Method and device for detecting corner point of tab, and storage medium

Abstract

This application discloses a method, apparatus, and storage medium for detecting corner points of electrode tabs, which can improve corner point detection efficiency. The method for detecting corner points of electrode tabs includes: determining the outline of an electrode assembly in an image to be detected; the electrode assembly includes a single battery cell, a tab connected to the single battery cell, and an adapter piece welded to the tab; based on the outline of the electrode assembly, determining multiple corner points on a target outline, where the target outline is the outline of the electrode assembly that includes a portion of the tab's outline; determining the region proportion corresponding to each of the multiple corner points, where the region proportion is the proportion of the electrode assembly's region within a predetermined area centered on the corner point; and determining a target corner point of the tab among the multiple corner points based on the region proportions corresponding to each corner point; the target corner point is a corner point of the tab adjacent to the background of the image to be detected, where the background refers to the area in the image to be detected excluding the electrode assembly.

Description

[0001] This application is a divisional application of Chinese Patent Application No. 202210841619.X, filed on July 18, 2022, entitled "Method and Apparatus for Corner Detection". Technical Field

[0002] This application relates to the field of image processing technology, and more specifically, to a method, apparatus, and storage medium for detecting the corner points of a tab. Background Technology

[0003] Corner points in an image typically refer to points where brightness changes drastically or points where the curvature of the image's edge contour curve reaches its maximum value. They are an important feature characterizing an image. Corner point detection is a crucial part of the automatic inspection of workpieces in industrial settings, and its ability and speed in extracting corner points directly affect the accuracy and efficiency of industrial automation inspection.

[0004] Current corner detection algorithms mainly fall into three categories: those based on grayscale images, those based on binary images, and those based on contour curves. Among these, contour-based corner detection methods are more widely used due to their lower error rate. However, existing contour-based corner detection methods have high computational complexity and are not suitable for detection scenarios requiring high efficiency. Therefore, there is an urgent need for an efficient corner detection method. Summary of the Invention

[0005] This application provides a method, apparatus, and storage medium for detecting corner points of tabs, which can reduce algorithm complexity and thus improve corner point detection efficiency.

[0006] In a first aspect, a method for detecting corner points of an electrode tab is provided, comprising: determining the contour of an electrode assembly in an image to be detected; the electrode assembly includes a single cell, a tab connected to the single cell, and an adapter piece welded to the tab; determining multiple corner points on a target contour based on the contour of the electrode assembly; the target contour being a contour of the electrode assembly that includes a portion of the tab's contour; determining the area proportions corresponding to the multiple corner points, the area proportions being the proportions of the area of ​​the electrode assembly within a predetermined area centered on the corner point; determining a target corner point of the tab among the multiple corner points according to the area proportions corresponding to the multiple corner points; the target corner point being a corner point of the tab adjacent to the background of the image to be detected, the background referring to the area in the image to be detected excluding the electrode assembly.

[0007] In the technical solution of this application, it is only necessary to determine whether a corner is a target corner by the area proportion, without the need for auxiliary confirmation from other corners. Compared with the existing methods, this reduces the number of traversals, reduces the complexity of the algorithm, and improves the efficiency of corner detection.

[0008] In some possible implementations, determining the target corner point of the electrode among the plurality of corner points based on the area proportions corresponding to the plurality of corner points includes: determining at least one candidate corner point among the plurality of corner points whose area proportion is greater than a predetermined value; and determining the target corner point among the at least one candidate corner point.

[0009] By comparing the area proportion with the predetermined value, interference points are filtered out by numerical comparison, leaving candidate corner points that meet the conditions. This helps to quickly determine the target corner point, thereby improving the detection efficiency of corner points.

[0010] In some possible implementations, determining the target corner point from the at least one candidate corner point includes: when there are multiple candidate corner points, determining the target corner point based on the positional relationship between the multiple candidate corner points and the center point of the electrode.

[0011] Since the positional relationship between the candidate corner points and the center point of the electrode is different, the target corner point can be determined at once from multiple candidate corner points by using this positional relationship, thereby improving the efficiency of corner point detection.

