Method and device for acquiring geographical coordinates of image boundary and building boundary

Abstract

The invention relates to the technical field of geographic information systems and address resolution, in particular to a method for acquiring geographic coordinates of an image boundary and a building boundary, and the method comprises the following steps: segmenting an input address input by a user and a storage address corresponding to the input address in an address database; obtaining a plurality of input sub-addresses and input vectorization sub-addresses respectively corresponding to the input sub-addresses; obtaining a plurality of storage sub-addresses and a storage vectorization sub-address corresponding to each storage sub-address; obtaining a target address based on a matching result of each input sub-address and the storage sub-address corresponding to the input sub-address, and the input vectorized sub-address and the storage vectorized sub-address; and according to the target address, obtaining a target picture comprising the target address, and determining target address boundary geographic coordinates of the target address and building boundary geographic coordinates in the target picture according to pixel coordinates of the target picture.

Description

Technical Field

[0001] Embodiments of the present invention belong to the technical field of geographic information systems and address resolution technologies, and particularly relate to a method and device for obtaining geographical coordinates of an image boundary and a building boundary. Background Art

[0002] In the field of geographical address resolution, existing technologies usually adopt a decentralized processing method. When a user inputs an address name, the system calls an address query interface provided by an online image service provider to return the first few relatively matching address results, and the user manually selects the correct address for subsequent operations. For geographical coordinate-related processing, generally only a page display at a certain scale is performed based on the central coordinate point, and operations such as accurately extracting the geographical coordinate range and embedded watermarks from the image on the image page are rarely involved.

[0003] The existing technical solutions have the following technical problems: First, each link is relatively independent and lacks effective integration, resulting in an insufficiently automated and intelligent processing flow; Second, the processing efficiency is low. The user needs to perform manual operations in different links, and one-stop geographical address-related operations cannot be achieved; Third, the functions for geographical coordinate extraction and processing are limited and cannot meet some requirements in terms of data security and personalized display.

[0004] In summary, the existing technology has the problems that each link of address resolution is relatively independent and lacks effective integration, resulting in a discontinuous processing flow, making it difficult to achieve automation and intelligence, and the coordinates associated with the address have poor security. Summary of the Invention

[0005] Embodiments of the present invention provide a method and device for obtaining geographical coordinates of an image boundary and a building boundary to solve the related problems of the existing technology.

[0006] Embodiments of the present invention provide a method for obtaining geographical coordinates of an image boundary and a building boundary, the method comprising: Segmenting the input address input by the user and the stored address corresponding to the input address in the address database respectively; obtaining a plurality of input sub-addresses and input vectorized sub-addresses corresponding to each input sub-address respectively; obtaining a plurality of stored sub-addresses and stored vectorized sub-addresses corresponding to each stored sub-address; Based on the matching result of each input sub-address and the stored sub-address corresponding to the input sub-address, and the input vectorized sub-address and the stored vectorized sub-address, obtaining a target address; Obtain a target picture including the target address according to the target address, and determine the target address boundary geographical coordinates of the target address and the building boundary geographical coordinates in the target picture according to the pixel coordinates of the target picture.

[0007] Specifically, obtaining the target address based on the matching result of each input sub-address and the corresponding stored sub-address, and the input vectorized sub-address and the stored vectorized sub-address includes: Perform a matching operation one by one using each input sub-address and the corresponding stored sub-address; When the input sub-address and the corresponding stored sub-address match successfully, use the input address corresponding to the input sub-address as the target address; When the input sub-address and the corresponding stored sub-address do not match, calculate the similarity between the input vectorized sub-address of the input sub-address and the stored vectorized sub-address of the stored sub-address. When the similarity is greater than a preset threshold, replace the input sub-address with the stored sub-address, and use the input address after the replacement as the target address.

[0008] Specifically, obtaining the target picture including the target address according to the target address, and determining the target address boundary geographical coordinates of the target address according to the pixel coordinates of the target picture includes: The target picture includes a first target picture; Scale the online image according to a first preset scaling ratio, and take a first target picture including the target address from the scaled online image centered on the target address according to a preset pixel size; Perform binarization processing and edge detection processing on the first target picture, and extract the target address pixel coordinates corresponding to the target address according to the pixel coordinates of the first target picture; Extract the target address boundary geographical coordinates corresponding to the target address according to the target address pixel coordinates.

