A housing vacancy area identification method, system, device and medium

Abstract

The application discloses a housing vacancy area identification method, system, device and medium. The method comprises the following steps: acquiring a night light image and a city land image of a target area; performing light intensity analysis based on the night light image and the city land image to obtain a city vacancy rate index of the target area; performing regression analysis on the night light image to obtain a night light value change trend of the target area; and obtaining a housing vacancy area distribution of the target area based on the city vacancy rate index and the night light value change trend. The application solves the problem that the prior art is difficult to dynamically capture population loss and its influence on housing vacancy, thereby leading to poor identification accuracy of vacant houses.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular to a method, system, device and medium for identifying vacant housing areas. Background Technology

[0002] Currently, monitoring housing vacancy is becoming increasingly important. Existing technologies mainly identify and simulate vacant housing areas through statistical models, remote sensing data analysis, or case-based reasoning models. These methods have already been applied in urban planning and land use management.

[0003] However, these technologies struggle to dynamically capture population loss and its impact on housing vacancy, limiting their effectiveness in complex urban expansion and contraction environments and resulting in poor accuracy in identifying vacant properties. Summary of the Invention

[0004] To overcome the problem that existing technologies are unable to dynamically capture population loss and its impact on housing vacancy, resulting in poor accuracy in identifying vacant housing, this application provides a method, system, device, and medium for identifying vacant housing areas.

[0005] Firstly, in order to solve the aforementioned technical problems, this application provides a method for identifying vacant housing areas, comprising:

[0006] Acquire nighttime light images and urban land use images of the target area;

[0007] Light intensity analysis was performed on nighttime light images and urban land use images to obtain the urban vacancy rate index of the target area.

[0008] Regression analysis was performed using nighttime light images to obtain the trend of nighttime light value changes in the target area;

[0009] Based on the urban vacancy rate index and nighttime light change trends, the distribution of vacant housing areas in the target region was obtained.

[0010] Secondly, this application also provides a housing vacancy area identification system, including:

[0011] The acquisition module is used to acquire nighttime light images and urban land use images of the target area;

[0012] The first analysis module is used to perform light intensity analysis based on nighttime light images and urban land use images to obtain the urban vacancy rate index of the target area.

[0013] The second analysis module is used to perform regression analysis using nighttime light images to obtain the trend of nighttime light value changes in the target area.

[0014] The distribution determination module is used to determine the distribution of vacant housing areas in a target region based on the city's vacancy rate index and nighttime light change trends.

[0015] Thirdly, this application also provides a computing device, including a memory, a processor, and a program stored in the memory and running on the processor, wherein the processor executes the program to implement the steps of the housing vacancy area identification method described above.

[0016] Fourthly, this application also provides a computer-readable storage medium storing instructions that, when executed on a terminal device, cause the terminal device to perform the steps of a method for identifying vacant housing areas.

[0017] The beneficial effects of this application are as follows: By analyzing the light intensity of nighttime light images and urban land use images of the target area, an urban vacancy rate index is obtained, which measures the degree of housing vacancy in the target area. Then, regression analysis is performed using the nighttime light images to obtain the trend of nighttime light value changes in the target area, dynamically capturing population loss trends. Finally, based on the urban vacancy rate index and the nighttime light change trend, the distribution of vacant housing in the target area is obtained. In this way, by combining the two dimensions of housing vacancy influencing factors—the degree of housing vacancy and the trend of population loss—the actual housing vacancy distribution in the target area can be dynamically predicted, making the identification of housing vacancy distribution more immediate and thus improving the accuracy of identifying vacant housing in the target area. Attached Figure Description

[0018] Figure 1 This is a flowchart illustrating an exemplary embodiment of a method for identifying vacant housing areas according to this application.

[0019] Figure 2 This is a schematic diagram illustrating the structure of a housing vacancy area identification system, which is an exemplary embodiment of this application. Detailed Implementation

[0020] The following embodiments are further explanations and supplements to this application and do not constitute any limitation on this application.

