A method and system for constructing a three-dimensional urban road space

Abstract

The application belongs to the technical field of road three-dimensional modeling, and discloses a construction method and system for urban road space three-dimensionalization, wherein the method comprises the following steps: acquiring road high-precision two-dimensional map information and longitudinal distribution information; establishing a high-precision three-dimensional terrain scene, and performing road screening and parameter setting based on the two-dimensional map information and the longitudinal distribution information; constructing a three-dimensional model of road space; acquiring a three-dimensional real scene model of a target area by using an unmanned aerial vehicle oblique photography technology; and performing deep learning matching to further improve the construction model precision. By combining the three-dimensional space model with the three-dimensional real scene model acquired by the oblique photography, the problems of single three-dimensional urban road network model, low precision, and non-compliance with actual conditions are solved, the construction of various types of urban road space three-dimensionalization can be well realized, and the generated urban three-dimensional road surface model can better meet the actual application requirements in terms of spatial precision and spatial form.

Description

Technical Field

[0001] This application relates to the field of road 3D modeling technology, and more specifically, to a method and system for constructing 3D urban road space. Background Technology

[0002] With the continuous development of urbanization, transportation networks are becoming increasingly sophisticated. Elevated roads, subways, underground passages, and surface roads intertwine to create a complex three-dimensional transportation network. Two-dimensional maps are no longer sufficient to intuitively represent such complex traffic characteristics. Therefore, three-dimensional visualization technology has emerged. Urban roads, as spatial links connecting different functional areas of a city and the main carriers of urban spatial information flow, have three-dimensional models that are an indispensable and important component of digital cities and three-dimensional city (3DCM) models. A road 3D model generally consists of a road surface model and its associated structure models, with the road surface model usually being the main body of the road 3D model.

[0003] Due to the significant differences in spatial structure and spatial information between urban roads and general intercity highways, existing methods for constructing 3D road surface models cannot fully meet the practical application requirements of 3D modeling of urban roads in terms of model refinement and overall data volume. Summary of the Invention

[0004] To address the aforementioned issues, this application provides a method and system for constructing three-dimensional urban road space.

[0005] This application provides a method and system for constructing three-dimensional urban road space, which adopts the following technical solution: A method for constructing a three-dimensional urban road space, the method comprising: Obtain high-precision two-dimensional map information of roads; Obtain road elevation information and longitudinal distribution information of bridges, tunnels, or intersecting and overlapping roads; A high-precision 3D terrain scene is established, and road screening and parameter settings are performed based on 2D map information and longitudinal distribution information to form the initial linear data of roads; By analyzing and integrating road parameters with 3D scene coordinate data, a 3D model of the road space is constructed. Using UAV oblique photography technology to obtain a 3D reality model of the target area; By using deep learning to match the physical model with the 3D model of the road space, the accuracy of the constructed model can be further improved.

[0006] Furthermore, the acquisition of high-precision two-dimensional road map information includes: Obtain information on the lanes and width of the road; Obtain information on road type and direction; Obtain information on traffic facilities in the middle and at the edges of roads.

[0007] The above technical solutions enable more refined acquisition of road information, allowing for a more intuitive and visual understanding of this road data, and further improving the accuracy of post-model building and data matching.

[0008] Furthermore, the step of performing deep learning matching between the entity model and the 3D model of the road space includes: The feature points of the real-world model obtained by oblique photography are associated with those of the 3D model of the road space. By finding corresponding feature points, coarse registration of the spatial point cloud is performed to obtain the complete point cloud result; The point cloud results are then finely registered to obtain a fused point cloud model. Irregular triangular mesh construction and texture mapping are performed on the fused point cloud model; Output a 3D fusion model.

[0009] By combining the physical model generated by the above technical solution with the three-dimensional model of the road space, the fineness and accuracy of the three-dimensional model are further improved, avoiding problems such as mismatch between the three-dimensional model and the actual situation due to data deviation or data lag.

[0010] This application also provides a three-dimensional construction system for urban road space, including: The data acquisition module is used to acquire high-precision two-dimensional map information, elevation information, and longitudinal distribution information of bridges, tunnels, or intersecting and overlapping roads to obtain a discrete point dataset of road information. The data processing module is used to analyze the discrete point dataset of collected road information and to analyze the correlation between discrete points; The data fusion module is used to fuse the collected two-dimensional road information data; The data separation module is used to parse the topological relationships of road information data and separate the node data of each road segment from the classified and merged road segment data; The road model building module analyzes and processes the road segment data and node data, and builds a three-dimensional road model based on the spatial characteristics of the three-dimensional road and road elevation data. The deep learning matching module performs deep learning matching and optimization between the entity model and the 3D model of the road space to obtain a high-precision 3D road model.

[0011] The storage and conversion module is used to store the generated 3D road model and convert its file format.

