A method, device and computer readable storage medium for alignment correction

Abstract

The present application provides an alignment correction method, device and computer-readable storage medium, the alignment correction method comprising: setting a cutting vector diagram of the marking point according to the marking point setting parameters; cutting the marking point array on the calibration object placed in the target area of ​​the base according to the cutting vector diagram, and identifying the center points of all the marking points in the marking point array to establish an initial bird's-eye view; performing perspective transformation on each unit rectangular area in the marking point array of the initial bird's-eye view to obtain the corresponding local bird's-eye view; splicing all the local bird's-eye views to obtain a recombined bird's-eye view that only includes the base target area; coordinate mapping the image coordinate system corresponding to the recombined bird's-eye view with the base coordinate system corresponding to the base format. Through the implementation of the scheme of the present application, the alignment correction method is used to associate the processing vector with the base to achieve auxiliary positioning of the product, which can effectively improve the product processing accuracy and processing efficiency.

Description

Technical Field

[0001] The present application relates to the technical field of material processing, and in particular to an alignment correction method, device and computer-readable storage medium. Background Art

[0002] In the field of material processing, after setting the processing vector of the cutting head (laser head or knife head), technicians often hope to know the processing trajectory of the cutting machine in advance during the actual processing. For example, when processing a plaid shirt, it is usually hoped that the cutting line can be cut on the edge of the plaid. In this case, the plaid shirt needs to be placed in the correct position for processing. If the processing trajectory cannot be visualized, the product can only be aligned according to experience, resulting in lower product cutting accuracy. Summary of the invention

[0003] The embodiments of the present application provide an alignment correction method, device and computer-readable storage medium, which can at least solve the problem of low product cutting accuracy caused by the inability to visualize the processing trajectory of the cutting process in the related art.

[0004] A first aspect of an embodiment of the present application provides an alignment correction method, which is applied to an automatic cutting device provided with a base, comprising:

[0005] Set the cutting vector diagram of the marking point according to the marking point setting parameters;

[0006] Cutting a marker array on a calibration object placed in a target area of ​​a base according to the cutting vector diagram, identifying the center points of all markers in the marker array, and establishing an initial bird's-eye view;

[0007] Performing perspective transformation on each unit rectangular area in the marker point array of the initial bird's-eye view to obtain a corresponding local bird's-eye view;

[0008] All the local bird's-eye views are spliced ​​together to obtain a reconstructed bird's-eye view that only includes the target area of ​​the base station;

[0009] Coordinate mapping is performed between the image coordinate system corresponding to the reorganized bird's-eye view and the base coordinate system corresponding to the base.

[0010] A second aspect of an embodiment of the present application provides an alignment correction device, which is applied to an automatic cutting device provided with a base, comprising:

[0011] A setting module is used to set the cutting vector diagram of the marking point according to the marking point setting parameters;

[0012] An establishment module is used to cut a marking point array on a calibration object placed in a target area of ​​a base station according to the cutting vector map, identify the center points of all marking points in the marking point array, and establish an initial bird's-eye view;

[0013] A transformation module, used for performing perspective transformation on each unit rectangular area in the marker point array of the initial bird's-eye view to obtain a corresponding local bird's-eye view;

[0014] A splicing module, used for splicing all the local bird's-eye views to obtain a reconstructed bird's-eye view containing only the target area of ​​the base station;

[0015] A mapping module is used to perform coordinate mapping between the image coordinate system corresponding to the reconstructed bird's-eye view and the base coordinate system corresponding to the base.

[0016] A third aspect of an embodiment of the present application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements each step of the alignment correction method provided in the first aspect of the embodiment of the present application.

[0017] A fourth aspect of an embodiment of the present application provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, each step of the alignment correction method provided in the first aspect of the embodiment of the present application is implemented.

