Freehand map grading slicing method for agriculture text travel science and technology service

Abstract

The invention relates to the technical field of map slicing, and discloses a freehand map hierarchical slicing method for agriculture tourism science and technology service, which comprises the following steps: acquiring a freehand map of a target area, determining a minimum enclosing rectangle covering the freehand map, and acquiring geographic coordinates of vertexes of the minimum enclosing rectangle; performing feature point detection on the hand-drawn map to obtain a feature point distribution map; determining a scaling hierarchy, slicing the hand-drawn map, and determining the row and column numbers of each tile; calculating a first coordinate of each tile, and calculating a second coordinate based on the geographic coordinate; judging whether the range covered by the first coordinate is within the range covered by the second coordinate, if so, calculating the pixel coordinate of the tile corresponding to the first coordinate in the hand-drawn map, and otherwise, setting the tile corresponding to the first coordinate as blank; querying feature points covered by the pixel coordinates in the feature distribution map, and resampling tiles corresponding to the pixel coordinates based on the feature points to obtain new tiles corresponding to each tile; and storing all the new tiles according to the scaling hierarchy and the row and column number corresponding to each tile. According to the invention, the quality of the hand-drawn map slice can be effectively improved; and meanwhile, the data storage pressure, the network transmission pressure and the front-end rendering pressure are reduced for the tile service application.

Description

Technical Field

[0001] The present invention relates to the technical field of map slicing, and in particular to a hierarchical slicing method for hand-drawn maps for agricultural, cultural, tourism and technological services. Background Art

[0002] Hand-drawn maps are maps made by hand. In the modern sense, hand-drawn maps are a combination of flat maps and three-dimensional painting art. They visualize iconic landscapes such as roads and buildings in the map, and present ordinary city maps in a more interesting way. They are often used in album printing, exhibition board production, electronic map guides, etc. Hand-drawn maps are drawn by map designers in professional drawing software. The original map data is high-precision vector graphics data with a large amount of data. Online map services have the characteristics of large data volume, high concurrency, and the need for fast response, so strict requirements are placed on the efficient transmission and loading of hand-drawn maps.

[0003] In actual engineering applications, different manufacturers have proposed some targeted map grading optimization slicing algorithms based on their own application scenarios and data conditions. Up to now, the mainstream map grading slicing schemes are mainly for surveying and mapping geographic information data such as satellite remote sensing images. The original data format is raster images, and the data content is real-life photos. The map slicing algorithm uses a fixed resampling algorithm to gradually reduce the image resolution, so that the map slices can better retain the image spectral characteristics at a large scale with low storage overhead. However, there are obvious differences between hand-drawn maps and satellite images. When traditional algorithms are applied to hand-drawn map data, there are many deficiencies: 1) Unlike raster images, hand-drawn maps are natural vector data with clear and sharp boundaries and bright colors. Traditional resampling methods will cause text and image lines to be blurred, and the map is less recognizable; 2) Satellite remote sensing images reflect the real scene of the region truthfully, and there is no distinction between primary and secondary content in the picture, while hand-drawn maps highly abstract the regional geographical pattern and major surface elements. The density of elements in different regions is different. Traditional resampling methods cannot effectively process non-uniformly distributed information, resulting in the main body of the map not being prominent; 3) When making hand-drawn maps, the details on the map need to be artistically processed, such as the outline of the terrain, the simplified representation of buildings, and the symbolization of vegetation. In addition, in order to enhance the visual effect, hand-drawn maps may require specially designed color and light and shadow effects, which are usually not necessary in satellite image tile services. Summary of the invention

[0004] The purpose of the present invention is to overcome at least one of the problems mentioned above and to provide a method for hierarchical slicing of hand-drawn maps for agricultural, cultural, tourism and technological services. The present invention can avoid the homogenization and low-quality problems of generated tiles in the prior art by taking different treatments for different landforms, thereby effectively improving the quality of hand-drawn map slicing; at the same time, it ensures that tiles effectively control and reduce the size of tile files while retaining details, thereby reducing data storage pressure, network transmission pressure and front-end rendering pressure for tile service applications.