[0009] Specifically, obtaining the target picture including the target address according to the target address, and determining the building boundary geographical coordinates in the target picture according to the pixel coordinates of the target picture includes: The target picture includes a second target picture; Scale the online image according to a second preset scaling ratio, and take a second target picture including the target address from the scaled online image centered on the target address according to a preset pixel size; Perform binary processing and edge detection processing on the building image in the second target image, and extract the building pixel coordinates corresponding to the building image according to the pixel coordinates of the second target image; Extract the building boundary geographical coordinates corresponding to the target address according to the building pixel coordinates.

[0010] Specifically, after determining the target address boundary geographical coordinates of the target address, it further includes: Convert the account serial number of the current user into binary watermark information with a preset length. When the number of coordinates in the target address boundary geographical coordinates is greater than or equal to the preset length, embed the binary watermark information into the target address boundary geographical coordinates in sequence according to the following formula: ; Where is the th coordinate in the target address boundary geographical coordinates, is the th binary value in the binary watermark information, represents the embedding method, that is, if is 0, then change the preset decimal position of the target address boundary geographical coordinates to an even number, and if is 1, then change the preset decimal position of the coordinates to an odd number.

[0011] Specifically, after embedding the binary watermark information into the target address boundary geographical coordinates, it further includes: Overlay the boundary of the target image corresponding to the target address and the boundary of the building in the target image on the base map of the online image and display it to the user; When receiving a command for the user to click on the boundary of the target image, find the standardized address corresponding to the target image in the standard address library, and display the boundary coordinates of the target image and the standardized address of the target image on the page; When receiving a command for the user to click on the building in the target image, find the standardized address corresponding to the building in the standard address library, and display the boundary coordinates of the building and the standardized address of the building on the page.

[0012] An embodiment of the present invention provides a device for obtaining image boundaries and building boundary geographical coordinates. The device includes: A first operation module, configured to respectively segment the input address input by the user and the stored address corresponding to the input address in the address database; obtain a plurality of input sub-addresses and input vectorized sub-addresses corresponding to each input sub-address; obtain a plurality of stored sub-addresses and stored vectorized sub-addresses corresponding to each stored sub-address; A second operation module, configured to obtain a target address based on the matching result of each input sub-address and the corresponding storage sub-address, and the input vectorized sub-address and the storage vectorized sub-address; A determination module, configured to obtain a target picture including the target address according to the target address, and determine the target address boundary geographical coordinates of the target address and the building boundary geographical coordinates in the target picture according to the pixel coordinates of the target picture.

[0013] Specifically, the second operation module is specifically configured to: Perform a matching operation on each input sub-address and the corresponding storage sub-address one by one; When the input sub-address and the corresponding storage sub-address match successfully, use the input address corresponding to the input sub-address as the target address; When the input sub-address and the corresponding storage sub-address do not match, calculate the similarity between the input vectorized sub-address of the input sub-address and the storage vectorized sub-address of the storage sub-address. When the similarity is greater than a preset threshold, replace the input sub-address with the storage sub-address, and use the input address after the replacement as the target address.

[0014] Specifically, the determination module is specifically configured to: The target picture includes a first target picture; Scale the online image according to a first preset scaling ratio, and take a first target picture including the target address from the scaled online image centered on the target address according to a preset pixel size; Perform binarization processing and edge detection processing on the first target picture, and extract the target address pixel coordinates corresponding to the target address according to the pixel coordinates of the first target picture; Extract the target address boundary geographical coordinates corresponding to the target address according to the target address pixel coordinates.

[0015] An electronic device according to an embodiment of the present invention, characterized in that the electronic device includes a processor, a memory, and a program or instruction stored on the memory and executable on the processor, and the program or instruction is executed by the processor to perform the above method steps for obtaining the geographical coordinates of the image boundary and the building boundary.

