Land type determination method and device, and electronic device

Abstract

This application discloses a method, apparatus, and electronic device for determining land types, relating to the field of data processing technology. The method includes: determining multiple first land types and corresponding first area data for each first land type in a target area based on digital elevation data; acquiring an orthophoto map of the target area; processing the orthophoto map using a target neural network model to obtain multiple second land types and corresponding second area data for each second land type in the target area; and comparing and analyzing the multiple first land types, the corresponding first area data, the multiple second land types, and the corresponding second area data to obtain multiple target land types and corresponding target area data for each target land type in the target area. This application solves the problem of low accuracy in identifying land types and area data of target areas in related technologies.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and more specifically, to a method and apparatus for determining land type, and electronic equipment. Background Technology

[0002] In the process of building a digital twin platform, it is often necessary to label the land types of the platform on a large scale. In particular, in water conservancy-related businesses such as river basins and reservoirs, it is necessary to estimate and calculate the economic losses of river basin flood risk disasters. This is highly dependent on the accuracy of the labeling of land types along the river.

[0003] Traditional methods often involve manual labeling or outlining based on common graphic image recognition technologies. However, regardless of the method, the efficiency and accuracy of labeling and outlining land type contours are extremely low.

[0004] Currently, there is no effective solution to the problem that the accuracy of identifying land types and corresponding area data in target areas is relatively low due to the reliance on manual identification in related technologies. Summary of the Invention

[0005] The main objective of this application is to provide a method, apparatus, and electronic device for determining land types, in order to solve the problem that the accuracy of identifying land types and corresponding area data of target areas is relatively low due to the reliance on manual identification in related technologies.

[0006] To achieve the above objectives, according to one aspect of this application, a method for determining land types is provided. The method includes: acquiring digital elevation data of a target area, and determining multiple first land types and first area data corresponding to each first land type based on the digital elevation data; acquiring an orthophoto map of the target area, processing the orthophoto map using a target neural network model to obtain multiple second land types and second area data corresponding to each second land type; and comparing and analyzing the multiple first land types, the first area data corresponding to each first land type, the multiple second land types, and the second area data corresponding to each second land type to obtain multiple target land types and target area data corresponding to each target land type in the target area.

[0007] Further, determining multiple first land types and corresponding first area data for each first land type in the target area based on the digital elevation data includes: preprocessing the digital elevation data to obtain an ordered numerical array, wherein the ordered numerical array includes multiple spatial coordinate data and multiple color value ranges of the target area; identifying the land types of the target area based on the height values ​​in the multiple color value ranges and the multiple spatial coordinate data to obtain the multiple first land types and corresponding first area data for each first land type.

[0008] Further, identifying the land type of the target area based on the multiple color value domains and the height values ​​in the multiple spatial coordinate data to obtain the multiple first land types and the first area data corresponding to each first land type includes: dividing the land range corresponding to the target area based on the multiple color value domains to obtain the land range value corresponding to each color value domain; for each land range value corresponding to a color value domain, if the land range value corresponding to the current color value domain is greater than a first preset threshold, then determining the area corresponding to the current color value domain as a first area range; determining the land type corresponding to the first area range based on the color value domain of the first area range and the height values ​​in the spatial coordinate data of the first area range; and determining the multiple first land types and the first area data corresponding to each first land type based on the land type corresponding to the first area range and the area data of the first area range.

[0009] Further, determining the land type corresponding to the first area range based on the color value range of the first area range and the height value in the spatial coordinate data of the first area range includes: determining multiple land types and the color value range and height value range corresponding to each land type; and determining the land type corresponding to the first area range based on the color value range and height value range corresponding to each land type, the color value range of the first area range, and the height value in the spatial coordinate data of the first area range.

[0010] Further, obtaining the orthophoto of the target region includes: scanning the target region to obtain an initial image corresponding to the target region; extracting the initial image according to the imaging equation to obtain a processed initial image; and cropping the processed initial image to obtain the orthophoto.

[0011] Further, processing the orthophoto map using a target neural network model to obtain multiple second land types and corresponding second area data for each second land type in the target area includes: dividing the orthophoto map into multiple grids; connecting grids with the same color value range according to the color value range of each grid to obtain a closed curve corresponding to each color value range; extracting the target connection point coordinates of the closed curves corresponding to each color value range; determining the second area range and area data of the second area range corresponding to each color value range based on the target connection point coordinates; identifying the land type of the second area range corresponding to each color value range to obtain the land type corresponding to the second area range; and determining multiple second land types and corresponding second area data for each second land type in the target area based on the area data of the second area range and the land type corresponding to the second area range.

[0012] Further, based on the plurality of first land types, the first area data corresponding to each first land type, the plurality of second land types, and the second area data corresponding to each second land type, a comparative analysis is performed to obtain the plurality of target land types and the target area data corresponding to each target land type of the target area. This includes: comparing and analyzing the plurality of first land types, the first area data corresponding to each first land type, the plurality of second land types, and the second area data corresponding to each second land type to obtain a target difference value; if the target difference value is less than a second preset threshold, then based on the plurality of first land types, the first area data corresponding to each first land type, the plurality of second land types, and the second area data corresponding to each second land type, a comparative analysis is performed to obtain the plurality of target land types and the target area data corresponding to each target land type of the target area.

[0013] Further, based on the plurality of first land types, the first area data corresponding to each first land type, the plurality of second land types, and the second area data corresponding to each second land type, a comparative analysis is performed to obtain the plurality of target land types and the target area data corresponding to each target land type of the target area. This includes: if the first area data corresponding to the first land type is equal to the second area data corresponding to the second land type, then the first land type and the first area data corresponding to the first land type are determined to be the target land type and the target area data corresponding to the target land type of the target area, wherein the first land type and the second land type are the same; if the first area data corresponding to the first land type is not equal to the second area data corresponding to the second land type, and the height value corresponding to the first land type is different from the height value corresponding to the second land type, then... If the values ​​are equal, the land area corresponding to the first land type and the land area corresponding to the second land type are merged, and the land type corresponding to the merged land area and the merged land area are used as the target land type and target area data corresponding to the target land type of the target area. If the first area data corresponding to the first land type and the second area data corresponding to the second land type are not equal, and the height value corresponding to the first land type and the height value corresponding to the second land type are not equal, a third area data is determined from the first area data and the second area data, and the land type corresponding to the third area data and the third area data are used as the target land type and target area data corresponding to the target land type of the target area. The third area data is the smallest area among the first area data and the second area data.

[0014] Furthermore, if the target difference value is greater than or equal to the second preset threshold, the method further includes: adjusting the color value range and the height value range corresponding to each land type according to the target difference value, and repeatedly executing the step of determining multiple first land types and first area data corresponding to each first land type of the target area based on the digital elevation data, until the target difference value is less than the second preset threshold.

