Road information acquisition method, device, equipment and medium

Abstract

A road information acquisition method, device, equipment and medium are disclosed, the method comprising: acquiring a road surface contour image; using a scale invariant feature transform (SIFT) algorithm to extract a plurality of feature points of the road surface contour image; sorting the plurality of feature points in a preset order; moving feature points located at a road surface edge in the plurality of feature points to a road surface center; determining encoding information of a plurality of target feature points in the plurality of feature points, the encoding information being used to represent road information. In this way, the SIFT algorithm can be used to extract a plurality of feature points of the road surface contour image that can represent key information of the road surface contour image, achieving the purpose of quickly extracting road surface feature information, and further achieving the purpose of quickly acquiring road information.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image processing, and relates to a road information acquisition method, device, equipment and medium, in particular to a road information acquisition method, device, equipment and medium based on a road surface contour image. BACKGROUND

[0002] Today, the speed / accuracy of map information updating based on satellite remote sensing has been greatly improved. The common method for extracting road surface information from satellite images is to use a deep neural network algorithm to segment the road surface, and the segmented road surface contour image is saved in the form of a mask. The current road surface contour mask only has basic image features. If you want to acquire road information, experienced personnel need to use a map annotation tool to annotate the road surface information, such as road connectivity, road length, road width, road surface state, etc. In dealing with more complex roads, such as intersections, multi-exit roundabouts, and crisscrossing road surfaces, more time is needed. Therefore, how to quickly acquire road information is a technical problem to be solved by those skilled in the art. SUMMARY

[0003] The present application provides a road information acquisition method and device based on a road surface contour image, which can quickly acquire road information.

[0004] To achieve the above purpose, one aspect of an embodiment of the present application provides a road information acquisition method, which comprises:

[0005] acquiring a road surface contour image;

[0006] using a scale-invariant feature transform (SIFT) algorithm to extract a plurality of feature points of the road surface contour image;

[0007] sequentially arranging the plurality of feature points according to a preset order;

[0008] moving the feature points located at the road surface edges in the plurality of feature points to the road surface center;

[0009] determining the encoding information of a plurality of target feature points in the plurality of feature points, and the encoding information is used to represent the road information.

[0010] In a specific implementation, moving the feature points located at the road surface edges in the plurality of feature points to the road surface center comprises:

[0011] determining the coordinates of a first feature point in the plurality of feature points;

[0012] determining the first road surface width at the position of the first feature point according to the coordinates of the first feature point;

[0013] According to the first segment road width and the coordinates of each feature point, the feature points in the first segment road are determined;

[0014] The feature points in the first segment road are moved to the center of the first segment road.

[0015] In a specific implementation, before the encoding information of the target feature points is determined, the method further comprises:

[0016] The feature points exceeding the road edge are removed from the plurality of feature points to obtain the target feature points.

[0017] In a specific implementation, before the encoding information of the target feature points is determined, the method further comprises:

[0018] The first slope of the first feature point and the second feature point and the second slope of the first feature point and the third feature point in the first coordinate system are determined.

[0019] When the difference between the second slope and the first slope is less than a threshold, it is determined that the first feature point, the second feature point and the third feature point are on a straight line.

[0020] One of the first feature point, the second feature point and the third feature point is removed.

[0021] In a specific implementation, removing one of the first feature point, the second feature point and the third feature point comprises:

[0022] The third feature point is removed, and the first feature point and the second feature point are taken as the target feature points.

[0023] In a specific implementation, the encoding information comprises:

[0024] The coordinates of the ith target feature point, the road width where the ith target feature point is located, the number of connected points of the ith target feature point, the coordinates of the (i+1)th target feature point, the distance between the (i+1)th target feature point and the ith target feature point, the slope between the (i+1)th target feature point and the ith target feature point, the coordinates of the (i+2)th target feature point, the distance between the (i+2)th target feature point and the ith target feature point, and the slope between the (i+2)th target feature point and the ith target feature point, wherein i is a positive integer greater than or equal to 1.

[0025] In a specific implementation, the preset order comprises an order along a specified axis direction in the first coordinate system.