[0016] The method provided by the present invention can achieve intelligent parsing and error correction of the geographical address input by the user, as well as effective extraction, secure processing and display of geographical coordinates, achieving the technical effects of improving the accuracy of address parsing, enriching the geographical information processing function and enhancing the user experience. Specifically, first, the address name input by the user is obtained, and sub-word segmentation and vector representation are performed using the BERT model. Then, the online image service interface is called to query, and the top 5 retrieval results are obtained. The BERT model is used to process the query results one by one and compare them with the sub-word set of the input address. If there is no match, the similarity is calculated for replacement and error correction to generate candidate addresses. Then, the standardized address is retrieved according to the corrected address and the address range is queried, and the picture is intercepted. After binarization and edge detection processing, the pixel coordinates are extracted, and then the real geographical coordinates are obtained. Finally, the user account serial number is converted into binary watermark information and embedded in the geographical coordinates. Finally, the address boundary and the building boundary are superimposed and displayed, and the corresponding coordinates and the standardized address can be displayed by clicking. The present invention can realize the automation and intelligence of geographical address processing, improve the overall processing efficiency, and facilitate the user to perform one-stop operations related to geographical addresses. Brief Description of the Drawings

[0017] Figure 1 It is a flowchart of a method for obtaining the geographical coordinates of the image boundary and the building boundary provided by an embodiment of the present invention; Figure 2 It is a schematic structural diagram of a device for obtaining the geographical coordinates of the image boundary and the building boundary provided by an embodiment of the present invention. Detailed Embodiments

[0018] To make the above objects, features, and advantages of the present application more obvious and understandable, the following detailed description of the specific embodiments of the present application will be made in conjunction with the accompanying drawings. Many specific details are set forth in the following description to facilitate a thorough understanding of the present application. However, the present application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without departing from the connotation of the present application. Therefore, the present application is not limited by the specific embodiments disclosed below.

[0019] In the description of the present application, it should be understood that if there are terms such as "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., the orientation or positional relationship indicated by these terms is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present application.

[0020] In addition, if the terms "first" and "second" appear, these terms are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include at least one such feature. In the description of this application, if the term "a plurality of" appears, the meaning of "a plurality of" is at least two, such as two, three, etc., unless otherwise specifically defined.

[0021] An embodiment of the present invention provides a method for obtaining the geographical coordinates of an image boundary and a building boundary, as Figure 1 shown, and the specific process is as follows: Step 11: Segment the input address input by the user and the stored address corresponding to the input address in the address database respectively; obtain a plurality of input sub-addresses and the input vectorized sub-addresses corresponding to each input sub-address respectively; obtain a plurality of stored sub-addresses and the stored vectorized sub-addresses corresponding to each stored sub-address; this step specifically includes the following content: Segment the input address input by the user to obtain the segmented input address set , and this input address set includes a plurality of input sub-addresses , where n is the number of input sub-addresses after segmentation, for example . At the same time, obtain the input vectorized sub-addresses corresponding to each input sub-address respectively, and obtain the input vectorized sub-address set including a plurality of input vectorized sub-addresses , n is the number of input sub-addresses after segmentation, for example .

[0022] Search for the stored address corresponding to the input address in the address database. At this time, multiple stored addresses may be found , and take a preset number of stored addresses, for example, the first five sorted stored addresses can be taken, for example . Perform the above segmentation operation on each stored address to obtain a plurality of stored sub-addresses corresponding to the stored address, for example , and then obtain the stored vectorized sub-addresses corresponding to each stored sub-address. For example, the stored vectorized sub-address set corresponding to is .

[0023] In this process, the Transformer Bidirectional Encoder Representations from Transformers (BERT) model can be used to segment the address.