[0021] The spatial distribution characteristics and changing patterns of vacant housing areas are important bases for assessing urban shrinkage patterns. Population loss is the direct cause of vacant housing areas, and lower population density inevitably leads to a slowdown in urban land expansion near vacant areas. At the same time, continuous dynamic population loss reflects the potential for regional housing vacancy, and potential vacant housing areas also limit urban spatial development.

[0022] Existing statistical models, remote sensing data analysis, or case-based reasoning models for identifying and simulating vacant housing areas have been applied in urban planning and land use management. However, these technologies suffer from limitations such as insufficient identification accuracy, difficulty in dynamically capturing population loss and its impact on housing vacancy, neglect of the spatial relationship between vacant areas and surrounding land use, and poor adaptability to the characteristics of special types of cities (such as resource-based cities). These limitations restrict their application in complex urban expansion and contraction environments.

[0023] To address the aforementioned problems, embodiments of this application provide a method, system, device, and medium for identifying vacant housing areas, which will be described in detail below.

[0024] The housing vacancy area identification method provided in this application embodiment can be specifically executed by a server. It should be noted that the server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms. No limitation is imposed here.

[0025] Please see Figure 1 , Figure 1 An exemplary embodiment of this application illustrates a method for identifying vacant housing areas, such as... Figure 1 As shown, this application provides a method for identifying vacant housing areas, including:

[0026] Step S11: Obtain nighttime light images and urban land use images of the target area;

[0027] Step S12: Analyze the light intensity based on nighttime light images and urban land use images to obtain the urban vacancy rate index of the target area;

[0028] Step S13: Perform regression analysis using nighttime light images to obtain the trend of nighttime light value changes in the target area;

[0029] Step S14: Based on the urban vacancy rate index and the nighttime light change trend, obtain the distribution of vacant housing areas in the target area.

[0030] This embodiment of a method for identifying vacant housing areas involves analyzing the light intensity of nighttime light images and urban land use images of a target area to obtain an urban vacancy rate index, which measures the degree of housing vacancy in the target area. Then, regression analysis is performed using the nighttime light images to obtain the trend of nighttime light value changes in the target area, dynamically capturing population loss trends. Finally, based on the urban vacancy rate index and the nighttime light change trend, the distribution of vacant housing in the target area is obtained. In this way, by combining the two dimensions of housing vacancy influencing factors—the degree of housing vacancy and the trend of population loss—the actual housing vacancy distribution in the target area can be dynamically predicted, making the identification of housing vacancy distribution more timely and thus improving the accuracy of vacant housing identification in the target area.

[0031] In the embodiment provided in this application, the larger the built-up area and the smaller the urban population, the lower the urban vacancy rate index, indicating a higher degree of housing vacancy. The urban vacancy rate index can indicate the relative situation between the speed of urban land expansion and the speed of urban population development, thereby effectively revealing the spatial differentiation pattern of housing vacancy and measuring the degree of housing vacancy.

[0032] Optionally, the nighttime light image includes the current nighttime image; light intensity analysis is performed based on the nighttime light image and the urban land use image to obtain the urban vacancy rate index of the target area, including:

[0033] The nighttime light image was divided into pixels using urban land use images to obtain non-residential area pixels and residential area pixels.

[0034] Based on the pixel information of non-residential area pixels and residential area pixels, the true light intensity of residential area pixels is obtained;

[0035] Based on urban land use images and actual light intensity, the first urban vacancy rate index of residential area pixels is calculated, and the second urban vacancy rate index of non-residential area pixels is determined to be 0.

[0036] The formula for calculating the vacancy rate index of the first city is as follows:

[0037]

[0038] Wherein, GTI represents the first urban vacancy rate index of residential area pixel d in the nighttime light image, DN R,d N represents the gray level of pixel d in the residential area. d This represents the number of urban land use image pixels contained in residential area pixel d;

[0039] The city vacancy rate index for the target area is formed based on the vacancy rate index of the first city and the vacancy rate index of the second city.

