A quantitative analysis method and system for urbanization intensity index

Abstract

This application discloses a quantitative analysis method and system for urbanization intensity index. The method includes: acquiring street view image data of a target city; determining the total undeveloped area of ​​the undeveloped environment and the total developed area of ​​the developed environment based on the street view image data; calculating the Shannon entropy of various elements in the undeveloped and developed environments; and using Shannon entropy to weight the total undeveloped and developed areas to obtain the urbanization intensity index of the target city. Therefore, by adopting the embodiments of this application, not only is the area ratio of the built environment to the undeveloped environment measured, but Shannon entropy is also introduced as a weighting factor for structural complexity, revealing the coupling relationship between urban spatial development scale and functional diversity. This enables accurate assessment of the urbanization intensity of different areas within a city, while improving the accuracy of the assessment of urban spatial functional diversity.

Description

Technical Field

[0001] This application relates to the field of urbanization level measurement technology, and in particular to a quantitative analysis method and system for urbanization intensity index. Background Technology

[0002] In the field of urban planning and management, with the accelerated pace of global urbanization, urban populations are growing exponentially, urban spatial forms are constantly evolving, and infrastructure is continuously expanding and improving. The spatial distribution differences between the built environment and the unbuilt environment brought about by urbanization, and their interaction with human activities, have become increasingly important topics in urban studies.

[0003] In related technologies, geography and urban science typically combine population size and population density thresholds to reflect complete settlement levels, thereby classifying urbanization levels. In research and policy discussions on urbanization levels, scholars and policymakers primarily focus on macro-level trends such as overall urban land use, population expansion, and macroeconomic growth.

[0004] However, existing methods mainly focus on overall urban trends at a macro scale, making it difficult to accurately assess the urbanization intensity of different areas within a city. Traditional remote sensing images are mostly taken from a top-down perspective, making it difficult to capture urban spatial details from a human eye's horizontal perspective, resulting in inaccurate assessments of the functional diversity of urban spaces. Summary of the Invention

[0005] This application provides a method and system for quantitative analysis of urbanization intensity index. To provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not intended as a general commentary, nor is it intended to identify key / important components or describe the scope of protection of these embodiments. Its sole purpose is to present some concepts in a simple form as a prelude to the detailed description that follows.

[0006] In a first aspect, embodiments of this application provide a method for quantitative analysis of urbanization intensity index, the method comprising:

[0007] Acquire street view image data of the target city;

[0008] Based on street view image data, determine the total undeveloped area of ​​the undeveloped environment and the total developed area of ​​the developed environment;

[0009] Calculate the Shannon entropy of various elements in both undeveloped and developed environments;

[0010] The urbanization intensity index of the target city is obtained by weighting the total undeveloped area and the total developed area using Shannon entropy.

[0011] Optionally, based on street view image data, determine the total undeveloped area of ​​the undeveloped environment and the total developed area of ​​the developed environment, including:

[0012] Street view image data is input into a pre-trained semantic segmentation model;

[0013] Output the semantic category label for each pixel in the street view image data;

[0014] Based on the semantic category label of each pixel, the street view image data is divided into multiple regions;

[0015] The various areas are divided into undeveloped and developed environments;

[0016] Calculate the total undeveloped area of ​​the undeveloped environment and the total developed area of ​​the developed environment.

[0017] Optional, multiple types of areas include natural areas, areas under construction, building areas, and areas with artificially planted greenery;

[0018] The various regions are divided into undeveloped and developed environments, including:

[0019] Convert the pixels of the natural region into actual area to obtain the area of ​​the natural region;

[0020] When the area of ​​the natural region is 0, the building area and the green plant area are considered as the constructed environment; or when the area of ​​the natural region is greater than 0, the building area is considered as the constructed environment.

[0021] Natural areas, areas under construction, and the sky areas of the target city are considered as undeveloped environments.

[0022] Optionally, the total undeveloped area of ​​the undeveloped environment and the total developed area of ​​the developed environment are calculated, including:

[0023] The pixels of the construction area, building area, and green plant area are converted into actual areas to obtain the area of ​​the construction area, the area of ​​the building area, and the area of ​​the green plant area.

[0024] When the area of ​​the natural area is 0, the sum of the area of ​​the building area and the area of ​​the green plant area is taken as the total area of ​​the constructed environment; or when the area of ​​the natural area is greater than 0, the area of ​​the building area is taken as the total area of ​​the constructed environment.

[0025] The total undeveloped area of ​​the undeveloped environment is calculated by summing the area of ​​the natural area, the area under construction, and the sky area of ​​the target city.

[0026] The expression for the total area of ​​the already constructed environment is as follows:

[0027]

[0028] in, This refers to the total area of ​​the already constructed environment. The building area is the area of ​​the building. The area of ​​green plants, Area of ​​the natural region;

[0029] The expression for the total undeveloped area of ​​the undeveloped environment is as follows:

[0030]

[0031] in, This refers to the total undeveloped area of ​​the undeveloped environment. The area under construction. The area of ​​the sky.