[0024] Step 12: Based on the matching results of each input sub - address and the corresponding storage sub - address, and the input vectorized sub - address and the storage vectorized sub - address, obtain the target address. Specifically, this step includes: Perform a one - to - one matching operation using each input sub - address and the corresponding storage sub - address. For example, for , use Each sub - address in is respectively matched with each sub - address in

[0025] When the input sub - address and the corresponding storage sub - address match successfully, then use the input address corresponding to the input sub - address as the target address; When the input sub - address and the corresponding storage sub - address do not match, calculate the similarity between the input vectorized sub - address of this input sub - address and the storage vectorized sub - address of this storage sub - address. When the similarity is greater than the preset threshold, replace the input sub - address with this storage sub - address, and use the input address after the replacement as the target address. For example: Compare with one by one. When and do not match, calculate the similarity between and . When the similarity value is greater than the preset threshold, use to replace Use the input address after the replacement as the target address , that is .

[0026] If after the matching and replacement processes involved in the above steps, no suitable replacement sub - word can be found to form a valid target address, then return a retrieval failure message to the user, indicating that the actual address cannot be accurately determined under the current conditions.

[0027] Step 13: According to the target address, obtain the target picture including the target address, and determine the target address boundary geographical coordinates of the target address and the building boundary geographical coordinates in the target picture based on the pixel coordinates of the target picture. The target picture includes the first target picture and the second target picture. This step specifically includes the following steps: Step A: Scale the online image according to the first preset scaling ratio of 1:n, with the target address as the center, and according to the preset pixel size , intercept from the scaled - down online image to include the target address The first target image .

[0028] Step B: Perform binarization processing and edge detection processing on the first target image, and extract the target address pixel coordinates corresponding to the target address according to the pixel coordinates of the first target image . The corresponding target address pixel coordinates

[0029] Step C: Extract the target address boundary geographical coordinates corresponding to the target address according to the target address pixel coordinates . At this time, the obtained target address boundary geographical coordinates are the real addresses of the boundaries of the target address range

[0030] Step D: Scale the online image according to the second preset scaling ratio of 1:m, and use the target address as the center, and according to the preset pixel size , intercept the second target image containing the target address from the online image after the scaling operation is completed ; Step E: Perform binarization processing and edge detection processing on the building image in the second target image , and extract the building pixel coordinates corresponding to the building image according to the pixel coordinates of the second target image Step F: Extract the building boundary geographical coordinates corresponding to the target address according to the building pixel coordinates . At this time, the obtained building boundary geographical coordinates are the real addresses of the building boundaries

[0031] In order to ensure the security of the obtained address data, after determining the target address boundary geographical coordinates and building boundary geographical coordinates of the target address, watermarks can also be added to the above real geographical coordinates. The specific process is as follows Taking adding a watermark to the target address boundary geographical coordinates as an example

[0032] Obtain the account serial number of the current user and convert it into binary watermark information with a preset length of .

[0033] When the number of coordinates in the target address boundary geographical coordinates is less than , no processing will be performed on the target address boundary geographical coordinates, and will be recorded as the target address boundary geographical coordinates after the watermark addition is completed .

[0034] ]>When the target address boundary geographical coordinates ​The number of intermediate coordinates is greater than or equal to Then read the coordinates in sequence according to the order and embed the binary watermark information into according to the following formula The coordinates after watermark embedding are denoted as : ; where is the th coordinate in the target address boundary geographical coordinates, is the th binary value in the binary watermark information, represents the embedding method, that is, if is 0, then the preset position of the decimal part of the target address boundary geographical coordinates is changed to an even number, and if is 1, then the preset position of the decimal part of the coordinates is changed to an odd number.

[0035] For the building boundary geographical coordinates, the watermark information can also be added in the above manner, which will not be elaborated here.

[0036] In order to better display the image, after adding the watermark information to the target address boundary geographical coordinates and the building boundary geographical coordinates of the target address as described above, it further includes: Overlay the boundary of the target image corresponding to the target address and the boundary of the building within the target image on the base map of the online image and display it to the user; When receiving the command that the user clicks on the boundary of the target image, find the standardized address corresponding to the target image in the standard address library, and display the boundary coordinates of the target image and the standardized address of the target image on the page; When receiving the command that the user clicks on the building within the target image, find the standardized address corresponding to the building in the standard address library, and display the boundary coordinates of the building and the standardized address of the building on the page.