[0040] In the embodiment provided in this application, the nighttime light image is divided into pixels using urban land use images. This approach takes into account the spatial relationship between vacant areas and surrounding land use. The initial division of the nighttime light image into residential and non-residential pixels is performed directly based on the urban land use situation in the urban land use image. The first urban vacancy rate index is calculated based solely on the urban land use image and the actual light intensity, which reduces the computational workload of the urban vacancy rate index and improves the computational efficiency of the urban vacancy rate index. This, in turn, improves the efficiency of subsequent identification of the distribution of vacant housing areas in the target region.

[0041] Optionally, the nighttime light image is obtained by dividing the nighttime light image using the current urban land use image into pixels, resulting in non-residential area pixels and residential area pixels, including:

[0042] The urban land use image and the nighttime light image are overlaid to calculate the urban land area ratio of each pixel in the nighttime light image; the pixel size of the nighttime light image is larger than the pixel size of the urban land use image.

[0043] The formula for calculating the urban land area ratio is as follows:

[0044]

[0045] Where UAR represents the proportion of urban land use, N d N represents the number of second pixels in the urban land use image contained within a single pixel in a nighttime light image. t This indicates the maximum number of urban land use images contained in a single pixel within a nighttime light image;

[0046] Pixels in nighttime light images with a city area ratio less than a preset value are considered non-residential area pixels; the preset value is 20%.

[0047] Pixels in nighttime light images whose urban area ratio is greater than or equal to a preset value are designated as residential area pixels.

[0048] In the embodiment provided in this application, urban land use images and nighttime light images are overlaid to understand the inclusion relationship and quantity of overlap between each pixel in the nighttime light image and urban land use pixels in the urban land use image, thereby obtaining the urban land area ratio of each pixel in the nighttime light image. Then, pixels in the nighttime light image with an urban land area ratio greater than or equal to a preset value are designated as residential area pixels, which can eliminate lights in non-residential areas such as commercial service land and roads in the nighttime light image. Pixels in the nighttime light image with an urban land area ratio less than the preset value are designated as non-residential area pixels. This makes it easier to obtain an accurate urban vacancy rate index by calculating only the first urban vacancy rate index of non-residential area pixels, reducing the amount of calculation required for the urban vacancy rate index, improving the calculation efficiency of the urban vacancy rate index, and thus improving the identification efficiency of the distribution of housing vacancy areas in the target area.

[0049] In the embodiment provided in this application, the urban land use image of the target area is obtained by extracting urban land use based on the land use classification data of the target area and resampling it to a resolution of 10m×10m. The maximum number N of urban land use image pixels contained in a single pixel of the nighttime light image is defined as follows: t It is 2500.

[0050] Optionally, the true light intensity of residential area pixels is obtained by utilizing pixel information from non-residential area pixels and residential area pixels, including:

[0051] Obtain the first original grayscale value and the first number of pixels in the non-residential area, and obtain the second original grayscale value of pixels in the residential area;

[0052] The true light intensity of the pixels in the residential area is calculated using the first original gray value, the first number of pixels, and the second original gray value.

[0053] The formula for calculating actual light intensity is as follows:

[0054]

[0055] Among them, DN R,d DN represents the gray level of pixel d in the residential area, that is, the actual light intensity of pixel d in the residential area. P,d N represents the second original gray value of the residential area pixel d. non-resi DN represents the number of the first cell in a non-residential area. non-resi The sum of the gray values ​​of non-residential area pixels, DN non-resi,k This represents the first original gray value of pixel k in the non-residential area.

[0056] In this embodiment provided by this application, by using the first original grayscale value and the first number of non-residential area pixels, and based on the second original grayscale value of residential area pixels, the influence of the first original grayscale value of non-residential area pixels is removed. This makes the calculated true light intensity of residential area pixels closer to the true value, thereby improving the accuracy of the true light intensity. This, in turn, improves the accuracy of the urban vacancy rate index subsequently calculated using the true light intensity, and further improves the accuracy of the distribution of vacant housing areas in the target area obtained based on the urban vacancy rate index. Specifically, the true light intensity of non-residential area pixels is determined to be 0.

