Target positioning method, target and device

Abstract

This application provides a target localization method, a target, and an apparatus. This application constructs a global feature template for target matching, maps the target image to a target mapping image based on planar mapping, and then finds a matching region in the target mapping image that matches the global feature template based on template matching. Based on the matching region, the origin and the direction of the coordinate axes in the target coordinate system corresponding to the target are determined (equivalent to locating the global feature template from the target). Camera calibration is then performed based on the target coordinate system. This allows for correct target coordinate system localization and camera calibration even when the target has large-area defects, provided the global feature template remains intact.

Description

Technical Field

[0001] This application relates to the field of machine vision, and in particular to target localization methods, targets, and devices. Background Technology

[0002] A target, such as a two-dimensional target (also called a planar target), contains a virtual target coordinate system and feature points. Feature points can be dots, corners, or other feature points that can be detected by image detection algorithms. Here, a corner can be a special vertex. For example, for a chessboard-shaped target with alternating squares of two different colors, the vertex shared by four squares can be called a corner.

[0003] If the target is defective during the camera calibration process, it will result in the target not being fully captured, affecting the camera calibration. Summary of the Invention

[0004] This application provides a target positioning method, a target, and a device to achieve camera calibration even when the target is not fully captured in the image.

[0005] This application provides a target localization method, the method comprising:

[0006] In a geometric coordinate system with a specified target feature point in the target image as the origin, the geometric coordinate information of other target feature points in the target image is determined; the target image is obtained by image acquisition of a set target, and the specified target feature point is one of the target feature points in the target image;

[0007] Based on the geometric coordinates of each target feature point and the image coordinates of each target feature point in the image coordinate system corresponding to the target image, a target mapping image is determined; the target pattern in the target mapping image and the target pattern in the target image satisfy the set matching conditions.

[0008] Based on the constructed global feature template for target matching, a matching region matching the global feature template is found in the target mapping image. The origin and the direction of the coordinate axes in the target coordinate system corresponding to the target are determined according to the matching region. The geometric coordinate information of each target feature point is adjusted according to the origin and the direction of the coordinate axes in the target coordinate system. The adjusted geometric coordinate information of each target feature point is used for camera calibration.

[0009] This application provides a target, which is used for target positioning according to the method described above. A global feature template matching the target is placed at a designated position in the target. The target also includes other region blocks. The size of any region block satisfies a set matching condition with the size of the global feature template. The patterns in the other region blocks are the same, and the patterns in the other region blocks are different from the patterns in the global feature template.

[0010] This application provides a target localization device, the device comprising:

[0011] The determining unit is used to determine the geometric coordinate information of other target feature points in the target image in a geometric coordinate system with a specified target feature point in the target image as the origin; the target image is obtained by image acquisition of a set target, and the specified target feature point is one of the target feature points in the target image;

[0012] The mapping unit is used to determine the target mapping image based on the geometric coordinate information of each target feature point and the image coordinate information of each target feature point in the image coordinate system corresponding to the target image; the target pattern in the target mapping image and the target pattern in the target image satisfy the set matching conditions;

[0013] The localization unit is used to find a matching region in the target mapping image that matches the global feature template based on the constructed target matching global feature template, determine the origin and the direction of the coordinate axes in the target coordinate system corresponding to the target based on the matching region, adjust the geometric coordinate information of each target feature point according to the origin and the direction of the coordinate axes of the target coordinate system, and use the adjusted geometric coordinate information of each target feature point for camera calibration.

[0014] This application provides an electronic device, which includes: a processor and a machine-readable storage medium;

[0015] The machine-readable storage medium is used to store machine-executable instructions;

[0016] The processor is configured to read and execute machine-executable instructions stored in the machine-readable storage medium to implement the method described above.