[0015] To achieve the above objectives, according to another aspect of this application, a land type determination apparatus is provided. The apparatus includes: a first acquisition unit, configured to acquire digital elevation data of a target area and determine, based on the digital elevation data, a plurality of first land types of the target area and first area data corresponding to each first land type; a second acquisition unit, configured to acquire an orthophoto map of the target area and process the orthophoto map using a target neural network model to obtain a plurality of second land types of the target area and second area data corresponding to each second land type; and a comparison unit, configured to perform comparative analysis based on the plurality of first land types, the first area data corresponding to each first land type, the plurality of second land types, and the second area data corresponding to each second land type to obtain a plurality of target land types of the target area and target area data corresponding to each target land type.

[0016] Further, the first acquisition unit includes: a processing subunit, configured to preprocess the digital elevation data to obtain an ordered numerical array, wherein the ordered numerical array includes multiple spatial coordinate data of the target area and multiple color value domains of the target area; and a first identification subunit, configured to identify the land type of the target area based on the multiple color value domains and the height values ​​in the multiple spatial coordinate data, to obtain the multiple first land types and the first area data corresponding to each first land type.

[0017] Further, the identification subunit includes: a division module, used to divide the land area corresponding to the target area according to the plurality of color value domains to obtain a land area value corresponding to each color value domain; a first determination module, used to determine the area corresponding to the current color value domain as a first area range if the land area value corresponding to the current color value domain is greater than a first preset threshold for each color value domain; a second determination module, used to determine the land type corresponding to the first area range according to the color value domain of the first area range and the height value in the spatial coordinate data of the first area range; and a third determination module, used to determine the plurality of first land types and the first area data corresponding to each first land type according to the land type corresponding to the first area range and the area data of the first area range.

[0018] Further, the second determining module includes: a first determining submodule, used to determine multiple land types and the color value range and height value range corresponding to each land type; and a second determining submodule, used to determine the land type corresponding to the first area range based on the color value range and height value range corresponding to each land type, the color value range of the first area range, and the height value in the spatial coordinate data of the first area range.

[0019] Further, the first acquisition unit includes: a scanning subunit, used to scan the target area to obtain an initial image image corresponding to the target area; a first extraction subunit, used to extract the initial image image according to the imaging equation to obtain a processed initial image image; and a cropping subunit, used to crop the processed initial image image to obtain the orthophoto image.

[0020] Further, the second acquisition unit includes: a division subunit, used to divide the orthophoto image into multiple grids, and connect grids with the same color value range according to the color value range corresponding to each grid to obtain a closed curve corresponding to each color value range; a second extraction subunit, used to extract the target connection point coordinates of the closed curve corresponding to each color value range, and determine the second region range and the area data of the second region range according to the target connection point coordinates; a second identification subunit, used to identify the land type of the second region range corresponding to each color value range to obtain the land type corresponding to the second region range; and a determination subunit, used to determine multiple second land types of the target region and the second area data corresponding to each second land type according to the area data of the second region range and the land type corresponding to the second region range.

[0021] Further, the comparison unit includes: a first comparison subunit, used to compare and analyze the plurality of first land types, the first area data corresponding to each first land type, the plurality of second land types, and the second area data corresponding to each second land type to obtain a target difference value; and a second comparison subunit, used to, if the target difference value is less than a second preset threshold, compare and analyze the plurality of first land types, the first area data corresponding to each first land type, the plurality of second land types, and the second area data corresponding to each second land type to obtain the plurality of target land types of the target area and the target area data corresponding to each target land type.

[0022] Further, the second comparison subunit includes: a first processing module, configured to determine, if the first area data corresponding to the first land type is equal to the second area data corresponding to the second land type, that the first land type and the first area data corresponding to the first land type are the target land type and the target area data corresponding to the target land type of the target area, wherein the first land type and the second land type are the same; and a second processing module, configured to merge the land range corresponding to the first land type and the land range corresponding to the second land type if the first area data corresponding to the first land type is not equal to the second area data corresponding to the second land type, and the height value corresponding to the first land type is equal to the height value corresponding to the second land type. The third processing module is used to determine a third area data from the first area data and the second area data if the first area data corresponding to the first land type is not equal to the second area data corresponding to the second land type, and the height value corresponding to the first land type is not equal to the height value corresponding to the second land type. The third area data is the smallest area among the first area data and the second area data.

[0023] Furthermore, the device further includes: an adjustment unit, configured to, if the target difference value is greater than or equal to the second preset threshold, adjust the color value range corresponding to each land type and the height value range corresponding to each land type according to the target difference value, and repeatedly execute the step of determining multiple first land types of the target area and the first area data corresponding to each first land type based on the digital elevation data, until the target difference value is less than the second preset threshold.

[0024] To achieve the above objectives, according to one aspect of this application, an electronic device is provided, the electronic device including one or more processors and a memory, the memory being used to store the method for determining land type implemented by the one or more processors as described in any one of the above claims.

[0025] This application employs the following steps: acquiring digital elevation data of a target area, and determining multiple first land types and corresponding first area data for each first land type based on the digital elevation data; acquiring an orthophoto map of the target area, and processing the orthophoto map using a target neural network model to obtain multiple second land types and corresponding second area data for each second land type; comparing and analyzing the multiple first land types, the corresponding first area data, the multiple second land types, and the corresponding second area data to obtain multiple target land types and corresponding target area data for each target land type. This solves the problem in related technologies where manual identification of land types and corresponding area data in target areas is often used, resulting in low accuracy in identifying land types and area data of target areas. In this scheme, the first land type and the first area data corresponding to each first land type are obtained through digital elevation data of the target area. The second land type and the second area data corresponding to each second land type are obtained through a target neural network model and orthophoto map. Then, the two results are analyzed and compared to obtain the target land type and the target area data corresponding to each target land type of the final target area. By introducing digital elevation data and combining it with remote sensing orthophoto map, the accuracy of data identification from multiple dimensions is achieved, thereby improving the accuracy of identifying land type and area data of the target area. Attached Figure Description

[0026] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0027] Figure 1 This is a flowchart of a method for determining land type according to an embodiment of this application;

[0028] Figure 2 This is a flowchart of an optional land type determination method provided according to an embodiment of this application;

[0029] Figure 3 This is a schematic diagram of a land type determination device according to an embodiment of this application;

[0030] Figure 4 This is a schematic diagram of an electronic device provided according to an embodiment of this application. Detailed Implementation

[0031] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0032] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0033] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0034] It should be noted that all information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) involved in this disclosure are information and data authorized by the user or fully authorized by all parties. For example, this system has an interface with the relevant user or organization. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or organization through the interface, and obtain the relevant information after receiving consent from the aforementioned user or organization.