[0057] In the embodiment provided in this application, for the purpose of facilitating statistical analysis, the calculated actual light intensity of the residential area pixels is based on... Adjustment restrictions 。

[0058] Optionally, the nighttime light images include multiple consecutive historical nighttime images; regression analysis is performed using the nighttime light images to obtain the trend of nighttime light value changes in the target area, including:

[0059] Linear regression analysis was performed on pixels with the same location information in multiple consecutive historical night images to obtain the linear regression coefficients of the pixels corresponding to the location information.

[0060] The pixel linear regression coefficient is used as the trend of pixel light value change corresponding to the location information;

[0061] The nighttime light value change trend of the target area is formed based on the change trend of light values ​​of multiple pixels.

[0062] In the embodiment provided in this application, linear regression analysis is performed on pixels with the same location information in multiple consecutive historical nighttime images to establish a linear regression mathematical model, thereby calculating the pixel linear regression coefficient corresponding to each location information. The pixel linear regression coefficient is used as the trend of light value change for the pixel corresponding to the location information, and a nighttime light value change trend for the target area is formed based on the light value change trends of multiple pixels. In this way, the nighttime light value change trend of the target area obtained based on linear regression can reveal the pattern of light value change in the target area, effectively reflecting the population loss pattern. This facilitates subsequent dynamic prediction of the actual housing vacancy distribution in the target area based on the nighttime light value change trend that reflects the population loss pattern, making the identification of housing vacancy distribution more immediate and thus improving the accuracy of vacant housing identification in the target area.

[0063] In the embodiment provided in this application, regression analysis is a statistical analysis method for determining the relationship between two or more variables. When there is only one independent variable and one dependent variable, the relationship between them can be approximated by a straight line; this type of regression analysis is called simple linear regression analysis. For example, using historical nighttime images of the target area for five years each from 2011-2015 and 2016-2020, with time as the x-axis and the nighttime light intensity value of a single pixel in the historical nighttime images as the y-axis, a linear regression model is constructed for pixels corresponding to the same location information. The nighttime light intensity value of a single pixel in the historical nighttime images is calculated using the same method as the actual light intensity of a single pixel in the nighttime light images in the aforementioned embodiment.

[0064] Linear regression analysis was performed on pixels with identical location information in multiple consecutive historical nighttime images. The linear regression model for a single pixel is expressed as follows:

[0065] y = ax i +b+ε i ;

[0066]

[0067] Where y represents the nighttime light intensity value of a single pixel in a historical nighttime image, and x i Let represent the year i, where i is a positive integer; 'a' represents the linear regression coefficient of that single pixel, i.e., the trend of pixel light intensity changes; and 'b' represents the intercept of the nighttime light intensity value. This represents the average value across all years. ε represents the average nighttime light intensity of a single pixel over n years. i denoted by , where i represents the year.

[0068] When a is greater than 0, it indicates that the pixel light value is changing upward; when a is less than 0, it indicates that the pixel light value is changing downward; when a equals 0, it indicates that the pixel light value is not changing.

[0069] Optionally, based on the urban vacancy rate index and nighttime light change trends, the distribution of vacant housing areas in the target region can be obtained, including:

[0070] Based on the preset first vacancy classification strategy and the city vacancy rate index, the vacancy level of each pixel in the nighttime light image is obtained.

[0071] Based on the preset second vacancy classification strategy and the trend of nighttime light value changes, the potential vacancy level of each pixel in the nighttime light image is obtained.

[0072] Based on the vacancy level and potential vacancy level, the distribution of vacant housing areas in the target region is obtained.

[0073] In the embodiment provided in this application, based on the preset first vacancy classification strategy and the second vacancy classification strategy, the vacancy level and potential vacancy level of the pixels corresponding to the urban vacancy rate index and the nighttime light value change trend are determined respectively. Based on the level parameters of the two dimensions of vacancy level and potential vacancy level, the distribution of housing vacancy areas in the target area is obtained. The factors considered are more comprehensive, thereby improving the identification accuracy of vacant houses in the target area.