[0017] As can be seen from the above technical solutions, in this application, by constructing a global feature template for target matching, the target image is mapped to the target mapping image based on planar mapping. Then, based on template matching, the matching region that matches the global feature template is found in the target mapping image. Based on the matching region, the origin and the direction of the coordinate axes in the target coordinate system corresponding to the target are determined (which is equivalent to locating the global feature template from the target). Camera calibration is then performed based on the target coordinate system. This means that when there are large defects on the target, as long as the global feature template is intact, the correct target coordinate system can be located for camera calibration. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0019] Figure 1 A flowchart illustrating the method provided in this application embodiment;

[0020] Figure 2a This is a schematic diagram of the target image structure provided in an embodiment of this application;

[0021] Figure 2b This is a schematic diagram of the target mapping image structure provided in an embodiment of this application;

[0022] Figure 3 This is a schematic diagram of a binary image provided in an embodiment of this application;

[0023] Figures 4a to 4c A schematic diagram of a global feature template provided in an embodiment of this application;

[0024] Figures 5a to 5b A schematic diagram of the target provided in the embodiments of this application;

[0025] Figure 6 This is a schematic diagram illustrating possible positioning when camera lens distortion occurs, provided in an embodiment of this application.

[0026] Figure 7 This is a schematic diagram of the device structure provided in the embodiments of this application;

[0027] Figure 8 This is a structural diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0028] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0029] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0030] To enable those skilled in the art to better understand the technical solutions provided in the embodiments of this application, and to make the above-mentioned objectives, features and advantages of the embodiments of this application more apparent and understandable, the technical solutions in the embodiments of this application will be further described in detail below with reference to the accompanying drawings.

[0031] See Figure 1 , Figure 1 This is a flowchart illustrating a method provided in an embodiment of this application. This method can be applied to electronic devices such as cameras, but this embodiment is not specifically limited to such applications.

[0032] like Figure 1 As shown, the process may include the following steps:

[0033] Step 101: In a geometric coordinate system with the specified target feature point in the target image as the origin, determine the geometric coordinate information of other target feature points in the target image.

[0034] As one embodiment, a target image, such as a calibration board, can first be obtained by photographing the target with a camera. Optionally, the target can be a checkerboard calibration board. Then, the image coordinates of each target feature point, such as a target corner point, in the corresponding image coordinate system are obtained. Finally, in a geometric coordinate system with a specified target feature point in the target image as the origin, the geometric coordinates of the other target feature points are determined based on the image coordinates of the other target feature points and the specified target feature point.

[0035] In one embodiment, the specified target feature point can be the target feature point at the top left corner of the target image, such as a target corner point, or the target feature point closest to the top left corner of the target image, such as a target corner point, etc., and this embodiment is not specifically limited. For convenience, the geometric coordinate information of other target feature points besides the specified target feature point is expressed in units of the number of squares, such as checkerboard squares, in the target. This ultimately achieves the determination of the geometric coordinate information of all other target feature points in the target image within a geometric coordinate system with the specified target feature point in the target image as the origin, as described in step 101.

[0036] Step 102: Determine the target mapping image based on the geometric coordinate information of each target feature point and the image coordinate information of each target feature point in the image coordinate system corresponding to the target image.

[0037] As an example, in the specific implementation of step 102, the scaling factor k can be set first according to actual needs. k>1. In one embodiment, k=10. Then, based on the scaling factor k, the mapping coordinate information (x) of each target feature point is... r ,y r ) and its geometric coordinate information (x c ,y c The mapping relationship of (x) can be expressed as: r ,y r )=(kx c ,ky c Then, based on the image coordinates and mapping coordinates of each target feature point, the homography matrix is ​​calculated. There are many ways to calculate the homography matrix, and this embodiment is not specifically limited to any particular method. Finally, using the homography matrix, the target mapping image is determined through linear interpolation. Ultimately, this achieves the determination of the target mapping image based on the geometric coordinates of each target feature point and its image coordinates in the corresponding image coordinate system of the target image.

[0038] In this embodiment, the target mapping image here can specifically be a front view of the target image. Assume the number of target feature points in the target image is w. c ×h c Then the resolution (w) of the target-mapped image r ,h r It can be:

[0039] (w r ,h r )=(k(w c +1)+1,k(h c +1)+1).

[0040] Optionally, the target pattern in the target mapping image and the target pattern in the target image meet the set matching conditions, such as being completely identical. Figure 2a , Figure 2b Examples of target images and target mapping images are shown.

