成、方案效果模拟和方案各项指标展示。
  2. 根据权利要求书1所述的一种基于人工智能的城市道路网络自动生成方 法，其特征在于：所述步骤S1中，规划范围边界线为次干路，规划范围内只生成支路网；收集的规划范围的二维矢量数据为轮廓闭合的多边形地块，包含多边形的形状和大小信息。
  3. 根据权利要求书1所述的一种基于人工智能的城市道路网络自动生成方法，其特征在于：所述构建城市支路网络样本库，其具体操作步骤为通过开源数据平台采集中国城市的支路道路网络数据，输入地理信息平台；样本规划范围边界为次干路，规划范围内为支路网，样本数量为10000。
  4. 根据权利要求书1所述的一种基于人工智能的城市道路网络自动生成方法，其特征在于：所述构建统一量纲的锚点分布机器学习样本库，其具体操作步骤为将锚点分布样本库的矢量图像转化为1:2000比例尺，100dpi分辨率，300mm*300mm尺寸的位图图像，从而生成锚点分布机器学习样本库，样本数量为10000。
  5. 根据权利要求书1所述的一种基于人工智能的城市道路网络自动生成方法，其特征在于：所述步骤S2中，基于生成式对抗网络对抗训练锚点分布模型，其具体操作步骤为以高斯白噪声为输入数据，以锚点自动分布图像为输出数据，构建生成网络；以锚点自动分布图像与锚点分布机器学习样本图像为输入数据，设计损失函数，构建判别网络；所述生成网络与判别网络为卷积神经网络；通过对生成网络与判别网络进行迭代训练，使锚点自动分布图像逐渐逼近锚点分布机器学习样本图像。
  6. 根据权利要求书1所述的一种基于人工智能的城市道路网络自动生成方法，其特征在于：所述步骤S3中构建规则库：指标控制根据《城市道路交通规划设计规范》和《道路倒角半径规范》的规则库整理构建；
    表1：不同支路网规则指标控制
    控制项 控制参数范围 支路网间距 150-250m 道路红线宽度 12-15m 支路网内部倒角 10-15m 支路与外部次干路倒角 20-25m
  7. 根据权利要求书1所述的一种基于人工智能的城市道路网络自动生成方法，其特征在于：所述步骤S4中道路中心线布局方案是以新锚点为中心通过矩形扩张法生成对应道路中心线布局方案，其具体操作步骤为控制新的锚点分布方案以自身的每一个新锚点为中心，以相同的速率同时朝自己的四个正交方向进行正方形的扩张，当两个相邻的锚点的扩张边触碰时，或者扩张边全部超出规划范围时，则该条边停止扩张，其他边继续扩张，直到最终所有边界停止扩张，生成与锚点数量一致的矩形，整合矩形各边形成道路中心线布局，将规划范围外及与规划范围重叠的矩形边删除，将规划范围内的矩形边整合为唯一的不重叠线段。
  8. 根据权利要求书1所述的一种基于人工智能的城市道路网络自动生成方法，其特征在于：筛选可行的所述道路中心网络方案集，其具体操作步骤为判断通过矩形扩张法生成的道路中心线布局方案是否所有的道路中心线线段长度都在150-250m内，如果否，则废弃该方案；如果是，则将该方案输出至可行道路中心线布局方案集中。
  9. 根据权利要求书1所述的一种基于人工智能的城市道路网络自动生成方法，其特征在于：所述生成道路网络方案集，其具体步骤为将可行道路中心线布局方案自中心线往两侧分别扩张6-7.5m，形成12-15m宽度的道路红线，再在内部支路与支路交叉口处生成10-15m的道路红线倒角，在边界支路与次干路的交叉口处生成20-25m的道路红线倒角；将生成红线和倒角之后的道路网络方案集合，生成道路网络方案集。
  10. 根据权利要求书1所述的一种基于人工智能的城市道路网络自动生成方法，其特征在于：所述方案效果模拟与展示是指审查员可以通过操作杆在道路网络方案库中选择需要的道路网络方案在1920×1080分辨率55寸以上的显示设备进行展示方案图纸、方案效果模拟图和方案各项指标；所述方案效果模拟图，指以规划范围道路平面图为基础，利用建模软件对车行道和人行道进行贴图，其中车行道为沥青纹理贴图，人行道为砖块贴图；再对道路网模型进行渲染，并利用图像编辑软件将模型渲染图与无人机航拍的真实场景进行结合，形成方案效果模拟图进行展示；所述方案各项指标包括各条道路的等级、道路红线宽度、道路红线倒角，以及道路划分的街坊边长和面积、规划范围支路网密度、“十”字路口结点占全部路口结点的比例。
PCT/CN2020/124318 2020-09-04 2020-10-28 一种基于人工智能的城市道路网络自动生成方法 WO2022047958A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US17/616,293 US20220309203A1 (en) 2020-09-04 2020-10-28 Artificial intelligence-based automatic generation method for urban road network