[0035] In the construction of a digital twin infrastructure, large-scale labeling of land types is often required, especially in water conservancy-related operations such as river basins and reservoirs, where it is necessary to estimate and calculate economic losses from flood risks and disasters. This relies heavily on the accuracy of land type labeling along the riverbanks. To effectively improve the accuracy of land type labeling along the riverbanks, a method for determining land types is proposed.

[0036] The present invention will now be described in conjunction with preferred implementation steps. Figure 1 This is a flowchart of a land type determination method provided in an embodiment of this application, such as... Figure 1 As shown, the method includes the following steps:

[0037] Step S101: Obtain digital elevation data of the target area, and determine multiple first land types and the first area data corresponding to each first land type based on the digital elevation data;

[0038] Specifically, terrain data corresponding to the target area can be downloaded through a development platform. For example, geographic data information of the target area can be downloaded using a certain map software to obtain digital elevation data of the corresponding area. This set of data can directly or indirectly express the basic attributes of the terrain, such as slope, vertical height, terrain surface, terrain structure lines, etc. Different types of attribute parameters can map the corresponding land types to a certain extent. Therefore, multiple first land types of the target area and the first area data corresponding to each first land type can be determined through digital elevation data.

[0039] Step S102: Obtain the orthophoto map of the target area, process the orthophoto map through the target neural network model to obtain multiple second land types of the target area and the second area data corresponding to each second land type;

[0040] Specifically, an orthophoto map of the target area can be obtained by scanning a specific area from the air using a drone. Then, the orthophoto map can be processed by a target neural network model to obtain multiple second land types of the target area and the second area data corresponding to each second land type.

[0041] Step S103: Based on multiple first land types, the first area data corresponding to each first land type, multiple second land types, and the second area data corresponding to each second land type, a comparative analysis is performed to obtain multiple target land types and target area data corresponding to each target land type for the target area.

[0042] Specifically, the multiple first land types and the first area data corresponding to each first land type identified in step S101 are compared and analyzed with the multiple second land types and the second area data corresponding to each second land type identified in step S102 to determine whether there are differences in the identified land type attributes. Then, based on the comparison results, the land type attributes are corrected, adjusted and determined, and finally multiple target land types and target area data corresponding to each target land type are obtained for the target area.

[0043] In summary, the first land type and its corresponding first area data are obtained through digital elevation data of the target area. The second land type and its corresponding second area data are obtained through a target neural network model and orthophoto maps. The two results are then analyzed and compared to obtain the final target land type and its corresponding target area data for the target area. By introducing digital elevation data and combining it with remote sensing orthophoto maps, the accuracy of data identification from multiple dimensions is achieved, thereby improving the accuracy of identifying land type and area data of the target area.

[0044] Determining multiple first land types and corresponding first area data for each first land type in a target area using digital elevation data is crucial. Therefore, in the land type determination method provided in this application embodiment, determining multiple first land types and corresponding first area data for each first land type in a target area based on digital elevation data includes: preprocessing the digital elevation data to obtain an ordered numerical array, wherein the ordered numerical array includes multiple spatial coordinate data and multiple color value domains of the target area; identifying the land types of the target area based on the height values ​​in the multiple color value domains and multiple spatial coordinate data to obtain multiple first land types and corresponding first area data for each first land type.

[0045] Specifically, the topographic data corresponding to the target area can be downloaded through the development platform. Then, the acquired DEM topographic elevation data (including legend and geographic data) is preprocessed to obtain an ordered numerical array. The ordered numerical array includes parameters such as spatial coordinate data and color value range. Preprocessing includes conventional preprocessing methods such as filtering. Then, land type identification is performed based on the color value range and height characteristics of land types, resulting in multiple first land types and their corresponding first area data. The color value range and height characteristics of land types accurately identify the land types and corresponding area data of the target area.

[0046] To improve the efficiency of land type identification, the land type determination method provided in this application embodiment identifies the land type of a target area based on multiple color value domains and height values ​​in multiple spatial coordinate data, obtaining multiple first land types and first area data corresponding to each first land type. This includes: dividing the land range corresponding to the target area according to multiple color value domains to obtain a land range value corresponding to each color value domain; for each land range value corresponding to a color value domain, if the land range value corresponding to the current color value domain is greater than a first preset threshold, then the area corresponding to the current color value domain is determined as a first area range; determining the land type corresponding to the first area range based on the color value domain and height values ​​in the spatial coordinate data of the first area range; and determining multiple first land types and first area data corresponding to each first land type based on the land type corresponding to the first area range and the area data of the first area range.

[0047] Specifically, the land area corresponding to the target region is divided into regions using color value ranges in an ordered numerical array, resulting in a land area value for each color value range. Then, for each color value range, it is determined whether the land area value corresponding to that color value range is greater than a first preset threshold (e.g., 0.5 square meters). If the land area value corresponding to the current color value range is greater than the first preset threshold, then the region corresponding to that color value range is determined as the first region. Furthermore, based on the color value ranges and the height values ​​in the spatial coordinate data of the first region, the land type corresponding to the first region is determined, and the area data corresponding to that land type is obtained. Common land types include, but are not limited to, grassland, woodland, residential land, arable land, and water areas.

[0048] By dividing the target area and removing smaller areas from the division, the efficiency of land type identification can be effectively improved.

[0049] Optionally, in the land type determination method provided in this application embodiment, determining the land type corresponding to the first area range based on the color value range of the first area range and the height value in the spatial coordinate data of the first area range includes: determining multiple land types and the color value range and height value range corresponding to each land type; determining the land type corresponding to the first area range based on the color value range and height value range corresponding to each land type, the color value range of the first area range and the height value in the spatial coordinate data of the first area range.

[0050] Specifically, multiple land types are determined based on the color and height characteristics of land type attributes, and the color value range and height value range corresponding to each land type are determined. The land type corresponding to the first area is determined by the color value range and height value range corresponding to each land type, the color value range of the first area, and the height value in the spatial coordinate data of the first area.

[0051] In an optional embodiment, the criteria for determining whether land is forest land are as follows: The range is identified based on the corresponding color value range, and then a feature judgment is made based on height characteristics: Land with an area exceeding a certain size and a certain color value range, and height data within the range of (5m-10m, 10-15m, 15-20m), is identified as forest land. Land with a color value range of dark green (RGB values ​​within the dark green range) and a height range of 5-10, 10-15, or 15-20 meters is identified as forest land.

[0052] Optionally, in the land type determination method provided in this application embodiment, obtaining the orthophoto map of the target area includes: scanning the target area to obtain an initial image map corresponding to the target area; extracting the initial image map according to the imaging equation to obtain a processed initial image map; and cropping the processed initial image map to obtain an orthophoto map.

