Method, device and computer equipment for generating positioning points

Abstract

The present application relates to a method, device and computer equipment for generating positioning points. The method comprises: obtaining a target image; wherein the target image comprises an image of a chip and an image of a carrier texture; determining an initial positioning point of the chip in the target image; when the pixel value of the initial positioning point does not meet a preset threshold, searching in sequence with the initial positioning point as the center and a preset distance threshold as the interval to obtain a replacement positioning point whose pixel value corresponding to the initial positioning point meets the preset threshold; using the replacement positioning point, replacing the initial positioning point to obtain a target positioning point; wherein the target positioning point is used to locate the chip. The use of this method can improve the accuracy of generating positioning points.

Description

Technical Field

[0001] The present application relates to the field of machine vision technology, and in particular to a method, device, computer equipment, storage medium and computer program product for generating positioning points. Background Art

[0002] With the advancement of semiconductor manufacturing technology, new technologies have emerged that use high-magnification cameras to photograph and process transparent wafers. However, during the processing, the position of the wafer may shift due to factors such as thermal expansion and contraction. To solve this problem, engineers use image recognition to locate the wafer and determine the row and column coordinates of the wafer to correct the position shift caused by processing.

[0003] However, when processing wafers, external factors may affect the accuracy of wafer border recognition. Figure 1 As shown, a wide-angle camera is usually used to determine the wafer’s deflection point ( Figure 1 The black dots in the image are used to accurately locate the high-magnification camera to the wafer position (the gray filled part). However, this method may be affected by the interference of the stage gas path texture (gray lines) on the correction point, thus affecting the positioning accuracy of the wafer.

[0004] In the prior art, a white or near-infrared point light source is usually added to the top of the wafer, combined with the backlight source of the carrier, to increase the contrast between the wafer and the gas path texture, thereby further reducing the interference of the carrier gas path texture on the correction point. However, this method has extremely high hardware costs and cannot completely eliminate the interference caused by the carrier gas path texture, resulting in a high alarm rate for abnormal recognition. Summary of the invention

[0005] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product that can generate positioning points in response to the above technical problems.

[0006] In a first aspect, the present application provides a method for generating a positioning point. The method comprises:

[0007] Acquire a target image; wherein the target image includes an image of the chip and an image of the stage texture;

[0008] Determining an initial positioning point of the chip in the target image;

[0009] When the pixel value of the initial positioning point does not meet the preset threshold, the initial positioning point is taken as the center and the preset distance threshold is used as the interval to sequentially search for a replacement positioning point whose pixel value corresponding to the initial positioning point meets the preset threshold;

[0010] The initial positioning point is replaced by the replacement positioning point to obtain a target positioning point, wherein the target positioning point is used to position the chip.

[0011] In one of the embodiments, when the pixel value of the initial positioning point does not meet the preset threshold, taking the initial positioning point as the center and the preset distance threshold as the interval, sequentially searching to obtain a replacement positioning point whose pixel value corresponding to the initial positioning point meets the preset threshold includes:

[0012] When the pixel value of the initial positioning point meets the preset threshold, the initial positioning point is determined as the target positioning point;

[0013] When the pixel value of the initial positioning point does not meet the preset threshold, the initial positioning point is taken as the center and the preset distance threshold is used as the interval to sequentially search for a replacement positioning point whose pixel value corresponding to the initial positioning point meets the preset threshold.

[0014] In one embodiment, determining the initial positioning point of the chip in the target image includes:

[0015] Obtain the boundary information of the chip in the target image;

[0016] By using the preset distance threshold and the boundary information, the midpoints of the intersections of the vertical line in the preset direction and the chip boundary information are determined in sequence to obtain the initial positioning point.

[0017] In one embodiment, acquiring the target image includes:

[0018] Acquire an initial target image; wherein the initial target image includes pixel coordinate information corresponding to the initial target image;

[0019] Using a preset correction strategy, the pixel coordinate information of the initial target image is corrected to obtain pixel corrected coordinate information;

[0020] The pixel coordinate information is used to correct the target image.

[0021] In one embodiment, the target image includes an image captured by a wide-angle camera; the positioning point includes first coordinate information of the positioning point in the target image; after the initial positioning point is replaced by the replacement positioning point to obtain the target positioning point, the method further includes:

[0022] Determine the second coordinate information corresponding to the first coordinate information by using a preset conversion strategy between the first coordinate information and the second coordinate information; wherein the second coordinate information includes the coordinate information under the high-magnification camera corresponding to the first coordinate information under the wide-angle camera;

[0023] The high-power camera is positioned according to the second coordinate information to determine the image of the chip under the high-power camera.