[0041] Step 103: Based on the constructed global feature template that matches the target, find the matching region in the target mapping image that matches the global feature template, determine the origin and the direction of the coordinate axes in the target coordinate system corresponding to the target based on the matching region, adjust the geometric coordinate information of each target feature point according to the origin and the direction of the coordinate axes of the target coordinate system, and use the adjusted geometric coordinate information of each target feature point for camera calibration.

[0042] As an example, in step 103, there are many ways to find a matching region in the target mapping image that matches the global feature template based on the constructed global feature template that matches the target. For example, the target mapping image is divided into regions to obtain multiple region blocks; the size of each region block meets the set requirements, such as being the same as the size of the global feature template. Then, a target region block is selected from each region block. The matching degree between the target region block and the global feature template meets the set matching degree requirements. The selected target region block is determined as the matching region that matches the global feature template.

[0043] Optionally, in this embodiment, the target includes multiple squares of the same size. As an example, the size of the global feature template constructed for the target can be the same as the size of the squares in the target, such as a chessboard. Under this premise, the size of the region block can be the size of the squares.

[0044] Optionally, in this embodiment, the pattern of the global feature template is different from the pattern of other squares, such as a checkerboard, in the target other than the region block that matches the global feature template. Figure 2b The global feature template shown is compared with other squares in the target.

[0045] As an example, the aforementioned global feature template is a pre-set binary image. The pixel value of each pixel in this binary image, such as a grayscale value, may be one of two values: 0 and 1. For example, Figure 3 The example shown is a binary image where 0 represents black and 1 represents white.

[0046] Based on a pre-set binary image as the global feature template, the above selection of a target region block from each region block can include:

[0047] Step a1: Obtain the binarized result of each region block after binarization. This can be achieved by binarizing the pixel values ​​of each pixel within each region block, for example... Figure 3The binary image shown.

[0048] Step a2: Select the target region block from each region block based on the binarization result corresponding to each region block and the pre-set binary image.

[0049] As an example, in specific implementation of step a2, for each region block, the pixel positions in the corresponding binarized result are traversed, and the difference between the pixel value at that pixel position and the pixel value at the matching position in the pre-set binary image is calculated to obtain the pixel matching score corresponding to that pixel position. The pixel matching scores corresponding to each pixel position in the binarized result of the region block are summed to obtain the calculation result corresponding to that region block. From the calculation results corresponding to each region block, a target region block whose value meets the set requirements (such as minimum) is obtained. Finally, the target region block is selected from each region block.

[0050] As an example, after determining the matching region, the origin and orientation of the target in the real coordinate system (the target coordinate system corresponding to the target) can be determined. For example, the origin in the target coordinate system can be the center position of the matching region or the upper left / right corner, and the orientation, such as the positive direction of the y-axis in the target coordinate system, can be the orientation of the pattern in the matching region (e.g., Figure 2b (The triangle orientation of the matching area shown).

[0051] After determining the target coordinate system, the geometric coordinates of each target feature point can be adjusted based on this system. The adjusted target feature points are illustrated in the diagram. Then, camera calibration can be performed based on the adjusted geometric coordinates of each target feature point; the specific camera calibration process is not limited here.

[0052] It should be noted that this embodiment does not specifically limit the target to be composed of multiple squares, such as a chessboard; it can be applied to any template with similar global features, such as... Figure 2b The two-dimensional target shown is a global feature template. For example... Figure 4a The global feature template shown is the position of 5 large circles, or Figure 4b The global feature template shown is a convex equilateral triangle, or Figure 4c The global feature template for the dotted target shown consists of four feature rings, and so on. For different targets, the above process does not need to be changed; only the corresponding global feature template needs to be constructed. Furthermore, when a large area of ​​the target is missing, as long as the global feature template on the target is intact, the correct target coordinate system can be located.