[0053] Specifically, a drone can be used to scan the target area from high altitude to obtain an initial image of the target area in the current time and space. Using the corresponding imaging equations, a processed initial image can be extracted from the original non-orthophoto image (i.e., the initial image). Then, the processed initial image is cropped to obtain a high-quality orthophoto image. For example, the initial image can be cropped based on information such as the color value range of the target area.

[0054] The above steps improve the quality of the orthophoto image of the target area, thereby increasing the accuracy of the target neural network model in identifying the target.

[0055] How to process orthophotos using a target neural network model to obtain multiple second land types and corresponding second area data for each second land type in a target area is crucial. Therefore, in the land type determination method provided in this application embodiment, processing orthophotos using a target neural network model to obtain multiple second land types and corresponding second area data for each second land type in a target area includes: dividing the orthophoto into multiple grids; connecting grids with the same color value domain according to the color value domain of each grid to obtain a closed curve corresponding to each color value domain; extracting the target connection point coordinates of the closed curve corresponding to each color value domain, and determining the second area range and area data of the second area range corresponding to each color value domain based on the target connection point coordinates; identifying the land type of the second area range corresponding to each color value domain to obtain the land type corresponding to the second area range; and determining multiple second land types and corresponding second area data for each second land type in the target area based on the area data of the second area range and the land type corresponding to the second area range.

[0056] Specifically, the high-quality orthophotos collected are input into the target neural network model, which processes the orthophotos to obtain multiple second land types of the target area and the second area data corresponding to each second land type.

[0057] First, the orthophoto image is divided into multiple grids, for example, processed as 1cm square pixel grids. Then, based on the color value range corresponding to each grid, the multiple grids are divided and connected to obtain the second region range corresponding to each color value range. For example, pixels processed with the same color value range are locally connected to form closed regions, and the area of ​​the closed regions is calculated. The area data of the second region range and the second region range corresponding to each color value range can be obtained by extracting the coordinates of the target connection points of the closed curves corresponding to each color value range. The target connection points can be the coordinates of the intersection points of the boundary line segments of the closed curves: for example, the intersection points of the four sides of a square. The land type of the second region range corresponding to each color value range is identified to obtain the land type and the area data of the corresponding land type.

[0058] In an alternative embodiment, the second region range corresponding to each color value range can be obtained by extracting the coordinates of the connection points of the closed region (e.g., the coordinates of the intersection points of the boundary line segments of the closed region: the intersection points of the four sides of the square).

[0059] It should be noted that the target neural network model mentioned above can be a conventional type recognition network model.

[0060] Through the above steps, the target neural network model uses two-dimensional orthophoto maps to identify the land type of the target area.

[0061] To improve the accuracy of land type identification and area data identification, the land type determination method provided in this application embodiment involves comparing and analyzing multiple first land types, first area data corresponding to each first land type, multiple second land types, and second area data corresponding to each second land type to obtain multiple target land types and target area data corresponding to each target land type in the target area. This includes: comparing and analyzing multiple first land types, first area data corresponding to each first land type, multiple second land types, and second area data corresponding to each second land type to obtain a target difference value; if the target difference value is less than a second preset threshold, then comparing and analyzing multiple first land types, first area data corresponding to each first land type, multiple second land types, and second area data corresponding to each second land type to obtain multiple target land types and target area data corresponding to each target land type in the target area.

[0062] If the target difference value is greater than or equal to the second preset threshold, the process includes: adjusting the color value range and the height value range corresponding to each land type based on the target difference value, and repeatedly executing the steps of determining multiple first land types and the first area data corresponding to each first land type based on digital elevation data, until the target difference value is less than the second preset threshold.

[0063] Specifically, for multiple first land types, the first area data corresponding to each first land type, and multiple second land types and their corresponding second area data are compared and analyzed to determine the degree of difference between them. Starting from the boundary coordinates of any closed land type region, the data information of the same land type is compared and analyzed in a preset order to obtain the target difference value. Then, it is determined whether the target difference value is less than a second preset threshold (e.g., a difference of 30%). If the target difference value is less than the second preset threshold, the land type attributes are corrected and adjusted using the first land type, the first area data corresponding to each first land type, the second land type, and their corresponding second area data, thereby obtaining multiple target land types for the target region and the target area data corresponding to each target land type.

[0064] If the target difference value is greater than or equal to the second preset threshold, it indicates that there is an anomaly. It is necessary to adjust the color value range and the height value range corresponding to each land type, and repeat the steps of determining multiple first land types and the first area data corresponding to each first land type based on digital elevation data until the target difference value is less than the second preset threshold.

[0065] Optionally, in the land type determination method provided in this application embodiment, the comparison and analysis of multiple first land types, first area data corresponding to each first land type, multiple second land types, and second area data corresponding to each second land type to obtain multiple target land types and target area data corresponding to each target land type for the target area includes: if the first area data corresponding to the first land type is equal to the second area data corresponding to the second land type, then the first land type and the first area data corresponding to the first land type are determined as the target land type and the target area data corresponding to the target land type for the target area, wherein the first land type and the second land type are the same; if the first area data corresponding to the first land type is not equal to the second area data corresponding to the second land type, and the height data corresponding to the first land type is... If the height value is equal to the height value corresponding to the second land type, the land area corresponding to the first land type is merged with the land area corresponding to the second land type. The land type corresponding to the merged land area and the merged land area are used as the target land type and the target area data corresponding to the target land type of the target area. If the first area data corresponding to the first land type is not equal to the second area data corresponding to the second land type, and the height value corresponding to the first land type is not equal to the height value corresponding to the second land type, a third area data is determined from the first area data and the second area data. The land type corresponding to the third area data and the third area data are used as the target land type and the target area data corresponding to the target land type of the target area. The third area data is the smallest area among the first area data and the second area data.

[0066] Specifically, when comparing and analyzing multiple first land types, the first area data corresponding to each first land type, multiple second land types, and the second area data corresponding to each second land type to obtain multiple target land types and target area data corresponding to each target land type for the target area, the method includes: if the first area data corresponding to the first land type is equal to the second area data corresponding to the second land type, then the first land type and the first area data corresponding to the first land type are directly determined as the target land type and the target area data corresponding to the target land type for the target area, or the second land type and the second area data corresponding to each second land type are determined as the target land type and the target area data corresponding to the target land type.

[0067] If the comparison reveals that the first area data corresponding to the first land type is not equal to the second area data corresponding to the second land type, then the corresponding height data information of the two is determined. If the height value corresponding to the first land type is equal to the height value corresponding to the second land type, then the land range corresponding to the first land type and the land range corresponding to the second land type are directly merged, and the land type corresponding to the merged land range and the merged land range are used as the target land type and the target area data corresponding to the target land type of the target area.

