A positioning method and system for liquid-cooled plate stamping

Abstract

The present invention relates to the technical field of image processing, and specifically relates to a positioning method and system for liquid cooling plate stamping. The method includes: obtaining the response values of each pixel point in the image when the liquid cooling plate raw material is conveyed to the stamping station; clustering all pixel points based on the response values to obtain two clustering clusters, and taking the pixel points in the clustering cluster with the larger average response value as corner points; obtaining the center point of the circumscribed rectangle of the area enclosed by all corner points; when the distance between the center point and the standard center point of the standard image is greater than or equal to a set value, adjusting the position of the liquid cooling plate raw material. That is, the solution of the present invention can accurately position the position of the liquid cooling plate raw material during stamping.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing. More specifically, the present invention relates to a positioning method and system for stamping of liquid cooling plates. Background Art

[0002] As an important part of the power battery cooling system, liquid cooling plates are applied in fields such as automobiles, machinery, and electronics. Liquid cooling plates are obtained by stamping raw materials of liquid cooling plates, and during the stamping process of the raw materials of liquid cooling plates, workpiece positioning technology plays a crucial role.

[0003] Accurate workpiece positioning can ensure the position accuracy and product quality during the stamping process and improve production efficiency. Among them, workpiece positioning technology includes traditional positioning and intelligent positioning technology.

[0004] And the intelligent positioning technology includes the following several types:

[0005] (1) Laser ranging positioning: It realizes positioning by measuring the distance between the workpiece and the sensor. It has the advantages of high-speed measurement, high precision, and non-contact, but it is easily interfered by ambient light.

[0006] (2) Visual positioning: It mainly uses devices such as cameras or laser sensors to take pictures and measure the workpiece, and realizes positioning through image processing and pattern recognition algorithms. Visual positioning has the characteristics of high precision and non-contact, and can adapt to workpieces of various shapes and sizes.

[0007] In the prior art, the Harris corner detection algorithm, the detection method based on the Hessian matrix, or the method based on Susan corner detection is often used to extract corners from the image of the raw material of the liquid cooling plate, and the raw material of the liquid cooling plate is positioned according to the position of the corners.

[0008] In related technologies, for example, the Chinese patent application document with the publication number CN108428250A discloses an X-corner detection method applied to visual positioning and calibration. It samples the image by using an annular square window; and according to the image features of the X-corners, it preliminarily judges whether the sample data contains X-corners, and then excludes the repeatedly judged corners, and finally detects all the X-corners.

[0009] Although the above scheme can detect corners, however, since the raw materials of liquid cooling plates mainly use metal materials such as aluminum and copper, these metals have a high reflectivity, so the raw materials of liquid cooling plates will reflect light, which may cause the image of the production environment to exist on the surface of the raw materials of liquid cooling plates during the positioning process. At this time, corners will also be detected from the image of the production environment on the raw materials of liquid cooling plates, which will lead to false detection during positioning, and thus affect the positioning of the raw materials of liquid cooling plates. Summary of the Invention

[0010] The object of the present invention is to provide a positioning method and system for liquid cooling plate stamping, so as to solve the problem of inaccurate positioning during the stamping process of the raw material of the hydraulic plate in the prior art; for this purpose, the present invention provides solutions in the following two aspects.

[0011] In the first aspect, a positioning method for liquid cooling plate stamping provided by the present invention includes:

[0012] Obtaining the response values of each pixel point in the image when the raw material of the liquid cooling plate is conveyed to the stamping station;

[0013] Clustering all pixel points based on the response values to obtain two clustering clusters, and taking the pixel points in the clustering cluster with the larger mean response value as corner points;

[0014] Obtaining the center point of the circumscribed rectangle of the area surrounded by all corner points; when the distance between the center point and the standard center point of the standard image is greater than or equal to the set value, adjusting the position of the raw material of the liquid cooling plate;