[0018] As can be seen from the above, according to the alignment correction method, device and computer-readable storage medium provided by the present application, the cutting vector diagram of the marking point is set according to the marking point setting parameters; the marking point array is cut on the calibration object placed in the target area of ​​the base according to the cutting vector diagram, and the center points of all the marking points in the marking point array are identified to establish an initial bird's-eye view; each unit rectangular area in the marking point array of the initial bird's-eye view is perspective transformed to obtain the corresponding local bird's-eye view; all local bird's-eye views are spliced ​​to obtain a recombined bird's-eye view that only includes the target area of ​​the base; coordinate mapping is performed between the image coordinate system corresponding to the recombined bird's-eye view and the base coordinate system corresponding to the base. Through the implementation of the present application, the alignment correction method is used to associate the processing vector with the base to achieve auxiliary positioning of the product, which can effectively improve the product processing accuracy and processing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A schematic diagram of a flow chart of an alignment correction method provided in the first embodiment of the present application;

[0020] Figure 2 A cutting vector diagram provided in the first embodiment of the present application;

[0021] Figure 3 A reconstructed bird's-eye view provided for the first embodiment of the present application;

[0022] Figure 4 A schematic diagram of a flow chart of a distortion correction method provided in the first embodiment of the present application;

[0023] Figure 5 A schematic diagram of a program module of an alignment correction device provided in a second embodiment of the present application;

[0024] Figure 6 A schematic diagram of the structure of an electronic device provided in the third embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to make the purpose, features, and advantages of the invention of this application more obvious and easy to understand, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0026] In order to solve the problem of low product cutting accuracy caused by the inability to visualize the machining trajectory of the cutting process in the related art, the first embodiment of the present application provides an alignment correction method, which is applied to an automatic cutting device provided with a base, and the base has a bearing area, and the bearing area is used to place the product to be processed, such as Figure 1 The basic flow chart of the alignment correction method provided in this embodiment includes the following steps:

[0027] Step 101: Set the cutting vector diagram of the marking point according to the marking point setting parameters.

[0028] Specifically, the marking point setting parameters of this embodiment include: the number of marking points, the shape of marking points, the spacing between marking points, and the size of marking points. The marking points can also be called Mark points. The shapes of marking points can include circles, triangles, squares, rectangles, ellipses, etc. Because circles have good anisotropy, this embodiment preferably uses circles as marking points. In practical applications, the size of the marking points can be set by yourself. Under the fisheye lens, the larger the marking points, the better and more accurate the edge anti-blurring, but the longer the cutting time will be.

[0029] In an optional implementation of this embodiment, before the step of setting the cutting vector diagram of the marking points according to the marking point setting parameters, the step further includes: acquiring surface morphology information of the base; and determining the marking point setting parameters accordingly based on the surface morphology information.

[0030] Specifically, the surface morphology information of this embodiment includes: flatness information and surface area information. Under different base station formats, the alignment correction requirements are different, so the corresponding marking point setting parameters also need to be adaptively adjusted.

[0031] This embodiment takes the number of marking points as an example of the marking point setting parameter. In actual applications, the size of the base varies. In order to meet the correction accuracy requirements, the number of marking points can be set with reference to the surface area of ​​the base. In addition, in conventional implementations, the more marking points there are, the more accurate the subsequent bird's-eye view segmentation can be, and the better the local adaptability. However, due to the influence of the flatness of the base, it is also easy to overcorrect. For example, if the surface of the calibration object has local protrusions or depressions, the actual imaging should be offset. If there are too many marking points, the image segmentation accuracy is high and the alignment is incorrectly corrected. Therefore, in actual applications, the marking point setting parameters are adaptively determined by referring to the surface morphology of the base format to ensure the effectiveness of subsequent alignment correction.

[0032] like Figure 2 The figure shows a cutting vector diagram provided in the present embodiment, wherein the number of marking points is 15, the marking point array composed of the 15 marking points is a 5*3 array, the marking point shape is circular, the marking point diameter is 5 mm, and the cutting vector is shown in the grid lines in the figure. It should be understood that in actual applications, the cutting points can be arranged at equal intervals or at unequal intervals, depending on actual usage requirements.

[0033] Step 102: cut a marker array on the calibration object placed in the target area of ​​the base according to the cutting vector map, identify the center points of all markers in the marker array, and establish an initial bird's-eye view.

[0034] Specifically, the calibration object of this embodiment can be white paper or a wooden board, among which white paper is easy to mark and the wooden board has a higher flatness. This embodiment preferably uses white paper as the calibration object, which is cut according to the size of the base format and placed flatly in the target area of ​​the base bearing area, and then the cutting head is controlled to cut on the calibration object according to the cutting vector diagram. Finally, the image captured by the camera (a conventional camera or a fisheye camera with distortion correction) is used to identify the marking points and establish a bird's-eye view.