[0012] Furthermore, the road model building module is also used for road area texture mapping, adding road structures and ancillary traffic facilities.

[0013] The above technical solutions enrich road information and further improve the precision of the 3D model.

[0014] In summary, this application has the following beneficial technical effects: The method for constructing three-dimensional urban road space provided in this application combines a three-dimensional spatial model with a three-dimensional real-world model obtained by oblique photography, which solves the problems of single three-dimensional urban road network models, low accuracy, and non-compliance with actual conditions. It can better realize the three-dimensional construction of various types of urban road surface space, and the generated urban three-dimensional road surface model can better meet the needs of practical applications in terms of spatial accuracy and spatial morphology. Attached Figure Description

[0015] Figure 1 This is a flowchart illustrating an embodiment of the method for constructing three-dimensional urban road space according to this application. Figure 2 A flowchart illustrating the process of deep learning matching between a physical model and a 3D model of the road space; Figure 3 This is a structural schematic diagram of an embodiment of the urban road space three-dimensional construction system of this application. Detailed Implementation

[0016] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0017] The term "exemplary" as used herein means "serving as an example, embodiment, or illustration." Any embodiment illustrated herein as "exemplary" is not necessarily to be construed as superior or better than other embodiments. Furthermore, numerous specific details are set forth in the following detailed description to better illustrate this application. Those skilled in the art will understand that this application can be practiced without certain specific details. In some instances, methods, means, elements, and circuits well known to those skilled in the art have not been described in detail in order to highlight the spirit of this disclosure.

[0018] Example 1: The following is in conjunction with the appendix Figure 1-3 This application will be described in further detail.

[0019] This application discloses a method for constructing a three-dimensional urban road space, including: S1: Obtain high-precision two-dimensional map information of the road; S2: Obtain road elevation information and longitudinal distribution information of bridges, tunnels, or intersecting and overlapping roads; S3: Establish a high-precision 3D terrain scene, and perform road screening and parameter setting based on 2D map information and longitudinal distribution information to form the initial linear data of roads; S4: Analyze and integrate road parameters with 3D scene coordinate data to construct a 3D model of the road space; S5: Use UAV oblique photography technology to obtain a 3D real-world model of the target area; S6: Deep learning is used to match the physical model with the 3D model of the road space to further improve the accuracy of the construction model.

[0020] The acquisition of high-precision two-dimensional road map information includes: a. Obtain information on the lanes and width of the road; b. Obtain information on the type and direction of the road; c. Obtain information on traffic facilities in the middle and at the edges of the road.

[0021] The above technical solutions enable more refined acquisition of road information, allowing for a more intuitive and visual understanding of this road data, and further improving the accuracy of post-model building and data matching.

[0022] Please see Figure 2 The steps for deep learning matching between the entity model and the 3D model of the road space include: S601: Associate the feature points of the real-world model obtained by oblique photography with the feature points of the road space 3D model; S602: Coarse registration of spatial point clouds is performed by finding corresponding feature points to obtain complete point cloud results; S603: Perform fine registration on the point cloud results to obtain a fused point cloud model; S604: Perform irregular triangular mesh construction and texture mapping on the fused point cloud model; S605: Outputs a 3D fusion model.

[0023] By combining the physical model generated by oblique photogrammetry with the 3D road space model, the fineness and accuracy of the 3D model are further improved, avoiding problems such as mismatch between the 3D model and the actual situation due to data deviation or data lag.

[0024] Please see Figure 3 This embodiment also provides a three-dimensional urban road space construction system, including: The data acquisition module is used to acquire high-precision two-dimensional map information, elevation information, and longitudinal distribution information of bridges, tunnels, or intersecting and overlapping roads to obtain a discrete point dataset of road information. The data processing module is used to analyze the discrete point dataset of collected road information and to analyze the correlation between discrete points; The data fusion module is used to fuse the collected two-dimensional road information data; The data separation module is used to parse the topological relationships of road information data and separate the node data of each road segment from the classified and merged road segment data; The road model building module analyzes and processes the road segment data and node data, and builds a three-dimensional road model based on the spatial characteristics of the three-dimensional road and road elevation data. The deep learning matching module performs deep learning matching and optimization between the entity model and the 3D model of the road space to obtain a high-precision 3D road model.

[0025] The storage and conversion module is used to store the generated 3D road model and convert its file format.

[0026] Furthermore, the road model building module is also used for road area texture mapping, adding road structures and ancillary traffic facilities, making the road information richer and further improving the precision of the 3D model.

[0027] This application combines a three-dimensional spatial model with a three-dimensional real-world model obtained by oblique photography, which solves the problems of single three-dimensional city-level road network models, low accuracy, and non-compliance with actual conditions. It can better realize the three-dimensional construction of various road surface spaces in urban areas, and the generated urban three-dimensional road surface model can better meet the needs of practical applications in terms of spatial accuracy and spatial morphology.

