Urban three-dimensional space parameter capturing and rapid modeling method and system

Abstract

The invention discloses an urban three-dimensional space parameter capturing and rapid modeling method and system, and the method comprises the steps: remotely controlling an unmanned aerial vehicle carrying an infrared imaging high-definition camera to carry out the aerial photographing of the global space of a target city, and obtaining an urban refined aerial photographing image; processing the urban refined aerial photo to obtain urban three-dimensional space parameters; classifying the city density data and the city height data by using a clustering algorithm to obtain a clustering result; performing deep recognition on the urban refined aerial image based on a clustering result to realize urban complex geometrical morphology low-dimension processing to obtain an urban average geometrical morphology height; quickly constructing an urban three-dimensional space geometric model based on the clustering result and the urban average geometric morphology height; and predicting and displaying the urban physical environment high-resolution distribution result of the target city. The method is suitable for rapid construction of a three-dimensional space geometric model of a city of any scale and rapid simulation of the physical environment, has universality, and has important significance for reducing the simulation cost of the urban physical environment and realizing sustainable development of the urban environment.

Description

Technical Field

[0001] The invention belongs to the technical field of urban physical environment simulation, and in particular relates to a method and system for capturing and rapidly modeling urban three-dimensional space parameters based on aerial images. Background Art

[0002] The rapid development of urbanization is accompanied by the diversification and density of urban geometric forms, which makes the physical environment parameters of cities show uneven distribution patterns, which easily leads to environmental problems such as high temperature heat waves and air pollution. This not only poses a threat to the life and health of urban residents (such as increasing the incidence and even mortality of cardiovascular and respiratory diseases), but also sharply increases energy consumption and carbon emissions, affecting the sustainable development of cities. Therefore, exploring the correlation between urban form and urban physical environment parameters is of great significance to improving urban environmental problems.

[0003] The simulation prediction method based on computational fluid dynamics is a commonly used technical means to explore the correlation between urban morphology and urban physical environment parameters. This method includes steps such as geometric model construction, spatial grid division, boundary condition definition and environmental parameter calculation. Given the complex and dense characteristics of urban geometry, existing simulation prediction methods often face problems such as long time and high cost in high-precision geometric model construction and grid division. For example, a detailed simulation of the full-scale physical environment of a city takes at least 1-3 months, which also greatly increases the cost of simulation prediction.

[0004] Therefore, how to efficiently capture the three-dimensional spatial parameters of the city and build a rapid modeling system is of great significance to reducing the cost of urban physical environment simulation and achieving sustainable development of the urban environment. Summary of the invention

[0005] The purpose of the present invention is to provide a method and system for capturing and rapidly modeling urban three-dimensional spatial parameters, so as to realize rapid construction of complex urban geometric models and rapid simulation of physical environments, thereby helping to reduce the cost of urban physical environment simulation.

[0006] In order to solve the above technical problems, the present invention is implemented through the following technical solutions: A method for capturing and rapidly modeling urban three-dimensional space parameters comprises the following steps: S100, remotely control an unmanned aerial vehicle equipped with an infrared imaging high-definition camera to take aerial photos of the target city and obtain detailed aerial photos of the city; S200, processing the acquired refined aerial photograph of the city to obtain three-dimensional space parameters of the city, wherein the three-dimensional space parameters of the city include city density data and city height data; S300, using a clustering algorithm to classify the obtained urban density data and urban height data, thereby obtaining a regional division result of the urban horizontal dimension and a level division result of the urban vertical dimension; S400, based on the obtained results of the city horizontal dimension area division and the city vertical dimension level division, deep recognition is performed on the city refined aerial image to achieve low-dimensional processing of the city's complex geometric form, thereby obtaining the average geometric form height of the city; S500, based on the city horizontal dimension area division result, the city vertical dimension level division result and the city average geometric form height, quickly construct an urban three-dimensional space geometric model of the target city; S600: Use the constructed three-dimensional urban space geometric model to predict the high-resolution distribution results of the urban physical environment of the target city and display the prediction results.

[0007] Furthermore, in step S100, the refined aerial image of the city includes: a digital surface model of the city, a digital ground model and their corresponding aerial thermal images.

[0008] Furthermore, in step S200, the method for processing the city's refined aerial photography is: S201, performing image segmentation and classification processing on the aerial thermal image, so as to extract the urban geometry and structural shadows of the target city; S202: Combining the digital surface model with the digital ground model to efficiently capture urban density data and urban height data.