[0015] Wherein, the response value is the product of the correction coefficient and the initial response value; the initial response value is obtained by using the Harris algorithm; the correction coefficient is positively correlated with the edge tendency degree of the corresponding pixel point and negatively correlated with the corresponding protrusion degree; the edge tendency degree is: ; is the standard deviation of the protrusion degree of the pixel points within the neighborhood range of the i-th pixel point, is the mean value of the protrusion degree of all pixel points in the image, , , , are respectively the mean values of the pixel values of all pixel points in the R channel and the mean values of the pixel values in the B channel in the columns where the two pixel points adjacent to the left and right of the i-th pixel point are located, and are respectively the mean values of the pixel values of all pixel points in the V channel in the rows where the two pixel points adjacent to the top and bottom of the i-th pixel point are located, and norm( ) is a normalization function; the protrusion degree characterizes the prominent situation of each pixel point in the HSV color space in the image.

[0016] In the above solution, by obtaining the prominence degree and edge tendency degree of each pixel point in the HSV color space of the image of the liquid cooling plate raw material, the correction coefficient of the pixel point is determined, and the initial response value of each pixel point in the image obtained by using Harris corner detection is corrected. The corner points in the image of the liquid cooling plate raw material are determined through the corrected response value, and the corner points of the actual liquid cooling plate raw material are determined. The center point of the circumscribed rectangle of the area surrounded by all the corner points is obtained, and the position of this center point is compared with the standard center point to position the liquid cooling plate raw material; the solution of the present invention not only weakens the influence of specular reflection on the liquid cooling plate raw material on the positioning of the liquid cooling plate raw material through the determined corrected response value, improves the positioning accuracy, but also has a simple method and is easy to implement.

[0017] Optionally, the prominence degree is the average value of the degrees of the three channels of each pixel point in the HSV color space, and the channel degree is: ; 、 are respectively the pixel value of the i-th pixel point on the l channel, the number of pixel points with the same value as the i-th pixel point, is the maximum value of the pixel points on the l channel, N is the total number of pixel points in the image, max( ) is the maximum value function, and the l channel is any one of the h, s, and v channels.

[0018] By obtaining the prominence degree above, the highlighting situation of each pixel point in the HSV color space can be determined.

[0019] Optionally, the correction coefficient is: , is the edge tendency degree of the i-th pixel point, is the prominence degree of the i-th pixel point.

[0020] The above provides a calculation method for determining the correction coefficient.

[0021] Optionally, the K-means algorithm is used to cluster all pixel points based on the response value.

[0022] Optionally, the process of obtaining the standard center point is as follows:

[0023] Obtain the standard response value of each pixel point in the standard image;

[0024] Cluster all pixel points in the standard image based on the standard response value to obtain two clusters, and use the pixel points in the cluster with the larger average standard response value as the standard corner points;

[0025] Take the center point of the circumscribed rectangle of the area surrounded by the standard corner points as the standard center point.

[0026] The standard center point of the obtained standard image with the correct position can be used as a reference standard for positioning the raw material of the liquid cooling plate.

[0027] Optionally, the distance is the Euclidean distance between the coordinate position of the center point and the coordinate position of the standard center.

[0028] Optionally, it further includes stamping the raw material of the liquid cooling plate when the distance between the center point and the standard center point of the standard image is less than a set value.

[0029] Based on the calculated distance above, it can accurately determine whether the position of the raw material of the liquid cooling plate is appropriate.

[0030] In the second aspect, a positioning system for stamping a liquid cooling plate includes:

[0031] A processor;

[0032] A memory that stores computer instructions for positioning the stamping of the liquid cooling plate. When the computer instructions are run by the processor, the system executes the above-mentioned positioning method for stamping the liquid cooling plate.

[0033] The beneficial effects of the present invention are:

[0034] The solution of the present invention corrects the initial response values of each pixel point in the image obtained by using Harris corner detection through a correction coefficient, which can reduce the influence of other interference regions in the image of the raw material of the liquid cooling plate due to specular reflection of the raw material of the liquid cooling plate on the positioning of the raw material of the liquid cooling plate, improve the positioning accuracy, and the method is simple and easy to implement. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features, and advantages of the exemplary embodiments of the present invention will become readily understood. In the drawings, several embodiments of the present invention are shown in an exemplary rather than restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0036] Figure 1 Schematically shows the flowchart of the steps of a positioning method for stamping a liquid cooling plate in this embodiment;

[0037] Figure 2 Schematically shows the conveying diagram of the raw material of the liquid cooling plate before stamping;

[0038] Figure 3 Schematically shows the structural block diagram of a positioning system for stamping a liquid cooling plate in this embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0039] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts belong to the protection scope of the present invention.