[0037] The method provided by the present invention can achieve intelligent parsing and error correction of the user-input geographical address, as well as effective extraction, secure processing, and display of geographical coordinates, achieving the technical effects of improving the accuracy of address parsing, enriching the geographical information processing function, and enhancing the user experience. Specifically, first, the address name input by the user is obtained, and sub-word segmentation and vectorized expression are performed using the BERT model. Then, the online image service interface is called to query and obtain the top 5 retrieval results. The BERT model is used to process the query results one by one and compare them with the sub-word set of the input address. If there is no match, the similarity is calculated for replacement and error correction to generate a candidate address. Then, the standardized address is retrieved according to the corrected address, and the address range is queried. The picture is intercepted, and the pixel coordinates are extracted after binarization and edge detection processing. Then, the real geographical coordinates are obtained. Finally, the user account serial number is converted into binary watermark information and embedded in the geographical coordinates. Finally, the address boundary and the building boundary are superimposed and displayed, and the corresponding coordinates and the standardized address can be displayed by clicking. The present invention can realize the automation and intelligence of geographical address processing, improve the overall processing efficiency, and facilitate the user to perform one-stop operations related to geographical addresses.

[0038] An embodiment of the present invention provides a device for obtaining the geographical coordinates of an image boundary and a building boundary, as Figure 2 shown. The device includes: A first operation module 21, configured to perform segmentation on the input address input by the user and the stored address corresponding to the input address in the address database respectively; obtain a plurality of input sub-addresses and input vectorized sub-addresses corresponding to each input sub-address respectively; obtain a plurality of stored sub-addresses and stored vectorized sub-addresses corresponding to each stored sub-address; A second operation module 22, configured to obtain a target address based on the matching result of each input sub-address and the stored sub-address corresponding to the input sub-address, and the input vectorized sub-address and the stored vectorized sub-address; A determination module 23, configured to obtain a target picture including the target address according to the target address, and determine the geographical coordinates of the target address boundary of the target address and the geographical coordinates of the building boundary in the target picture according to the pixel coordinates of the target picture.

[0039] The second operation module 22 is specifically configured to: Perform a matching operation one by one using each input sub-address and the stored sub-address corresponding to the input sub-address; When the input sub-address and the stored sub-address corresponding to the input sub-address match successfully, use the input address corresponding to the input sub-address as the target address; When the input sub - address does not match the corresponding storage sub - address, calculate the similarity between the input vectorized sub - address of the input sub - address and the storage vectorized sub - address of the storage sub - address. When the similarity is greater than the preset threshold, replace the storage sub - address with the input sub - address, and use the input address after replacement as the target address.

[0040] The determining module 23 is specifically configured to: The target picture includes a first target picture; Scale the online image according to a first preset scaling ratio, and centered on the target address, intercept a first target picture containing the target address from the scaled - down online image according to a preset pixel size; Perform binarization processing and edge detection processing on the first target picture, and extract the target address pixel coordinates corresponding to the target address according to the pixel coordinates of the first target picture; Extract the target address boundary geographical coordinates corresponding to the target address according to the target address pixel coordinates.

[0041] The determining module 23 specifically includes: The target picture includes a second target picture; Scale the online image according to a second preset scaling ratio, and centered on the target address, intercept a second target picture containing the target address from the scaled - down online image according to a preset pixel size; perform binarization processing and edge detection processing on the building image in the second target picture, extract the building pixel coordinates corresponding to the building image according to the pixel coordinates of the second target picture; extract the building boundary geographical coordinates corresponding to the target address according to the building pixel coordinates.

[0042] The device further includes an embedding module 24 for: Convert the account serial number of the current user into binary watermark information of a preset length. When the number of coordinates in the target address boundary geographical coordinates is greater than or equal to the preset length, embed the binary watermark information into the target address boundary geographical coordinates in sequence according to the following formula: ; Where is the th coordinate in the target address boundary geographical coordinates, is the th binary value in the binary watermark information, represents the embedding method, that is, if is 0, then change the decimal preset position of the target address boundary geographical coordinates to an even number. If If it is 1, the preset position of the decimal part of the coordinate is changed to an odd number.