[0024] In one embodiment, the conversion strategy is obtained by:

[0025] Obtaining sample first coordinate information and sample second coordinate information;

[0026] The conversion strategy is established using the sample first coordinate information and the sample second coordinate information.

[0027] In a second aspect, the present application also provides a device for generating a positioning point. The device comprises:

[0028] An image acquisition module, used to acquire a target image; wherein the target image includes an image of the chip and an image of the stage texture;

[0029] A positioning point determination module, used to determine the initial positioning point of the chip in the target image;

[0030] The positioning point determination module is further configured to, when the pixel value of the initial positioning point does not meet the preset threshold, sequentially search with the initial positioning point as the center and the preset distance threshold as the interval to obtain a replacement positioning point whose pixel value corresponding to the initial positioning point meets the preset threshold;

[0031] The positioning point determination module is further used to replace the initial positioning point with the replacement positioning point to obtain a target positioning point; wherein the target positioning point is used to locate the chip.

[0032] In one embodiment, the positioning point determination module includes:

[0033] A positioning point determination submodule, configured to determine the initial positioning point as a target positioning point when a pixel value of the initial positioning point meets a preset threshold;

[0034] The positioning point determination submodule is also used to, when the pixel value of the initial positioning point does not meet the preset threshold, sequentially search with the initial positioning point as the center and the preset distance threshold as the interval to obtain a replacement positioning point whose pixel value corresponding to the initial positioning point meets the preset threshold.

[0035] In one embodiment, the positioning point determination module includes:

[0036] The boundary acquisition submodule is used to obtain the boundary information of the chip in the target image;

[0037] The positioning point determination submodule is used to use a preset distance threshold and the boundary information to sequentially determine the midpoint of the intersection of the vertical line in the preset direction and the chip boundary information to obtain the initial positioning point.

[0038] In one embodiment, the image acquisition module includes:

[0039] An image acquisition submodule, used to acquire an initial target image; wherein the initial target image includes pixel coordinate information corresponding to the initial target image;

[0040] An image correction submodule, used to correct the pixel coordinate information of the initial target image using a preset correction strategy to obtain pixel correction coordinate information;

[0041] The image acquisition submodule is also used to obtain a target image using the pixel correction coordinate information.

[0042] In one embodiment, the device further comprises:

[0043] A coordinate conversion module, used to determine second coordinate information corresponding to the first coordinate information by using a preset conversion strategy between the first coordinate information and the second coordinate information; wherein the second coordinate information includes coordinate information under a high-magnification camera corresponding to the first coordinate information under a wide-angle camera;

[0044] The image acquisition module is further used to position the high-magnification camera according to the second coordinate information, and determine the image of the chip under the high-magnification camera.

[0045] In one embodiment, the coordinate conversion module includes:

[0046] A sample acquisition submodule, used to acquire sample first coordinate information and sample second coordinate information;

[0047] The strategy establishment submodule is used to establish the conversion strategy using the sample first coordinate information and the sample second coordinate information.

[0048] In a third aspect, the present application further provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method for generating a positioning point as described in any one of the embodiments of the present disclosure is implemented.

[0049] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for generating a positioning point as described in any one of the embodiments of the present disclosure is implemented.

[0050] In a fifth aspect, the present application further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the method for generating a positioning point as described in any one of the embodiments of the present disclosure is implemented.

[0051] The above-mentioned method, device, computer equipment, storage medium and computer program product for generating positioning points confirm the chip initial positioning points of the target image and judge the pixel value of the initial positioning points to determine whether the initial positioning points are affected by the carrier texture, and further replace the initial positioning points by finding the positioning points that are not affected to obtain the target positioning points for positioning the chip. By judging the pixel value of the initial positioning points, the initial positioning points that are interfered by the carrier texture can be accurately screened out, providing a data basis for the confirmation of the interference positioning points, and improving the accuracy of the determination of the interference positioning points. At the same time, by finding other positioning points that meet the preset threshold to replace the interference positioning points, the target positioning points are all positioning points that are not affected by the carrier texture, which improves the accuracy of the target positioning points and further improves the accuracy of positioning the chip using the target positioning points. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 This is the application environment background map of this solution;

[0053] Figure 2 is a schematic diagram of a flow chart of a method for generating a positioning point in one embodiment;

[0054] Figure 3 A schematic diagram of replacing a positioning point search in one embodiment;

[0055] Figure 4 A schematic diagram of a process for determining pixel values ​​in an embodiment;