[0035] Step 103: Perform perspective transformation on each unit rectangular area in the marker point array of the initial bird's-eye view to obtain a corresponding local bird's-eye view.

[0036] Specifically, in this embodiment, after connecting the marking points in the initial bird's-eye view, a plurality of unit rectangular areas can be formed. Taking the aforementioned 5*3 marking point array as an example, it can be finally divided into 8 unit rectangular areas. In this embodiment, each unit rectangular area in the initial bird's-eye view is treated as an independent individual and perspective transformed, so as to obtain a plurality of bird's-eye views containing only parts of the target area. The width and height of the image after the perspective transformation of a single area is calculated according to the format size of the divided area and the target DPI, and the required image width and height after the perspective transformation of each actual area are calculated. The image width is equal to the actual width divided by 25.4 multiplied by the DPI. Similarly, the image height is equal to the actual height divided by 25.4 multiplied by the DPI.

[0037] In some implementations of the present embodiment, before the above-mentioned step of performing perspective transformation on each unit rectangular area in the marker point array of the initial bird's-eye view, it also includes: obtaining the target cutting accuracy of the automatic cutting device; determining the array division strategy according to the target cutting accuracy; and dividing the marker point array of the initial bird's-eye view into multiple unit rectangular areas according to the array division strategy.

[0038] Specifically, in practical applications, the division of the initial bird's-eye view will also play an important role in the correction result. This embodiment takes into account that different cutting accuracy requirements usually correspond to different correction requirements. This embodiment adaptively divides the marker point array with reference to the cutting accuracy requirements. For example, when the cutting accuracy requirement is high, the marker point array can be divided more finely, and if the cutting accuracy requirement is relatively low, the marker point array can be divided slightly roughly.

[0039] Step 104: stitch all the local bird's-eye views together to obtain a reconstructed bird's-eye view that only includes the base target area.

[0040] Specifically, after obtaining multiple local bird's-eye views, this embodiment splices and reorganizes all the local bird's-eye views to form a complete bird's-eye view that only contains the target area, thereby completing the extraction of the target area. Continuing with the example of the aforementioned 5*3 array of marker points composed of 15 marker points, as Figure 3 Shown is a reconstructed bird's-eye view provided by this embodiment.

[0041] Step 105 : coordinate mapping the image coordinate system corresponding to the reorganized bird's-eye view and the base coordinate system corresponding to the base.

[0042] Specifically, this embodiment reorganizes the bird's-eye view coordinate system and establishes a mapping relationship with the base coordinate system so that the cutting vector can be correctly associated with the base of the cutting device. The specific actual position on the base can be calculated through the image coordinates, thereby achieving auxiliary positioning during product processing.

[0043] like Figure 4The figure is a flow chart of a distortion correction method provided by the present embodiment. In some implementations of the present embodiment, before the step of identifying the center point of all the marking points in the marking point array, the following process is also included:

[0044] S401, dividing the entire base area into multiple local areas;

[0045] S402, obtaining reference images taken by the fisheye camera with respect to the calibration objects placed in each local area;

[0046] S403, calculating the internal and external parameters of the camera according to the coordinates of the marking points in each reference image;

[0047] S404: Perform distortion correction on the fisheye camera based on internal and external parameters of the camera.

[0048] Specifically, in practical applications, alignment correction is applicable to undistorted images captured by ordinary cameras, and also to distortion-corrected images captured by fisheye cameras. As for the distortion correction of fisheye cameras, this embodiment can divide the base format into multiple local areas according to the size of the calibration object, and then place the calibration object in these multiple local areas respectively. The same position has different placement methods and postures, and different correction effects are achieved for different placement postures. After repeated comparative tests, it is found that different positions usually need to be tilted toward the camera for the best effect. Further, the calibration objects in different placement positions are imaged by the fisheye camera, and the internal and external parameters of the camera can be inferred by the coordinates of the marked points identified in the image. Finally, the distortion correction of the fisheye camera can be achieved based on the internal and external parameters.