[0032] Optionally, calculate the Shannon entropy of various elements in both unbuilt and built environments, including:

[0033] The semantic category label of each pixel is deduplicated to obtain multiple semantic categories;

[0034] Calculate the pixel percentage of each semantic category in the unbuilt environment;

[0035] Calculate the Shannon entropy of each element in the unbuilt environment based on the pixel percentage of each semantic category.

[0036] Calculate the pixel percentage of each semantic category in the constructed environment;

[0037] Based on the pixel proportion of each semantic category in the constructed environment, calculate the Shannon entropy of each type of element in the constructed environment; where the expression for calculating the Shannon entropy is:

[0038]

[0039] in, For Shannon entropy, For the first The percentage of pixels in a semantic category.

[0040] Optionally, Shannon entropy is used to weight the total undeveloped area and the total developed area to obtain the urbanization intensity index of the target city, including:

[0041] Calculate the ratio of the total area already constructed to the total area not yet constructed;

[0042] Calculate the entropy ratio of Shannon entropy for each element in the constructed environment to that of each element in the unconstructed environment;

[0043] Multiply the area ratio by the entropy ratio to obtain the product result;

[0044] The results of the area calculation are normalized to obtain the urbanization intensity index of the target city.

[0045] Optionally, the expression for calculating the urbanization intensity index is:

[0046]

[0047] in, Urbanization intensity index Z-Score normalization function, used to normalize values ​​to between 0 and 1. This represents the total area already constructed. This refers to the total area not yet constructed. For the Shannon entropy of various elements in the constructed environment, The Shannon entropy is the sum of the entropy of various elements in the unconstructed environment; among them,

[0048] The Z-Score normalization function is expressed as follows:

[0049]

[0050] Normalized value The result of multiplying the area ratio and the entropy ratio.

[0051] Optionally, a pre-trained semantic segmentation model is generated by following these steps:

[0052] Obtain an image dataset containing city street views;

[0053] The image data in the image dataset is manually labeled to assign semantic category labels to the pixels of each image, thus obtaining training samples for the model.

[0054] Deep learning models are used as semantic segmentation models;

[0055] Based on the training samples of the model, machine learning is performed on the semantic segmentation model to obtain a pre-trained semantic segmentation model.

[0056] Optionally, based on the model training samples, machine learning is performed on the semantic segmentation model to obtain a pre-trained semantic segmentation model, including:

[0057] Input the training samples of the model into the semantic segmentation model, and output the model loss value;

[0058] Generate a pre-trained semantic segmentation model when the model loss value is minimized;

[0059] Alternatively, if the model loss value has not reached its minimum, continue executing the step of inputting the model training samples into the semantic segmentation model until the model loss value reaches its minimum.

[0060] Secondly, a quantitative analysis system for an urbanization intensity index, the system comprising:

[0061] The acquisition module is used to acquire street view image data of the target city;

[0062] The determination module is used to determine the total undeveloped area of ​​the undeveloped environment and the total developed area of ​​the developed environment based on street view image data;

[0063] The first calculation module is used to calculate the Shannon entropy of various elements in both unbuilt and built environments.

[0064] The second calculation module is used to perform weighted calculations on the total undeveloped area and the total developed area using Shannon entropy to obtain the urbanization intensity index of the target city.

[0065] The technical solutions provided in this application embodiment may include the following beneficial effects:

[0066] In this embodiment, actual street view image data can capture changes at the micro-level of the city. By introducing Shannon entropy, not only the area ratio of urban space is considered, but also the functional diversity and complexity of the space. This allows the urbanization intensity index to reflect not only the physical expansion of urban space, but also the functional richness and complexity of the space, revealing the coupling relationship between the scale of urban spatial development and functional diversity. It can accurately assess the urbanization intensity of different areas within the city, while improving the accuracy of the assessment of the functional diversity of urban space.

[0067] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0068] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0069] Figure 1 This is a flowchart illustrating a quantitative analysis method for urbanization intensity index provided in an embodiment of this application;

[0070] Figure 2 This is a schematic diagram illustrating the quantitative analysis process of an urbanization intensity index provided in this application;

[0071] Figure 3 This is a flowchart illustrating a semantic segmentation model training method provided in this application;

[0072] Figure 4 This is a model architecture diagram of a semantic segmentation model provided in this application;

[0073] Figure 5 This is a schematic diagram of the structure of a quantitative analysis system for urbanization intensity index provided in an embodiment of this application;

[0074] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0075] The following description and accompanying drawings fully illustrate specific embodiments of this application to enable those skilled in the art to practice them.

[0076] It should be understood that the described embodiments are merely some, not all, of the embodiments in this application. All other embodiments obtained by those skilled in the art based on the embodiments in this application without inventive effort are within the scope of protection of this application.

[0077] In the following description, when referring to the accompanying drawings, the same numbers in different drawings denote the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of systems and methods consistent with some aspects of this application as detailed in the appended claims.