[0040] Specifically, as Figure 1 shown, a positioning method for liquid cooling plate stamping in this embodiment includes the following steps:

[0041] Step S1, obtain an image of the liquid cooling plate raw material when it is conveyed to the stamping station. Specifically, an industrial camera is used, and standard images at the stamping station and images of the liquid cooling plate raw material when it is conveyed to the stamping station are collected through a fixed shooting angle.

[0042] The above standard image is an image with the correct position during stamping.

[0043] Step S2, calculate the response values of each pixel point in the image.

[0044] The process of obtaining the response value in this embodiment is as follows:

[0045] Step S21, use the Harris algorithm to detect the image to obtain the initial response values of each pixel point in the image.

[0046] Among them, the Harris algorithm, that is, Harris corner detection, determines corners by calculating the corner response function values of each pixel point in the image. This algorithm is based on the change of pixel gray values in the image, and determines the corner positions by calculating the gradient and second-order matrix of pixel gray values. Its specific implementation steps include: (1) convert the image to a grayscale image, (2) calculate the gradient in the image, (3) calculate the second-order matrix, (4) calculate the response function values of each pixel point, and (5) screen out corners according to the threshold.

[0047] In this embodiment, the Harris corner detection is used to calculate the response function values of each pixel point in the image, and the response function values are used as the initial response values. Since the Harris corner detection is a prior art, it will not be elaborated here too much.

[0048] Step S22, calculate the correction coefficient of each pixel point, and use the correction coefficient to correct the initial response value to obtain the response value.

[0049] It should be noted that since the surface of the liquid cooling plate raw material is smooth, there may be light reflection, causing the image of the production environment to appear on the surface of the liquid cooling plate. Some of the pixel points in the reflected image of the production environment may have a relatively high response function value, resulting in the detection of corner points corresponding to the image of the production environment in the image of the liquid cooling plate raw material. These corner points are not the real corner points in the image, so they will interfere with the stamping positioning of the liquid cooling plate raw material. Therefore, in order to further reduce the influence of pixel points in the specular reflection image area, it is also necessary to correct the initial response value using a correction coefficient to obtain the response value.

[0050] Among them, the process of obtaining the correction coefficient is as follows:

[0051] First, calculate the prominence of each pixel point.

[0052] In this embodiment, considering that the pixel values of most pixel points in the image of the liquid cooling plate raw material are generated by the natural color of the liquid cooling plate raw material, and a small part is the color of other objects generated by specular reflection, and its brightness is relatively high. Therefore, the present invention calculates the prominence of each pixel point according to the pixel values of the pixel points in the HSV color space of the image of the liquid cooling plate raw material.

[0053] Specifically, after converting the image of the liquid cooling plate raw material from the RGB color space to the HSV color space, calculate the prominence of each pixel point through the pixel values of the pixel points in the HSV color space.

[0054] Among them, the prominence of each pixel point is the average value of the degrees of the three channels of the corresponding pixel point in the HSV color space. The specific calculation method is as follows:

[0055] ; where is the prominence of the i-th pixel point, is the channel degree of the i-th pixel point on the l channel, ; L is the set of the h, s, and v channels, , are respectively the pixel value of the i-th pixel point on the l channel, the number of pixel points with the same value as the i-th pixel point, is the maximum value of the pixel points on the l channel, N is the total number of pixel points in the image, max( ) is the maximum value function, and the l channel is any one of the h, s, and v channels.

[0056] Among them, the pixel value of each pixel point on the l channel can be hue, saturation, or brightness, and this pixel value has corresponding values based on different channels.