[0056] Figure 5 A schematic diagram of a process for confirming an initial positioning point in one embodiment;

[0057] Figure 6 is a schematic diagram of an initial positioning point in one embodiment;

[0058] Figure 7 A schematic diagram of a process of acquiring a target image in one embodiment;

[0059] Figure 8 A schematic diagram of a process of acquiring an image using a high-magnification camera in one embodiment;

[0060] Fig. 9 A schematic diagram of a process for establishing a conversion strategy in one embodiment;

[0061] Fig.10 A schematic diagram of a first process flow of a method for generating a positioning point in one embodiment;

[0062] Fig.11 A second flow chart of a method for generating a positioning point in one embodiment;

[0063] Fig.12 is a structural block diagram of a device for generating a positioning point in an embodiment;

[0064] Fig.13 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0065] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0066] In one embodiment, Figure 2 As shown, a method for generating a positioning point is provided. This embodiment takes the method applied to a terminal as an example for explanation. It can be understood that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0067] Step S100, acquiring a target image; wherein the target image includes an image of the chip and an image of the stage texture.

[0068] In an exemplary embodiment, the target image may include an image on the chip and an image of a texture on the carrier, etc.; wherein the chip may include a wafer, etc.; the carrier may be used to place the chip on the carrier, photograph and identify the chip, etc.; the carrier texture may include the air path texture and other textures on the carrier, etc.; specifically, the target image may include an image obtained by photographing and identifying the chip on the carrier through the backlight area of ​​a wide-angle camera, etc.

[0069] Step S200, determining an initial positioning point of the chip in the target image.

[0070] In an exemplary embodiment, the initial positioning point may include a preset direction and a preset distance, obtaining the border points of the chip in the target image, starting from the preset direction, taking the midpoint of the chip border points in the vertical direction corresponding to the preset direction at intervals of a preset distance, and determining all midpoints as initial positioning points, etc.; in another exemplary embodiment, the initial positioning point may be obtained by feature point recognition, reference pattern design, etc.; specifically, feature point recognition may be achieved by processing corner points, edges, intersections, etc. of the chip; reference pattern design may be achieved by designing reference patterns of positioning points (e.g., marks, grids, etc.), which do not change with process changes, to further determine the position of the chip, etc.

[0071] Step S300, when the pixel value of the initial positioning point does not meet the preset threshold, searching in sequence with the initial positioning point as the center and the preset distance threshold as the interval to obtain a replacement positioning point whose pixel value corresponding to the initial positioning point meets the preset threshold.

[0072] In an exemplary embodiment, the pixel value may include a grayscale value, an RGB value, an HSL value, etc.; and a preset threshold is designed according to the gas path texture of the carrier and the color of the chip. If the pixel value of the initial positioning point does not meet the preset threshold, it is determined that the initial positioning point has been affected by the gas path texture, so the initial positioning point is taken as the center and the preset distance threshold is used as the interval to search outward in sequence, specifically, Figure 3 As shown, the five-pointed star point represents the affected initial positioning point, and the pixel values ​​of the surrounding points are judged in sequence according to the distance, and then the unaffected points are determined to replace the initial positioning point. It can be understood that when judging the pixel values ​​of the surrounding points, they can be judged one by one, and when a point with a pixel value that meets a preset threshold is found, the search is stopped, etc.; for example, the judgment order is "upper left - upper - upper right - right - lower right - lower - lower left - left", then when the pixel value of the upper left is judged to meet the threshold, the upper left point will be directly determined as the replacement positioning point, and the judgment will be stopped, and the subsequent points will not be judged.

[0073] Step S400: using the replacement positioning point to replace the initial positioning point to obtain a target positioning point; wherein the target positioning point is used to locate the chip.

[0074] In an exemplary embodiment, the initial positioning point is replaced by a replacement positioning point to obtain a target positioning point. It can be understood that the positioning point may include multiple positioning points, that is, multiple initial positioning points, wherein the multiple initial positioning points may include some initial positioning points whose pixel values ​​meet the threshold and some initial positioning points whose pixel values ​​do not meet the preset threshold. In this case, only the initial positioning points whose pixel values ​​do not meet the preset threshold are replaced to obtain multiple new positioning points, that is, the target positioning points. It can be understood that the target positioning point may include the positioning point whose pixel value meets the preset threshold among the initial positioning points, and the replacement positioning point whose pixel value meets the preset threshold and is replaced, etc.