[0078] In the description of this application, it should be understood that the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances. Furthermore, in the description of this application, unless otherwise stated, "multiple" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship.

[0079] This application provides a quantitative analysis method and system for urbanization intensity index to solve the problems existing in the aforementioned related technical issues. The following will be discussed in conjunction with the appendix... Figure 1 -Appendix Figure 4 This application provides a detailed description of the quantitative analysis method for the urbanization intensity index provided in its embodiments. This method can be implemented using a computer program and can run on a quantitative analysis system for the urbanization intensity index based on the von Neumann architecture. This computer program can be integrated into applications or run as a standalone tool application.

[0080] Please see Figure 1 This is a flowchart illustrating a method for quantitative analysis of urbanization intensity index, as provided in this application embodiment. Figure 1 As shown, the method in this application embodiment may include the following steps:

[0081] S101, acquire street view image data of the target city;

[0082] The target city is the specific city or a specific area within a city that requires an urbanization intensity assessment. Street view image data consists of urban images taken from a street view perspective, which typically include urban landscape elements such as buildings, roads, and green spaces.

[0083] In some embodiments of this application, a target city or region is determined. Street view images of the target city are obtained from street view image service providers (such as Google Street View, Mapillary, etc.), ensuring that the downloaded images cover all parts of the target city or region. Image data can be obtained using APIs or manual download methods to obtain street view image data.

[0084] S102, Based on street view image data, determine the total undeveloped area of ​​the undeveloped environment and the total developed area of ​​the developed environment;

[0085] Undeveloped areas refer to land areas within a city that have not yet undergone large-scale construction or development. These areas may include natural surfaces (such as forests, grasslands, and rivers), vacant lots, temporary building areas, and the visible "sky" in the urban space. The total undeveloped area is the total area of ​​undeveloped areas identified in street view imagery data. Conversely, developed areas refer to land areas within a city that have already been developed or constructed. These areas include man-made structures such as buildings, roads, bridges, and parking lots, as well as artificial green spaces such as street greenbelts and roadside trees. The total developed area is the total area of ​​developed areas identified in street view imagery data.

[0086] In some embodiments of this application, the specific process of determining the total undeveloped area of ​​the undeveloped environment and the total developed area of ​​the developed environment based on street view image data includes: inputting street view image data into a pre-trained semantic segmentation model; outputting the semantic category label of each pixel in the image corresponding to the street view image data; dividing the street view image data into multiple regions based on the semantic category label of each pixel; dividing the multiple regions into undeveloped environment and developed environment; and calculating the total undeveloped area of ​​the undeveloped environment and the total developed area of ​​the developed environment.

[0087] Semantic segmentation is a deep learning model used to assign a specific category label to each pixel in an image, thereby identifying the boundaries of different objects and scenes within the image. A pixel is the basic unit of an image, and each pixel can have attributes such as color and brightness. A semantic category label is a label assigned to each pixel in the image during semantic segmentation, indicating the category to which the pixel belongs, such as "building," "road," or "vegetation." Multi-class regions divide the image into multiple categories based on the semantic category labels of the pixels; each region consists of pixels with the same semantic category label.

[0088] In some embodiments of this application, the specific process of generating a pre-trained semantic segmentation model includes: acquiring an image dataset containing urban street scenes; manually annotating the image data in the image dataset to set semantic category labels for each pixel of the image to obtain model training samples; using a deep learning model as the semantic segmentation model; and performing machine learning on the semantic segmentation model based on the model training samples to obtain a pre-trained semantic segmentation model.

[0089] The results of the annotation are shown in Table 1.

[0090]

[0091] Specifically, the process of performing machine learning on the semantic segmentation model based on the model training samples to obtain a pre-trained semantic segmentation model includes: inputting the model training samples into the semantic segmentation model and outputting the model loss value; generating the pre-trained semantic segmentation model when the model loss value reaches its minimum; or, if the model loss value does not reach its minimum, continuing to execute the step of inputting the model training samples into the semantic segmentation model until the model loss value reaches its minimum.

[0092] The various types of areas include natural areas, areas under construction, building areas, and areas with artificially planted greenery.

[0093] In some embodiments of this application, the specific process of dividing multiple types of areas into undeveloped and developed environments includes: converting the pixels of natural areas into actual areas to obtain the area of ​​natural areas; when the area of ​​natural areas is 0, classifying building areas and green plant areas as developed environments; or when the area of ​​natural areas is greater than 0, classifying building areas as developed environments; and classifying natural areas, areas under construction, and the sky area of ​​the target city as undeveloped environments.

[0094] In some embodiments of this application, the specific process of calculating the total unconstructed area of ​​the unconstructed environment and the total constructed area of ​​the constructed environment includes: converting the pixels of the construction area, building area, and green plant area into actual areas to obtain the construction area area, building area area, and green plant area area; when the natural area area is 0, summing the building area area and green plant area area to obtain the total constructed area of ​​the constructed environment; or when the natural area area is greater than 0, using the building area area as the total constructed area of ​​the constructed environment; and summing the natural area area, construction area area, and sky area of ​​the target city to obtain the total unconstructed area of ​​the unconstructed environment.

