CN-116343025-B - Land type determining method and device and electronic equipment

CN116343025BCN 116343025 BCN116343025 BCN 116343025BCN-116343025-B

Abstract

The application discloses a method and a device for determining land types and electronic equipment, and relates to the technical field of data processing, wherein the method comprises the steps of determining a plurality of first land types of a target area and first area data corresponding to each first land type according to digital elevation data; the method comprises the steps of obtaining an orthographic image of a target area, processing the orthographic image through 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 comparing and analyzing the plurality of second land types and second area data corresponding to each second land type according to the first area data corresponding to each first 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. The method and the device solve the problem that the accuracy rate of identifying the land type and the area data of the target area is low in the related technology.

Inventors

You Yongmin
Request for anonymity

Assignees

久瓴(上海)智能科技有限公司

Dates

Publication Date: 20260505
Application Date: 20230208

Claims (10)

1. A method of determining a land type, comprising: acquiring digital elevation data of a target area, and determining a plurality of first land types of the target area and first area data corresponding to each first land type according to the digital elevation data; acquiring an orthographic image of the target area, and processing the orthographic image through 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; According to the first area data corresponding to each first land type, comparing and analyzing the second area data corresponding to each second land type and the 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; According to the first area data corresponding to each first land type, comparing and analyzing the second area data corresponding to each second land type with the second land type, and obtaining a plurality of target land types of the target area and target area data corresponding to each target land type comprises the following steps: Comparing and analyzing the first area data corresponding to each first land type, the 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 greater than or equal to a second preset threshold, the method further includes: And adjusting 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 executing the steps of determining a plurality of first land types of the target area and first area data corresponding to each first land type according to the digital elevation data until the target difference value is smaller than the second preset threshold value.
2. The method of claim 1, wherein determining a plurality of first land types for the target area and first area data corresponding to each first land type from the digital elevation data comprises: preprocessing the digital elevation data to obtain an ordered value array, wherein the ordered value array comprises a plurality of space coordinate data of the target area and a plurality of color value fields of the target area; and identifying the land type of the target area according to the plurality of color value fields and the height values in the plurality of space coordinate data, and obtaining the plurality of first land types and first area data corresponding to each first land type.
3. The method of claim 2, wherein identifying the land type of the target area based on the plurality of color value ranges and the height values in the plurality of spatial coordinate data, obtaining the plurality of first land types and the first area data corresponding to each first land type comprises: Dividing the land range corresponding to the target area according to the plurality of color value fields to obtain a land range value corresponding to each color value field; For the land range value corresponding to each color value range, if the land range value corresponding to the current color value range is larger than a first preset threshold value, determining that the area corresponding to the current color value range is a first area range; determining a 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 space coordinate data of the first area range; And determining the 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.
4. A method according to claim 3, wherein determining the land type to which the first area range corresponds from the color value range of the first area range and the height value in the spatial coordinate data of the first area range comprises: determining a plurality of land types, a color value range corresponding to each land type and a height value range corresponding to each land type; And determining the land type corresponding to the first area range according to the color value range corresponding to each land type and the height value in the color value range of the first area range and the space coordinate data of the first area range.
5. The method of claim 1, wherein acquiring an orthographic image of the target region comprises: scanning the target area to obtain an initial image corresponding to the target area; extracting the initial image according to a conformation equation to obtain a processed initial image; and cutting the processed initial image graph to obtain the orthographic image graph.
6. The method of claim 1, wherein processing the orthographic image with a target neural network model to obtain a plurality of second land types for the target area and second area data corresponding to each second land type comprises: dividing the orthophoto map into a plurality of grids, and connecting the 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; Extracting target connection point coordinates of a closed curve corresponding to each color value range, and determining a second area range corresponding to each color value range and area data of the second area range according to the target connection point coordinates; Identifying the land type of a second area range corresponding to each color value range to obtain the land type corresponding to the second area range; and determining a plurality of second land types of the target area and second area data corresponding to each second land type according to the area data of the second area range and the land type corresponding to the second area range.
7. The method of claim 1, wherein performing a comparative analysis on the first area data corresponding to each of the plurality of first land types, the second area data corresponding to each of the plurality of second land types, and the second area data corresponding to each of the plurality of second land types to obtain the plurality of target land types and the target area data corresponding to each of the target land types for the target area comprises: And if the target difference value is smaller than a second preset threshold value, comparing and analyzing the plurality of second land types and the second area data corresponding to each second land type according to the first area data corresponding to each first land type and the plurality of first land types to obtain a plurality of target land types of the target area and the target area data corresponding to each target land type.
8. The method of claim 7, wherein performing a comparative analysis on the first area data corresponding to each of the plurality of first land types, the second area data corresponding to each of the plurality of second land types, and the second area data corresponding to each of the plurality of second land types to obtain the plurality of target land types and the target area data corresponding to each of the target land types for the target area comprises: If the first area data corresponding to the first land type is equal to the second area data corresponding to the second land type, determining that the first area data corresponding to the first land type and the first land type are target area data corresponding to a target land type and a 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, fusing the land range corresponding to the first land type with the land range corresponding to the second land type, and taking the land type corresponding to the fused land range and the fused land range as target area data corresponding to the target land type and the target land type of the target area; and 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, determining third area data from the first area data and the second area data, and taking the land type corresponding to the third area data and the third area data as target area data corresponding to the target land type and the target land type of the target area, wherein the third area data is the smallest area in the first area data and the second area data.
9. A land type determining apparatus, comprising: the first acquisition unit is used for acquiring digital elevation data of a target area and determining a plurality of first land types of the target area and first area data corresponding to each first land type according to the digital elevation data; The second acquisition unit is used for acquiring an orthographic image of the target area, and processing the orthographic image through 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; The comparison unit is used for carrying out comparison analysis on the first area data corresponding to each first land type, the second land types and the second area data corresponding to each second land type according to the first land types, so as to obtain a plurality of target land types of the target area and target area data corresponding to each target land type; The comparison unit comprises a first comparison subunit, a second comparison subunit and a comparison unit, wherein the first comparison subunit is used for comparing and analyzing a plurality of first land types, first area data corresponding to each first land type, a plurality of second land types and second area data corresponding to each second land type to obtain a target difference value; The device further comprises an adjusting unit, wherein the adjusting unit is used for adjusting 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 if the target difference value is larger than or equal to a second preset threshold value, and repeatedly executing the steps of determining a plurality of first land types of the target area and first area data corresponding to each first land type according to the digital elevation data until the target difference value is smaller than the second preset threshold value.
10. An electronic device comprising one or more processors and a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of determining a land type of any of claims 1-8.