[0012] In some possible implementations, the positional relationship includes the distance between the candidate corner point and the center point of the electrode; determining the target corner point based on the positional relationship between the plurality of candidate corner points and the center point of the electrode includes: determining the candidate corner point corresponding to the largest distance among the plurality of distances as the target corner point.

[0013] In some possible implementations, determining multiple corner points on a target contour based on the contour of the electrode assembly includes: determining the target contour based on the contour of the electrode assembly; and using each vertex of the polygon corresponding to the target contour as the multiple corner points.

[0014] The target contour is extracted from the contour of the electrode assembly to obtain the contour including the tabs. Then, corner points are obtained from the contour including the tabs. Compared with obtaining all corner points of the contour of the electrode assembly first and then obtaining corner points on the contour including the tabs, the number of corner points obtained is reduced, which helps to improve the efficiency of corner point detection.

[0015] In some possible implementations, determining the target contour based on the contour of the electrode assembly includes: determining at least one region of interest in the image to be detected; and determining the target contour in the at least one region of interest.

[0016] By setting a region of interest in the image to be detected, the scope of the image that needs to be analyzed and processed can be narrowed down, thus improving the efficiency of corner detection.

[0017] In some possible implementations, the step of using each vertex of the polygon corresponding to the target contour as the plurality of corner points includes: processing the target contours corresponding to the at least one region of interest respectively through a polygon approximation algorithm to obtain at least one polygon corresponding to each of the target contours; and using each vertex of the polygon corresponding to each target contour as the plurality of corner points.

[0018] In the area to be detected, multiple regions of interest (ROIs) can be set to acquire corner points. When there are many corner points on the contour of the electrode assembly, setting multiple ROIs can further reduce the number of corner points acquired, thereby reducing the number of traversals and computational load, and improving the efficiency of corner point detection. Furthermore, obtaining the polygon corresponding to the target contour through a polygon approximation method can reduce the number of corner points that need to be processed subsequently, further improving the efficiency of corner point detection.

[0019] In some possible implementations, determining the contour of the electrode assembly in the image to be detected includes: binarizing the image to be detected to obtain a binarized image of the image to be detected; and determining the contour of the electrode assembly based on the edge curves of the electrode assembly in the binarized image.

[0020] After binarizing the image to be detected, the entire image can present a clear black and white effect to highlight the outline of the electrode assembly, so that the outline of the electrode assembly can be quickly extracted through the edge curve of the binarized image.

[0021] In some possible implementations, the predetermined area is circular.

[0022] Setting the predetermined area as a circle facilitates the rapid determination of the proportion of the electrode component's area within the predetermined area. It also avoids the need to consider the impact of angle on the area proportion, as is required for other angled images, thereby improving the accuracy of corner detection.

[0023] In some possible implementations, the radius of the circle is 10 pixels.

[0024] Setting the radius of the circular predefined area to 10 pixels can prevent other corner points from being included in the predefined area due to an excessively large radius value, which would affect the calculation of the area ratio of the current corner point. Conversely, setting the radius too small can cause low accuracy. This value can more reasonably and effectively calculate the area ratio, thereby improving the accuracy of corner point detection.

[0025] In some possible implementations, the predetermined value is 0.6.

[0026] Setting the preset value to 0.6 can exclude corner points on approximately straight lines, which is beneficial for quickly obtaining target corner points and improving the efficiency of corner point detection.

[0027] In a second aspect, a device for detecting the corner points of a tab is provided, comprising a processor and a memory, wherein the memory is used to store a program, and the processor is used to call and run the program from the memory to perform the method for detecting the corner points of a tab in the first aspect or any possible implementation thereof.

[0028] Thirdly, a computer-readable storage medium is provided, including a computer program that, when run on a computer, causes the computer to perform the method for detecting the corner points of the tabs in the first aspect or any possible implementation thereof.

[0029] Fourthly, a computer program product containing instructions is provided, which, when executed by a computer, cause the computer to perform the method for detecting the corner points of the tabs in the first aspect or any possible implementation thereof. Attached Figure Description

[0030] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the embodiments of this application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on the drawings without creative effort.