[0095] Specifically, the expression for the total area of ​​the constructed environment is as follows:

[0096]

[0097] in, This refers to the total area of ​​the already constructed environment. The building area is the area of ​​the building. The area of ​​green plants, Area of ​​the natural region;

[0098] The expression for the total undeveloped area of ​​the undeveloped environment is as follows:

[0099]

[0100] in, This refers to the total undeveloped area of ​​the undeveloped environment. The area under construction. The area of ​​the sky.

[0101] It should be noted that the unbuilt environment refers to spatial units that have not yet been covered or integrated by systematic urban construction. This mainly includes naturally exposed ground, temporary construction areas, and the "sky" view within urban spaces. Unbuilt elements, such as fences and makeshift sheds, often exhibit fragmentation, discontinuity, and low order. These spatial states lack stable functional structures and belong to the "intermediate zone" between the natural and built states in the urbanization process, reflecting a morphological characteristic of coexistence of uncertainty and transition.

[0102] S103, calculate the Shannon entropy of various elements in both unbuilt and built environments;

[0103] In the context of semantic segmentation, a feature refers to a different object or region in an image that is identified and classified. These features can be natural features (such as trees or water bodies), man-made features (such as buildings or roads), or any other category identified in the image. Shannon entropy is a concept in information theory used to measure the uncertainty or randomness of information. In image processing and pattern recognition, Shannon entropy can be used to measure the uniformity or diversity of the distribution of different categories in an image. Specifically, it calculates the negative sum of the expected values ​​of the logarithmic probability distributions of the probabilities of each type of feature in the image.

[0104] In some embodiments of this application, the specific process for calculating the Shannon entropy of various elements in the unbuilt environment and the built environment includes: deduplicating the semantic category label of each pixel to obtain multiple semantic categories; calculating the pixel proportion of each semantic category in the unbuilt environment; calculating the Shannon entropy of various elements in the unbuilt environment based on the pixel proportion of each semantic category in the unbuilt environment; calculating the pixel proportion of each semantic category in the built environment; and calculating the Shannon entropy of various elements in the built environment based on the pixel proportion of each semantic category in the built environment. The expression for calculating the Shannon entropy is as follows:

[0105]

[0106] in, For Shannon entropy, For the first The percentage of pixels in a semantic category.

[0107] S104 uses Shannon entropy to weight the total undeveloped area and the total developed area to obtain the urbanization intensity index of the target city.

[0108] In some embodiments of this application, the specific process of using Shannon entropy to weight the total undeveloped area and the total developed area to obtain the urbanization intensity index of the target city includes: calculating the area ratio of the total developed area and the total undeveloped area; calculating the entropy ratio of the Shannon entropy of various elements in the developed environment to the Shannon entropy of various elements in the undeveloped environment; productting the area ratio and the entropy ratio to obtain the product result; and normalizing the product result to obtain the urbanization intensity index of the target city.

[0109] Specifically, the expression for calculating the urbanization intensity index is as follows:

[0110]

[0111] in, Urbanization intensity index Z-Score normalization function, used to normalize values ​​to between 0 and 1. This represents the total area already constructed. This refers to the total area not yet constructed. For the Shannon entropy of various elements in the constructed environment, The Shannon entropy is the sum of the entropy of various elements in the unconstructed environment; among them,

[0112] The Z-Score normalization function is expressed as follows:

[0113]

[0114] Normalized value The result of multiplying the area ratio and the entropy ratio.

[0115] Specifically, It reflects the proportional relationship between the built environment and the unbuilt environment in terms of quantity (area), and measures the scale and degree of development; The introduction of a comparison of spatial structural complexity reflects the heterogeneity and diversity within space. When urbanization intensity is high, if the built environment has abundant structures (high entropy) while the unbuilt environment has simple structures (low entropy), then... This indicates that the built-up area not only accounts for a large proportion but also has rich spatial functions; if one type of element dominates the built environment (such as large areas of bare building walls). A value close to or less than 1, even with a high level of development, suggests that the constructed space has a single function.

[0116] For example Figure 2 As shown, Figure 2 This is a schematic diagram illustrating the quantitative analysis process of an urbanization intensity index provided in this application. First, street view images are acquired. Semantic segmentation is then performed on the street view images to obtain built and unbuilt environments. The total built area and Shannon entropy in the built environment are determined, and the total unbuilt area and Shannon entropy² in the unbuilt environment are determined. This is then calculated using the formula... The calculated results are then normalized using the Z-Score normalization function to obtain the final urbanization intensity index.