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010923489.5A CN112052547B (zh) 2020-09-04 2020-09-04 一种基于人工智能的城市道路网络自动生成方法
CN202010923489.5 2020-09-04

Publications (1)

Publication Number Publication Date
WO2022047958A1 true WO2022047958A1 (zh) 2022-03-10

Family

ID=73607061

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/124318 WO2022047958A1 (zh) 2020-09-04 2020-10-28 一种基于人工智能的城市道路网络自动生成方法

Country Status (3)

Country Link
US (1) US20220309203A1 (zh)
CN (1) CN112052547B (zh)
WO (1) WO2022047958A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116797055A (zh) * 2023-08-28 2023-09-22 日照朝力信息科技有限公司 一种基于物联网的城市道路规划方法及系统

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112651059B (zh) * 2020-12-18 2022-11-08 东南大学 一种基于人工智能的控规地块城市设计多方案生成方法
CN112683286A (zh) * 2021-03-16 2021-04-20 季华实验室 拓扑路网地图的建立方法、系统、存储介质及电子设备
CN113064958B (zh) * 2021-04-26 2021-11-23 广州筑鼎建筑与规划设计院有限公司 基于图传视频处理技术和数据分析的城市规划设计勘察数据建立处理方法
CN114297176A (zh) * 2021-12-15 2022-04-08 东南大学 基于人工智能的中国古典园林假山自动生成方法及系统
EP4357734A1 (en) * 2022-10-19 2024-04-24 Electronics and Telecommunications Research Institute Method, image processing apparatus, and system for generating road image by using two-dimensional map data
CN115935489A (zh) * 2023-01-10 2023-04-07 广东省建筑设计研究院有限公司 一种基于bim的城市道路选线三维比选方法
CN116385878B (zh) * 2023-03-29 2023-10-20 阿里巴巴（中国）有限公司 道路中心线提取方法、分布式系统、服务器和存储介质
CN116167148B (zh) * 2023-04-26 2023-07-07 青岛理工大学 基于局域微气候的城市街区形态优化方法及其系统
CN117131581B (zh) * 2023-10-26 2024-02-13 乘木科技(珠海)有限公司 一种数字孪生城市道路的构建系统及方法
CN117213471B (zh) * 2023-11-08 2024-02-02 国家电投集团科学技术研究院有限公司 露天矿区的路网图像获取方法、装置和电子设备
CN117407479A (zh) * 2023-12-13 2024-01-16 中电建水环境科技有限公司 基于gis的城市排水管网子汇水区自动快速划分方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101640001A (zh) * 2009-07-08 2010-02-03 北京交通大学 一种面向仿真系统的道路网络绘制装置与方法
CN102175256A (zh) * 2010-12-27 2011-09-07 浙江工业大学 一种基于进化树拓扑路网构建的路径规划确定方法
US8384776B2 (en) * 2009-04-22 2013-02-26 Toyota Motor Engineering And Manufacturing North America, Inc. Detection of topological structure from sensor data with application to autonomous driving in semi-structured environments
CN106096798A (zh) * 2016-07-05 2016-11-09 南京航空航天大学 一种可达性最优条件下的城市路网优化方法
CN109472390A (zh) * 2018-09-12 2019-03-15 郑颖尔 基于机器学习的规划方案智能生成方法及系统