[0009] Furthermore, in step S300, the method for classifying the city density data and the city height data is: S301, first clustering the urban density data (in the x and y directions), and dividing the urban horizontal dimension into regions according to the density of the urban layout; S302, then based on the urban area division, further clustering the height data (z direction) to achieve the urban vertical dimension level division; S303. Finally, the clustering results of arrangement category m and height category n are obtained. The arrangement category m represents the regional division result of the city's horizontal dimension, and the height category n represents the level division result of the city's vertical dimension.

[0010] Furthermore, in step S400, the method for low-dimensional processing of the complex geometric form of the city is: S401, according to the obtained city horizontal dimension area division result and city vertical dimension level division result, select a color and its corresponding RGB value to represent a cluster, that is, there are m×n colors in the cluster result; S402, for a divided area with densely arranged buildings, the area is divided into small blocks based on the size of a small block; For the divided areas with sparsely arranged buildings, the area is divided into small blocks based on the size of medium-sized blocks; S403, identifying and counting the pixel RGB values ​​corresponding to each small block in the densely arranged and sparsely arranged building division areas, calculating the proportion of each color in each small block, and taking the geometric height in the block corresponding to the maximum proportion as the average geometric height of the block.

[0011] Furthermore, in step S500, the method for quickly building the urban three-dimensional space geometric model is: S501, collecting the city horizontal dimension area division result, the city vertical dimension level division result and the city average geometric height, and using them as the city three-dimensional space geometric model data for modeling; S502: extracting and normalizing the data features of the urban three-dimensional space geometric model data using a modal recognition algorithm, thereby constructing a homogenized data set and uploading it to a cloud service platform; S503, encoding and converting the urban three-dimensional space geometric model data, and implanting a finite volume grid algorithm, and further combining with a fluid dynamics (CFD) calculation software to achieve adaptive and rapid modeling of urban geometric morphology.

[0012] Furthermore, in step S600, the prediction method of the urban physical environment is: S601. Use the built urban three-dimensional space geometric model and fluid dynamics (CFD) numerical simulation software to quickly predict the urban physical environment of the target city and obtain the prediction results; S602, comparing the prediction results with the results of capturing the digital surface and ground thermal images of the city; when the error exceeds a set percentage threshold, clustering the three-dimensional space of the city is performed again and the physical environment is predicted until the error is lower than the set percentage threshold; S603. Finally, the urban physical environment prediction results are visualized.

[0013] A system for capturing and rapidly modeling urban three-dimensional space parameters, comprising: An unmanned aerial vehicle equipped with a high-definition infrared imaging camera and capable of remote control is responsible for remote aerial photography of the target city or region and collecting detailed aerial images of the target city or region; The geometric model data processing integrated system is responsible for adopting the above-mentioned urban geometric form rapid modeling and physical environment simulation corresponding methods to carry out urban geometric form rapid modeling and physical environment simulation for the target city or region.

[0014] A computer device includes: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus, and the memory is used to store at least one executable instruction, wherein the executable instruction enables the processor to execute operations corresponding to the above-mentioned urban three-dimensional space parameter capture and rapid modeling method.

[0015] A computer-readable storage medium stores at least one executable instruction, and the executable instruction enables a processor to execute operations corresponding to the above-mentioned urban three-dimensional space parameter capture and rapid modeling method.

[0016] The beneficial effects of the present invention are: 1. The present invention proposes a rapid modeling system for complex three-dimensional urban space, which significantly reduces the cost of global-scale urban simulation prediction by performing low-dimensional data processing on complex geometric shapes.

[0017] 2. The present invention is based on a rapid modeling system, which realizes high-resolution physical environment visualization and dynamic display, can ensure that the prediction accuracy of global environmental parameters is less than 10%, and can provide refined prediction data at any horizontal position and vertical height in the city in real time.

[0018] 3. The urban three-dimensional space parameter capture and rapid modeling method and system proposed in the present invention are suitable for the rapid construction of three-dimensional space geometric models and rapid simulation of physical environments in cities of any size. They are universal and have important significance for reducing the cost of urban physical environment simulation and achieving sustainable development of urban environment.

[0019] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the invention and implement it according to the contents of the specification, the following is a detailed description of the preferred embodiments of the present invention in conjunction with the accompanying drawings. The specific implementation of the present invention is given in detail by the following embodiments and their accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings: Figure 1 It is a schematic diagram of the system framework and step flow of the present invention.

[0021] Figure 2 This is the urban building form clustering result obtained by the method of the present invention.