[0075] In an exemplary embodiment, the method for generating positioning points can be applied to the processing of chips, which includes a wide-angle camera and a high-power lens camera; the target image is an image under the wide-angle camera, and the target positioning points are positioning points under the wide-angle camera. The target positioning points can be converted into positioning points under the high-power camera through a certain strategy, and the high-power camera can accurately locate the chip in real time based on the positioning points. In an exemplary embodiment, after obtaining the target positioning points, the high-power camera can locate the chip position in real time based on the target positioning points. If a few positioning points disappear among the target positioning points, the positioning can continue to be performed based on the remaining target positioning points. If a number of positioning points greater than a threshold disappear among the target positioning points, the wide-angle camera can be used again to determine the target image and redetermine the target positioning points.

[0076] In the above-mentioned method for generating positioning points, the initial positioning points of the chip of the target image are confirmed, and the pixel values ​​of the initial positioning points are judged to determine whether the initial positioning points are affected by the carrier texture, and the initial positioning points are further replaced by finding the positioning points that are not affected, so as to obtain the target positioning points used to locate the chip. By judging the pixel values ​​of the initial positioning points, the initial positioning points that are interfered by the carrier texture can be accurately screened out, providing a data basis for the confirmation of the interference positioning points, and improving the accuracy of the determination of the interference positioning points. At the same time, by finding other positioning points that meet the preset threshold to replace the interference positioning points, the target positioning points are all positioning points that are not affected by the carrier texture, which improves the accuracy of the target positioning points and further improves the accuracy of positioning the chip using the target positioning points.

[0077] In one embodiment, Figure 4 As shown, when the pixel value of the initial positioning point does not meet the preset threshold, the initial positioning point is taken as the center and the preset distance threshold is used as the interval to sequentially search for a replacement positioning point whose pixel value corresponding to the initial positioning point meets the preset threshold, including:

[0078] Step S301: when the pixel value of the initial positioning point meets a preset threshold, the initial positioning point is determined as a target positioning point.

[0079] Step S302, when the pixel value of the initial positioning point does not meet the preset threshold, searching in sequence with the initial positioning point as the center and the preset distance threshold as the interval to obtain a replacement positioning point whose pixel value corresponding to the initial positioning point meets the preset threshold.

[0080] In an exemplary embodiment, the initial positioning point may include multiple positioning points, etc.; wherein, the pixel values ​​of some initial positioning points may meet the preset threshold, while the pixel values ​​of some initial positioning points may not meet the preset threshold, etc.

[0081] In an exemplary embodiment, if the pixel value at the initial positioning point meets the preset threshold, it can be considered that the initial positioning point is not affected by the stage texture, and the initial positioning point is determined as the target positioning point, etc. In an exemplary embodiment, if the pixel value at the initial positioning point does not meet the preset threshold, it can be considered that the initial positioning point has been affected by the stage texture, and it is necessary to find a replacement positioning point that meets the threshold. Specifically, with the initial positioning point as the center, the search is gradually outward with the preset distance threshold as the interval, and when a point whose pixel value meets the preset threshold is found, the point is determined as the replacement positioning point, etc.

[0082] In this embodiment, the pixel value of the initial positioning point is judged to determine whether the initial positioning point has been interfered with by the carrier texture. When it is determined that the initial positioning point is interfered with, the corresponding replacement positioning point is found. The initial positioning point interfered with by the carrier texture and the initial positioning point not interfered with by the carrier texture can be accurately determined. The judgment of the pixel points provides a data basis for the confirmation of the interfered positioning point, thereby improving the accuracy of the identification of the interfered positioning point.

[0083] In one embodiment, Figure 5 As shown, the determining of the initial positioning point of the chip in the target image includes:

[0084] Step S201, obtaining the boundary information of the chip in the target image.

[0085] Step S202, using a preset distance threshold and the boundary information, sequentially determine the midpoints of the intersections of a vertical line in a preset direction and the chip boundary information to obtain the initial positioning point.

[0086] In an exemplary embodiment, obtaining the initial feature point may include using a preset distance threshold, drawing a vertical line in the preset direction at intervals of a distance threshold, and the midpoint of the two intersections of the vertical line and the boundary information is the initial positioning point. Specifically, it may include drawing a straight line perpendicular to the preset direction every time a distance threshold is passed through the preset direction, and there are two intersections between the straight line and the boundary information, and the midpoint of the intersection is the initial feature point.