[0117] Among them, the Urbanization Intensity Index (UII) uses urban micro-spatial locations as the unit of analysis. It not only measures the area ratio of the built environment to the unbuilt environment (natural surface, built-up land, sky, etc.), but also introduces semantic entropy as a weighting factor for structural complexity, systematically revealing the coupling relationship between the scale of urban spatial development and functional diversity. The UII possesses good spatial stability and methodological transferability, providing important support for research in urban renewal, spatial equity assessment, and human perception modeling.

[0118] It should be noted that, compared with the urbanization intensity measured by traditional remote sensing methods, the UII constructed based on street view images in this application can more effectively supplement the lack of identification of micro-built environment characteristics from a macro perspective, and provide a more human-centered measurement method for urban environmental assessment.

[0119] In one possible implementation, after obtaining the Urbanization Intensity Index (UII), the correlation between the UII and factors such as residents' quality of life, air quality, and traffic conditions can be analyzed to obtain the analysis results. Based on the analysis results, urban planning schemes, such as increasing green space, optimizing transportation networks, and improving the residential environment, can be automatically matched from a strategy library. Finally, the urban planning schemes are exported as reports and fed back to the client for display. Methods such as Pearson correlation coefficient and Spearman rank correlation coefficient can be used to quantify the linear relationship between the UII value and various factors. For example, a model can be fitted using collected data, with UII as the independent variable and residents' quality of life, air quality, and traffic conditions as dependent variables. Appropriate statistical models, such as linear regression, logistic regression, or machine learning models, can be used to analyze the relationship between the independent and dependent variables.

[0120] Through this implementation, the municipal government can more scientifically identify areas in the city where green space needs to be increased and formulate reasonable green space planning strategies. The increase in green space helps alleviate the urban heat island effect, improves the quality of the urban ecological environment, and enhances the quality of life for residents. At the same time, continuous monitoring by the Urban Environment (UII) provides dynamic feedback for urban planning, ensuring the achievement of planning goals.

[0121] In this embodiment, actual street view image data can capture changes at the micro-level of the city. By introducing Shannon entropy, not only the area ratio of urban space is considered, but also the functional diversity and complexity of the space. This allows the urbanization intensity index to reflect not only the physical expansion of urban space, but also the functional richness and complexity of the space, revealing the coupling relationship between the scale of urban spatial development and functional diversity. It can accurately assess the urbanization intensity of different areas within the city, while improving the accuracy of the assessment of the functional diversity of urban space.

[0122] Please see Figure 3 The figure illustrates a flowchart of a semantic segmentation model training method provided in this application embodiment. As shown, the method in this application embodiment may include the following steps:

[0123] S201, Obtain an image dataset containing city street scenes;

[0124] S202, The image data in the image dataset is manually labeled to set semantic category labels for each pixel of the image to obtain model training samples;

[0125] S203 uses a deep learning model as the semantic segmentation model;

[0126] For example Figure 4 As shown, the semantic segmentation model includes an input layer, an encoding block, a decoding block, and an output head. Input data consists of city street scene images, typically RGB three-channel images, with sizes adjustable according to specific needs, such as 256×256×3 or 512×512×3. The main function of the encoding block is to extract features from the input image, usually implemented using a convolutional neural network (CNN). A pre-trained model (such as ResNet, VGG, MobileNet, etc.) can be used as the encoder to improve model performance and training speed. The decoder progressively upsamples the high-order features extracted by the encoder, restoring them to the same spatial resolution as the input image, and performs pixel-level classification. The output head finally outputs the segmentation result.

[0127] S204, Input the training samples of the model into the semantic segmentation model and output the model loss value;

[0128] S205, if the model loss value reaches its minimum, generate a pre-trained semantic segmentation model; or, if the model loss value does not reach its minimum, continue executing the step of inputting the model training samples into the semantic segmentation model until the model loss value reaches its minimum.

[0129] In this embodiment, actual street view image data can capture changes at the micro-level of the city. By introducing Shannon entropy, not only the area ratio of urban space is considered, but also the functional diversity and complexity of the space. This allows the urbanization intensity index to reflect not only the physical expansion of urban space, but also the functional richness and complexity of the space, revealing the coupling relationship between the scale of urban spatial development and functional diversity. It can accurately assess the urbanization intensity of different areas within the city, while improving the accuracy of the assessment of the functional diversity of urban space.

[0130] The following are system embodiments of this application, which can be used to execute the method embodiments of this application. For details not disclosed in the system embodiments of this application, please refer to the method embodiments of this application.

[0131] Please see Figure 5 This illustration shows a schematic diagram of a quantitative analysis system for urbanization intensity index provided in an exemplary embodiment of this application. This quantitative analysis system for urbanization intensity index can be implemented as all or part of an electronic device through software, hardware, or a combination of both. System 1 includes an acquisition module 10, a determination module 20, a first calculation module 30, and a second calculation module 40.

[0132] Module 10 is used to acquire street view image data of the target city;

[0133] The determination module 20 is used to determine the total undeveloped area of ​​the undeveloped environment and the total developed area of ​​the developed environment based on street view image data;

[0134] The first calculation module 30 is used to calculate the Shannon entropy of various elements in the unbuilt environment and the built environment;

[0135] The second calculation module 40 is used to perform weighted calculations on the total undeveloped area and the total developed area using Shannon entropy to obtain the urbanization intensity index of the target city.