[0057] Exemplarily, the channel degrees of each pixel point on the h, s, and v channels respectively , , is:

[0058] ;

[0059] ;

[0060] ;

[0061] wherein, 、 and are the hue, saturation and brightness of the i-th pixel point respectively, 、 and are the maximum hue, maximum saturation and maximum brightness appearing in the image respectively, is the number of pixel points having the same hue as the i-th pixel point, is the number of pixel points having the same saturation as the i-th pixel point, is the number of pixel points having the same brightness as the i-th pixel point, N is the number of pixel points in the image, and max( ) is the maximum value function.

[0062] wherein, taking the h channel as an example, reflects the proportion of the pixel value of the i-th pixel point on the h channel, the smaller it is, the fewer the number of pixel points having the same hue as the i-th pixel point, the more prominent the pixel point in the image of the liquid cooling plate raw material, and the greater the prominence degree of the pixel point; the larger the value, the more the number of pixel points having the same hue as the pixel point, the less prominent the pixel point in the image of the liquid cooling plate raw material, and the smaller the prominence degree of the pixel point. reflects the extreme degree of the i-th pixel point in terms of hue. The larger this value, the closer the i-th pixel point is to the maximum hue or minimum hue in the image, the more significant the i-th pixel point, and the greater the prominence degree of the pixel point; the smaller this value, the greater the gap between the i-th pixel point and the maximum hue or minimum hue in the image, the less significant the pixel point, and the smaller the prominence degree of the pixel point.

[0063] Since the calculation methods of the channel degrees of the above three channels are similar, therefore, the analysis of the s channel and v channel will not be elaborated.

[0064] Since the HSV color space can well separate color information and brightness information, therefore, by obtaining the prominence degree of each pixel point, the significant situation of each pixel point is characterized.

[0065] Secondly, calculate the edge tendency degree of each pixel point.

[0066] Since the specular reflection images on the raw material of the liquid cooling plate will interfere with the generation of subsequent corner points, thereby affecting the positioning of the raw material of the liquid cooling plate. Also, because the specular reflection images on the raw material of the liquid cooling plate may also appear at the outer contour edge of the raw material of the liquid cooling plate, this phenomenon exacerbates the generation of specular reflection images on the raw material of the liquid cooling plate for the corner points on the contour of the raw material of the liquid cooling plate, thereby affecting the positioning of the raw material of the liquid cooling plate.

[0067] Therefore, the present invention calculates the edge tendency degree of pixel points according to the prominence degree of pixel points in the image of the raw material of the liquid cooling plate and the pixel value distribution of the image of the raw material of the liquid cooling plate.

[0068] Specifically, the calculation method of the edge tendency degree is as follows:

[0069] ; where is the edge tendency degree of the i-th pixel point, is the standard deviation of the prominence degree of pixel points within the neighborhood range of the i-th pixel point, is the mean value of the prominence degree of all pixel points in the image, and are respectively the average values of the R-channel pixel values of all pixel points in the columns where the two pixel points adjacent to the left and right of the i-th pixel point are located, and are respectively the average values of the B-channel pixel values of all pixel points in the columns where the pixel points adjacent to the left and right of the i-th pixel point are located, and are respectively the average values of the V-channel pixel values of all pixel points in the rows where the two pixel points adjacent to the top and bottom of the i-th pixel point are located, and norm( ) is a linear normalization function.

[0070] The above linear normalization function can adopt the maximum-minimum normalization method or the Z-score normalization.

[0071] Represents the local difference in the prominence of the i-th pixel. When the i-th pixel is at the outer contour edge of the image of the liquid cooling plate raw material, some of the pixels in the neighborhood of the i-th pixel belong to the liquid cooling plate raw material and some belong to the image background. At this time, the prominences of the pixels in the neighborhood range of this pixel vary greatly, so the standard deviation of the prominences of the pixels in the neighborhood range of the i-th pixel is large; when the i-th pixel is inside the image of the liquid cooling plate raw material, most of the pixels in the neighborhood of the i-th pixel belong to the liquid cooling plate raw material, so the standard deviation of the prominences of the pixels in the neighborhood range of the i-th pixel is small. Therefore, the smaller this value is, the more likely the i-th pixel is to be inside the image of the liquid cooling plate raw material, and the smaller the edge tendency degree of the i-th pixel; the larger this value is, the more likely the i-th pixel is to be on the outer contour edge of the image of the liquid cooling plate raw material, and the larger the edge tendency degree of the i-th pixel.