[0005] In order to achieve the above-mentioned object, the present invention provides a method for hierarchical slicing of hand-drawn maps for agricultural, cultural, tourism and technology services, the method comprising: Obtain a hand-drawn map of the target area, determine a minimum bounding rectangle covering the hand-drawn map, and obtain the geographic coordinates of the vertices of the minimum bounding rectangle; Performing feature point detection on the hand-drawn map to obtain a feature point distribution map; Determine a zoom level, slice the hand-drawn map based on the zoom level and the geographic coordinates of the vertex, and determine the row and column numbers of each tile; Calculate the coordinates of the vertices of each tile under the Web Mercator projection to obtain a first coordinate, and calculate the coordinates of the geographic coordinates under the Web Mercator projection to obtain a second coordinate; Determine whether the range covered by the first coordinate is within the range covered by the second coordinate, if yes, calculate the pixel coordinates of the tile corresponding to the first coordinate in the hand-drawn map, otherwise, set the tile corresponding to the first coordinate to blank; Querying the feature points covered by the pixel coordinates in the feature distribution map, and resampling the tiles corresponding to the pixel coordinates based on the feature points to obtain new tiles corresponding to each tile; All new tiles are stored according to the zoom level and the row and column numbers corresponding to each tile to complete the slicing.

[0006] Furthermore, the process of obtaining a hand-drawn map of the target area, determining a minimum bounding rectangle covering the hand-drawn map, and obtaining geographic coordinates of vertices of the minimum bounding rectangle specifically includes: (1) Obtain a satellite image of the target area, mark the locations with the same positions in the hand-drawn map and the satellite image, and obtain a set of mapping sets of points with the same name; (2) Select any point from the set of homonymous point mappings, determine the pixel coordinates of the point on the hand-drawn map and the geographic coordinates of the point on the satellite image, and determine the initial Helmert transformation relationship between the pixel coordinates and the geographic coordinates based on the pixel coordinates and the geographic coordinates of the point; (3) Substitute the other points in the same-name point mapping set into the initial Helmert transformation relationship one by one, adjust the error and parameters, and obtain the final Helmert transformation relationship; (4) Substitute the pixels of the minimum circumscribed rectangle into the final Helmert transformation relationship to obtain the geographic coordinates of all pixels. (5) Read the geographic coordinates of the four vertices of the minimum circumscribed rectangle from the geographic coordinates of all the pixel points.

[0007] Furthermore, the locations at the same position in the hand-drawn map and the satellite image are marked, wherein the points at the same position are selected from road intersections and / or turning points of land features.

[0008] Furthermore, the hand-drawn map is subjected to feature point detection to obtain a feature point distribution map, wherein the feature points include at least one of edge points, line inflection points, feature point of land object category and scale-invariant feature point. The edge points are used to identify sharp boundaries in the hand-drawn map; The line inflection point is used to identify the area where the line in the hand-drawn map is obviously bent; The scale-invariant feature points are points in the hand-drawn map that do not change according to the transformation conditions, wherein the transformation conditions include illumination, color, noise, and affine transformation; The feature points of the ground object category are used to distinguish different ground objects, and the ground objects include house walls, forest vegetation and water bodies.

[0009] Furthermore, slicing the hand-drawn map based on the zoom level and the geographic coordinates of the vertices and determining the row and column numbers of each tile includes: calculating the coordinates of the geographic coordinates of the vertices under the Web Mercator projection; calculating the spatial resolution of each tile based on the zoom level; calculating the row and column numbers of each tile based on the coordinates of the geographic coordinates of the vertices under the Web Mercator projection and the spatial resolution of each tile.

[0010] Furthermore, the pixel coordinates of the tile corresponding to the first coordinates in the hand-drawn map are calculated in the following manner:

[0011]

[0012] in, is the number of horizontal pixels of the original hand-drawn map, It is the number of vertical pixels of the hand-drawn map.

[0013] Further, querying the feature points covered by the pixel coordinates in the feature distribution map, and resampling the tiles corresponding to the pixel coordinates based on the feature points, specifically includes: (1) Calculate the importance weight of the feature points contained in the tile corresponding to the pixel coordinates; (2) If the importance weight is greater than 200, a high-fidelity resampling method is used for the tile corresponding to the pixel coordinate; otherwise, a low-fidelity resampling method is used for the tile corresponding to the pixel coordinate.

[0014] Furthermore, when calculating the importance weights of the feature points contained in the tile corresponding to the pixel coordinates, if the feature points are of multiple types, the importance weights are accumulated.

[0015] Furthermore, the high-fidelity resampling method is a trilinear interpolation resampling method, and after resampling, the tiles are sharpened using a Sobel operator.

[0016] Furthermore, the low-fidelity resampling method is a nearest neighbor resampling method.