[0087] In an exemplary embodiment, the chip may include an irregularly shaped chip, etc. The boundary information may be obtained by taking a picture with a wide-angle camera, etc. It is understandable that after obtaining the boundary information, the preset distance threshold may be used to obtain the initial positioning point at the midpoint of the chip boundary information in the preset direction. Specifically, a preset direction and a distance threshold are defined, and according to the preset direction, at each interval of a distance threshold, a vertical line of the preset direction is taken to obtain two intersections with the chip boundary, and the midpoint between the two intersections is an initial positioning point, etc.

[0088] In an exemplary embodiment, the initial positioning point can be determined as follows: Figure 6 As shown, the outermost circle is the frame of the carrier, and the gray lines inside are the texture of the carrier; the gray filled part is the chip; the preset direction of this figure is the up and down direction, so the two points of the chip frame are obtained from the left and right at every preset distance, and the middle point, that is, the black dot in the figure, is calculated; the initial positioning point is obtained, and it can be understood that all the black dots in the figure are the initial positioning points; there are some initial positioning points among the initial positioning points that coincide with the texture of the carrier, then the initial positioning point is the disturbed point, which has been marked with the positive direction in the figure, that is, the initial positioning point framed by the square frame is the disturbed initial positioning point, etc.

[0089] In this embodiment, by using the boundary information of the chip in the target image, the midpoint of the chip boundary information in the preset direction is determined in sequence to obtain the initial positioning point. The preset distance threshold and boundary information can be used to determine the midpoint on the chip boundary and determine it as the initial positioning point, so that the method for determining the initial positioning point can be applicable to chip types of different shapes, thereby improving the accuracy of generating the positioning point. The preset direction and distance threshold provide a data basis for the generation of the positioning point, and the initial positioning point with the generated error can be found, further improving the accuracy of generating the initial positioning point.

[0090] In one embodiment, Figure 7 As shown, the acquiring of the target image includes:

[0091] Step S101, obtaining an initial target image; wherein the initial target image includes pixel coordinate information corresponding to the initial target image.

[0092] Step S102: using a preset correction strategy, correct the pixel coordinate information of the initial target image to obtain pixel corrected coordinate information.

[0093] Step S103, using the pixel correction coordinate information to obtain a target image.

[0094] In an exemplary embodiment, the initial target image is a texture image of the backlight chip and the stage under a wide-angle camera. It is understandable that the image may be distorted when the wide-angle camera is used for shooting, so a correction strategy is needed to correct the initial target image. The correction strategy may include obtaining the coordinate information of each pixel point of the initial target image and correcting the coordinates. The corrected pixel coordinates constitute the corrected target image. Specifically, the pixel coordinates of the initial target image may be corrected using the following formula (1):

[0095] (1)

[0096] Among them, x corrected ,y corrected They represent the x and y coordinates after correction respectively; x and y represent the coordinates before correction respectively; k1, k2, k3, p1, p2, and r are all distortion parameters. The coordinates can be corrected by adjusting the distortion parameters.

[0097] In an exemplary embodiment, the pixel coordinate information may include coordinates corresponding to a pixel coordinate system in an image, etc. For example, the pixel point at the upper left corner is the point (0,0), and the coordinates of the pixel points are obtained in sequence with one pixel point as a unit.

[0098] In this embodiment, the pixel coordinate information of the initial target image is corrected by using a correction strategy to obtain the target image, which can improve the accuracy of the target image, further improve the accuracy of the positioning point, and improve the accuracy of chip positioning.

[0099] In one embodiment, Figure 8 As shown, the target image includes an image captured by a wide-angle camera; the positioning point includes first coordinate information of the positioning point in the target image; after the initial positioning point is replaced by the replacement positioning point to obtain the target positioning point, the following further includes:

[0100] Step S500, using a preset conversion strategy between the first coordinate information and the second coordinate information, determining second coordinate information corresponding to the first coordinate information; wherein the second coordinate information includes coordinate information under a high-magnification camera corresponding to the first coordinate information under a wide-angle camera.

[0101] In an exemplary embodiment, the conversion strategy may include the relationship between the first coordinate under the wide-angle camera and the second coordinate under the high-power camera. The specific conversion strategy may be converted as follows:

[0102] (2)

[0103] Among them, Plist represents the first coordinate information under the wide-angle camera; Qlist represents the second coordinate information under the high-magnification camera; M represents the conversion matrix between the first coordinate information and the second coordinate information, etc.

[0104] Step S600: positioning the high-power camera according to the second coordinate information, and determining the image of the chip under the high-power camera.

[0105] In an exemplary embodiment, the second coordinate information may include the second coordinate information of the target positioning point in the high-power camera coordinate system, that is, the target positioning point under the high-power camera; through the target positioning point under the high-power camera, the high-power camera is accurately positioned to the chip, and the image of the chip under the high-power camera is determined.