[0043] The device further includes a display module 25 for: Overlaying the boundary of the target image corresponding to the target address and the boundary of the building within the target image on the base map of the online image for display to the user; when receiving a command for the user to click on the boundary of the target image, searching for the standardized address corresponding to the target image in the standard address library, and displaying the boundary coordinates of the target image and the standardized address of the target image on the page; when receiving a command for the user to click on a building within the target image, searching for the standardized address corresponding to the building in the standard address library, and displaying the boundary coordinates of the building and the standardized address of the building on the page.

[0044] An embodiment of the present invention provides an electronic device, the electronic device includes a processor, a memory, and a program or instruction stored on the memory and executable on the processor, and the program or instruction is executed by the processor to perform the steps of the above method for obtaining the geographical coordinates of the image boundary and the building boundary.

[0045] In this application, unless otherwise clearly specified and limited, if terms such as "installation", "connection", "connection", "fixation" appear, these terms should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or integrated; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two components or the interaction relationship between two components, unless otherwise clearly limited. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific situations.

[0046] In this application, unless otherwise clearly specified and limited, if there is a description such as a first feature "on" or "under" a second feature, its meaning can be that the first and second features are in direct contact, or the first and second features are indirectly in contact through an intermediate medium. Moreover, the first feature being "above", "above", and "on" the second feature can be that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is at a higher horizontal height than the second feature. The first feature being "under", "below", and "under" the second feature can be that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is at a lower horizontal height than the second feature.

[0047] It should be noted that if an element is referred to as "fixed to" or "disposed on" another element, it can be directly on the other element or there may also be an intermediate element. If an element is considered to be "connected to" another element, it can be directly connected to the other element or there may be an intermediate element at the same time. If any, the terms "vertical", "horizontal", "upper", "lower", "left", "right" and similar expressions used in this application are only for the purpose of illustration and do not represent the only implementation. The technical features of the above-described embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as within the scope described in this specification.

[0048] The above-described embodiments only represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patent application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the appended claims.

Claims

1. A method for obtaining the geographical coordinates of an image boundary and a building boundary, characterized in that, The method includes: Segmenting the input address input by the user and the storage address corresponding to the input address in the address database respectively; obtaining a plurality of input sub - addresses and input vectorized sub - addresses corresponding to each input sub - address respectively; obtaining a plurality of storage sub - addresses and storage vectorized sub - addresses corresponding to each storage sub - address; Based on the matching result of each input sub - address and the storage sub - address corresponding to the input sub - address, and the input vectorized sub - address and the storage vectorized sub - address, obtaining a target address; According to the target address, obtaining a target picture including the target address, and determining the target address boundary geographical coordinates of the target address and the building boundary geographical coordinates in the target picture according to the pixel coordinates of the target picture.

2. The method according to claim 1, wherein The obtaining of the target address based on the matching result of each input sub - address and the storage sub - address corresponding to the input sub - address, and the input vectorized sub - address and the storage vectorized sub - address includes: Performing a matching operation one by one using each input sub - address and the storage sub - address corresponding to the input sub - address; When the input sub - address and the storage sub - address corresponding to the input sub - address match successfully, taking the input address corresponding to the input sub - address as the target address; When the input sub - address and the storage sub - address corresponding to the input sub - address do not match, calculating the similarity between the input vectorized sub - address of the input sub - address and the storage vectorized sub - address of the storage sub - address. When the similarity is greater than a preset threshold, replacing the input sub - address with the storage sub - address, and taking the input address after the replacement as the target address.

3. The method according to claim 1, characterized in that, The obtaining of the target picture including the target address according to the target address, and determining the target address boundary geographical coordinates of the target address according to the pixel coordinates of the target picture includes: The target picture includes a first target picture; Scaling the online image according to a first preset scaling ratio, centering on the target address, and intercepting a first target picture including the target address from the scaled - down online image according to a preset pixel size; Performing binarization processing and edge detection processing on the first target picture, and extracting the target address pixel coordinates corresponding to the target address according to the pixel coordinates of the first target picture; Extracting the target address boundary geographical coordinates corresponding to the target address according to the target address pixel coordinates.