[0022] Figure 3 It is the average geometric height result obtained in the method of the present invention.

[0023] Figure 4 It is the urban physical environment prediction result obtained by the method of the present invention. DETAILED DESCRIPTION

[0024] The preferred embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings so that the purpose, features and advantages of the invention can be more clearly understood. It should be understood that the embodiments shown in the accompanying drawings are not intended to limit the scope of the present invention, but are only intended to illustrate the essential spirit of the technical solution of the present invention.

[0025] In the following description, certain specific details are set forth for the purpose of illustrating various disclosed embodiments to provide a thorough understanding of the various disclosed embodiments. However, those skilled in the relevant art will recognize that the embodiments may be practiced without one or more of these specific details. In other cases, well-known devices, structures, and techniques associated with the present application may not be shown or described in detail to avoid unnecessarily obscuring the description of the embodiments.

[0026] Unless the context requires otherwise, throughout the specification and claims, the word "comprise" and variations such as "include" and "have" should be construed in an open, inclusive sense, ie, should be interpreted as "including, but not limited to."

[0027] References throughout the specification to "one embodiment" or "an embodiment" indicate that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment. Thus, the appearances of "in one embodiment" or "in an embodiment" in various places throughout the specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any manner in one or more embodiments.

[0028] As used in this specification and the appended claims, the singular forms "a," "an," and "the" include plural referents unless the context clearly dictates otherwise. It should be noted that the term "or" is generally employed in its sense including "and / or" unless the context clearly dictates otherwise.

[0029] In addition, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0030] See also Figure 1 As shown, a method for capturing and rapidly modeling urban three-dimensional space parameters comprises the following steps: S100, remotely controlling an unmanned aerial vehicle 1 equipped with an infrared imaging high-definition camera 2 to take aerial photos of the global space of a target city to obtain a detailed aerial photo of the city.

[0031] The detailed aerial image of the city includes: a digital surface model of the city, a digital ground model and its corresponding aerial thermal image.

[0032] S200: Process the acquired refined aerial photos of the city to obtain the three-dimensional space parameters of the city, wherein the three-dimensional space parameters of the city include the city density data and the city height data. The specific method is: The aerial thermal images are subjected to image segmentation and classification processing, so as to extract the urban geometry and structural shadows of the target city, and then the digital surface model and the digital ground model are combined to realize the efficient capture of urban density data and urban height data.

[0033] S300: Using a clustering algorithm, the obtained urban density data and urban height data are classified to obtain the urban horizontal dimension regional division results and the urban vertical dimension level division results. The specific method is: First, the urban density data (x and y directions) are clustered, and the urban horizontal dimension area division is carried out according to the density of the urban layout; then, based on the urban area division, the height data (z direction) is further clustered to realize the urban vertical dimension level division; finally, the clustering results of arrangement category m and height category n are obtained, and the arrangement category m represents the urban horizontal dimension area division result, and the height category n represents the urban vertical dimension level division result.

[0034] The specific calculation formula is as follows: Given a data sample: ; (2) Select the number of clusters based on the sum of squared errors (SSE): ; (3) The shortest distance between sample data and centroid As a principle, select the initial cluster center; (4) Calculate the distance between the sample data and each cluster center and assign it to the cluster with the closest distance: ; (5) Calculate the average value of each cluster sample data to obtain the new cluster center; (6) Repeat steps (4) and (5) until the sample data distribution remains unchanged.

[0035] S400: Based on the obtained city horizontal dimension area division results and city vertical dimension level division results, perform depth recognition on the city refined aerial image to achieve low-dimensional processing of the city's complex geometric form, thereby obtaining the average geometric form height of the city. The specific method is: According to the obtained city horizontal dimension regional division results and city vertical dimension level division results (arrangement category m, height category n), a color and its corresponding RGB value are selected to represent a cluster, that is, there are a total of m×n colors in the cluster results; For areas with densely arranged buildings, the area is divided into small blocks based on the size of small blocks (such as 180m); for areas with sparsely arranged buildings, the area is divided into small blocks based on the size of medium blocks (such as 400m); Identify and count the pixel RGB values ​​corresponding to each small block in the densely arranged and sparsely populated building division areas, calculate the proportion of each color in each small block, and take the geometric height in the block corresponding to the maximum proportion as the average geometric height of the block.