[0026] In still another aspect, the embodiment of the present application further provides a device for acquiring road information based on a road profile image, which comprises an acquisition unit, an extraction unit, an ordering unit, an adjustment unit and a determination unit, wherein,

[0027] The acquisition unit is configured to acquire a road surface profile image;

[0028] The extraction unit is configured to extract a plurality of feature points of the road surface profile image by using a scale-invariant feature transform (SIFT) algorithm;

[0029] The sorting unit is configured to sort the plurality of feature points according to a preset order;

[0030] The adjustment unit is configured to move a feature point located at a road surface edge in the plurality of feature points to a road surface center;

[0031] The determination unit is configured to determine encoding information of a plurality of target feature points in the plurality of feature points, the encoding information being used to represent road information.

[0032] In a specific implementation, the adjustment unit is configured to:

[0033] determine a coordinate of a first feature point in the plurality of feature points;

[0034] determine a first road surface width at a position of the first feature point according to the coordinate of the first feature point;

[0035] determine feature points in a first road surface according to the first road surface width and the coordinate of each feature point;

[0036] move the feature points in the first road surface to a center of the first road surface.

[0037] In a specific implementation, the device provided by the present application further includes a removal unit, and the removal unit is configured to:

[0038] remove a feature point exceeding a road surface edge in the plurality of feature points to obtain the plurality of target feature points.

[0039] In a specific implementation, the determination unit is configured to:

[0040] determine a first slope of a first feature point and a second feature point and a second slope of the first feature point and a third feature point in the plurality of feature points in a first coordinate system;

[0041] when a difference between the second slope and the first slope is less than a threshold value, determine that the first feature point, the second feature point and the third feature point are on a straight line;

[0042] the removal unit is configured to remove one of the first feature point, the second feature point and the third feature point.

[0043] In a specific implementation, the removal unit is configured to:

[0044] remove the third feature point and take the first feature point and the second feature point as the target feature points.

[0045] In a specific implementation, the encoded information includes:

[0046] coordinates of the i-th target feature point, a road width where the i-th target feature point is located, a number of connected points of the i-th target feature point, coordinates of the i+1-th target feature point, a distance between the i+1-th target feature point and the i-th target feature point, a slope between the i+1-th target feature point and the i-th target feature point, coordinates of the i+2-th target feature point, a distance between the i+2-th target feature point and the i-th target feature point, and a slope between the i+2-th target feature point and the i-th target feature point, where i is a positive integer greater than or equal to 1.

[0047] In a specific implementation, the preset order includes an order along a specified axis direction in the first coordinate system.

[0048] In still another aspect of the embodiments of the present application, a computer device is provided, which includes at least one processor, and a memory storing computer instructions executable on the processor, the instructions being executed by the processor to implement the computer program of the above method steps.

[0049] In still another aspect of the embodiments of the present application, a computer readable storage medium is provided, which stores a computer program executable by a processor to implement the above method steps.

[0050] The present application has at least the following beneficial technical effects:

[0051] In the embodiments of the present application, the SIFT algorithm can extract a plurality of feature points of the road profile image which can represent the key information of the road profile image, so as to quickly extract the road feature information, and further to quickly acquire the road information.

[0052] In the embodiments of the present application, the redundant feature points are removed, so as to quickly label the road information and to quickly process the selection of the road path. BRIEF DESCRIPTION OF DRAWINGS

[0053] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description only some embodiments of the present application, and for those skilled in the art, other embodiments can be obtained without creative labor on the basis of these drawings.

[0054] Figure 1 A flowchart of a road information acquisition method based on a road profile image according to an embodiment of the present application is provided.

[0055] Figure 2 A flowchart of a method for acquiring road information based on a road surface profile image is provided for an embodiment of the present application.

[0056] Figure 3 An adjustment diagram of feature points in a road surface profile image is provided for an embodiment of the present application.

[0057] Figure 4 A slope calculation diagram of feature points in a road surface profile image is provided for an embodiment of the present application.

[0058] Figure 5 A flowchart of a method for acquiring road information based on a road surface profile image is provided for an embodiment of the present application.

[0059] Figure 6 A diagram of a road surface profile image is provided for an embodiment of the present application.

[0060] Figure 7 A diagram of coding information of a road surface path is provided for an embodiment of the present application.

[0061] Figure 8 A diagram of road surface path planning is provided for an embodiment of the present application.

[0062] Figure 9 A diagram of an acquisition device for road information based on a road surface profile image is provided for an embodiment of the present application.