[0074] The second vacancy classification strategy is shown in Table 1. When the pixel light value change trend is less than -0.1, the potential vacancy level of the corresponding pixel is high; when the pixel light value change trend is greater than or equal to -0.1 and less than or equal to 0.1, the potential vacancy level of the corresponding pixel is medium; when the pixel light value change trend is greater than 0.1, the potential vacancy level of the corresponding pixel is low.

[0075] Table 1

[0076] high a<-0.1 middle -0.1≤a≤0.1 Low a>0.1

[0077] Optionally, based on a preset first vacancy classification strategy and an urban vacancy rate index, the vacancy level of each pixel in the nighttime light image is obtained, including:

[0078] The city vacancy rate index is classified using mean-standard deviation to obtain one standard deviation.

[0079] The formula for calculating one standard deviation is as follows:

[0080]

[0081] in, x represents the average urban vacancy rate index of each pixel in the nighttime light image. i σ represents the urban vacancy rate index of the i-th pixel in the nighttime light image, n represents the number of pixels in the nighttime light image, and σ represents one standard deviation.

[0082] Based on the preset first vacancy classification strategy, one standard deviation, and urban vacancy rate index, the vacancy level of pixels in the nighttime light image corresponding to the urban vacancy rate index is determined.

[0083] In the embodiment provided in this application, the first vacancy classification strategy is to divide the urban vacancy rate index into four vacancy levels as shown in Table 2, using one standard deviation as a reference value. In Table 2, in... When the corresponding pixel vacancy level is high; At that time, the corresponding pixel vacancy level is relatively high; in At that time, the corresponding pixel vacancy level is relatively low; in At that time, the corresponding pixel vacancy level is low. Areas with high and high vacancy levels are designated as existing vacant housing areas.

[0084] Table 2

[0085]

[0086] Optionally, based on the vacancy level and potential vacancy level, the distribution of vacant housing areas in the target area is obtained, including:

[0087] Based on the preset vacancy zone division strategy and the vacancy level and potential vacancy level of each pixel in the nighttime light image, the housing area type of each pixel is obtained.

[0088] Based on the area composed of pixels corresponding to the same housing area type, a regional distribution location of the target area is formed, and the distribution of housing vacancy areas in the target area is obtained.

[0089] In the embodiment provided in this application, based on a preset vacancy area division strategy and the vacancy level and potential vacancy level of each pixel in the nighttime light image, the housing area type of each pixel is obtained. Then, based on the areas formed by pixels corresponding to the same housing area type, a regional distribution location of the target area is formed, thus obtaining the housing vacancy area distribution of the target area. In this way, by combining the two dimensions of housing vacancy influencing factors—the degree of housing vacancy and the population loss trend—the actual housing vacancy distribution of the target area is dynamically predicted, making the identification of housing vacancy distribution more immediate. This improves the accuracy of identifying vacant houses in the target area, thereby achieving accurate division of housing vacancy areas.

[0090] The vacancy zone classification strategy involves overlaying the vacancy level and potential vacancy level of each pixel in the nighttime light image to identify existing vacant housing areas and potential vacant housing areas. The resulting housing area type for each pixel is shown in Table 3. In Table 3, when the vacancy level is high / relatively high and the potential vacancy level is high / medium, the corresponding housing area type is a vacant housing area; when the vacancy level is low / relatively low and the potential vacancy level is medium / low, the corresponding housing area type is a densely populated residential area; when the vacancy level is high / relatively high and the potential vacancy level is low, or when the vacancy level is low / relatively low and the potential vacancy level is high, the corresponding housing area type is a mixed area.