[0106] In this embodiment, by using a preset conversion strategy, the first coordinate information under the wide-angle camera is converted to the second coordinate information under the high-magnification camera, and the image of the chip under the high-magnification camera is determined using the second coordinate information. The high-magnification camera can accurately locate the chip, improving the accuracy of the chip under the high-magnification camera.

[0107] In one embodiment, Fig. 9 As shown, the conversion strategy is obtained in the following manner:

[0108] Step S501, obtaining sample first coordinate information and sample second coordinate information.

[0109] In an exemplary embodiment, the sample first coordinate information and the sample second coordinate information may include taking a picture of the stage before acquiring the target image (i.e., taking a picture of the chip, etc.), taking a picture of the stage using a wide-angle camera and a high-magnification camera respectively, and obtaining the first coordinate of the stage texture downloaded by the wide-angle camera and the second coordinate of the stage texture downloaded by the high-magnification camera; and determining them as the sample first coordinate information and the sample second coordinate information, etc. respectively.

[0110] Step S502: Determine the conversion strategy using the sample first coordinate information and the sample second coordinate information.

[0111] In an exemplary embodiment, the least square method may be used to determine the conversion strategy, etc. Specifically, the conversion strategy may be calculated using the following formula (3):

[0112] ∑ i Qx[i] Qy[i] 1 - M ∙ Px[i] Py[i] 1 2 = min (3)

[0113] Among them, Qx[i] and Qy[i] represent the second coordinate information of the i-th pixel sample, Px[i] and Py[i] represent the first coordinate information of the i-th pixel sample; M represents the conversion strategy; assuming that N pixels , pi is a 2D vector, corresponding to the N axis coordinate points , qi is a 2D vector; in actual use, it can be considered as a perfect fit, that is, min is set to 0; that is, the following formula (4) is obtained, and M, that is, the conversion strategy, is obtained:

[0114] M=(X T X) -1 X T Y (4)

[0115] Where M represents the conversion strategy; X represents the sample first coordinate information matrix; Y represents the sample second coordinate information matrix; Specifically, the reasoning of formula (4) is as follows: X×MY=0; Adding the sample second coordinate on both sides simultaneously obtains X×M=Y; Multiplying the transpose of the sample first coordinate matrix on both sides simultaneously obtains X T ×X×M=X T ×Y; multiply both sides by (X T ×X) -1 We get M = (X T X) -1 X T Y et al.

[0116] In this embodiment, a conversion strategy is obtained through the sample first coordinate information and the sample second coordinate information, which can improve the accuracy of converting the first coordinate information under the wide-angle camera into the second coordinate information under the high-magnification camera, and further improve the precise positioning of the chip by the high-magnification camera.

[0117] In an exemplary embodiment, the method for generating the positioning point can be as follows: Fig.10 The implementation shown specifically includes:

[0118] Step S901, special extraction of the gas path texture image of the backlight area under the wide-angle camera: the visual system of the wide-angle camera and the high-magnification camera can be used to shoot the backlight image of the stage under the wide-angle camera, and the image is opened and closed through the image binarization algorithm to remove the interference points of the dirty stage; the image is expanded by the expansion algorithm to expand and widen the gas path texture area in the image, and the expansion kernel refers to the FOV of the high-magnification camera, and a certain redundancy is set as the position area to avoid the subsequent shooting points; after identifying the backlight area through the image algorithm, the gas path texture area of ​​the backlight area is extracted; the gas path texture pixel area is extracted, etc.

[0119] Step S902, establishing the relationship between the wide-angle camera coordinate system and the high-magnification camera axial coordinate system; specifically, it may include using a preset correction strategy to correct the coordinates of the gas path texture pixel area extracted in step S901; and using the corrected gas path texture coordinates under the wide-angle camera and the gas path texture coordinates under the high-magnification camera to establish the relationship between the wide-angle camera coordinate system and the high-magnification camera axial coordinate system.

[0120] Step S903, chip contour extraction and camera position calculation; specifically, it may include extracting the chip contour under the wide-angle camera image field of view, determining the initial positioning point, and judging the grayscale value of the positioning point. If the grayscale value does not meet the preset threshold, it means that the initial positioning point is interfered by the texture of the carrier, and it is necessary to select a suitable position nearby to avoid the texture. With the initial positioning point as the midpoint, a diffusion search is performed near the positioning point to find a point whose grayscale value meets the preset threshold to replace the initial positioning point, etc.