[0017] Compared with the prior art, the present invention has the following beneficial effects: The present invention first performs feature point detection on a hand-drawn map to obtain a feature point distribution map corresponding to the hand-drawn map, then divides the hand-drawn map according to the zoom level and the geographic coordinates of the vertices of the minimum circumscribed rectangle of the hand-drawn map to obtain a group of tiles and the row and column numbers corresponding to each tile, then queries the feature points contained in each tile, and adopts different resampling methods according to the feature points, thereby overcoming the problem of homogenized and low-quality tiles generated by traditional algorithms, and significantly improving the quality of hand-drawn map slices; at the same time, the quality and size of the tiles are balanced to ensure that the tiles effectively control and reduce the size of tile files while retaining details, thereby reducing the data storage pressure, network transmission pressure, and front-end rendering pressure for tile service applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a flowchart of a hand-drawn map hierarchical slicing method for agricultural, cultural and tourism technology services according to Embodiment 1 of the present invention; Figure 2 is a schematic diagram of a hand-drawn map of a target area in Example 1 of the present invention; Figure 3 is a calibration map of the target area in Example 1 of the present invention; Figure 4 is a schematic diagram of characteristic points of buildings and trees in Example 1 of the present invention; Figure 5 Schematic diagram of a tile slice hierarchical division method according to Embodiment 1 of the present invention; Figure 6This is a schematic diagram of slicing a hand-drawn map according to Embodiment 1 of the present invention into tiles of levels 7-20; Figure 7 is a sampling comparison diagram of the high-fidelity resampling method and the low-fidelity resampling method in Example 1 of the present invention; Figure 8 It is a framework diagram of a hand-drawn map hierarchical slicing method for agricultural, cultural, tourism and technological services in an embodiment of the present invention. DETAILED DESCRIPTION

[0019] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0020] In the description of the present invention, it should be noted that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance.

[0021] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0022] Furthermore, in the description of the present invention, unless otherwise specified, “plurality” means two or more.

[0023] Example 1 like Figure 1 As shown, a hand-drawn map hierarchical slicing method for agricultural, cultural, and tourism technology services in a preferred embodiment of an embodiment of the present invention includes: S1: Obtain a hand-drawn map of the target area, determine the minimum bounding rectangle covering the hand-drawn map, and obtain the geographic coordinates of the vertices of the minimum bounding rectangle; In one possible embodiment, a hand-drawn map of the target area is Figure 2 As shown, it can be seen Figure 2It is an agricultural area map, which mainly includes farmland, trees, crops and houses. Specifically, S1 includes: (1) Obtain a satellite image of the target area, mark the locations at the same position in the hand-drawn map and the satellite image, and obtain a set of mappings of points with the same name. In this embodiment, the locations at the same position are road intersections and / or corners of land features. The marking results are shown in Figure 3 ; (2) Select any point from the set of homonymous point mappings, determine the pixel coordinates of the point in the hand-drawn map and the geographic coordinates of the point in the satellite image, and determine the initial Helmert transformation relationship between the pixel coordinates and the geographic coordinates based on the pixel coordinates and the geographic coordinates of the point. Specifically, let the pixel coordinates of the point be , the geographic coordinates of the point with the same name on the satellite image are , based on these two coordinates, the initial Helmert transformation relationship can be determined as follows: ; (3) Substitute the other points in the same-name point mapping set into the initial Helmert transformation relationship one by one, adjust the error and parameters, and obtain the final Helmert transformation relationship. Specifically, the final Helmert transformation relationship is: ; (4) Substitute the pixels of the minimum circumscribed rectangle into the final Helmert transformation relationship to obtain the geographic coordinates of all pixels. (5) Read the geographic coordinates of the four vertices of the minimum bounding rectangle from the geographic coordinates of all the pixel points. Specifically, read the geographic coordinates of the four vertices of the minimum bounding rectangle, recorded as , the geographic coordinates of the minimum enclosing rectangle are:

[0024] .