[0068] If the comparison reveals that the first area data corresponding to the first land type is not equal to the second area data corresponding to the second land type, and the height value corresponding to the first land type is also not equal to the height value corresponding to the second land type, then the one with the smallest area among the first area data and the second area data is determined as the target land type and the target area data corresponding to the target land type of the target area.

[0069] The above steps effectively improve the accuracy of identifying target land types and corresponding target area data for target regions.

[0070] In an alternative embodiment, the following can be employed: Figure 2 The flowchart shown illustrates the identification of land types. Specifically, in step S201, the target land type and its corresponding area data are generated using elevation data and color values ​​from the DEM (Digital Elevation Model). In step S202, a convolutional neural network model is used to draw connected curves on the XY-axis plane of the orthophoto map and identify the land type and its area data for the target area. In step S203, the land type attribute data of the land area identified in S202 is compared with the land type attribute data identified in S201. Starting from the boundary coordinate point of any closed land type area, the comparison is performed on land type attribute data with the same coordinate values ​​in a preset order to identify whether there are differences in land type attributes. Based on the comparison results, the land type attributes are corrected, adjusted, and determined.

[0071] The land type determination method provided in this application embodiment obtains digital elevation data of a target area and determines multiple first land types and corresponding first area data of each first land type based on the digital elevation data; obtains an orthophoto map of the target area and processes the orthophoto map using a target neural network model to obtain multiple second land types and corresponding second area data of each second land type; and compares and analyzes the multiple first land types, the corresponding first area data, the multiple second land types, and the corresponding second area data to obtain multiple target land types and corresponding target area data of each target land type. This method solves the problem in related technologies where manual identification of land types and corresponding area data of target areas is often used, resulting in low accuracy in identifying land types and area data of target areas. In this scheme, the first land type and the first area data corresponding to each first land type are obtained through digital elevation data of the target area. The second land type and the second area data corresponding to each second land type are obtained through a target neural network model and orthophoto map. Then, the two results are analyzed and compared to obtain the target land type and the target area data corresponding to each target land type of the final target area. By introducing digital elevation data and combining it with remote sensing orthophoto map, the accuracy of data identification from multiple dimensions is achieved, thereby improving the accuracy of identifying land type and area data of the target area.

[0072] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0073] This application also provides a land type determination device. It should be noted that the land type determination device of this application can be used to execute the land type determination method provided in this application. The land type determination device provided in this application is described below.

[0074] Figure 3 This is a schematic diagram of a land type determination device according to an embodiment of this application. Figure 3 As shown, the device includes: a first acquisition unit 301, a second acquisition unit 302, and a comparison unit 303.

[0075] The first acquisition unit 301 is used to acquire digital elevation data of the target area and determine multiple first land types and first area data corresponding to each first land type based on the digital elevation data.

[0076] The second acquisition unit 302 is used to acquire an orthophoto map of the target area, and process the orthophoto map through a target neural network model to obtain multiple second land types of the target area and the second area data corresponding to each second land type.

[0077] The comparison unit 303 is used to compare and analyze multiple first land types, the first area data corresponding to each first land type, multiple second land types, and the second area data corresponding to each second land type to obtain multiple target land types and target area data corresponding to each target land type in the target area.

[0078] The land type determination device provided in this application embodiment acquires digital elevation data of a target area through a first acquisition unit 301, and determines multiple first land types and corresponding first area data of each first land type based on the digital elevation data; a second acquisition unit 302 acquires an orthophoto map of the target area, processes the orthophoto map through a target neural network model, and obtains multiple second land types and corresponding second area data of each second land type; a comparison unit 303 compares and analyzes the multiple first land types and corresponding first area data, multiple second land types and corresponding second area data of each second land type to obtain multiple target land types and corresponding target area data of each target land type. This solves the problem in related technologies where manual identification of land types and corresponding area data of target areas is often used, resulting in low accuracy in identifying land types and area data of target areas. In this scheme, the first land type and the first area data corresponding to each first land type are obtained through digital elevation data of the target area. The second land type and the second area data corresponding to each second land type are obtained through a target neural network model and orthophoto map. Then, the two results are analyzed and compared to obtain the target land type and the target area data corresponding to each target land type of the final target area. By introducing digital elevation data and combining it with remote sensing orthophoto map, the accuracy of data identification from multiple dimensions is achieved, thereby improving the accuracy of identifying land type and area data of the target area.

[0079] Optionally, in the land type determination device provided in this application embodiment, the first acquisition unit includes: a processing subunit, used to preprocess digital elevation data to obtain an ordered numerical array, wherein the ordered numerical array includes multiple spatial coordinate data of the target area and multiple color value domains of the target area; and a first identification subunit, used to identify the land type of the target area based on the height values ​​in the multiple color value domains and multiple spatial coordinate data, to obtain multiple first land types and first area data corresponding to each first land type.

[0080] Optionally, in the land type determination device provided in this application embodiment, the identification subunit includes: a division module, used to divide the land range corresponding to the target area according to multiple color value ranges to obtain the land range value corresponding to each color value range; a first determination module, used to determine the area corresponding to the current color value range as the first area range if the land range value corresponding to the current color value range is greater than a first preset threshold for each color value range; a second determination module, used to determine the land type corresponding to the first area range according to the color value range of the first area range and the height value in the spatial coordinate data of the first area range; and a third determination module, used to determine multiple first land types and first area data corresponding to each first land type according to the land type corresponding to the first area range and the area data of the first area range.

[0081] Optionally, in the land type determination device provided in the embodiments of this application, the second determination module includes: a first determination submodule, used to determine multiple land types and the color value range and height value range corresponding to each land type; and a second determination submodule, used to determine the land type corresponding to the first area range based on the color value range and height value range corresponding to each land type, the color value range of the first area range, and the height value in the spatial coordinate data of the first area range.

[0082] Optionally, in the land type determination device provided in this application embodiment, the first acquisition unit includes: a scanning subunit for scanning the target area to obtain an initial image map corresponding to the target area; a first extraction subunit for extracting the initial image map according to the imaging equation to obtain a processed initial image map; and a cropping subunit for cropping the processed initial image map to obtain an orthophoto map.

[0083] Optionally, in the land type determination device provided in this application embodiment, the second acquisition unit includes: a division subunit, used to divide the orthophoto image into multiple grids, and connect grids with the same color value domain according to the color value domain corresponding to each grid to obtain a closed curve corresponding to each color value domain; a second extraction subunit, used to extract the target connection point coordinates of the closed curve corresponding to each color value domain, and determine the second area range and the area data of the second area range corresponding to each color value domain based on the target connection point coordinates; a second identification subunit, used to identify the land type of the second area range corresponding to each color value domain to obtain the land type corresponding to the second area range; and a determination subunit, used to determine multiple second land types of the target area and the second area data corresponding to each second land type based on the area data of the second area range and the land type corresponding to the second area range.