[0031] Figure 1 This is a schematic flowchart of a method for detecting the corner points of a tab provided in an embodiment of this application;

[0032] Figure 2 This is a schematic diagram of an image to be detected provided in an embodiment of this application;

[0033] Figure 3 This is a schematic flowchart of another method for detecting the corner points of a tab provided in an embodiment of this application;

[0034] Figure 4 This is a schematic process diagram of another method for detecting the corner points of a tab provided in an embodiment of this application;

[0035] Figure 5 This is a schematic diagram of the structure of a corner detection device for a tab provided in an embodiment of this application. Detailed Implementation

[0036] The embodiments of the technical solution of this application will now be described in detail with reference to the accompanying drawings. These embodiments are only used to more clearly illustrate the technical solution of this application and are therefore merely examples, and should not be used to limit the scope of protection of this application.

[0037] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0038] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0039] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0040] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0041] In the description of the embodiments of this application, the technical terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," and "circumferential" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing the embodiments of this application and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the embodiments of this application.

[0042] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0043] Corner points are an important feature representing an image. Corner point detection is a crucial step in automated workpiece inspection in industrial settings, and its ability and speed in extracting corner points directly impact the accuracy and efficiency of industrial automation inspection. Existing corner point detection algorithms can be broadly categorized into three types: model-based methods, grayscale-based methods, and contour-based methods. Among these, corner point extraction based on contour curves is widely used in industrial inspection due to its lower computational cost and higher accuracy. Existing methods initially extract candidate corner points on the contour and then determine whether the middle corner point is a true corner point by the angle of the line connecting three corner points. This method involves a large number of iterations, leading to high algorithm complexity and affecting corner point detection efficiency. Furthermore, when detecting corner points on tabs, the workpiece in the image may include multiple objects, some of which may overlap, making the detection or localization of tab corner points even more difficult.

[0044] In view of this, embodiments of this application provide a method for detecting corner points of an electrode assembly. First, the outline of the electrode assembly in the image to be detected is determined. Then, based on the outline of the electrode assembly, multiple corner points on the target outline are determined. Next, the region proportion corresponding to each corner point is calculated. This region proportion refers to the proportion of the area excluding the background within a predetermined region centered on the current corner point. Whether the corner point is a target corner point is determined by the relationship between the region proportion and a predetermined value. The corner point detection method of this application only needs to compare the region proportion of the current corner point with a predetermined value to confirm whether it is a target corner point, without requiring auxiliary confirmation from other corner points. Compared with existing methods, this reduces the number of traversals, reduces algorithm complexity, and improves the efficiency of corner point detection.

[0045] Figure 1 This is a method 100 for detecting the corner points of the tab in an embodiment of this application. The method 100 specifically includes the following steps 110 to 140.

[0046] 110. Determine the outline of the electrode assembly in the image to be detected.

[0047] Here, the electrode assembly includes a single battery cell, a tab connected to the single battery cell, and an adapter piece welded to the tab.

[0048] like Figure 2 As shown, the image to be tested is an image of the electrode assembly captured by a camera. The image includes a background 10, a battery cell body 11, a tab 12, and an adapter plate 13. The electrode assembly includes three objects: the battery cell body 11, the tab 12, and the adapter plate 13. The tab 12 is welded to the other object, namely the adapter plate 13, and the two partially overlap.

[0049] In this embodiment of the application, the outline of the electrode assembly can be extracted by the edge curve of the binarized image of the image to be detected, that is, the intersection of black and white.

[0050] 120. Based on the contour of the electrode assembly, determine multiple corner points on the target contour.

[0051] Among them, multiple corner points are the corner points of the outline of the electrode assembly in the image to be detected, and the outline of the electrode assembly includes the outline of the tab.

[0052] The image to be inspected can be, for example, an image obtained by capturing the tab with a camera, to detect the corner points of the tab. In the scenario of workpiece inspection, the tab can be the entire workpiece or a specific component of the workpiece.