[0063] Figure 10 A diagram of an embodiment of a computer device is provided for the present application.

[0064] Figure 11 A diagram of an embodiment of a computer readable storage medium is provided for the present application. DETAILED DESCRIPTION

[0065] In order to make the objectives, technical solutions and advantages of the present application clearer, further detailed descriptions will be made to the embodiments of the present application with reference to the accompanying drawings.

[0066] It should be noted that all the expressions of "first" and "second" in the embodiments of the present application are used to distinguish two same-named different entities or different parameters, and it can be seen that "first" and "second" are only used for the convenience of description, and should not be understood as a limitation of the embodiments of the present application, and subsequent embodiments will not be described one by one.

[0067] Based on the above purpose, in a first aspect of the embodiments of the present application, an embodiment of a method for acquiring road information based on a road surface profile image is provided. Figure 1 A diagram of an embodiment of a method for acquiring road information provided by the present application is shown. As shown in the diagram,Figure 1 As shown in the method for acquiring road information, the execution subject of the method can be a computer, and the method can include S101, S102, S103, S104, S105, and S106 (part of the steps are optional steps), wherein S101, S102, S103, S104, S105, and S106 are specifically as follows:

[0068] S101, acquire a road profile image.

[0069] The road profile image can be understood as a road profile image collected by a satellite. For example, as shown in the road profile image. Figure 6

[0070] In this step, S101 can be specifically implemented as reading image information of the road profile image, and the image information can include pixel sizes of the image, such as the length and width of the image. In actual applications, the road profile image can be a rectangle or a square, which is not specifically limited in the embodiments of the present application.

[0071] S102, extract a plurality of feature points of the road profile image by using a scale invariant feature transform (SIFT) algorithm.

[0072] The scale invariant feature transform (SIFT) algorithm is a local feature description algorithm in the field of image processing. The SIFT algorithm has not only scale invariance, but also good detection effect when the image is rotated, the image brightness is changed, and the shooting position is moved.

[0073] The plurality of feature points are used to represent key information of the road profile image, such as position, corner point, and contour shape.

[0074] In this way, the SIFT algorithm can extract a plurality of feature points of the road profile image, which can represent the key information of the road profile image, so as to achieve the purpose of quickly extracting road feature information.

[0075] S103, sort the plurality of feature points according to a preset order.

[0076] The preset order can be any order set in advance. For example, the preset order can include an order along a specified axis direction in a first coordinate system. For example, in a rectangular coordinate system, the preset order can refer to an order of the X axis from left to right. Alternatively, the preset order can refer to an order of the Y axis from bottom to top. Of course, it can also be other coordinate axes or directions in other coordinate systems, which are not specifically limited in the embodiments of the present application.

[0077] ​Since some of the feature points extracted by the SIFT algorithm are located at the edge of the road surface, in order to improve the accuracy of path planning, the feature points located at the edge of the road surface are moved to the center of the road surface. As described in S104, in particular:

[0078] S104, moving the feature points located at the edge of the road surface in the plurality of feature points to the center of the road surface.

[0079] It can be understood that the feature points located at the edge of the road surface are located on the road surface contour, or close to the road surface contour, or deviate from the center line of the road surface.

[0080] In a specific implementation manner, as shown in Figure 2 S104 can be specifically implemented as: S1041, determining the coordinates of a first feature point in the plurality of feature points. S1042, determining a first road surface width at the position of the first feature point according to the coordinates of the first feature point. S1043, determining the feature points in the first road surface according to the first road surface width and the coordinates of each feature point. S1044, moving the feature points in the first road surface to the center of the first road surface.

[0081] For example, as shown in Figure 2 and Figure 3 , assuming that the coordinates of the first feature point A are (X, Y), where X is less than Y. As shown in Figure 3 (a), the coordinates of the first feature point A deviate from the center line of the road surface. At this time, the first feature point A needs to be moved to the center of the road surface. Specifically: selecting the minimum value of the coordinates X and Y as the first road surface a width corresponding to the first feature point A, that is, the first road surface a width is X*X rectangle. Then, as shown in Figure 3 (b), the first feature point A falls into the X*X rectangular region, and the first feature point A is moved to the center of the first road surface a. Finally, the schematic diagram of the first feature point A after moving is obtained as shown in Figure 3 (c). Similarly, the plurality of feature points can be moved by the above-mentioned manner, which will not be described one by one.