[0053] As an example, in conjunction with the target localization method described above, this embodiment can also design a corresponding target. Optionally, the target designed here differs from traditional targets, such as traditional checkerboard markers. Optionally, a global feature template matching the target is added to a corner of the target in this embodiment, for example... Figure 5a or Figure 5b As shown, this study aims to determine the consistency of the target coordinate system when different cameras shoot targets from different angles, thereby improving the robustness and stability of camera calibration.

[0054] This embodiment adds a global feature template matching the target to a certain corner of the target, ensuring that when determining the geometric coordinates of target feature points, such as target corner points, in the target coordinate system, it is not necessary to replace some target areas, such as the target checkerboard, with QR codes or other feature patterns, as is done in the existing method. This avoids the impact on the grayscale distribution around the target corner points (including the origin) caused by replacing some target areas, such as the target checkerboard, with QR codes or other feature patterns.

[0055] Furthermore, in this embodiment, when the camera lens distortion is large, only a portion of the target feature points can be selected for homography matrix calculation. For example, only the target feature points in the four corner regions of the target image can be used for calculation. Specifically, as follows: Figure 6 As shown, this is to improve anti-distortion performance.

[0056] The methods provided in the embodiments of this application have been described above. The apparatus provided in the embodiments of this application is described below:

[0057] See Figure 7 , Figure 7 This is a structural diagram of the device provided in an embodiment of this application. Figure 7 As shown, the device includes:

[0058] The determining unit is used to determine the geometric coordinate information of other target feature points in the target image in a geometric coordinate system with a specified target feature point in the target image as the origin; the target image is obtained by image acquisition of a set target, and the specified target feature point is one of the target feature points in the target image;

[0059] The mapping unit is used to determine the target mapping image based on the geometric coordinate information of each target feature point and the image coordinate information of each target feature point in the image coordinate system corresponding to the target image; the target pattern in the target mapping image and the target pattern in the target image satisfy the set matching conditions;

[0060] The localization unit is used to find a matching region in the target mapping image that matches the global feature template based on the constructed target matching global feature template, determine the origin and the direction of the coordinate axes in the target coordinate system corresponding to the target based on the matching region, adjust the geometric coordinate information of each target feature point according to the origin and the direction of the coordinate axes of the target coordinate system, and use the adjusted geometric coordinate information of each target feature point for camera calibration.

[0061] Optionally, determining the target mapping image based on the geometric coordinates of each target feature point and the image coordinates of each target feature point in the image coordinate system corresponding to the target image includes: for each target feature point, determining the mapping coordinates of the target feature point based on its geometric coordinates and a preset mapping coefficient k; calculating the homography matrix based on the image coordinates and mapping coordinates of each target feature point; and using the homography matrix and linear interpolation to determine the target mapping image.

[0062] Optionally, the resolution (w) of the target mapping image r ,h r )for:

[0063] (w r ,h r )=(k(w c +1)+1,k(h c +1)+1);

[0064] Where k represents the preset mapping coefficient, w c ×h c This indicates the number of target feature points in the target image or the target mapping image.

[0065] Optionally, finding a matching region in the target mapping image that matches the global feature template based on the constructed target matching global feature template includes:

[0066] The target mapping image is divided into regions to obtain multiple region blocks; the size of each region block and the size of the global feature template meet the set requirements.

[0067] Select a target region block from each region block. If the matching degree between the selected target region block and the global feature template meets the set matching degree requirement, the selected target region block is determined as the matching region that matches the global feature template.

[0068] Optionally, the global feature template is a pre-set binary image;

[0069] The step of selecting a target region block from each region block includes: obtaining the binarization result of each region block after binarization processing; and selecting the target region block from each region block based on the binarization result of each region block and the pre-set binary image.

[0070] Optionally, the designated target feature point is a target feature point in the upper left corner of the target image; determining the geometric coordinate information of other target feature points in the target image in a geometric coordinate system with the designated target feature point in the target image as the origin includes: for each target feature point in the target image other than the designated target feature point, determining the geometric coordinate information of the target feature point based on the image coordinate information of the target feature point in the image coordinate system and the image coordinate information of the designated target feature point in the image coordinate system.

[0071] The apparatus provided in the embodiments of this application has been described above.