[0049] In some implementations of this embodiment, the step of mapping the image coordinate system corresponding to the reorganized bird's-eye view with the base coordinate system corresponding to the base format specifically includes: mapping the image coordinate system corresponding to the reorganized bird's-eye view with the base coordinate system corresponding to the base according to a preset coordinate mapping formula. When the lower left corner is the origin of the base coordinate system and the upper left corner is the origin of the image coordinate system, the coordinate mapping formula is expressed as:

[0050] PixSizeW=DW / RW

[0051] PixSizeH=DH / RH

[0052] (Pxi,Pyi)=(Pxw / PixSizeW,DH-Pyw / PixSizeH);

[0053] PixSizeW represents the actual distance represented by an image pixel in the horizontal direction, and PixSizeH represents the actual distance represented by an image pixel in the vertical direction. The units of both are mm / pix. The smaller the value, the higher the accuracy. (RW*RH) represents the image resolution, (DW*DH) represents the range of the target area of ​​the base, (Pxi, Pyi) represents the coordinate value of the coordinate point in the image coordinate system, and (Pxw, Pyw) represents the coordinate value of the coordinate point in the base coordinate system.

[0054] Specifically, in this embodiment, establishing coordinate mapping involves two coordinate systems, an image coordinate system and an absolute coordinate system. The image coordinate system is the coordinate system of the bird's-eye view image after imaging, and the absolute coordinate system is the coordinate system where the cutting vector map is located.

[0055] Based on the technical solution of the embodiment of the present application described above, a cutting vector diagram of the marking points is set according to the marking point setting parameters; the marking point array is cut on the calibration object placed in the target area of ​​the base according to the cutting vector diagram, and the center points of all the marking points in the marking point array are identified to establish an initial bird's-eye view; each unit rectangular area in the marking point array of the initial bird's-eye view is perspective transformed to obtain a corresponding local bird's-eye view; all local bird's-eye views are spliced ​​to obtain a recombined bird's-eye view that only includes the target area of ​​the base; coordinate mapping is performed between the image coordinate system corresponding to the recombined bird's-eye view and the base coordinate system corresponding to the base. Through the implementation of the solution of the present application, the alignment correction method is used to associate the processing vector with the base to achieve auxiliary positioning of the product, which can effectively improve the product processing accuracy and processing efficiency.

[0056] Figure 5 An alignment correction device is provided in the second embodiment of the present application. The alignment correction device can be used to implement the alignment correction method in the above-mentioned embodiment. Figure 5 As shown, the alignment correction device mainly includes:

[0057] A setting module 501, used to set a cutting vector diagram of a marking point according to marking point setting parameters;

[0058] Establishing module 502, for cutting a marker array on a calibration object placed in a target area of ​​a base station according to a cutting vector diagram, identifying the center points of all markers in the marker array, and establishing an initial bird's-eye view;

[0059] The transformation module 503 is used to perform perspective transformation on each unit rectangular area in the marker point array of the initial bird's-eye view to obtain a corresponding local bird's-eye view;

[0060] A splicing module 504 is used to splice all the local bird's-eye views to obtain a reconstructed bird's-eye view that only includes the base station target area;

[0061] The mapping module 505 is used to perform coordinate mapping between the image coordinate system corresponding to the reconstructed bird's-eye view and the base coordinate system corresponding to the base.

[0062] In some implementations of the present embodiment, the alignment correction device of the present embodiment also includes: a distortion correction module, which is used to: divide the overall area of ​​the base into multiple local areas; obtain reference images taken by the fisheye camera with the calibration objects placed in each local area; infer the internal and external parameters of the camera based on the coordinates of the marking points in each reference image; and perform distortion correction on the fisheye camera based on the internal and external parameters of the camera.

[0063] In some implementations of this embodiment, the alignment correction device of this embodiment also includes: a determination module, used to: obtain surface morphology information of the base, wherein the surface morphology information includes: flatness information, surface area information; and determine the marking point setting parameters accordingly based on the surface morphology information.

[0064] In some implementations of this embodiment, the alignment correction device of this embodiment also includes: a division module, used to obtain the target cutting accuracy of the automatic cutting device; determine the array division strategy according to the target cutting accuracy; according to the array division strategy, divide the marking point array of the initial bird's-eye view into multiple unit rectangular areas.