[0084] Optionally, in the land type determination device provided in this application embodiment, the comparison unit includes: a first comparison subunit, used to compare and analyze multiple first land types, first area data corresponding to each first land type, multiple second land types, and second area data corresponding to each second land type to obtain a target difference value; and a second comparison subunit, used to compare and analyze multiple first land types, first area data corresponding to each first land type, multiple second land types, and second area data corresponding to each second land type if the target difference value is less than a second preset threshold, to obtain multiple target land types of the target area and target area data corresponding to each target land type.

[0085] Optionally, in the land type determination device provided in this application embodiment, the second comparison subunit includes: a first processing module, configured to determine the first land type and the first area data corresponding to the first land type as the target land type and the target area data corresponding to the target land type of the target area if the first area data corresponding to the first land type is equal to the second area data corresponding to the second land type, wherein the first land type and the second land type are the same; and a second processing module, configured to compare the land range corresponding to the first land type with the land range corresponding to the second land type if the first area data corresponding to the first land type is not equal to the second area data corresponding to the second land type, and the height value corresponding to the first land type is equal to the height value corresponding to the second land type. The corresponding land areas are merged, and the land type corresponding to the merged land area and the merged land area are used as the target land type and the target area data corresponding to the target land type of the target area; the third processing module is used to determine the third area data from the first area data and the second area data if the first area data corresponding to the first land type is not equal to the second area data corresponding to the second land type, and the height value corresponding to the first land type is not equal to the height value corresponding to the second land type. The land type corresponding to the third area data and the third area data are used as the target land type and the target area data corresponding to the target land type of the target area, wherein the third area data is the smallest area among the first area data and the second area data.

[0086] Optionally, in the land type determination device provided in this application embodiment, the device further includes: an adjustment unit, configured to adjust the color value range and the height value range corresponding to each land type according to the target difference value if the target difference value is greater than or equal to a second preset threshold, and repeatedly execute the step of determining multiple first land types of the target area and the first area data corresponding to each first land type based on digital elevation data until the target difference value is less than the second preset threshold.

[0087] The aforementioned land type determination device includes a processor and a memory. The first acquisition unit 301, the second acquisition unit 302, and the comparison unit 303 are all stored in the memory as program units. The processor executes the aforementioned program units stored in the memory to achieve the corresponding functions.

[0088] The processor contains a kernel, which retrieves the corresponding program unit from memory. One or more kernels can be configured, and accurate identification of land types can be achieved by adjusting kernel parameters.

[0089] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0090] This invention provides a computer-readable storage medium having a program stored thereon, which, when executed by a processor, implements a method for determining land types.

[0091] This invention provides a processor for running a program, wherein the program executes a method for determining land type during runtime.

[0092] like Figure 4 As shown, this embodiment of the invention provides an electronic device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs the following steps: acquiring digital elevation data of a target area, and determining multiple first land types and first area data corresponding to each first land type based on the digital elevation data; acquiring an orthophoto map of the target area, and processing the orthophoto map through a target neural network model to obtain multiple second land types and second area data corresponding to each second land type; and comparing and analyzing the multiple first land types, the first area data corresponding to each first land type, the multiple second land types, and the second area data corresponding to each second land type to obtain multiple target land types and target area data corresponding to each target land type of the target area.

[0093] Optionally, determining multiple first land types and corresponding first area data for each first land type in the target area based on digital elevation data includes: preprocessing the digital elevation data to obtain an ordered numerical array, wherein the ordered numerical array includes multiple spatial coordinate data and multiple color value ranges of the target area; identifying the land types of the target area based on the height values ​​in the multiple color value ranges and multiple spatial coordinate data to obtain multiple first land types and corresponding first area data for each first land type.

[0094] Optionally, identifying the land type of the target area based on multiple color value domains and height values ​​in multiple spatial coordinate data to obtain multiple first land types and first area data corresponding to each first land type includes: dividing the land range corresponding to the target area based on multiple color value domains to obtain a land range value corresponding to each color value domain; for each land range value corresponding to a color value domain, if the land range value corresponding to the current color value domain is greater than a first preset threshold, then determining the area corresponding to the current color value domain as the first area range; determining the land type corresponding to the first area range based on the color value domain and height values ​​in the spatial coordinate data of the first area range; and determining multiple first land types and first area data corresponding to each first land type based on the land type corresponding to the first area range and the area data of the first area range.

[0095] Optionally, determining the land type corresponding to the first area range based on the color value range of the first area range and the height value in the spatial coordinate data of the first area range includes: determining multiple land types and the color value range and height value range corresponding to each land type; and determining the land type corresponding to the first area range based on the color value range and height value range corresponding to each land type, the color value range of the first area range, and the height value in the spatial coordinate data of the first area range.

[0096] Optionally, obtaining an orthophoto of the target area includes: scanning the target area to obtain an initial image of the target area; extracting the initial image from the initial image according to the imaging equation to obtain a processed initial image; and cropping the processed initial image to obtain an orthophoto.

[0097] Optionally, processing the orthophoto map using a target neural network model to obtain multiple second land types and corresponding second area data for each second land type in the target area includes: dividing the orthophoto map into multiple grids; connecting grids with the same color value range according to the color value range of each grid to obtain a closed curve corresponding to each color value range; extracting the target connection point coordinates of the closed curves corresponding to each color value range; determining the second area range and area data of the second area range corresponding to each color value range based on the target connection point coordinates; identifying the land type of the second area range corresponding to each color value range to obtain the land type corresponding to the second area range; and determining multiple second land types and corresponding second area data for each second land type in the target area based on the area data of the second area range and the land type corresponding to the second area range.

[0098] Optionally, based on multiple first land types, the first area data corresponding to each first land type, multiple second land types, and the second area data corresponding to each second land type, a comparative analysis is performed to obtain multiple target land types and target area data corresponding to each target land type for the target area. This includes: comparing and analyzing multiple first land types, the first area data corresponding to each first land type, multiple second land types, and the second area data corresponding to each second land type to obtain a target difference value; if the target difference value is less than a second preset threshold, then based on multiple first land types, the first area data corresponding to each first land type, multiple second land types, and the second area data corresponding to each second land type, a comparative analysis is performed to obtain multiple target land types and target area data corresponding to each target land type for the target area.