[0025] S2: Detect feature points on the hand-drawn map to obtain a feature point distribution map; In a feasible embodiment, feature point detection is performed on the hand-drawn map to obtain a feature point distribution map. Feature points include edge points, line inflection points, feature points of land object categories, and scale-invariant feature points. Different feature points can extract features of different elements in the hand-drawn map, specifically: Edge points are used to identify sharp boundaries in the hand-drawn map, such as hand-drawn lines, strokes, color block mutation areas, etc. This embodiment uses the Sobel edge detection algorithm to extract edge points; Line inflection points are used to identify areas where lines in the hand-drawn map are obviously bent, such as road intersections, building eaves and corners, and text. This embodiment uses the Harris corner point detection algorithm to extract feature points; The scale-invariant feature points are points in the hand-drawn map that do not change according to the transformation conditions, wherein the transformation conditions include illumination, color, noise and affine transformation. In this embodiment, the SIFT operator is used to detect the scale-invariant feature points. The feature points of the ground objects are used to distinguish different ground objects, including house walls, forest vegetation and water bodies. This embodiment uses the K-means clustering algorithm to classify pixels. The schematic diagram of the feature points of buildings and forests is shown in the figure. Figure 4 shown.

[0026] S3: Determine the zoom level, slice the hand-drawn map based on the zoom level and the geographic coordinates of the vertices, and determine the row and column numbers of each tile; In a feasible embodiment, the hand-drawn map is divided into levels according to the tile grid. The tile grid is defined as: in the EPSG:3857 plane coordinate system, the global range is projected into a rectangle of equal width and height, with the 0th level tile representing the global range, and each level of tile is divided into four equal parts into the next level of tiles, with a maximum of 24 levels, see Figure 5 The hand-drawn map of this embodiment is sliced ​​into 7-20 tiles. Figure 6 The user end sends a data request to the backend based on the map view range and the current zoom level. Assuming that the longitude range of the frontend current view is [lon1, lon2], the latitude range is [lat1, lat2], and the zoom level is z, the corresponding tile request format is as follows: [BaseURL] / getTile?minX=[lon1]&minY=[lat1]&maxX=[lon2]&maxY=[lat2]&level=[z]&fromat=PNG.

[0027] Suppose the geographic coordinates of a point are ,in represents longitude, Represents latitude. Convert it to Web Mercator projection coordinates (WebMercatorX, WebMercatorY) as follows: (1) Longitude Convert to WebMercatorX:

[0028] in is the radius of the Earth, ; (2) Convert latitude to radians. The conversion formula is:

[0029] (3) Convert to WebMercatorY:

[0030] According to the above conversion method, the longitudes of the upper left and lower right of the map view range are , ,latitude , , we can know the coordinate range of the view range under the Web Mercator projection, which is recorded as [WebMercatorX1, WebMercatorX2], [WebMercatorY1, WebMercatorY2].

[0031] Assuming the current zoom level is level, according to the tile partitioning rules in S3, the spatial resolution of each tile at the current level is:

[0032] Where C is the circumference of the earth, C= , R is the image resolution of each tile, the default is 512 pixels.

[0033] According to the Mercator projection coordinates and tile spatial resolution, the row and column numbers of the tile to which the projection coordinates belong at the current zoom level (that is, the number of the tile covering the coordinate point) can be calculated:

[0034] Substituting the coordinates of the current map view range under the Web Mercator projection into the formula, we can get the tile number list corresponding to the current view range, which is recorded as , .

[0035] S4: Calculate the coordinates of the vertices of each tile under the Web Mercator projection to obtain the first coordinates, calculate the coordinates of the geographic coordinates under the Web Mercator projection to obtain the second coordinates; In a feasible embodiment, suppose a tile T is numbered , then the coordinates of the upper left corner of the tile in the Web Mercator projection are:

[0036] Similarly, the coordinates of the lower right corner vertex of the tile under the Web Mercator projection are:

[0037] The above coordinates are also the first coordinates. According to the above projection coordinate transformation method, the latitude and longitude coordinates of the original hand-drawn image can be converted into Mercator projection coordinates, which can be expressed as:

[0038]

[0039] in, is the Mercator projection coordinate of the upper left vertex of the hand-drawn map, The Mercator projection coordinates for the lower right vertex of the hand-drawn map.

[0040] S5: Determine whether the range covered by the first coordinate is within the range covered by the second coordinate. If so, calculate the pixel coordinates of the tile corresponding to the first coordinate in the hand-drawn map. Otherwise, set the tile corresponding to the first coordinate to blank. In a feasible embodiment, the tile vertex coordinates are compared with the original image vertex coordinates. If the tile coverage is outside the original image, the tile content is empty. Otherwise, the pixel coordinates of the tile vertex in the original hand-painted image are calculated. Taking the upper left corner vertex as an example, the calculation method is as follows:

[0041] in is the number of horizontal pixels of the original hand-drawn map, It is the number of vertical pixels of the hand-drawn map.