[0136] It should be noted that the urbanization intensity index quantitative analysis system provided in the above embodiments is only illustrated by the division of the above functional modules when executing the urbanization intensity index quantitative analysis method. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the equipment can be divided into different functional modules to complete all or part of the functions described above. In addition, the urbanization intensity index quantitative analysis system and the urbanization intensity index quantitative analysis method embodiments provided in the above embodiments belong to the same concept, and the implementation process is detailed in the method embodiments, which will not be repeated here.

[0137] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0138] In this embodiment, actual street view image data can capture changes at the micro-level of the city. By introducing Shannon entropy, not only the area ratio of urban space is considered, but also the functional diversity and complexity of the space. This allows the urbanization intensity index to reflect not only the physical expansion of urban space, but also the functional richness and complexity of the space, revealing the coupling relationship between the scale of urban spatial development and functional diversity. It can accurately assess the urbanization intensity of different areas within the city, while improving the accuracy of the assessment of the functional diversity of urban space.

[0139] This application also provides a computer-readable medium having program instructions stored thereon, which, when executed by a processor, implement the quantitative analysis method for the urbanization intensity index provided in the above-described method embodiments.

[0140] This application also provides a computer program product containing instructions that, when run on a computer, causes the computer to perform a quantitative analysis method for the urbanization intensity index of the various method embodiments described above.

[0141] Please see Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 6As shown, the electronic device 1000 may include: at least one processor 1001, at least one network interface 1004, a user interface 1003, a memory 1005, and at least one communication bus 1002.

[0142] The communication bus 1002 is used to realize the connection and communication between these components.

[0143] The user interface 1003 may include a display screen and a camera. Optionally, the user interface 1003 may also include a standard wired interface and a wireless interface.

[0144] The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0145] The processor 1001 may include one or more processing cores. The processor 1001 connects to various parts within the electronic device 1000 using various interfaces and lines. It executes various functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 1005, and by calling data stored in the memory 1005. Optionally, the processor 1001 may be implemented using at least one hardware form selected from Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), and Programmable Logic Array (PLA). The processor 1001 may integrate one or more of the following: a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), and a modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content to be displayed on the screen; and the modem handles wireless communication. It is understood that the modem may also be implemented as a separate chip without being integrated into the processor 1001.

[0146] The memory 1005 may include random access memory (RAM) or read-only memory. Optionally, the memory 1005 may include a non-transitory computer-readable storage medium. The memory 1005 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 1005 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 1005 may also be at least one storage system located remotely from the aforementioned processor 1001. Figure 6 As shown, the memory 1005, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and a quantitative analysis application for the urbanization intensity index.

[0147] exist Figure 6 In the illustrated electronic device 1000, the user interface 1003 is mainly used to provide an input interface for the user and to acquire user input data; while the processor 1001 can be used to call the quantitative analysis application of the urbanization intensity index stored in the memory 1005, and specifically perform the following operations:

[0148] Acquire street view image data of the target city;

[0149] Based on street view image data, determine the total undeveloped area of ​​the undeveloped environment and the total developed area of ​​the developed environment;

[0150] Calculate the Shannon entropy of various elements in both undeveloped and developed environments;

[0151] The urbanization intensity index of the target city is obtained by weighting the total undeveloped area and the total developed area using Shannon entropy.

[0152] In one embodiment, when the processor 1001 determines the total undeveloped area of ​​the undeveloped environment and the total developed area of ​​the developed environment based on street view image data, it specifically performs the following operations:

[0153] Street view image data is input into a pre-trained semantic segmentation model;

[0154] Output the semantic category label for each pixel in the street view image data;

[0155] Based on the semantic category label of each pixel, the street view image data is divided into multiple regions;

[0156] The various areas are divided into undeveloped and developed environments;

[0157] Calculate the total undeveloped area of ​​the undeveloped environment and the total developed area of ​​the developed environment.

[0158] In one embodiment, when the processor 1001 divides multiple types of regions into unbuilt and built environments, it specifically performs the following operations:

[0159] Convert the pixels of the natural region into actual area to obtain the area of ​​the natural region;

[0160] When the area of ​​the natural region is 0, the building area and the green plant area are considered as the constructed environment; or when the area of ​​the natural region is greater than 0, the building area is considered as the constructed environment.

[0161] Natural areas, areas under construction, and the sky areas of the target city are considered as undeveloped environments.

[0162] In one embodiment, when the processor 1001 calculates the total undeveloped area of ​​the undeveloped environment and the total developed area of ​​the developed environment, it specifically performs the following operations:

[0163] The pixels of the construction area, building area, and green plant area are converted into actual areas to obtain the area of ​​the construction area, the area of ​​the building area, and the area of ​​the green plant area.