[0072] Based on the same application concept as the method described above, embodiments of this application also provide an electronic device, such as... Figure 8 As shown, the electronic device includes: a processor and a machine-readable storage medium; the machine-readable storage medium is used to store machine-executable instructions; the processor is used to read and execute the machine-executable instructions stored in the machine-readable storage medium to implement the method described above.

[0073] Based on the same concept as the above-described method, this application also provides a machine-readable storage medium storing a plurality of computer instructions, which, when executed by a processor, can implement the method disclosed in the above-described examples of this application.

[0074] For example, the aforementioned machine-readable storage medium can be any electronic, magnetic, optical, or other physical storage device that can contain or store information such as executable instructions, data, etc. For instance, machine-readable storage media can be: RAM (Random Access Memory), volatile machine-readable storage media, non-volatile machine-readable storage media, flash memory, storage drives (such as hard disk drives), solid-state drives, any type of storage disk (such as optical discs, DVDs, etc.), or similar storage media, or combinations thereof.

[0075] The systems, devices, modules, or units described in the above embodiments can be implemented by a computer or entity, or by a product with a certain function. A typical implementation device is a computer, which can be a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email sending and receiving device, game console, tablet computer, wearable device, or any combination of these devices.

[0076] For ease of description, the above devices are described separately by function as various units. Of course, in implementing this application, the functions of each unit can be implemented in one or more software and / or hardware.

[0077] 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, embodiments of 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 machine-readable storage media, CD-ROMs, optical machine-readable storage media, etc.) containing computer-usable program code.

[0078] 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.

[0079] Furthermore, these computer program instructions can also be stored in a computer-readable and machine-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 and machine-readable storage medium produce an article of manufacture including instruction means, which are implemented in the process. Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0080] 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.

[0081] The above description is merely an embodiment of this application and is not intended to limit 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 principle of this application should be included within the scope of the claims of this application.

Claims

1. A target localization method, characterized in that, The method includes: In a geometric coordinate system with a specified target feature point in the target image as the origin, the geometric coordinate information of other target feature points in the target image is determined; the target image is obtained by image acquisition of a set target, and the specified target feature point is one of the target feature points in the target image; Based on the geometric coordinates of each target feature point and the image coordinates of each target feature point in the image coordinate system corresponding to the target image, a target mapping image is determined; the target pattern in the target mapping image and the target pattern in the target image satisfy the set matching conditions. Based on the constructed global feature template for target matching, a matching region matching the global feature template is found in the target mapping image. The origin and the direction of the coordinate axes in the target coordinate system corresponding to the target are determined according to the matching region. The geometric coordinate information of each target feature point is adjusted according to the origin and the direction of the coordinate axes of the target coordinate system. The pattern of the global feature template is different from the pattern of other areas in the target except for the matching region matching the global feature template. The adjusted geometric coordinate information of each target feature point is used for camera calibration.

2. The method according to claim 1, characterized in that, The process of determining the target mapping image based on the geometric coordinate information of each target feature point and the image coordinate information of each target feature point in the image coordinate system corresponding to the target image includes: For each target feature point, based on the geometric coordinates of that feature point and the preset mapping coefficients... Determine the mapping coordinate information of the target feature points; The homography matrix is ​​calculated based on the image coordinates and mapping coordinates of each target feature point; The target mapping image is determined using the homography matrix and linear interpolation.

3. The method according to claim 1 or 2, characterized in that, The resolution of the target mapping image for: ； in, This represents the preset mapping coefficients. This indicates the number of target feature points in the target image or the target mapping image.

4. The method according to claim 1, characterized in that, The step of finding a matching region in the target mapping image that matches the global feature template based on the constructed target matching includes: The target mapping image is divided into regions to obtain multiple region blocks; the size of each region block and the size of the global feature template meet the set requirements. Select a target region block from each region block. If the matching degree between the selected target region block and the global feature template meets the set matching degree requirement, the selected target region block is determined as the matching region that matches the global feature template.

5. The method according to claim 4, characterized in that, The global feature template is a pre-set binary image; The step of selecting a target region block from each region block includes: obtaining the binarization result of each region block after binarization processing; and selecting the target region block from each region block based on the binarization result of each region block and the pre-set binary image.