[0082] S105, determining the encoding information of a plurality of target feature points in the plurality of feature points, the encoding information being used to represent road information.

[0083] The encoding information can include: coordinates of the i-th target feature point, a road surface width where the i-th target feature point is located, a number of connected points of the i-th target feature point, coordinates of the i+1-th target feature point, a distance between the i+1-th target feature point and the i-th target feature point, a slope between the i+1-th target feature point and the i-th target feature point, coordinates of the i+2-th target feature point, a distance between the i+2-th target feature point and the i-th target feature point, and a slope between the i+2-th target feature point and the i-th target feature point. The i is a positive integer greater than or equal to 1.

[0084] As shown in Table 1, assuming that i is 1, the first target feature point is p1, the second target feature point is p2, and the third target feature point is p3, encoding information of the first target feature point p1, the second target feature point p2, and the third target feature point p3 is as shown in Table 1, and specifically is: Figure 4

[0085] Table 1

[0086]

[0087]

[0088] In some embodiments, in order to remove redundant feature points, as shown in Table 1, before S105 is performed, the method provided by the embodiment of the application further includes: Figure 5

[0089] S106, removing a feature point exceeding a road surface edge in the plurality of feature points to obtain a plurality of target feature points.

[0090] In a specific implementable manner, S106 can be specifically implemented as: S1061, determining, in the first coordinate system, a first slope between a first feature point and a second feature point and a second slope between the first feature point and a third feature point in the plurality of feature points. S1062, when a difference between the second slope and the first slope is less than a threshold value, determining that the first feature point, the second feature point, and the third feature point are on a straight line. S1063, removing one of the first feature point, the second feature point, and the third feature point. In a specific implementable manner, S1063 can be specifically implemented as: removing the third feature point, and taking the first feature point and the second feature point as target feature points.

[0091] As an example, as described above, as shown in Table 1, assuming that i is 1, the first target feature point is p1, the second target feature point is p2, and the third target feature point is p3, encoding information of the first target feature point p1, the second target feature point p2, and the third target feature point p3 is as shown in Table 1, and specifically is: Figure 4 ​​As shown, assuming that in the rectangular coordinate system, the first feature point is p1, the second feature point is p2, and the third feature point is p3. The X-axis is the horizontal axis. At this time, the slope of the first feature point p1 and the first feature point p2 is a1, and the slope of the first feature point p1 and the third feature point p3 is a2. If a2-a1<3°, it is considered that the first feature point p1, the second feature point p2 and the third feature point p3 exist on a straight line, and then the third feature point p3 is a redundant point and can be removed.

[0092] In this way, the redundant feature points are removed, the road information can be labeled faster, and the road path selection work can be processed faster.

[0093] In practical applications, Figure 6 As shown in the road surface profile image, after the steps of S101-S106 are processed, the encoding information of each feature point is obtained Figure 7 As shown in the road surface profile image, after the steps of S101-S106 are processed, the encoding information of each feature point is obtained Figure 8 As shown in the road surface profile image, after the steps of S101-S106 are processed, the encoding information of each feature point is obtained

[0094] Based on the above purpose, a second aspect of an embodiment of the present application provides a device for acquiring road information based on a road surface profile image, as shown in Figure 9 The device 900 can include an acquisition unit 901, an extraction unit 902, an ordering unit 903, an adjustment unit 904, and a determination unit 905, wherein

[0095] The acquisition unit 901 is configured to acquire a road surface profile image;

[0096] The extraction unit 902 is configured to extract a plurality of feature points of the road surface profile image by using a scale-invariant feature transform (SIFT) algorithm;

[0097] The ordering unit 903 is configured to order the plurality of feature points according to a preset order;

[0098] The adjustment unit 904 is configured to move a feature point located at an edge of a road surface to a center of the road surface among the plurality of feature points;

[0099] The determination unit 905 is configured to determine encoding information of a plurality of target feature points in the plurality of feature points, and the encoding information is used to represent road information.