[0099] Optionally, based on multiple first land types, the first area data corresponding to each first land type, multiple second land types, and the second area data corresponding to each second land type, a comparative analysis is performed to obtain multiple target land types and target area data corresponding to each target land type for the target area. This includes: if the first area data corresponding to the first land type is equal to the second area data corresponding to the second land type, then the first land type and the first area data corresponding to the first land type are determined as the target land type and the target area data corresponding to the target land type for the target area, wherein the first land type and the second land type are the same; if the first area data corresponding to the first land type is not equal to the second area data corresponding to the second land type, and the height value corresponding to the first land type is different from that corresponding to the second land type... If the height values ​​are equal, the land area corresponding to the first land type and the land area corresponding to the second land type will be merged, and the land type corresponding to the merged land area and the merged land area will be used as the target land type and the target area data corresponding to the target land type of the target area. If the first area data corresponding to the first land type and the second area data corresponding to the second land type are not equal, and the height value corresponding to the first land type and the height value corresponding to the second land type are not equal, then a third area data will be determined from the first area data and the second area data, and the land type corresponding to the third area data and the third area data will be used as the target land type and the target area data corresponding to the target land type of the target area. The third area data is the smallest area among the first area data and the second area data.

[0100] Optionally, if the target difference value is greater than or equal to a second preset threshold, the method further includes: adjusting the color value range and height value range corresponding to each land type based on the target difference value, and repeatedly executing the step of determining multiple first land types of the target area and the first area data corresponding to each first land type based on digital elevation data, until the target difference value is less than the second preset threshold. The device mentioned in this article can be a server, PC, PAD, mobile phone, etc.

[0101] This application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program having the following method steps: acquiring digital elevation data of a target area, and determining multiple first land types and first area data corresponding to each first land type based on the digital elevation data; acquiring an orthophoto map of the target area, processing the orthophoto map through a target neural network model to obtain multiple second land types and second area data corresponding to each second land type; and comparing and analyzing the multiple first land types, the first area data corresponding to each first land type, the multiple second land types, and the second area data corresponding to each second land type to obtain multiple target land types and target area data corresponding to each target land type of the target area.

[0102] Optionally, determining multiple first land types and corresponding first area data for each first land type in the target area based on digital elevation data includes: preprocessing the digital elevation data to obtain an ordered numerical array, wherein the ordered numerical array includes multiple spatial coordinate data and multiple color value ranges of the target area; identifying the land types of the target area based on the height values ​​in the multiple color value ranges and multiple spatial coordinate data to obtain multiple first land types and corresponding first area data for each first land type.

[0103] Optionally, identifying the land type of the target area based on multiple color value domains and height values ​​in multiple spatial coordinate data to obtain multiple first land types and first area data corresponding to each first land type includes: dividing the land range corresponding to the target area based on multiple color value domains to obtain a land range value corresponding to each color value domain; for each land range value corresponding to a color value domain, if the land range value corresponding to the current color value domain is greater than a first preset threshold, then determining the area corresponding to the current color value domain as the first area range; determining the land type corresponding to the first area range based on the color value domain and height values ​​in the spatial coordinate data of the first area range; and determining multiple first land types and first area data corresponding to each first land type based on the land type corresponding to the first area range and the area data of the first area range.

[0104] Optionally, determining the land type corresponding to the first area range based on the color value range of the first area range and the height value in the spatial coordinate data of the first area range includes: determining multiple land types and the color value range and height value range corresponding to each land type; and determining the land type corresponding to the first area range based on the color value range and height value range corresponding to each land type, the color value range of the first area range, and the height value in the spatial coordinate data of the first area range.

[0105] Optionally, obtaining an orthophoto of the target area includes: scanning the target area to obtain an initial image of the target area; extracting the initial image from the initial image according to the imaging equation to obtain a processed initial image; and cropping the processed initial image to obtain an orthophoto.

[0106] Optionally, processing the orthophoto map using a target neural network model to obtain multiple second land types and corresponding second area data for each second land type in the target area includes: dividing the orthophoto map into multiple grids; connecting grids with the same color value range according to the color value range of each grid to obtain a closed curve corresponding to each color value range; extracting the target connection point coordinates of the closed curve corresponding to each color value range; and determining the second area range and area data corresponding to each color value range based on the target connection point coordinates; identifying the land type of the second area range corresponding to each color value range to obtain the land type corresponding to the second area range; and determining multiple second land types and corresponding second area data for each second land type in the target area based on the area data of the second area range and the land type corresponding to the second area range.

[0107] Optionally, based on multiple first land types, the first area data corresponding to each first land type, multiple second land types, and the second area data corresponding to each second land type, a comparative analysis is performed to obtain multiple target land types and target area data corresponding to each target land type for the target area. This includes: comparing and analyzing multiple first land types, the first area data corresponding to each first land type, multiple second land types, and the second area data corresponding to each second land type to obtain a target difference value; if the target difference value is less than a second preset threshold, then based on multiple first land types, the first area data corresponding to each first land type, multiple second land types, and the second area data corresponding to each second land type, a comparative analysis is performed to obtain multiple target land types and target area data corresponding to each target land type for the target area.

[0108] Optionally, based on multiple first land types, the first area data corresponding to each first land type, multiple second land types, and the second area data corresponding to each second land type, a comparative analysis is performed to obtain multiple target land types and target area data corresponding to each target land type for the target area. This includes: if the first area data corresponding to the first land type is equal to the second area data corresponding to the second land type, then the first land type and the first area data corresponding to the first land type are determined as the target land type and the target area data corresponding to the target land type for the target area, wherein the first land type and the second land type are the same; if the first area data corresponding to the first land type is not equal to the second area data corresponding to the second land type, and the height value corresponding to the first land type is different from that corresponding to the second land type... If the height values ​​are equal, the land area corresponding to the first land type and the land area corresponding to the second land type will be merged, and the land type corresponding to the merged land area and the merged land area will be used as the target land type and the target area data corresponding to the target land type of the target area. If the first area data corresponding to the first land type and the second area data corresponding to the second land type are not equal, and the height value corresponding to the first land type and the height value corresponding to the second land type are not equal, then a third area data will be determined from the first area data and the second area data, and the land type corresponding to the third area data and the third area data will be used as the target land type and the target area data corresponding to the target land type of the target area. The third area data is the smallest area among the first area data and the second area data.

[0109] Optionally, if the target difference value is greater than or equal to the second preset threshold, the method further includes: adjusting the color value range and the height value range corresponding to each land type according to the target difference value, and repeatedly executing the step of determining multiple first land types and the first area data corresponding to each first land type based on digital elevation data, until the target difference value is less than the second preset threshold.