[0121] Step S904, the axial position of the high-power camera is determined; specifically, it may include obtaining the axial coordinates of the locating point in the high-power camera coordinate system according to the pixel position of the locating point under the wide-angle camera determined above, and using the relationship between the wide-angle camera coordinate system and the high-power camera coordinate system obtained in step S902, and using the high-power camera to accurately locate the chip, etc.

[0122] In actual use, Fig.11 The schematic diagram implementation shown includes:

[0123] Calculate the initial positioning point position of the image under the wide-angle camera;

[0124] Determine whether the pixel value of the initial positioning point meets the preset requirements;

[0125] If it is less than the threshold, search for suitable coordinates based on the current point diffusion; and continue to determine whether the pixel value of the positioning point meets the preset requirements;

[0126] If it is greater than the threshold, the coordinates of the positioning point under the high-magnification camera are calculated, and the high-magnification camera is positioned to the chip.

[0127] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0128] Based on the same inventive concept, the embodiment of the present application also provides a device for generating a positioning point for implementing the method for generating a positioning point involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the method above, so the specific definition in the embodiment of the device for generating one or more positioning points provided below can refer to the definition of the method for generating a positioning point above, and will not be repeated here.

[0129] In one embodiment, Fig.12 As shown, a device 100 for generating a positioning point is provided, comprising: an image acquisition module 101 and a positioning point determination module 102, wherein:

[0130] An image acquisition module, used to acquire a target image; wherein the target image includes an image of the chip and an image of the stage texture;

[0131] A positioning point determination module, used to determine the initial positioning point of the chip in the target image;

[0132] The positioning point determination module is further configured to, when the pixel value of the initial positioning point does not meet the preset threshold, sequentially search with the initial positioning point as the center and the preset distance threshold as the interval to obtain a replacement positioning point whose pixel value corresponding to the initial positioning point meets the preset threshold;

[0133] The positioning point determination module is further used to replace the initial positioning point with the replacement positioning point to obtain a target positioning point; wherein the target positioning point is used to locate the chip.

[0134] In one embodiment, the positioning point determination module includes:

[0135] A positioning point determination submodule, configured to determine the initial positioning point as a target positioning point when a pixel value of the initial positioning point meets a preset threshold;

[0136] The positioning point determination submodule is also used to, when the pixel value of the initial positioning point does not meet the preset threshold, sequentially search with the initial positioning point as the center and the preset distance threshold as the interval to obtain a replacement positioning point whose pixel value corresponding to the initial positioning point meets the preset threshold.

[0137] In one embodiment, the positioning point determination module includes:

[0138] The boundary acquisition submodule is used to obtain the boundary information of the chip in the target image;

[0139] The positioning point determination submodule is used to use a preset distance threshold and the boundary information to sequentially determine the midpoint of the intersection of the vertical line in the preset direction and the chip boundary information to obtain the initial positioning point.

[0140] In one embodiment, the image acquisition module includes:

[0141] An image acquisition submodule, used to acquire an initial target image; wherein the initial target image includes pixel coordinate information corresponding to the initial target image;

[0142] An image correction submodule, used to correct the pixel coordinate information of the initial target image using a preset correction strategy to obtain pixel correction coordinate information;

[0143] The image acquisition submodule is also used to obtain a target image using the pixel correction coordinate information.

[0144] In one embodiment, the device further comprises:

[0145] A coordinate conversion module, used to determine second coordinate information corresponding to the first coordinate information by using a preset conversion strategy between the first coordinate information and the second coordinate information; wherein the second coordinate information includes coordinate information under a high-magnification camera corresponding to the first coordinate information under a wide-angle camera;

[0146] The image acquisition module is further used to position the high-magnification camera according to the second coordinate information, and determine the image of the chip under the high-magnification camera.

[0147] In one embodiment, the coordinate conversion module includes:

[0148] A sample acquisition submodule, used to acquire sample first coordinate information and sample second coordinate information;

[0149] The strategy establishment submodule is used to establish the conversion strategy using the sample first coordinate information and the sample second coordinate information.

[0150] Each module in the above-mentioned positioning point generation device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each of the above modules.