[0164] When the area of ​​the natural area is 0, the sum of the area of ​​the building area and the area of ​​the green plant area is taken as the total area of ​​the constructed environment; or when the area of ​​the natural area is greater than 0, the area of ​​the building area is taken as the total area of ​​the constructed environment.

[0165] The total undeveloped area of ​​the undeveloped environment is calculated by summing the area of ​​the natural area, the area under construction, and the sky area of ​​the target city.

[0166] The expression for the total area of ​​the already constructed environment is as follows:

[0167]

[0168] in, This refers to the total area of ​​the already constructed environment. The building area is the area of ​​the building. The area of ​​green plants, Area of ​​the natural region;

[0169] The expression for the total undeveloped area of ​​the undeveloped environment is as follows:

[0170]

[0171] in, This refers to the total undeveloped area of ​​the undeveloped environment. The area under construction. The area of ​​the sky.

[0172] In one embodiment, when the processor 1001 calculates the Shannon entropy of various elements in both unbuilt and built environments, it specifically performs the following operations:

[0173] The semantic category label of each pixel is deduplicated to obtain multiple semantic categories;

[0174] Calculate the pixel percentage of each semantic category in the unbuilt environment;

[0175] Calculate the Shannon entropy of each element in the unbuilt environment based on the pixel percentage of each semantic category.

[0176] Calculate the pixel percentage of each semantic category in the constructed environment;

[0177] Based on the pixel proportion of each semantic category in the constructed environment, calculate the Shannon entropy of each type of element in the constructed environment; where the expression for calculating the Shannon entropy is:

[0178]

[0179] in, For Shannon entropy, For the first The percentage of pixels in a semantic category.

[0180] In one embodiment, when processor 1001 performs a weighted calculation of the total undeveloped area and the total developed area using Shannon entropy to obtain the urbanization intensity index of the target city, it specifically performs the following operations:

[0181] Calculate the ratio of the total area already constructed to the total area not yet constructed;

[0182] Calculate the entropy ratio of Shannon entropy for each element in the constructed environment to that of each element in the unconstructed environment;

[0183] Multiply the area ratio by the entropy ratio to obtain the product result;

[0184] The results of the area calculation are normalized to obtain the urbanization intensity index of the target city.

[0185] In one embodiment, when the processor 1001 generates a pre-trained semantic segmentation model, it specifically performs the following operations:

[0186] Obtain an image dataset containing city street views;

[0187] The image data in the image dataset is manually labeled to assign semantic category labels to the pixels of each image, thus obtaining training samples for the model.

[0188] Deep learning models are used as semantic segmentation models;

[0189] Based on the training samples of the model, machine learning is performed on the semantic segmentation model to obtain a pre-trained semantic segmentation model.

[0190] In one embodiment, when the processor 1001 performs machine learning on the semantic segmentation model based on the model training samples to obtain a pre-trained semantic segmentation model, it specifically performs the following operations:

[0191] Input the training samples of the model into the semantic segmentation model, and output the model loss value;

[0192] Generate a pre-trained semantic segmentation model when the model loss value is minimized;

[0193] Alternatively, if the model loss value has not reached its minimum, continue executing the step of inputting the model training samples into the semantic segmentation model until the model loss value reaches its minimum.

[0194] In this embodiment, actual street view image data can capture changes at the micro-level of the city. By introducing Shannon entropy, not only the area ratio of urban space is considered, but also the functional diversity and complexity of the space. This allows the urbanization intensity index to reflect not only the physical expansion of urban space, but also the functional richness and complexity of the space, revealing the coupling relationship between the scale of urban spatial development and functional diversity. It can accurately assess the urbanization intensity of different areas within the city, while improving the accuracy of the assessment of the functional diversity of urban space.

[0195] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The program for quantitative analysis of the urbanization intensity index can be stored in a computer-readable storage medium. When executed, the program can include the processes of the embodiments of the methods described above. The storage medium can be a magnetic disk, optical disk, read-only memory, or random access memory, etc.

[0196] The above-disclosed embodiments are merely preferred embodiments of this application and should not be construed as limiting the scope of this application. Therefore, any equivalent variations made in accordance with the claims of this application shall still fall within the scope of this application.

Claims

1. A quantitative analysis method for urbanization intensity index, characterized in that, The method includes: Acquire street view image data of the target city; Determining the total undeveloped area of ​​the undeveloped environment and the total developed area of ​​the developed environment based on the street view image data includes: inputting the street view image data into a pre-trained semantic segmentation model; outputting the semantic category label of each pixel in the image corresponding to the street view image data; dividing the street view image data into multiple regions based on the semantic category label of each pixel; dividing the multiple regions into undeveloped environments and developed environments; calculating the total undeveloped area of ​​the undeveloped environment and the total developed area of ​​the developed environment; the multiple regions include natural areas, areas under construction, building areas, and areas with artificially planted green plants; the semantic segmentation model is a deep learning model used to assign each pixel in the image to a specific category label to identify the boundaries of different objects and scenes in the image; Calculate the Shannon entropy of various elements in the unbuilt environment and the built environment; Shannon entropy is used to measure the uniformity or diversity of the distribution of different categories in an image; The urbanization intensity index of the target city is obtained by weighting the total undeveloped area and the total developed area using the Shannon entropy.