[0091] Table 3

[0092]

[0093] This application presents a method for identifying vacant housing areas. Based on nighttime light image data of the target area, it improves the application of the urban vacancy rate index and linear regression model of nighttime light images to accurately identify existing and potential vacant housing areas and dynamically capture the impact of population loss on housing vacancy. This significantly improves the accuracy and dynamic monitoring capability of vacant housing area identification, breaking through the limitations of traditional methods in capturing spatial dynamic changes and the constraint effect of vacant areas, and providing innovative technical support for urban land use optimization and sustainable development. The advantages of this application are: (1) It solves the problem of insufficient accuracy in traditional vacant housing area identification, significantly improving the accuracy of vacant area identification; (2) The model fully utilizes nighttime light data and the urban vacancy rate index to effectively capture the dynamic change characteristics of vacant housing areas; (3) The vacant housing area index can serve as a key constraint in the urban expansion simulation process. Based on the accurate identification of existing and potential vacant housing areas, it more realistically reflects the impact of population loss on the urban spatial pattern, significantly improving the accuracy and reliability of urban expansion simulation, and providing scientific support for urban land use planning.

[0094] Please see Figure 2 , Figure 2 An exemplary embodiment of this application illustrates a housing vacancy area identification system, such as... Figure 2 As shown, this application provides a housing vacancy area identification system 200, including:

[0095] The acquisition module 201 is used to acquire nighttime light images and urban land use images of the target area;

[0096] The first analysis module 202 is used to perform light intensity analysis based on nighttime light images and urban land use images to obtain the urban vacancy rate index of the target area.

[0097] The second analysis module 203 is used to perform regression analysis using nighttime light images to obtain the changing trend of nighttime light values ​​in the target area.

[0098] The distribution determination module 204 is used to obtain the distribution of vacant housing areas in the target area based on the urban vacancy rate index and the trend of nighttime light changes.

[0099] This embodiment of a housing vacancy area identification system analyzes the nighttime light images and urban land images of the target area acquired by the acquisition module 201 using a first analysis module 202 to obtain an urban vacancy rate index for the target area. This index measures the degree of housing vacancy in the target area. Then, a second analysis module 203 performs regression analysis on the nighttime light images to obtain the trend of nighttime light value changes in the target area, dynamically capturing population loss trends. Finally, a distribution determination module 204 determines the housing vacancy distribution in the target area based on the urban vacancy rate index and the nighttime light change trend. By combining the housing vacancy level and population loss trends—two dimensions of influencing factors—the system dynamically predicts the actual housing vacancy distribution in the target area, making the identification of housing vacancy distribution more immediate and thus improving the accuracy of identifying vacant housing in the target area.

[0100] Optionally, the nighttime light image includes the current nighttime image; the first analysis module is specifically used for:

[0101] The nighttime light image was divided into pixels using urban land use images to obtain non-residential area pixels and residential area pixels.

[0102] Based on the pixel information of non-residential area pixels and residential area pixels, the true light intensity of residential area pixels is obtained;

[0103] Based on urban land use images and actual light intensity, the first urban vacancy rate index of residential area pixels is calculated, and the second urban vacancy rate index of non-residential area pixels is determined to be 0.

[0104] The city vacancy rate index for the target area is formed based on the vacancy rate index of the first city and the vacancy rate index of the second city.

[0105] Optionally, the first analysis module is specifically used for:

[0106] The urban land use image and the nighttime light image are overlaid to calculate the urban land area ratio of each pixel in the nighttime light image; the pixel size of the nighttime light image is larger than the pixel size of the urban land use image.

[0107] Pixels in nighttime light images with a city area ratio less than a preset value are considered as non-residential area pixels.

[0108] Pixels in nighttime light images whose urban area ratio is greater than or equal to a preset value are designated as residential area pixels.

[0109] Optionally, the first analysis module is specifically used for:

[0110] Obtain the first original grayscale value and the first number of pixels in the non-residential area, and obtain the second original grayscale value of pixels in the residential area;

[0111] The true light intensity of the pixels in the residential area is calculated using the first original gray value, the first number of pixels, and the second original gray value.