[0151] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Fig.13 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for generating a positioning point is realized. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0152] Those skilled in the art will understand that Fig.13 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0153] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0154] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0155] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0156] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for generating a positioning point, characterized in that: The method comprises: Acquire a target image; wherein the target image includes an image of the chip and an image of the stage texture; the target image is obtained by photographing the chip on the stage and the stage texture of the stage; the target image includes an image captured by a wide-angle camera; Obtain the boundary information of the chip in the target image; Using the preset distance threshold and the boundary information, the midpoints of the intersections of the vertical line in the preset direction and the chip boundary information are sequentially determined to obtain an initial positioning point; When the pixel value of the initial positioning point does not meet the preset threshold, the initial positioning point is taken as the center and the preset distance threshold is used as the interval to sequentially search for a replacement positioning point whose pixel value corresponding to the initial positioning point meets the preset threshold; Using the replacement positioning point, the initial positioning point is replaced to obtain a target positioning point; wherein the target positioning point is used to locate the chip; the target positioning point includes first coordinate information of the target positioning point in the target image; Determine the second coordinate information corresponding to the first coordinate information by using a preset conversion strategy between the first coordinate information and the second coordinate information; wherein the second coordinate information includes coordinate information under a high-power camera corresponding to the first coordinate information under a wide-angle camera; the method for obtaining the conversion strategy includes obtaining sample first coordinate information and sample second coordinate information, and establishing the conversion strategy by using the sample first coordinate information and the sample second coordinate information; The high-power camera is positioned according to the second coordinate information to determine the image of the chip under the high-power camera.

2. The method according to claim 1, characterized in that When the pixel value of the initial positioning point does not meet the preset threshold, searching in sequence with the initial positioning point as the center and the preset distance threshold as the interval to obtain a replacement positioning point whose pixel value corresponding to the initial positioning point meets the preset threshold includes: When the pixel value of the initial positioning point meets the preset threshold, the initial positioning point is determined as the target positioning point; When the pixel value of the initial positioning point does not meet the preset threshold, the initial positioning point is taken as the center and the preset distance threshold is used as the interval to sequentially search for a replacement positioning point whose pixel value corresponding to the initial positioning point meets the preset threshold.

3. The method according to claim 1, characterized in that The acquiring of the target image comprises: Acquire an initial target image; wherein the initial target image includes pixel coordinate information corresponding to the target image; Using a preset correction strategy, the pixel coordinate information of the initial target image is corrected to obtain pixel corrected coordinate information; The pixel coordinate information is used to correct the target image.

4. The method according to claim 1, characterized in that The obtaining of the first coordinate information of the sample and the second coordinate information of the sample includes: The stage is photographed using a wide-angle camera and a high-power camera to obtain sample first coordinate information of the stage texture downloaded by the wide-angle camera and sample second coordinate information of the stage texture downloaded by the high-power camera.

5. A device for generating a positioning point, characterized in that: The device comprises: An image acquisition module, used to acquire a target image; wherein the target image includes an image of the chip and an image of the stage texture; the target image is obtained by photographing the chip on the stage and the stage texture of the stage; the target image includes an image captured by a wide-angle camera; A positioning point determination module is used to obtain the boundary information of the chip in the target image; using a preset distance threshold and the boundary information, the midpoint of the intersection of the vertical line in the preset direction and the chip boundary information is determined in sequence to obtain an initial positioning point; The positioning point determination module is further configured to, when the pixel value of the initial positioning point does not meet the preset threshold, sequentially search with the initial positioning point as the center and the preset distance threshold as the interval to obtain a replacement positioning point whose pixel value corresponding to the initial positioning point meets the preset threshold; The positioning point determination module is further used to replace the initial positioning point with the replacement positioning point to obtain a target positioning point; wherein the target positioning point is used to locate the chip; and the target positioning point includes first coordinate information of the target positioning point in the target image; A coordinate conversion module, used to determine the second coordinate information corresponding to the first coordinate information by using a preset conversion strategy between the first coordinate information and the second coordinate information; wherein the second coordinate information includes the coordinate information under the high-power camera corresponding to the first coordinate information under the wide-angle camera; the acquisition method of the conversion strategy includes acquiring the sample first coordinate information and the sample second coordinate information, and establishing the conversion strategy by using the sample first coordinate information and the sample second coordinate information; The image acquisition module is further used to position the high-magnification camera according to the second coordinate information, and determine the image of the chip under the high-magnification camera.

6. The device according to claim 5, characterized in that The positioning point determination module includes: An image acquisition submodule, used to acquire an initial target image; wherein the initial target image includes pixel coordinate information corresponding to the target image; An image correction submodule, used to correct the pixel coordinate information of the initial target image using a preset correction strategy to obtain pixel correction coordinate information; The image acquisition submodule is also used to obtain a target image using the pixel correction coordinate information.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 4 are implemented.

8. 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 of the method according to any one of claims 1 to 4 are implemented.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images