[0028] The functions achievable by the method for constructing three-dimensional urban road space are all performed by computer equipment, which includes one or more processors and one or more memories. The one or more memories store at least one piece of program code, which is loaded and executed by the one or more processors to realize the functions of the method for constructing three-dimensional urban road space.

[0029] The processor fetches instructions from memory one by one, analyzes the instructions, and then performs the corresponding operations according to the instructions, generating a series of control commands to enable the various parts of the computer to act automatically, continuously, and in a coordinated manner, forming an organic whole. This enables the input of programs and data, as well as the calculation and output of results. The arithmetic or logical operations generated in this process are all performed by the arithmetic unit. The memory includes a read-only memory (ROM), which is used to store computer programs. The memory is equipped with external protection devices.

[0030] For example, a computer program can be divided into one or more modules, one or more of which are stored in memory and executed by a processor to perform the present invention. The one or more modules can be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in a terminal device.

[0031] Those skilled in the art will understand that the above description of the service equipment is merely an example and does not constitute a limitation on the terminal equipment. It may include more or fewer components than described above, or a combination of certain components, or different components, such as input / output devices, network access devices, buses, etc.

[0032] The processor referred to can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. This processor is the control center of the terminal device, connecting various parts of the user terminal via various interfaces and lines.

[0033] The aforementioned memory can be used to store computer programs and / or modules. The aforementioned processor implements various functions of the aforementioned terminal device by running or executing the computer programs and / or modules stored in the memory, and by calling data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as information collection template display function, product information publishing function, etc.); the data storage area may store data created based on the use of the berth status display system (such as product information collection templates corresponding to different product types, product information that different product providers need to publish, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0034] If the modules / units integrated into the terminal device are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the modules / units in the systems of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the functions of the various system embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0035] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0036] The above are all preferred embodiments of this application, and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the structure, shape and principle of this application should be covered within the scope of protection of this application.

Claims

1. A method for constructing a three-dimensional urban road space, characterized in that, The method includes: Obtain high-precision two-dimensional map information of roads; Obtain road elevation information and longitudinal distribution information of bridges, tunnels, or intersecting and overlapping roads; A high-precision 3D terrain scene is established, and road screening and parameter settings are performed based on 2D map information and longitudinal distribution information to form the initial linear data of roads; By analyzing and integrating road parameters with 3D scene coordinate data, a 3D model of the road space is constructed. Using UAV oblique photography technology to obtain a 3D reality model of the target area; Deep learning is used to match the physical model with the 3D model of the road space to further improve the accuracy of the construction model; The acquisition of high-precision two-dimensional road map information includes: Obtain information on the lanes and width of the road; Obtain information on road type and direction; Obtain information on traffic facilities in the middle and at the edges of the road; The steps for deep learning matching of the entity model with the 3D model of the road space include: The feature points of the real-world model obtained by oblique photography are associated with those of the 3D model of the road space. By finding corresponding feature points for coarse registration, a complete point cloud result is obtained; The point cloud results are then finely registered to obtain a fused point cloud model. Irregular triangular mesh construction and texture mapping are performed on the fused point cloud model; Output a 3D fusion model.

2. A three-dimensional construction system for urban road space, characterized in that, include: The data acquisition module is used to acquire high-precision two-dimensional map information, elevation information, and longitudinal distribution information of bridges, tunnels, or intersecting and overlapping roads to obtain a discrete point dataset of road information. The data processing module is used to analyze the discrete point dataset of collected road information and to analyze the correlation between discrete points; The data fusion module is used to fuse the collected two-dimensional road information data; The data separation module is used to parse the topological relationships of road information data and separate the node data of each road segment from the classified and merged road segment data; The road model building module analyzes and processes the road segment data and node data, and builds a three-dimensional road model based on the spatial characteristics of the three-dimensional road and road elevation data. The deep learning matching module performs deep learning matching and optimization between the entity model and the 3D model of the road space to obtain a high-precision 3D road model. The storage module is used to store the generated 3D road model; The acquisition of high-precision two-dimensional road map information includes: Obtain information on the lanes and width of the road; Obtain information on road type and direction; Obtain information on traffic facilities in the middle and at the edges of the road; The steps for deep learning matching of the entity model with the 3D model of the road space include: The feature points of the real-world model obtained by oblique photography are associated with those of the 3D model of the road space. By finding corresponding feature points for coarse registration, a complete point cloud result is obtained; The point cloud results are then finely registered to obtain a fused point cloud model. Irregular triangular mesh construction and texture mapping are performed on the fused point cloud model; Output a 3D fusion model.

3. The urban road space three-dimensional construction system according to claim 2, characterized in that: The road model building module is also used for road area texture mapping, adding road structures and ancillary traffic facilities.

Images