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106023161B (zh) * 2016-05-12 2019-01-18 南京师范大学 一种破碎山脊线的自动关联方法
US10740532B1 (en) * 2018-12-20 2020-08-11 Cadence Design Systems, Inc. Route driven placement of fan-out clock drivers
CN110333714B (zh) * 2019-04-09 2022-06-10 武汉理工大学 一种无人驾驶汽车路径规划方法和装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8384776B2 (en) * 2009-04-22 2013-02-26 Toyota Motor Engineering And Manufacturing North America, Inc. Detection of topological structure from sensor data with application to autonomous driving in semi-structured environments
CN101640001A (zh) * 2009-07-08 2010-02-03 北京交通大学 一种面向仿真系统的道路网络绘制装置与方法
CN102175256A (zh) * 2010-12-27 2011-09-07 浙江工业大学 一种基于进化树拓扑路网构建的路径规划确定方法
CN106096798A (zh) * 2016-07-05 2016-11-09 南京航空航天大学 一种可达性最优条件下的城市路网优化方法
CN109472390A (zh) * 2018-09-12 2019-03-15 郑颖尔 基于机器学习的规划方案智能生成方法及系统

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116797055A (zh) * 2023-08-28 2023-09-22 日照朝力信息科技有限公司 一种基于物联网的城市道路规划方法及系统
CN116797055B (zh) * 2023-08-28 2023-11-07 日照朝力信息科技有限公司 一种基于物联网的城市道路规划方法及系统

Also Published As

Publication number Publication date
CN112052547A (zh) 2020-12-08
US20220309203A1 (en) 2022-09-29
CN112052547B (zh) 2021-07-23

Similar Documents

Publication Publication Date Title
WO2022047958A1 (zh) 一种基于人工智能的城市道路网络自动生成方法
CN112651059B (zh) 一种基于人工智能的控规地块城市设计多方案生成方法
Kostakos et al. Traffic in the smart city: Exploring city-wide sensing for traffic control center augmentation
WO2017101277A1 (zh) 一种基于互联网词频的城市认知地图生成方法
CN106599332A (zh) 一种三维数字方案辅助设计与展现方法
CN106126816B (zh) 重复建筑自动感知下的大规模als建筑点云建模方法
Wang et al. Generative urban design using shape grammar and block morphological analysis
Luo et al. A rule-based city modeling method for supporting district protective planning
Luo et al. Analysis of urban ventilation potential using rule-based modeling
CN113932810B (zh) 基于多源地理信息模型的城市轨道三维导航地图优化方法
Zhou et al. Green urban garden landscape simulation platform based on high-resolution image recognition technology and GIS
CN113032877A (zh) 基于bim技术施工场地临建方案的优化方法
Wang et al. Intelligent traffic analytics: From monitoring to controlling
CN115758532A (zh) 一种方格网式城市道路网络人工智能自动生成方法
Nasir et al. Conceptual model of 3D asset management based on myspata to support smart city application in Malaysia
Bianchi et al. An innovational digital tool in GIS procedure: Mapping adriatic coast in abruzzo region to support design of slow mobility routes
Cheng Automated site layout of temporary construction facilities using geographic information systems (GIS)
Gao et al. A procedural generation method of urban roads based on osm
Sabri et al. An innovative tool for optimised development envelope control (dec) analysis and scenario building in digital twin
Guzzetti et al. Built environment: modelling the urban space
CN111753110A (zh) 一种城市建设地图统计实现方法
Kazemi Knowledge-based generalisation of road networks
CN114186718B (zh) 一种基于卫星影像的输变电工程智能管理方法及系统
CN113688873B (zh) 一种具有直观交互能力的矢量路网生成方法
Liu Research on Rapid Parameterized Modeling of CityEngine in the Application of Smart Campus Platform

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20952200

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20952200

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 20952200

Country of ref document: EP

Kind code of ref document: A1