[0110] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0111] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0112] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0113] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0114] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0115] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0116] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0117] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0118] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0119] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for determining land type, characterized in that, include: Obtain digital elevation data of the target area, and determine multiple first land types and first area data corresponding to each first land type based on the digital elevation data; Obtain an orthophoto map of the target area, process the orthophoto map using a target neural network model, and obtain multiple second land types of the target area and second area data corresponding to each second land type; Based on the multiple first land types, the first area data corresponding to each first land type, the multiple second land types, and the second area data corresponding to each second land type, a comparative analysis is performed to obtain the multiple target land types of the target area and the target area data corresponding to each target land type. Specifically, based on the plurality of first land types, the first area data corresponding to each first land type, the plurality of second land types, and the second area data corresponding to each second land type are compared and analyzed to obtain the plurality of target land types and the target area data corresponding to each target land type of the target area, including: The target difference value is obtained by comparing and analyzing the first area data corresponding to each of the multiple first land types, the multiple second land types, and the second area data corresponding to each second land type. If the target difference value is greater than or equal to a second preset threshold, the method further includes: Based on the target difference value, the color value range and the height value range corresponding to each land type are adjusted, and the steps of determining multiple first land types and the first area data corresponding to each first land type based on the digital elevation data are repeated until the target difference value is less than the second preset threshold.

2. The method according to claim 1, characterized in that, Determining multiple first land types and corresponding first area data for each first land type in the target area based on the digital elevation data includes: The digital elevation data is preprocessed to obtain an ordered numerical array, wherein the ordered numerical array includes multiple spatial coordinate data of the target area and multiple color value ranges of the target area; The land type of the target area is identified based on the multiple color value ranges and the height values ​​in the multiple spatial coordinate data, thereby obtaining the multiple first land types and the first area data corresponding to each first land type.

3. The method according to claim 2, characterized in that, Based on the multiple color value ranges and the height values ​​in the multiple spatial coordinate data, the land type of the target area is identified to obtain the multiple first land types and the first area data corresponding to each first land type, including: The land area corresponding to the target area is divided according to the multiple color value ranges to obtain the land area value corresponding to each color value range; For each color value range corresponding to a land range value, if the land range value corresponding to the current color value range is greater than a first preset threshold, then the area corresponding to the current color value range is determined to be the first area range. Based on the color value range of the first area and the height value in the spatial coordinate data of the first area, the land type corresponding to the first area is determined; Based on the land type corresponding to the first area and the area data of the first area, the plurality of first land types and the first area data corresponding to each first land type are determined.

4. The method according to claim 3, characterized in that, Based on the color value range of the first area and the height value in the spatial coordinate data of the first area, the land type corresponding to the first area is determined as follows: Determine multiple land types and the corresponding color value range and height value range for each land type; Based on the color value range corresponding to each land type, the height value range corresponding to each land type, the color value range of the first area range, and the height value in the spatial coordinate data of the first area range, the land type corresponding to the first area range is determined.

5. The method according to claim 1, characterized in that, Obtaining the orthophoto image of the target area includes: The target area is scanned to obtain an initial image of the target area; The initial image is extracted according to the imaging equation to obtain the processed initial image; The processed initial image is cropped to obtain the orthophoto image.

6. The method according to claim 1, characterized in that, By processing the orthophoto map using a target neural network model, multiple second land types of the target area and the corresponding second area data for each second land type are obtained, including: The orthophoto image is divided into multiple grids. Grids with the same color value range are connected according to the color value range corresponding to each grid to obtain a closed curve corresponding to each color value range. Extract the target connection point coordinates of the closed curve corresponding to each color value range, and determine the second region range and the area data of the second region range corresponding to each color value range based on the target connection point coordinates; The land type corresponding to the second region range for each color value range is identified to obtain the land type corresponding to the second region range; Based on the area data of the second region and the land type corresponding to the second region, multiple second land types and second area data corresponding to each second land type are determined for the target region.

7. The method according to claim 1, characterized in that, Based on the plurality of first land types, the first area data corresponding to each first land type, and the plurality of second land types and the second area data corresponding to each second land type, a comparative analysis is performed to obtain the plurality of target land types and the target area data corresponding to each target land type for the target area, including: If the target difference value is less than the second preset threshold, then the multiple first land types, the first area data corresponding to each first land type, the multiple second land types, and the second area data corresponding to each second land type are compared and analyzed to obtain the multiple target land types of the target area and the target area data corresponding to each target land type.

8. The method according to claim 7, characterized in that, Based on the plurality of first land types, the first area data corresponding to each first land type, and the plurality of second land types and the second area data corresponding to each second land type, a comparative analysis is performed to obtain the plurality of target land types and the target area data corresponding to each target land type for the target area, including: If the first area data corresponding to the first land type is equal to the second area data corresponding to the second land type, then the first land type and the first area data corresponding to the first land type are determined to be the target land type and the target area data corresponding to the target land type of the target area, wherein the first land type and the second land type are the same; If the first area data corresponding to the first land type is not equal to the second area data corresponding to the second land type, and the height value corresponding to the first land type is equal to the height value corresponding to the second land type, then the land range corresponding to the first land type and the land range corresponding to the second land type are merged, and the land type corresponding to the merged land range and the merged land range are used as the target land type and the target area data corresponding to the target land type of the target area. If the first area data corresponding to the first land type is not equal to the second area data corresponding to the second land type, and the height value corresponding to the first land type is not equal to the height value corresponding to the second land type, then a third area data is determined from the first area data and the second area data, and the land type corresponding to the third area data and the third area data are taken as the target land type and the target area data corresponding to the target land type of the target area, wherein the third area data is the smallest one among the first area data and the second area data.

9. A land type determination device, characterized in that, include: The first acquisition unit is used to acquire digital elevation data of the target area, and determine multiple first land types of the target area and first area data corresponding to each first land type based on the digital elevation data; The second acquisition unit is used to acquire an orthophoto map of the target area, and process the orthophoto map through a target neural network model to obtain multiple second land types of the target area and second area data corresponding to each second land type; The comparison unit is used to compare and analyze the multiple first land types, the first area data corresponding to each first land type, the multiple second land types, and the second area data corresponding to each second land type to obtain the multiple target land types and the target area data corresponding to each target land type of the target area. The comparison unit includes: a first comparison subunit, used to compare and analyze multiple first land types, first area data corresponding to each first land type, multiple second land types, and second area data corresponding to each second land type to obtain a target difference value; The device further includes an adjustment unit, configured to, if the target difference value is greater than or equal to a second preset threshold, adjust the color value range and the height value range corresponding to each land type based on the target difference value, and repeatedly execute the step of determining multiple first land types of the target area and the first area data corresponding to each first land type based on digital elevation data, until the target difference value is less than the second preset threshold.

10. An electronic device, characterized in that, It includes one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the method for determining land type according to any one of claims 1 to 8.

Images