[0042] S6: querying the feature points covered by the pixel coordinates in the feature distribution map, resampling the tiles corresponding to the pixel coordinates based on the feature points, and obtaining new tiles corresponding to each tile; In a feasible embodiment, a corresponding resampling strategy is selected according to the category and distribution of feature points. For areas with a small image area but densely distributed feature points (such as buildings, roads, artificial surfaces, etc.), a high-fidelity resampling method (trilinear interpolation) is used, and sharpening is performed after interpolation to ensure that the image lines are clear and visible. For areas with a large image area but sparsely distributed feature points (such as natural surfaces, trees and vegetation, etc.), a low-fidelity fast resampling method (nearest neighbor sampling) is used to improve the image processing speed. The specific resampling method is as follows: (1) According to the feature point type defined in S2, define the importance weight of each type of feature point; the importance weight of the feature point is as follows:

[0043] (2) For each tile, traverse all the feature points it contains, query the feature point type and accumulate the importance weight, and finally get the tile importance weight. If a feature point has multiple types, the importance weight is accumulated (for example, a point is both a feature point on a building and a line inflection point).

[0044] (3) Set the tile importance threshold. When the tile importance weight exceeds 200, it is considered an important tile and uses the trilinear interpolation resampling method and the Sobel operator for sharpening to retain image details to the greatest extent. When the tile importance weight is less than 200, it is considered an ordinary tile and uses the nearest neighbor sampling method to increase the resampling speed. The comparison of the two resampling methods is as follows Figure 7 .

[0045] S7: All new tiles are stored according to the zoom level and the row and column numbers corresponding to each tile, completing the slicing.

[0046] Example 2 In order to verify the superiority of the method proposed in Example 1, this example compares the performance of the method in Example 1 with the traditional method. The comparison results are as follows:

[0047] The superiority of the method of the present invention can be seen from the above table.

[0048] Example 3 An embodiment of the present invention also provides a computer-readable storage medium, on which is stored a computer program for a method for hierarchical slicing of hand-drawn maps for agricultural, cultural, tourism and technological services. When the computer program for the method for hierarchical slicing of hand-drawn maps for agricultural, cultural, tourism and technological services is processed, the steps of the method for hierarchical slicing of hand-drawn maps for agricultural, cultural, tourism and technological services are implemented.

[0049] In summary, the embodiment of the present invention provides a hierarchical slicing method for hand-drawn maps of agricultural, cultural, and tourism technology services, which first detects feature points on the hand-drawn map to obtain a feature point distribution map corresponding to the hand-drawn map, then slices the hand-drawn map according to the zoom level and the vertex geographic coordinates of the minimum circumscribed rectangle of the hand-drawn map, obtains a group of tiles and the row and column numbers corresponding to each tile, and then queries the feature points contained in each tile, adopts different resampling methods according to the feature points, overcomes the problem of homogenization and low quality of tiles generated by traditional algorithms, and significantly improves the quality of hand-drawn map slicing; at the same time, it balances the quality and size of the tiles, ensures that the tiles retain details, effectively controls and reduces the size of tile files, and reduces the data storage pressure, network transmission pressure, and front-end rendering pressure for tile service applications. .

[0050] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and substitutions can be made without departing from the technical principles of the present invention. These improvements and substitutions should also be regarded as the scope of protection of the present invention.

Claims

1. A hand-drawn map hierarchical slicing method for agricultural, cultural, tourism and technology services, characterized in that: The method comprises the following steps: Obtain a hand-drawn map of the target area, determine a minimum bounding rectangle covering the hand-drawn map, and obtain the geographic coordinates of the vertices of the minimum bounding rectangle; Performing feature point detection on the hand-drawn map to obtain a feature point distribution map; Determine a zoom level, slice the hand-drawn map based on the zoom level and the geographic coordinates of the vertex, and determine the row and column numbers of each tile; Calculate the coordinates of the vertices of each tile under the Web Mercator projection to obtain a first coordinate, and calculate the coordinates of the geographic coordinates under the Web Mercator projection to obtain a second coordinate; Determine whether the range covered by the first coordinate is within the range covered by the second coordinate, if so, calculate the pixel coordinates of the tile corresponding to the first coordinate in the hand-drawn map, otherwise, set the tile corresponding to the first coordinate to blank; Querying the feature points covered by the pixel coordinates in the feature distribution map, and resampling the tiles corresponding to the pixel coordinates based on the feature points to obtain new tiles corresponding to each tile; All new tiles are stored according to the zoom level and the row and column numbers corresponding to each tile to complete the slicing.