[0036] S500: Based on the horizontal dimension area division result of the city, the vertical dimension level division result of the city and the average geometric height of the city, a three-dimensional urban space geometric model of the target city is quickly constructed. The specific method is: Collect the results of the horizontal dimension area division of the city, the results of the vertical dimension level division of the city and the average geometric height of the city, and use them as the urban three-dimensional space geometric model data for modeling; Using a modal recognition algorithm, the data features of the urban three-dimensional spatial geometric model data are extracted and normalized, thereby constructing a homogenized data set and uploading it to a cloud service platform; The urban three-dimensional space geometric model data is encoded and transformed, and a finite volume mesh algorithm is implanted, and further combined with the OpenFOAM open source software platform to achieve adaptive and rapid modeling of urban geometric morphology.

[0037] S600: Use the constructed urban three-dimensional spatial geometric model to predict the high-resolution distribution results of the urban physical environment of the target city and display the prediction results. The specific method is: Using the built urban three-dimensional space geometric model and fluid dynamics (CFD) numerical simulation software, the urban physical environment of the target city is quickly predicted to obtain the prediction results; the prediction results are compared with the urban digital surface and ground thermal image capture results; when the error exceeds the set percentage threshold (such as 10%), the urban three-dimensional space is clustered and divided again and the physical environment is predicted until the error is lower than the set percentage threshold (such as 10%); finally, the urban physical environment prediction results are visualized.

[0038] Take Nanjing Xinjiekou and its surrounding areas as an example, and refer to the method of the present invention to implement the following steps: 1) Remotely control an unmanned aerial vehicle equipped with an infrared imaging high-definition camera to take aerial photos of Nanjing Xinjiekou and its surrounding areas, obtain refined aerial images, perform image segmentation and classification on the refined aerial images, extract geometric shapes and their shadows, and obtain building height and density data of Nanjing Xinjiekou and its surrounding areas.

[0039] 2) Cluster the density data and divide them into regions in the horizontal dimension. On this basis, further cluster the height data and divide them into levels in the vertical dimension. See Figure 2 As shown, the final clustering result of arrangement category m and height category n is obtained.

[0040] 3) Identify the RGB values ​​of the three cluster colors in the obtained clustering results and calculate the color proportion of each area, see Figure 3 As shown, the geometric height in the block corresponding to the maximum proportion is taken as the average geometric height of the block.

[0041] 4) Based on the urban area division results in step 2) and the average geometric height in step 3), quickly build a three-dimensional urban spatial geometric model, and then predict the high-resolution distribution results of the urban physical environment, and refer to Figure 4 The prediction results are shown in FIG. 1 . This embodiment reduces the computation cost by 90% and the computation error by 8.4%.

[0042] The present invention also provides a system for capturing and rapidly modeling urban three-dimensional space parameters, including: an unmanned aerial vehicle 1 equipped with an infrared imaging high-definition camera 2 and capable of remote control, and a geometric model data processing integrated system. The remotely controlled unmanned aerial vehicle equipped with an infrared imaging high-definition camera is responsible for remotely photographing the target city or region and collecting detailed aerial photos of the target city or region; The geometric model data processing integrated system is responsible for adopting the above-mentioned urban geometric form rapid modeling and physical environment simulation corresponding methods to perform urban geometric form rapid modeling and physical environment simulation on the target city or region.

[0043] The present invention also provides a computer device, comprising: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus, and the memory is used to store at least one executable instruction, wherein the executable instruction enables the processor to execute operations corresponding to the above-mentioned urban three-dimensional space parameter capture and rapid modeling method.

[0044] The present invention also provides a computer-readable storage medium, in which at least one executable instruction is stored, and the executable instruction enables a processor to execute operations corresponding to the above-mentioned urban three-dimensional space parameter capture and rapid modeling method.

[0045] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for capturing and rapidly modeling urban three-dimensional space parameters, characterized in that: The steps include: S100, remotely control an unmanned aerial vehicle equipped with an infrared imaging high-definition camera to take aerial photos of the target city and obtain detailed aerial photos of the city; S200, processing the acquired refined aerial photograph of the city to obtain three-dimensional space parameters of the city, wherein the three-dimensional space parameters of the city include city density data and city height data; S300, using a clustering algorithm to classify the obtained urban density data and urban height data, thereby obtaining a regional division result of the urban horizontal dimension and a level division result of the urban vertical dimension; S400, based on the obtained results of the city horizontal dimension area division and the city vertical dimension level division, deep recognition is performed on the city refined aerial image to achieve low-dimensional processing of the city's complex geometric form, thereby obtaining the average geometric form height of the city; S500, based on the city horizontal dimension area division result, the city vertical dimension level division result and the city average geometric form height, quickly construct an urban three-dimensional space geometric model of the target city; S600: Use the constructed three-dimensional urban space geometric model to predict the high-resolution distribution results of the urban physical environment of the target city and display the prediction results.