[0112] Optionally, the nighttime light images include multiple consecutive historical nighttime images; the second analysis module is specifically used for:

[0113] Linear regression analysis was performed on pixels with the same location information in multiple consecutive historical night images to obtain the linear regression coefficients of the pixels corresponding to the location information.

[0114] The pixel linear regression coefficient is used as the trend of pixel light value change corresponding to the location information;

[0115] The nighttime light value change trend of the target area is formed based on the change trend of light values ​​of multiple pixels.

[0116] Optionally, the distribution determination module is specifically used for:

[0117] Based on the preset first vacancy classification strategy and the city vacancy rate index, the vacancy level of each pixel in the nighttime light image is obtained.

[0118] Based on the preset second vacancy classification strategy and the trend of nighttime light value changes, the potential vacancy level of each pixel in the nighttime light image is obtained.

[0119] Based on the vacancy level and potential vacancy level, the distribution of vacant housing areas in the target region is obtained.

[0120] Optionally, the distribution determination module is specifically used for:

[0121] Based on the preset vacancy zone division strategy and the vacancy level and potential vacancy level of each pixel in the nighttime light image, the housing area type of each pixel is obtained.

[0122] Based on the area composed of pixels corresponding to the same housing area type, a regional distribution location of the target area is formed, and the distribution of housing vacancy areas in the target area is obtained.

[0123] It should be noted that the housing vacancy area identification system and the housing vacancy area identification method provided in the above embodiments belong to the same concept. The specific operation methods of each module and unit have been described in detail in the method embodiments and will not be repeated here. In practical applications, the housing vacancy area identification system provided in the above embodiments can be assigned to different functional modules as needed, that is, the internal structure of the system can be divided into different functional modules to complete all or part of the functions described above. This is not a limitation here.

[0124] A computing device according to an embodiment of this application includes a memory, a processor, and a program stored in the memory and running on the processor. When the processor executes the program, it implements some or all of the steps of the above-described method for identifying vacant housing areas.

[0125] The computing device can be a computer, and the corresponding program is computer software. The parameters and steps of the computing device mentioned above in this application can be referred to the parameters and steps in the embodiment of the housing vacancy area identification method above, and will not be repeated here.

[0126] This application embodiment provides a computer-readable storage medium storing instructions that, when executed, perform the steps of the aforementioned method for identifying vacant housing areas.

[0127] The computer-readable storage medium may be a transient computer-readable storage medium or a non-transitory computer-readable storage medium.

[0128] The technical solutions of this disclosure can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes one or more instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of this disclosure. The aforementioned computer-readable storage medium can be a non-transitory computer-readable storage medium, including: USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks, and other media capable of storing program code; it can also be a transient computer-readable storage medium.

[0129] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0130] Those skilled in the art will recognize that this application can be implemented as a system, method, or computer program product. Therefore, this disclosure can be implemented in the following forms: it can be entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software, generally referred to herein as a "module" or "system." Furthermore, in some embodiments, this application can also be implemented as a computer program product contained in one or more computer-readable media, which contains computer-readable program code. Computer-readable storage media can be, for example, but not limited to—electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof.

[0131] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0132] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A method for identifying vacant housing areas, characterized in that, include: Acquire nighttime light images and urban land use images of the target area; The nighttime light image is divided into pixels using the urban land use image to obtain non-residential area pixels and residential area pixels; wherein, the pixels in the nighttime light image are mixed pixels containing both residential and non-residential land, and the pixel division is based on the urban land area ratio in the urban land use image; Based on the pixel information of the non-residential area pixels and the residential area pixels, the true light intensity of the residential area pixels is obtained; Based on the urban land use image and the actual light intensity, the first urban vacancy rate index of the residential area pixel is calculated, and the second urban vacancy rate index of the non-residential area pixel is determined to be 0. The city vacancy rate index of the target area is formed based on the first city vacancy rate index and the second city vacancy rate index; Regression analysis was performed using the nighttime light images to obtain the trend of nighttime light value changes in the target area; Based on the preset first vacancy classification strategy and the city vacancy rate index, the vacancy level of each pixel in the nighttime light image is obtained; Based on the preset second vacancy classification strategy and the nighttime light value change trend, the potential vacancy level of each pixel in the nighttime light image is obtained; Based on the vacancy level and the potential vacancy level, the distribution of vacant housing areas in the target area is obtained by coupling and judging through a vacancy area division strategy.