2. A hand-drawn map hierarchical slicing method for agricultural, cultural, tourism and technological services according to claim 1, characterized in that: The process of obtaining a hand-drawn map of the target area, determining a minimum bounding rectangle covering the hand-drawn map, and obtaining geographic coordinates of vertices of the minimum bounding rectangle includes: (1) Obtain a satellite image of the target area, mark the locations with the same positions in the hand-drawn map and the satellite image, and obtain a set of mapping sets of points with the same name; (2) Select any point from the set of homonymous point mappings, determine the pixel coordinates of the point on the hand-drawn map and the geographic coordinates of the point on the satellite image, and determine the initial Helmert transformation relationship between the pixel coordinates and the geographic coordinates based on the pixel coordinates and the geographic coordinates of the point; (3) Substitute the other points in the same-name point mapping set into the initial Helmert transformation relationship one by one, adjust the error and parameters, and obtain the final Helmert transformation relationship; (4) Substitute the pixels of the minimum circumscribed rectangle into the final Helmert transformation relationship to obtain the geographic coordinates of all pixels. (5) Read the geographic coordinates of the four vertices of the minimum circumscribed rectangle from the geographic coordinates of all the pixel points.

3. A hand-drawn map hierarchical slicing method for agricultural, cultural, tourism and technological services according to claim 2, characterized in that: The same locations in the hand-drawn map and the satellite image are marked, wherein the same locations are selected from road intersections and / or turning points of land features.

4. A hand-drawn map hierarchical slicing method for agricultural, cultural, tourism and technology services according to claim 1, wherein The characteristic is that The feature point detection is performed on the hand-drawn map to obtain a feature point distribution map, wherein the feature points include at least one of edge points, line inflection points, feature points of land object categories and scale-invariant feature points. The edge points are used to identify sharp boundaries in the hand-drawn map; The line inflection point is used to identify the area where the line in the hand-drawn map is obviously bent; The scale-invariant feature points are points in the hand-drawn map that do not change according to the transformation conditions, wherein the transformation conditions include illumination, color, noise, and affine transformation; The feature points of the ground object category are used to distinguish different ground objects, and the ground objects include house walls, forest vegetation and water bodies.

5. A hand-drawn map hierarchical slicing method for agricultural, cultural, tourism and technology services according to claim 1, wherein The characteristic is that The slicing of the hand-drawn map based on the zoom level and the geographic coordinates of the vertices, and determining the row and column numbers of each tile, includes: calculating the coordinates of the geographic coordinates of the vertices under the Web Mercator projection; calculating the spatial resolution of each tile based on the zoom level; and calculating the row and column numbers of each tile based on the coordinates of the geographic coordinates of the vertices under the Web Mercator projection and the spatial resolution of each tile.

6. A hand-drawn map hierarchical slicing method for agricultural, cultural and tourism technology services according to claim 1, wherein The characteristic is that the pixel coordinates of the tile corresponding to the first coordinates in the hand-drawn map are calculated in the following manner: in, is the number of horizontal pixels of the original hand-drawn map, It is the number of vertical pixels of the hand-drawn map.

7. A hand-drawn map hierarchical slicing method for agricultural, cultural, tourism and technology services according to claim 1, wherein The characteristic is that Querying the feature points covered by the pixel coordinates in the feature distribution map, and resampling the tiles corresponding to the pixel coordinates based on the feature points, specifically includes: (1) Calculate the importance weight of the feature points contained in the tile corresponding to the pixel coordinates; (2) If the importance weight is greater than 200, a high-fidelity resampling method is used for the tile corresponding to the pixel coordinate; otherwise, a low-fidelity resampling method is used for the tile corresponding to the pixel coordinate.

8. A hand-drawn map hierarchical slicing method for agricultural, cultural, tourism and technology services according to claim 7, wherein The characteristic lies in that, when calculating the importance weights of the feature points contained in the tile corresponding to the pixel coordinates, if the feature points are of multiple types, the importance weights are accumulated.

9. A method for hierarchical slicing of hand-drawn maps for agricultural, cultural, tourism and technology services according to claim 7, wherein The method is characterized in that the high-fidelity resampling method is a trilinear interpolation resampling method, and after resampling, the Sobel operator is used to sharpen the tiles.

10. A hand-drawn map hierarchical slicing method for agricultural, cultural, tourism and technology services according to claim 7, It is characterized in that The low-fidelity resampling method is a nearest neighbor resampling method.

Images