4. The method according to claim 1, wherein The obtaining of the target picture including the target address according to the target address, and determining the building boundary geographical coordinates in the target picture according to the pixel coordinates of the target picture includes: The target picture includes a second target picture; Scaling the online image according to a second preset scaling ratio, centering on the target address, and intercepting a second target picture including the target address from the scaled - down online image according to a preset pixel size; Performing binarization processing and edge detection processing on the building image in the second target picture, and extracting the building pixel coordinates corresponding to the building image according to the pixel coordinates of the second target picture; Extract the geographical coordinates of the building boundary corresponding to the target address according to the pixel coordinates of the building.

5. The method according to claim 1, wherein After determining the geographical coordinates of the target address boundary of the target address, it further includes: Convert the account serial number of the current user into binary watermark information of a preset length. When the number of coordinates in the geographical coordinates of the target address boundary is greater than or equal to the preset length, embed the binary watermark information into the geographical coordinates of the target address boundary in sequence according to the following formula: ； wherein is the th coordinate in the geographical coordinates of the target address boundary, is the th binary value in the binary watermark information, represents the embedding method, that is, if is 0, then change the preset position of the decimal part of the geographical coordinates of the target address boundary to an even number; if is 1, then change the preset position of the decimal part of the coordinate to an odd number.

6. The method according to claim 5, wherein After the binary watermark information is embedded into the geographical coordinates of the target address boundary, it further includes: Overlay the boundary of the target image corresponding to the target address and the boundary of the building in the target image on the base map of the online image and display it to the user; When receiving a command for the user to click on the boundary of the target image, find the standardized address corresponding to the target image in the standard address library, and display the boundary coordinates of the target image and the standardized address of the target image on the page; When receiving a command for the user to click on a building within the target image, find the standardized address corresponding to the building in the standard address library, and display the boundary coordinates of the building and the standardized address of the building on the page.

7. An apparatus for obtaining the geographical coordinates of an image boundary and a building boundary, characterized in that, The device includes: A first operation module, configured to separately segment the input address input by the user and the stored address corresponding to the input address in the address database; obtain a plurality of input sub-addresses and input vectorized sub-addresses corresponding to each input sub-address respectively; obtain a plurality of stored sub-addresses and stored vectorized sub-addresses corresponding to each stored sub-address; A second operation module, configured to obtain a target address based on the matching result of each input sub-address and the stored sub-address corresponding to the input sub-address, and the input vectorized sub-address and the stored vectorized sub-address; A determination module, configured to obtain a target image including the target address according to the target address, and determine the geographical coordinates of the target address boundary of the target address and the geographical coordinates of the building boundary in the target image according to the pixel coordinates of the target image.

8. The device according to claim 7, characterized in that, The second operation module is specifically configured to: Perform a matching operation on each input sub-address and the stored sub-address corresponding to the input sub-address one by one; When the input sub-address and the stored sub-address corresponding to the input sub-address match successfully, use the input address corresponding to the input sub-address as the target address; When the input sub-address and the stored sub-address corresponding to the input sub-address do not match, calculate the similarity between the input vectorized sub-address of the input sub-address and the stored vectorized sub-address of the stored sub-address. When the similarity is greater than a preset threshold, replace the input sub-address with the stored sub-address, and use the input address after the replacement as the target address.

9. The device according to claim 7, characterized in that, The determination module is specifically configured to: The target image includes a first target image; Scale the online image according to a first preset scaling ratio, and intercept a first target image including the target address from the scaled online image according to a preset pixel size with the target address as the center. Perform binarization processing and edge detection processing on the first target picture, and extract the target address pixel coordinates corresponding to the target address according to the pixel coordinates of the first target picture; Extract the target address boundary geographical coordinates corresponding to the target address according to the target address pixel coordinates.

10. An electronic device, characterized in that, The electronic device includes a processor, a memory, and a program or instruction stored on the memory and executable on the processor, and the program or instruction is executed by the processor to perform the steps of the method for obtaining the image boundary and the building boundary geographical coordinates according to any one of claims 1-6.

Images