[0100] In a specific implementation, the adjustment unit 904 is configured to:

[0101] Determine the coordinates of a first feature point in the plurality of feature points;

[0102] Determine a first road surface width at a position of the first feature point according to the coordinates of the first feature point;

[0103] According to the first road surface width and the coordinates of each feature point, the feature points in the first road surface are determined;

[0104] The feature points in the first road surface are moved to the center of the first road surface.

[0105] In a specific implementation, the apparatus 900 further includes a removing unit 906, configured to:

[0106] Remove the feature points exceeding the road surface edge from the plurality of feature points to obtain a plurality of target feature points.

[0107] In a specific implementation, the determining unit 905 is configured to:

[0108] Determine, in the first coordinate system, a first slope of the first feature point and the second feature point and a second slope of the first feature point and the third feature point in the plurality of feature points.

[0109] When the difference between the second slope and the first slope is less than a threshold value, it is determined that the first feature point, the second feature point and the third feature point are on a straight line.

[0110] The removing unit 906 is configured to remove one of the first feature point, the second feature point and the third feature point.

[0111] In a specific implementation, the removing unit 906 is configured to:

[0112] Remove the third feature point and take the first feature point and the second feature point as the target feature points.

[0113] In a specific implementation, the encoding information includes:

[0114] The coordinates of the i-th target feature point, the road surface width where the i-th target feature point is located, the number of connected points of the i-th target feature point, the coordinates of the i+1-th target feature point, the distance between the i+1-th target feature point and the i-th target feature point, the slope between the i+1-th target feature point and the i-th target feature point, the coordinates of the i+2-th target feature point, the distance between the i+2-th target feature point and the i-th target feature point, and the slope between the i+2-th target feature point and the i-th target feature point, where i is a positive integer greater than or equal to 1.

[0115] In a specific implementation, the preset order includes an order along a specified axis direction in the first coordinate system.

[0116] According to the embodiment of the present application, the road surface profile image is acquired; the scale invariant feature transform (SIFT) algorithm is used to extract a plurality of feature points of the road surface profile image; the plurality of feature points are sorted according to a preset order; the feature points located at the road surface edge in the plurality of feature points are moved to the road surface center; and the encoding information of a plurality of target feature points in the plurality of feature points is determined, the encoding information being used to represent the road information. In this way, the SIFT algorithm can extract the plurality of feature points of the road surface profile image which can represent the key information of the road surface profile image, so as to achieve the purpose of quickly extracting the road surface feature information. Furthermore, the road information can be quickly acquired.

[0117] Figure 10 An embodiment of the computer device provided by the present application is shown in the schematic diagram. As shown in the diagram, Figure 10 the computer device of the embodiment of the present application executes the method as described above.

[0118] The present application further provides a computer readable storage medium. Figure 11 An embodiment of the computer readable storage medium provided by the present application is shown in the schematic diagram. As shown in the diagram, Figure 11 the computer readable storage medium 031 stores a computer program 032 which, when executed by a processor, executes the method as described above.

[0119] Finally, it should be noted that those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by a computer program to instruct related hardware, and the program can be stored in a computer readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments of the method. The storage medium of the program can be a magnetic disc, an optical disc, a read-only memory (ROM) or a random access memory (RAM), etc. The above-mentioned embodiments of the computer program can achieve the same or similar effects as the corresponding method embodiments.

[0120] The above is the exemplary embodiments disclosed by the present application, but it should be noted that various changes and modifications can be made without departing from the scope of the embodiments disclosed by the present application defined in the claims. The functions, steps and / or acts of the method claims described in the embodiments disclosed herein need not be performed in any particular order. In addition, although the elements disclosed in the embodiments of the present application can be described or claimed in singular form, they can also be understood as plural unless explicitly limited as singular.

[0121] It should be understood that, as used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises", "comprising", "includes" and / or "including", as used herein, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0122] The above embodiment serial numbers of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments.

[0123] A person of ordinary skill in the art can understand that all or part of the steps of the above-mentioned embodiments can be completed by hardware, or by program instructing relevant hardware to complete, and the program can be stored in a computer readable storage medium. The storage medium mentioned above can be a read-only memory, a hard disk, an optical disk, etc.

[0124] Those skilled in the art will understand that the above discussion of any of the embodiments is merely exemplary and is not intended to suggest that the scope of the embodiments disclosed herein (including the claims) is limited to these examples. In the spirit of the embodiments of the present application, the above embodiments or technical features in different embodiments can also be combined, and there are many other changes of different aspects of the embodiments of the present application as described above. In order to be brief, they are not provided in details. Therefore, any omission, modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of the present application shall be included in the protection scope of the embodiments of the present application.