2. The urban three-dimensional space parameter capture and rapid modeling method according to claim 1 is characterized in that: In step S100, the refined aerial image of the city includes: a digital surface model of the city, a digital ground model and their corresponding aerial thermal images.

3. The urban three-dimensional space parameter capture and rapid modeling method according to claim 2 is characterized in that: In step S200, the method for processing the city's refined aerial photography is: S201, performing image segmentation and classification processing on the aerial thermal image, so as to extract the urban geometry and structural shadows of the target city; S202: Combining the digital surface model with the digital ground model to efficiently capture urban density data and urban height data.

4. The urban three-dimensional space parameter capture and rapid modeling method according to claim 1 is characterized in that: In step S300, the method for classifying the city density data and the city height data is: S301, first clustering the urban density data, and dividing the urban horizontal dimension into regions according to the density of urban layout; S302, then based on the urban area division, further clustering the height data to achieve the urban vertical dimension level division; S303. Finally, the clustering results of arrangement category m and height category n are obtained. The arrangement category m represents the regional division result of the city's horizontal dimension, and the height category n represents the level division result of the city's vertical dimension.

5. The method for capturing and rapidly modeling urban three-dimensional space parameters according to claim 4 is characterized in that: In step S400, the method for low-dimensional processing of complex urban geometric forms is: S401, according to the obtained city horizontal dimension area division result and city vertical dimension level division result, select a color and its corresponding RGB value to represent a cluster, that is, there are m×n colors in the cluster result; S402, for a divided area with densely arranged buildings, the area is divided into small blocks based on the size of a small block; For the divided areas with sparsely arranged buildings, the area is divided into small blocks based on the size of medium-sized blocks; S403, identifying and counting the pixel RGB values ​​corresponding to each small block in the densely arranged and sparsely arranged building division areas, calculating the proportion of each color in each small block, and taking the geometric height in the block corresponding to the maximum proportion as the average geometric height of the block.

6. The urban three-dimensional space parameter capture and rapid modeling method according to claim 1 is characterized in that: In step S500, the method for quickly building the urban three-dimensional space geometric model is: S501, collecting the city horizontal dimension area division result, the city vertical dimension level division result and the city average geometric height, and using them as the city three-dimensional space geometric model data for modeling; S502: extracting and normalizing the data features of the urban three-dimensional space geometric model data using a modal recognition algorithm, thereby constructing a homogenized data set and uploading it to a cloud service platform; S503, encoding and converting the urban three-dimensional space geometric model data, and implanting a finite volume grid algorithm, and further combining with fluid mechanics calculation software to achieve adaptive and rapid modeling of urban geometric morphology.

7. The urban three-dimensional space parameter capture and rapid modeling method according to claim 1 is characterized in that: In step S600, the method for predicting the urban physical environment is: S601. Use the built urban three-dimensional space geometric model and fluid mechanics numerical simulation software to quickly predict the urban physical environment of the target city and obtain the prediction results; S602, comparing the prediction results with the results of capturing the digital surface and ground thermal images of the city; when the error exceeds a set percentage threshold, clustering the three-dimensional space of the city is performed again and the physical environment is predicted until the error is lower than the set percentage threshold; S603. Finally, the urban physical environment prediction results are visualized.

8. A system for capturing and rapidly modeling urban three-dimensional space parameters, characterized in that: include: An unmanned aerial vehicle equipped with a high-definition infrared imaging camera and capable of remote control is responsible for remote aerial photography of the target city or region and collecting detailed aerial images of the target city or region; The geometric model data processing integrated system is responsible for using the urban three-dimensional space parameter capture and rapid modeling method as described in any one of claims 1 to 7 to perform urban geometric form rapid modeling and physical environment simulation on the target city or region.

9. A computer device, characterized in that: include: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus, and the memory is used to store at least one executable instruction, wherein the executable instruction enables the processor to perform operations corresponding to the urban three-dimensional space parameter capture and rapid modeling method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer storage medium stores at least one executable instruction, and the executable instruction enables the processor to execute operations corresponding to the urban three-dimensional space parameter capture and rapid modeling method as described in any one of claims 1 to 7.

Images