2. The method according to claim 1, characterized in that, The process of dividing the multiple types of areas into undeveloped and developed environments includes: The pixels of the natural region are converted into actual areas to obtain the area of ​​the natural region; When the area of ​​the natural area is 0, the building area and the green plant area are considered as a constructed environment; or when the area of ​​the natural area is greater than 0, the building area is considered as a constructed environment. The natural area, the area under construction, and the sky area of ​​the target city are considered as the undeveloped environment.

3. The method according to claim 1, characterized in that, The calculation of the total undeveloped area of ​​the undeveloped environment and the total developed area of ​​the developed environment includes: Convert the pixels of the construction area, building area and green plant area into actual areas to obtain the area of ​​the construction area, the area of ​​the building area and the area of ​​the green plant area. When the area of ​​the natural area is 0, the sum of the area of ​​the building area and the area of ​​the green plant area is taken as the total area of ​​the constructed environment; or when the area of ​​the natural area is greater than 0, the area of ​​the building area is taken as the total area of ​​the constructed environment. The sum of the area of ​​the natural area, the area of ​​the area under construction, and the sky area of ​​the target city is taken as the total undeveloped area of ​​the undeveloped environment; The expression for the total area of ​​the already constructed environment is as follows: in, This refers to the total area of ​​the already constructed environment. The building area is the area of ​​the building. The area of ​​green plants, Area of ​​the natural region; The expression for the total undeveloped area of ​​the undeveloped environment is as follows: in, This refers to the total undeveloped area of ​​the undeveloped environment. The area under construction. The area of ​​the sky.

4. The method according to claim 1, characterized in that, The calculation of Shannon entropy for various elements in the undeveloped environment and the developed environment includes: The semantic category label of each pixel is deduplicated to obtain multiple semantic categories; Calculate the pixel percentage of each semantic category in the unbuilt environment; Based on the pixel proportion of each semantic category in the unbuilt environment, calculate the Shannon entropy of each type of element in the unbuilt environment; Calculate the pixel percentage of each semantic category in the constructed environment; Based on the pixel proportion of each semantic category in the constructed environment, calculate the Shannon entropy of each type of element in the constructed environment; wherein, the expression for calculating the Shannon entropy is: in, For Shannon entropy, For the first The percentage of pixels in a semantic category.

5. The method according to claim 1, characterized in that, The process of using the Shannon entropy to weight the total undeveloped area and the total developed area to obtain the urbanization intensity index of the target city includes: Calculate the area ratio of the total constructed area to the total unconstructed area; Calculate the entropy ratio of the Shannon entropy of each element in the constructed environment to the Shannon entropy of each element in the unconstructed environment; The product of the area ratio and the entropy ratio is obtained; The results of the area calculation are normalized to obtain the urbanization intensity index of the target city.

6. The method according to claim 5, characterized in that, The expression for calculating the urbanization intensity index is as follows: in, Urbanization intensity index Z-Score normalization function, used to normalize values ​​to between 0 and 1. This represents the total area already constructed. This refers to the total area not yet constructed. For the Shannon entropy of various elements in the constructed environment, The Shannon entropy is the sum of the entropy of various elements in the unconstructed environment; among them, The Z-Score normalization function is expressed as follows: Normalized value The product of the area ratio and the entropy ratio.

7. The method according to claim 1, characterized in that, Generate a pre-trained semantic segmentation model by following these steps: Obtain an image dataset containing city street views; The image data in the image dataset are manually labeled to assign semantic category labels to the pixels of each image, thus obtaining model training samples; Deep learning models are used as semantic segmentation models; Based on the training samples of the model, machine learning is performed on the semantic segmentation model to obtain a pre-trained semantic segmentation model.

8. The method according to claim 7, characterized in that, The step of performing machine learning on the semantic segmentation model based on the training samples of the model to obtain a pre-trained semantic segmentation model includes: Input the training samples of the model into the semantic segmentation model, and output the model loss value; When the model loss value is minimized, a pre-trained semantic segmentation model is generated. Alternatively, if the model loss value has not reached its minimum, the step of inputting the model training samples into the semantic segmentation model continues until the model loss value reaches its minimum.

9. A quantitative analysis system for urbanization intensity index implemented using the method described in any one of claims 1-8, characterized in that, The system includes: The acquisition module is used to acquire street view image data of the target city; The determination module is used to determine the total undeveloped area of ​​the undeveloped environment and the total developed area of ​​the developed environment based on the street view image data. The first calculation module is used to calculate the Shannon entropy of various elements in the unbuilt environment and the built environment; The second calculation module is used to perform weighted calculations on the total undeveloped area and the total developed area using the Shannon entropy to obtain the urbanization intensity index of the target city.

Images