Description

Land type determining method and device and electronic equipment Technical Field The application relates to the technical field of data processing, in particular to a method and a device for determining land types and electronic equipment. Background In the process of constructing the digital twin base, the land type of the base is required to be marked on a large scale, and particularly in the related water conservancy businesses such as a river basin, a reservoir and the like, the economic loss of the flood risk disaster of the river basin is required to be estimated and calculated, which is very dependent on the accuracy of marking the land type along the coast. The traditional mode mostly adopts manual marking or is based on common graphic image recognition technology for outlining, but the efficiency and the accuracy of marking and outlining the soil type outline are extremely low in any mode. Aiming at the problem that the accuracy rate of identifying the land type and the area data of the target area is low due to the fact that the land type and the area data of the target area are manually identified in the related art, no effective solution is proposed at present. Disclosure of Invention The application mainly aims to provide a method and a device for determining a land type and electronic equipment, and aims to solve the problem that in the related art, the land type and area data of a target area are manually identified, so that the accuracy rate of identifying the land type and the area data of the target area is low. In order to achieve the above object, according to one aspect of the present application, there is provided a method of determining a land type. The method comprises the steps of obtaining digital elevation data of a target area, determining a plurality of first land types of the target area and first area data corresponding to each first land type according to the digital elevation data, obtaining an orthophoto image of the target area, processing the orthophoto image through 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 comparing and analyzing the plurality of second land types and the second area data corresponding to each second land type according to the plurality of first land types and the first area data corresponding to each first land type to obtain a plurality of target land types of the target area and target area data corresponding to each target land type. Further, determining a plurality of first land types of the target area and first area data corresponding to each first land type according to the digital elevation data comprises preprocessing the digital elevation data to obtain an ordered number value array, wherein the ordered number value array comprises a plurality of space coordinate data of the target area and a plurality of color value fields of the target area, and identifying the land types of the target area according to the plurality of color value fields and the height values in the plurality of space coordinate data to obtain the first area data corresponding to the plurality of first land types and each first land type. Further, the method comprises the steps of identifying the land type of the target area according to the plurality of color value fields and the height value in the plurality of space coordinate data, and determining the land type corresponding to the first area according to the height value in the color value fields and the space coordinate data of the first area, wherein the land range corresponding to the target area is divided according to the plurality of color value fields to obtain a land range value corresponding to each color value field, and if the land range value corresponding to each color value field is larger than a first preset threshold value, determining the area corresponding to the current color value field as a first area range, determining the land type corresponding to the first area according to the color value fields of the first area range and the height value in the space coordinate data of the first area range, and determining the first land type corresponding to the plurality of first area types and the first area data corresponding to the first area range according to the land type corresponding to the first area range. Further, determining 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 space coordinate data of the first area range comprises determining a plurality of land types, a color value range corresponding to each land type and a height value range corresponding to each land type, and determining the land type corresponding to the first area range according to the color value range corresponding to each land type, the height value range corresponding to each land type, the color value range of the f