Claims

1. A method of acquiring road information, characterized by, The method comprises: acquiring a road surface profile image; extracting a plurality of feature points of the road surface profile image by using a scale invariant feature transform (SIFT) algorithm; sequencing the plurality of feature points according to a preset sequence; moving feature points located at a road surface edge to a road surface center, which comprises: determining coordinates of a first feature point among the plurality of feature points; determining a first road surface width at a position where the first feature point is located according to the coordinates of the first feature point; determining feature points within the first road surface according to the first road surface width and the coordinates of each feature point; and moving the feature points within the first road surface to the center of the first road surface; determining encoding information of a plurality of target feature points among the plurality of feature points, the encoding information being used to represent road information; wherein, before determining the encoding information of the plurality of target feature points among the plurality of feature points, the method further comprises: removing feature points beyond the road surface edge among the plurality of feature points to obtain the plurality of target feature points; further, determining a first slope of a first feature point and a second feature point and a second slope of the first feature point and a third feature point among the plurality of feature points in a first coordinate system; when a difference between the second slope and the first slope is less than a threshold value, determining that the first feature point, the second feature point and the third feature point are on a straight line; and removing one of the first feature point, the second feature point and the third feature point.

2. The method of claim 1, wherein, The removing one of the first feature point, the second feature point and the third feature point comprises: removing the third feature point and taking the first feature point and the second feature point as the target feature points.

3. The method of claim 1, wherein, The encoding information comprises: coordinates of an i-th target feature point, a road surface width where the i-th target feature point is located, a number of connected points of the i-th target feature point, coordinates of an i+1-th target feature point, a distance between the i+1-th target feature point and the i-th target feature point, a slope between the i+1-th target feature point and the i-th target feature point, coordinates of an i+2-th target feature point, a distance between the i+2-th target feature point and the i-th target feature point, and a slope between the i+2-th target feature point and the i-th target feature point, wherein i is a positive integer greater than or equal to 1.

4. The method of claim 1, wherein, The preset sequence comprises a sequence along a specified axis direction in a first coordinate system.

5. A road information acquisition device, characterized in that, The method comprises: an acquisition unit, an extraction unit, a sequencing unit, an adjustment unit and a determination unit, wherein the acquisition unit is configured to acquire a road surface profile image; the extraction unit is configured to extract a plurality of feature points of the road surface profile image by using a scale invariant feature transform (SIFT) algorithm; the sequencing unit is configured to sequence the plurality of feature points according to a preset sequence; the adjustment unit is configured to move feature points located at a road surface edge to a road surface center; the determination unit is configured to determine encoding information of a plurality of target feature points among the plurality of feature points, the encoding information being used to represent road information; and the determination unit is configured to determine encoding information of a plurality of target feature points among the plurality of feature points, the encoding information being used to represent road information. The adjusting unit is further configured to determine a coordinate of a first feature point in the plurality of feature points; determine a first road surface width at a position where the first feature point is located according to the coordinate of the first feature point; determine feature points in the first road surface according to the first road surface width and the coordinate of each feature point; and move the feature points in the first road surface to a center of the first road surface. The obtaining device further comprises modules for implementing the following functions: removing feature points in the plurality of feature points that are beyond a road surface edge to obtain the plurality of target feature points; further, determining a first slope of a first feature point and a second feature point and a second slope of the first feature point and a third feature point in the plurality of feature points in a first coordinate system; determining that the first feature point, the second feature point and the third feature point are on a straight line when a difference between the second slope and the first slope is less than a threshold value; and removing one of the first feature point, the second feature point and the third feature point.

6. A computer device, characterized by comprising: at least one processor; and a memory storing computer instructions executable on the processor, the instructions, when executed by the processor, implement the steps of the method of any one of claims 1-4.

7. A computer-readable storage medium storing a computer program, wherein the computer program comprises the following steps of: receiving a request for a resource from a client; determining whether the client is authorized to access the resource; and if the client is authorized to access the resource, providing the resource to the client. The computer program, when executed by the processor, implements the steps of the method of any one of claims 1-4.

Images