[0072] Reflects the difference in pixel values of the pixels in the column where the two pixels adjacent to the i-th pixel on the left and right are located in the R channel. Since the color of the conveyor roller (usually green) of the liquid cooling plate raw material is significantly different from that of the liquid cooling plate raw material (with metallic luster), that is, the pixel values of the two colors in the R channel and B channel have a large difference. Therefore The larger it is, the more likely the i-th pixel is to be at the edges on the left and right sides of the liquid cooling plate raw material, and the larger the edge tendency degree of the i-th pixel; The smaller it is, the lower the possibility that the i-th pixel is at the edges on the left and right sides of the liquid cooling plate raw material, and the smaller the edge tendency degree of the i-th pixel. Similarly, it will not be elaborated here.

[0073] Reflects the difference in pixel values of the pixels in the row where the two pixels adjacent to the i-th pixel above and below are located in the V channel. Since the surface of the liquid cooling plate raw material has metallic luster, while the conveyor roller and other background areas in the image do not have metallic luster, there is a certain difference in the pixel values of the pixels corresponding to the liquid cooling plate raw material in the image and the pixels in other parts of the image in the V channel. Therefore The larger it is, the more likely the i-th pixel is to be at the edges on the upper and lower sides of the liquid cooling plate raw material, and the larger the edge tendency degree of the i-th pixel; The smaller it is, the less likely the i-th pixel is to be at the edges on the upper and lower sides of the liquid cooling plate raw material, and the smaller the edge tendency degree of the i-th pixel.

[0074] The reason for the above to comprehensively reflect the edge tendency degree of the pixel by combining the color characteristics and brightness characteristics of the pixel is that the transportation of the liquid cooling plate raw material before stamping is achieved through the conveyor roller (see Figure 2, where the dashed long strip represents the conveying roller and the solid rectangle represents the raw material of the liquid cooling plate). The conveying roller has relatively distinct color features, such as green or red, etc. Therefore, the color of the conveying roller of the raw material of the liquid cooling plate (usually green) is significantly different from that of the raw material of the liquid cooling plate (with metallic luster).

[0075] Then, according to the prominence degree and edge tendency degree of each pixel point, a correction coefficient is obtained.

[0076] Specifically, the correction coefficient is positively correlated with the edge tendency degree of the corresponding pixel point and negatively correlated with the corresponding prominence degree.

[0077] In one embodiment, the correction coefficient is: , is the edge tendency degree of the i-th pixel point, is the prominence degree of the i-th pixel point.

[0078] Among them, The smaller is, the less likely the i-th pixel point is on the outer contour edge of the raw material of the liquid cooling plate. Then, the corrected response value of the i-th pixel point should be made smaller, making the i-th pixel point less likely to be recognized as a corner point. At this time, the correction intensity for the initial response value should be increased, that is, the correction coefficient needs to become smaller; on the contrary,

[0079] The larger is, the more likely the i-th pixel point is on the outer contour edge of the raw material of the liquid cooling plate. Then, there is no need to overly correct the initial response value, and the corrected response value of the pixel points on the outer contour of the raw material of the liquid cooling plate is maintained at the original level, that is, the correction coefficient should be close to 1 at this time.

[0079] To further reduce the initial response value of the pixel points in the specular reflection image area, through the prominence degree of the pixel points, is further corrected, that is, The larger is, the more likely the i-th pixel point is in the specular reflection image area on the raw material of the liquid cooling plate. Then, the greater the correction degree of is, further reducing the initial response value of the pixel points in the specular reflection image area on the image of the raw material of the liquid cooling plate; The smaller is, the lower the possibility that the i-th pixel point is in the specular reflection image area on the raw material of the liquid cooling plate. At this time, there is no need to further correct to maintain a relatively high response value for the pixel points at the outer contour of the image of the raw material of the liquid cooling plate, so that they can be recognized as corner points and the subsequent positioning of the raw material of the liquid cooling plate can be realized.