2. The method according to claim 1, characterized in that, The step of dividing the nighttime light image into pixels using the urban land use image to obtain non-residential area pixels and residential area pixels includes: The urban land use image and the nighttime light image are overlaid to calculate the urban land area ratio of each pixel in the nighttime light image; wherein the pixel size of the nighttime light image is larger than the pixel size of the urban land use image; Pixels in the nighttime light image whose urban area ratio is less than a preset value are designated as non-residential area pixels. Pixels in the nighttime light image whose urban area ratio is greater than or equal to the preset value are designated as residential area pixels.

3. The method according to claim 1, characterized in that, The process of obtaining the true light intensity of the residential area pixels based on the pixel information of the non-residential area pixels and the residential area pixels includes: Obtain the first original gray value and the first number of pixels in the non-residential area, and obtain the second original gray value of the pixels in the residential area; The true light intensity of the residential area pixels is calculated using the first original gray value, the first number of pixels, and the second original gray value.

4. The method according to any one of claims 1 to 3, characterized in that, The nighttime light images include multiple consecutive historical nighttime images; the regression analysis using the nighttime light images to obtain the changing trend of nighttime light values ​​in the target area includes: Linear regression analysis is performed on pixels with the same location information in multiple consecutive historical night images to obtain the linear regression coefficients of the pixels corresponding to the location information; The linear regression coefficient of the pixel is used as the trend of the change in the pixel light value corresponding to the location information; The nighttime light value change trend of the target area is formed based on the change trend of multiple pixel light values.

5. The method according to claim 1, characterized in that, The process of determining the distribution of vacant housing areas in the target area by coupling the vacancy level and the potential vacancy level through a vacancy area division strategy includes: Based on a preset vacancy zone division strategy, the vacancy level and potential vacancy level of each pixel in the nighttime light image are coupled and judged to obtain the housing area type of each pixel; Based on the area composed of pixels corresponding to the same housing area type, a regional distribution location of the target area is formed, and the distribution of housing vacancy areas in the target area is obtained.

6. A housing vacancy area identification system, characterized in that, include: The acquisition module is used to acquire nighttime light images and urban land use images of the target area; The first analysis module is used to divide the nighttime light image into pixels using the urban land use image to obtain non-residential area pixels and residential area pixels; wherein, the pixels in the nighttime light image are mixed pixels containing both residential and non-residential land, and the pixel division is based on the urban land area ratio in the urban land use image; based on the pixel information of the non-residential area pixels and the residential area pixels, the true light intensity of the residential area pixels is obtained; based on the urban land use image and the true light intensity, a first urban vacancy rate index of the residential area pixels is calculated, and a second urban vacancy rate index of the non-residential area pixels is determined to be 0; based on the first urban vacancy rate index and the second urban vacancy rate index, an urban vacancy rate index of the target area is formed; The second analysis module is used to perform regression analysis using the nighttime light images to obtain the changing trend of nighttime light values ​​in the target area. The distribution determination module is used to obtain the vacancy level of each pixel in the nighttime light image based on a preset first vacancy classification strategy and the city vacancy rate index; to obtain the potential vacancy level of each pixel in the nighttime light image based on a preset second vacancy classification strategy and the nighttime light value change trend; and to obtain the housing vacancy area distribution of the target area by coupling and discriminating the vacancy level and the potential vacancy level through a vacancy area division strategy.

7. A computing device comprising a memory, a processor, and a program stored in the memory and running on the processor, characterized in that, When the processor executes the program, it implements the steps of the housing vacancy area identification method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed on a terminal device, cause the terminal device to perform the steps of a housing vacancy identification method as described in any one of claims 1 to 5.

Images