6. The method according to claim 1, characterized in that, The designated target feature point is a target feature point in the upper left corner of the target image; The step of determining the geometric coordinate information of other target feature points in the target image in a geometric coordinate system with the specified target feature point in the target image as the origin includes: For each target feature point in the target image other than the specified target feature point, the geometric coordinate information of the target feature point is determined based on the image coordinate information of the target feature point in the image coordinate system and the image coordinate information of the specified target feature point in the image coordinate system.

7. A target, characterized in that, The target is used for target localization according to any one of claims 1 to 6, wherein a global feature template matching the target is placed at a designated position in the target, and the target also includes other region blocks, the size of any region block and the size of the global feature template satisfying a set matching condition, the patterns in the other region blocks are the same, and the patterns in the other region blocks are different from the patterns in the global feature template.

8. The target according to claim 7, characterized in that, The designated location refers to the position of at least one corner of the target; the pattern in the global feature template is a triangular pattern, and the other regions of the target are chessboard patterns.

9. A target positioning device, characterized in that, The device includes: The determining unit is used to determine the geometric coordinate information of other target feature points in the target image in a geometric coordinate system with a specified target feature point in the target image as the origin; the target image is obtained by image acquisition of a set target, and the specified target feature point is one of the target feature points in the target image; The mapping unit is used to determine the target mapping image based on the geometric coordinate information of each target feature point and the image coordinate information of each target feature point in the image coordinate system corresponding to the target image; the target pattern in the target mapping image and the target pattern in the target image satisfy the set matching conditions; The localization unit is used to find a matching region in the target mapping image that matches the global feature template based on the constructed target matching global feature template, determine the origin and the direction of the coordinate axes in the target coordinate system corresponding to the target based on the matching region, and adjust the geometric coordinate information of each target feature point according to the origin and the direction of the coordinate axes of the target coordinate system; wherein, the pattern of the global feature template is different from the pattern of other areas in the target except for the matching region that matches the global feature template; the adjusted geometric coordinate information of each target feature point is used for camera calibration.

10. The apparatus according to claim 9, characterized in that, The step of determining the target mapping image based on the geometric coordinate information of each target feature point and the image coordinate information of each target feature point in the image coordinate system corresponding to the target image includes: for each target feature point, based on the geometric coordinate information of that target feature point and a preset mapping coefficient... Determine the mapping coordinate information of the target feature points; calculate the homography matrix based on the image coordinate information and mapping coordinate information of each target feature point; use the homography matrix and determine the target mapping image through linear interpolation; and / or, The resolution of the target mapping image for: ； in, This represents the preset mapping coefficients. This indicates the number of target feature points in the target image or the target mapping image; and / or, The step of finding a matching region in the target mapping image that matches the global feature template based on the constructed target matching includes: The target mapping image is divided into regions to obtain multiple region blocks; the size of each region block and the size of the global feature template meet the set requirements. From each region block, a target region block is selected. If the matching degree between the selected target region block and the global feature template meets the set matching degree requirement, the selected target region block is determined as the matching region that matches the global feature template; and / or, The global feature template is a pre-set binary image; The step of selecting a target region block from each region block includes: obtaining the binarization result of each region block after binarization processing; selecting the target region block from each region block based on the binarization result of each region block and the pre-set binary image; and / or, The designated target feature point is a target feature point in the upper left corner of the target image; The step of determining the geometric coordinate information of other target feature points in the target image in a geometric coordinate system with the specified target feature point in the target image as the origin includes: For each target feature point in the target image other than the specified target feature point, the geometric coordinate information of the target feature point is determined based on the image coordinate information of the target feature point in the image coordinate system and the image coordinate information of the specified target feature point in the image coordinate system.

11. An electronic device, characterized in that, The electronic device includes: a processor and a machine-readable storage medium; The machine-readable storage medium is used to store machine-executable instructions; The processor is configured to read and execute machine-executable instructions stored in the machine-readable storage medium to implement the method as described in any one of claims 1 to 6.

Images