[0080] In this embodiment, the calculation method of the response value is as follows:

[0081] ;

[0082] Among them, is the response value of the i-th pixel point, is the initial response value of the i-th pixel point, is the correction coefficient of the i-th pixel point.

[0083] The obtained response value can exclude some pixel points with relatively high initial response values in the specular reflection image area on the raw material of the liquid cooling plate, avoiding being misidentified as the outer contour corner points of the raw material of the liquid cooling plate, and improving the positioning accuracy of the raw material of the liquid cooling plate.

[0084] Step S3: Cluster all pixel points based on the response value to obtain two clusters, and use the pixel points in the cluster with the larger mean response value as corner points.

[0085] In this embodiment, after obtaining the response values of each pixel point, all response values are clustered by the K-means clustering algorithm to obtain two clusters, and the pixel points in the cluster with the larger mean response value are used as corner points.

[0086] Step S4: Obtain the center point of the circumscribed rectangle of the area surrounded by all corner points; when the distance between the center point and the standard center point of the standard image is greater than or equal to the set value, adjust the position of the raw material of the liquid cooling plate.

[0087] In this embodiment, the center point of the circumscribed rectangle of the area surrounded by all obtained corner points is the intersection of the two diagonals of the circumscribed rectangle.

[0088] The above standard center point is obtained by obtaining the standard response values of each pixel point in the standard image; and clustering all pixel points in the standard image based on the standard response values to obtain two clusters, using the pixel points in the cluster with the larger mean standard response value as standard corner points; and using the center point of the circumscribed rectangle of the area surrounded by all standard corner points as the standard center point.

[0089] The obtaining process of the above standard center point is the same as the obtaining process of the center point, except for the selected image. Therefore, it will not be specifically described here.

[0090] In this embodiment, the Euclidean distance between the calculated coordinate position of the center point and the coordinate position of the standard center point is compared with the set value to determine whether the position of the raw material of the liquid cooling plate is accurate.

[0091] Specifically, if the Euclidean distance is less than the set value, the current position of the raw material of the liquid cooling plate is accurate, and the raw material of the liquid cooling plate is transported to the stamping position by a vacuum chuck for stamping; if the Euclidean distance is greater than or equal to the set value, the position of the raw material of the liquid cooling plate is inaccurate, and the position of the raw material of the liquid cooling plate needs to be adjusted.

[0092] The set value is 5. Of course, it can also be set according to the actual situation.

[0093] In the solution of the present invention, first, according to the pixel values of the pixel points in the liquid cooling plate raw material image in the HSV color space, the prominence degree of each pixel point is calculated, so that the highlighted area generated by specular reflection can be distinguished, thereby reducing its interference with subsequent edge detection and positioning. Then, based on the prominence degree of the pixel points on the liquid cooling plate raw material image and the pixel value distribution of the liquid cooling plate raw material image, the edge tendency degree of the pixel points is calculated, making full use of the differences between the liquid cooling plate raw material, the conveying roller, and the image background in the image in different color spaces, further enhancing the recognition ability of the actual edges in the liquid cooling plate raw material, reducing background interference, and improving the accurate positioning of the liquid cooling plate raw material. Finally, the initial response value is corrected according to the edge tendency degree of each pixel point, and the stamping positioning of the liquid cooling plate raw material is performed through the corrected response value, so that the stamping positioning of the liquid cooling plate raw material can adapt to complex scenarios such as specular reflection and light changes on the surface of the liquid cooling plate raw material, improving the stability and reliability of the positioning.

[0094] The present invention also provides a positioning system for liquid cooling plate stamping. As Figure 3 shown, the system includes a processor and a memory. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, a positioning method for liquid cooling plate stamping according to the above of the present invention is implemented.