[0065] In some implementations of this embodiment, the mapping module is specifically used to: coordinate map the image coordinate system corresponding to the reorganized bird's-eye view with the base coordinate system corresponding to the base according to a preset coordinate mapping formula. Wherein, when the lower left corner is the origin of the base coordinate system and the upper left corner is the origin of the image coordinate system, the coordinate mapping formula is expressed as:

[0066] PixSizeW=DW / RW

[0067] PixSizeH=DH / RH

[0068] (Pxi,Pyi)=(Pxw / PixSizeW,DH-Pyw / PixSizeH);

[0069] PixSizeW represents the actual distance represented by an image pixel in the horizontal direction, PixSizeH represents the actual distance represented by an image pixel in the vertical direction, (RW*RH) represents the image resolution, (DW*DH) represents the range of the base target area, (Pxi, Pyi) represents the coordinate value of the coordinate point in the image coordinate system, and (Pxw, Pyw) represents the coordinate value of the coordinate point in the base coordinate system.

[0070] It should be noted that the alignment correction methods in the first and second embodiments can be implemented based on the alignment correction device provided in this embodiment. Ordinary technical personnel in the relevant field can clearly understand that for the convenience and conciseness of description, the specific working process of the alignment correction device described in this embodiment can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0071] According to the alignment correction device provided by this embodiment, the cutting vector diagram of the marking point is set according to the marking point setting parameters; the marking point array is cut on the calibration object placed in the target area of ​​the base according to the cutting vector diagram, and the center points of all the marking points in the marking point array are identified to establish an initial bird's-eye view; each unit rectangular area in the marking point array of the initial bird's-eye view is perspective transformed to obtain the corresponding local bird's-eye view; all local bird's-eye views are spliced ​​to obtain a recombined bird's-eye view that only includes the target area of ​​the base; the image coordinate system corresponding to the recombined bird's-eye view is mapped to the base coordinate system corresponding to the base. Through the implementation of the present application scheme, the alignment correction method is used to associate the processing vector with the base to achieve auxiliary positioning of the product, which can effectively improve the product processing accuracy and processing efficiency.

[0072] See also Figure 6 , Figure 6 The third embodiment of the present application provides an electronic device. The electronic device can be used to implement the alignment correction method in the above embodiment. Figure 6 As shown, the electronic device mainly includes:

[0073] Memory 601, processor 602, bus 603, and a computer program stored in memory 601 and executable on processor 602, memory 601 and processor 602 are connected via bus 603. When processor 602 executes the computer program, the alignment correction method in the aforementioned embodiment is implemented. The number of processors may be one or more.

[0074] The memory 601 may be a high-speed random access memory (RAM) memory, or a non-volatile memory, such as a disk memory. The memory 601 is used to store executable program codes, and the processor 602 is coupled to the memory 601 .

[0075] Furthermore, the present application also provides a computer-readable storage medium, which may be disposed in the electronic device in the above embodiments. Figure 6 Memory in the illustrated embodiment.

[0076] The computer readable storage medium stores a computer program, and when the program is executed by the processor, the alignment correction method in the aforementioned embodiment is implemented. Furthermore, the computer storable medium can also be a U disk, a mobile hard disk, a read-only memory (ROM), a RAM, a magnetic disk or an optical disk, and other media that can store program codes.

[0077] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0078] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0079] In addition, each functional module in each embodiment of the present application can be integrated into a processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above integrated modules can be implemented in the form of hardware or software functional modules.

[0080] If the integrated module is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a readable storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned readable storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, ROM, RAM, magnetic disks, or optical disks.