[0095] The system also includes other components well-known to those skilled in the art such as a communication bus and a communication interface. Their settings and functions are known in the art, so they will not be described in detail here.

[0096] In the present invention, the aforementioned memory may be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory (RRAM), a dynamic random access memory (DRAM), a static random access memory (SRAM), an enhanced dynamic random access memory (EDRAM), a high-bandwidth memory (HBM), a hybrid memory cube (HMC), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of the device or accessible or connectable to the device. Any application or module described in the present invention may be implemented by computer-readable / executable instructions stored or otherwise maintained by such a computer-readable medium.

[0097] In the description of this specification, "a plurality of" means at least two, for example, two, three, or more, etc., unless otherwise specifically defined.

[0098] Although this specification has shown and described multiple embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will think of many changes, alterations, and alternative ways without departing from the spirit and scope of the present invention. It should be understood that various alternatives to the embodiments of the present invention described herein may be employed in the practice of the present invention.

Claims

1. A positioning method for liquid cooling plate stamping, characterized in that: include: Obtaining the response value of each pixel in the image when the liquid cooling plate raw material is conveyed to the stamping station; All pixels are clustered based on the response value to obtain two clusters, and each pixel in the cluster with the larger mean response value is taken as a corner point; Obtain the center point of the circumscribed rectangle of the area enclosed by all corner points; when the distance between the center point and the standard center point of the standard image is greater than or equal to a set value, adjust the position of the liquid cooling plate raw material; Among them, the response value is the product of the correction coefficient and the initial response value; the initial response value is obtained by using the Harris algorithm; the correction coefficient is positively correlated with the edge tendency of the corresponding pixel point and negatively correlated with the corresponding protrusion degree; Edge tendency for: ; is the standard deviation of the pixel prominence within the neighborhood of the i-th pixel, is the mean value of the prominence of all pixels in the image, , , , are the mean pixel values ​​of all pixels in the column of the two pixels adjacent to the i-th pixel on the left and right sides in the R channel and the mean pixel values ​​of all pixels in the B channel, respectively. and are the mean values ​​of the pixel values ​​of all pixels in the row of the two pixels above and below the i-th pixel in the V channel, norm() is the normalization function; the prominence degree represents the prominence of each pixel in the image in the HSV color space; The prominence degree is the average of the three channel degrees of each pixel in the HSV color space; Channel degree for: ; , are the pixel value of the i-th pixel on channel l and the number of pixels with the same value as the i-th pixel, is the maximum value of pixels on the l channel, N is the total number of pixels in the image, max() is the maximum value function, and the l channel is any one of the h, s and v channels.

2. A positioning method for liquid cooling plate stamping according to claim 1, characterized in that: The correction factor for: , is the edge tendency of the i-th pixel, is the prominence of the i-th pixel.

3. A positioning method for liquid cooling plate stamping according to claim 1, characterized in that: The clustering of all pixels based on the response values ​​adopts the K-means algorithm.

4. A positioning method for liquid cooling plate stamping according to claim 1, characterized in that: The process of obtaining the standard center point is as follows: Obtain the standard response value of each pixel in the standard image; Clustering all pixel points in the standard image based on the standard response value to obtain two clusters, and taking each pixel point in the cluster with a larger standard response value mean as a standard corner point; The center point of the circumscribed rectangle of the area enclosed by all standard corner points is taken as the standard center point.

5. A positioning method for liquid cooling plate stamping according to claim 1, characterized in that: The distance is the Euclidean distance between the coordinate position of the center point and the coordinate position of the standard center.

6. A positioning method for liquid cooling plate stamping according to claim 5, characterized in that: The method also includes punching the liquid cooling plate raw material when the distance between the center point and the standard center point of the standard image is smaller than a set value.

7. A positioning system for liquid cooling plate stamping, characterized in that: include: processor; A memory storing computer instructions for positioning of liquid cooling plate stamping, wherein when the computer instructions are executed by the processor, the system executes a positioning method for liquid cooling plate stamping according to any one of claims 1-6.

Images