[0081] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described action sequence, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0082] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0083] The above is a description of the alignment correction method, device and computer-readable storage medium provided in the present application. For technicians in this field, according to the ideas of the embodiments of the present application, there may be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. An alignment correction method, applied to an automatic cutting device provided with a base, characterized in that: include: Set the cutting vector diagram of the marking point according to the marking point setting parameters; Cutting a marker array on a calibration object placed in a target area of ​​a base according to the cutting vector diagram, identifying the center points of all markers in the marker array, and establishing an initial bird's-eye view; Performing perspective transformation on each unit rectangular area in the marker point array of the initial bird's-eye view to obtain a corresponding local bird's-eye view; All the local bird's-eye views are spliced ​​together to obtain a reconstructed bird's-eye view that only includes the target area of ​​the base station; Coordinate mapping is performed between an image coordinate system corresponding to the reconstructed bird's-eye view and a base coordinate system corresponding to the base; The step of coordinate mapping the image coordinate system corresponding to the reorganized bird's-eye view and the base coordinate system corresponding to the base comprises: According to a preset coordinate mapping formula, coordinate mapping is performed between the image coordinate system corresponding to the reconstructed bird's-eye view and the base coordinate system corresponding to the base; wherein, when the lower left corner is taken as the origin of the base coordinate system and the upper left corner is taken as the origin of the image coordinate system, the coordinate mapping formula is expressed as: ； Indicates the actual distance represented by an image pixel in the horizontal direction. Indicates the actual distance represented by an image pixel in the vertical direction. Indicates the image resolution, represents the range of the base target area, ( ) represents the coordinate value of the coordinate point on the image coordinate system, ( ) represents the coordinate value of the coordinate point on the base coordinate system.

2. The alignment correction method according to claim 1, characterized in that: Before the step of identifying the center point of all the marking points in the marking point array, the method further includes: Dividing the entire base area into a plurality of local areas; Obtain reference images taken by a fisheye camera with respect to the calibration objects placed in each of the local areas; Calculate the camera internal and external parameters according to the coordinates of the marked points in each of the reference images; Distortion correction is performed on the fisheye camera based on the camera internal and external parameters.

3. The alignment correction method according to claim 1, characterized in that: Before the step of setting the cutting vector diagram of the marking point according to the marking point setting parameters, the method further includes: Acquiring surface morphology information of the base; wherein the surface morphology information includes: flatness information and surface area information; The marking point setting parameters are determined accordingly based on the surface morphology information.

4. The alignment correction method according to claim 1, characterized in that: The marking point setting parameters include: the number of marking points, the shape of marking points, the spacing between marking points, and the size of marking points.

5. The alignment correction method according to claim 1, characterized in that: Before the step of performing perspective transformation on each unit rectangular area in the marker point array of the initial bird's-eye view, the method further includes: Obtaining a target cutting accuracy of the automatic cutting device; Determining an array division strategy according to the target cutting accuracy; According to the array division strategy, the marking point array of the initial bird's-eye view is divided into a plurality of unit rectangular areas.

6. The alignment correction method according to claim 1, characterized in that: The marking point array is a 5*3 array, and the number of the unit rectangular areas is 8.

7. An alignment correction device, applied to an automatic cutting device provided with a base, characterized in that: include: A setting module is used to set the cutting vector diagram of the marking point according to the marking point setting parameters; An establishment module is used to cut a marking point array on a calibration object placed in a target area of ​​a base station according to the cutting vector map, identify the center points of all marking points in the marking point array, and establish an initial bird's-eye view; A transformation module, used for performing perspective transformation on each unit rectangular area in the marker point array of the initial bird's-eye view to obtain a corresponding local bird's-eye view; A splicing module, used for splicing all the local bird's-eye views to obtain a reconstructed bird's-eye view containing only the target area of ​​the base station; A mapping module is used to coordinately map the image coordinate system corresponding to the reconstructed bird's-eye view with the base coordinate system corresponding to the base according to a preset coordinate mapping formula; wherein, when the lower left corner is taken as the origin of the base coordinate system and the upper left corner is taken as the origin of the image coordinate system, the coordinate mapping formula is expressed as: ； Indicates the actual distance represented by an image pixel in the horizontal direction. Indicates the actual distance represented by an image pixel in the vertical direction. Indicates the image resolution, represents the range of the base target area, ( ) represents the coordinate value of the coordinate point on the image coordinate system, ( ) represents the coordinate value of the coordinate point on the base coordinate system.

8. An electronic device, characterized in that: include: Memory, processor and bus; The bus is used to realize the connection and communication between the memory and the processor; The processor is used to execute the computer program stored in the memory; When the processor executes the computer program, the steps in the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in the method according to any one of claims 1 to 6 are implemented.

Images