[0053] It should be noted that when the electrode tab is a component on a workpiece, the image of the workpiece captured by the camera may include not only the electrode tab but also other objects. The electrode tab and other objects may be separate from each other or may overlap. This overlap can be complete or partial. For example... Figure 2 The image to be tested shown is an electrode assembly captured by a camera. The image includes a background 10, a battery cell body 11, a tab 12, and an adapter plate 13. The electrode assembly includes three objects: the battery cell body 11, the tab 12, and the adapter plate 13. The tab 12 is welded to the other object, namely the adapter plate 13, and the two partially overlap.

[0054] When the tab is a component on a workpiece, there can be one or more tabs in the image to be inspected, for example... Figure 2 It has four tabs, but this application does not limit this.

[0055] The image to be detected includes an electrode assembly and an environmental background. The electrode assembly includes a tab. By determining the position of the corner point on the contour curve of the tab, the tab can be quickly located, thereby quickly completing the subsequent analysis of the tab.

[0056] The outline of an electrode assembly refers to the lines that form the outer edge of the electrode assembly when it is separated from the background. The outline of a tab refers to the lines that form the outer edge of the tab when it is separated from the background. When a tab overlaps with parts of other objects, the outline of the electrode assembly includes the outline of the tab, and the corner points on the outline of the tab are on the outline of the electrode assembly.

[0057] In this embodiment, a target contour including the tab can be extracted from the outline of the electrode assembly using a rectangular frame of the region of interest, and then multiple corner points can be determined on the target contour.

[0058] 130. Determine the area proportion corresponding to each of the multiple corner points. The area proportion is the percentage of the electrode assembly area within a predetermined region centered on the corner point.

[0059] After obtaining multiple corner points, each corner point is traversed, and the area proportion corresponding to each corner point is calculated. The area proportion refers to the proportion of the electrode component's area within a predetermined area centered on the currently traversed corner point.

[0060] 140. Based on the area proportions corresponding to multiple corner points, determine the target corner point of the electrode among multiple corner points.

[0061] When the electrode overlaps with portions of other objects, the target corner point refers to the corner point in the image to be detected where the electrode is adjacent to the background of the image to be detected. The background refers to the area in the image to be detected excluding the electrode assembly. For example... Figure 2 As shown, corner points 1 to 8 are target corner points adjacent to the electrode 12 and the background 10. After obtaining multiple corner points, interference points among the multiple corner points can be eliminated according to the area proportion to determine the target corner point of the electrode.

[0062] The corner detection method for tabs provided in this application embodiment only needs to determine whether the corner is the target corner by the region proportion, without the need for auxiliary confirmation from other corners. Compared with the existing methods, it reduces the number of traversals, reduces the complexity of the algorithm, and improves the efficiency of corner detection.

[0063] Optionally, in some embodiments, step 140 may involve obtaining at least one candidate corner point among multiple corner points whose area proportion is greater than a predetermined value, and then obtaining the target corner point from at least one candidate corner point.

[0064] It should be understood that the above embodiments first compare the proportion of each of the multiple regions with a predetermined value. When the proportion of a region is greater than the predetermined value, the corner point corresponding to that proportion is listed as a candidate corner point. After traversing all corner points, there may be one or more candidate corner points. When there is only one candidate corner point, that candidate corner point is the target corner point. When there are multiple candidate corner points, a target corner point needs to be determined from the multiple candidate corner points.

[0065] It should be noted that a predetermined range can also be compared with the regional proportion. When the regional proportion is within the predetermined range, the corner point corresponding to that regional proportion can be listed as a candidate corner point.

[0066] By comparing the area proportion with the predetermined value, interference points are filtered out by numerical comparison, leaving candidate corner points that meet the conditions. This helps to quickly determine the target corner point, thereby improving the detection efficiency of corner points.

[0067] Optionally, in some embodiments, obtaining the target corner point from at least one candidate corner point may include: when there are multiple candidate corner points, determining the target corner point based on the positional relationship between the multiple candidate corner points and the center point of the electrode.

[0068] Positional relationships can include distance or orientation between candidate corner points and the center point of the pole piece, or both. Each candidate corner point has a different positional relationship with the center point of the pole piece, and the target corner point can be determined from among the multiple candidate corner points by setting the positional relationship. For example, the candidate corner point furthest from the center point of the pole piece can be selected as the target corner point, or a candidate corner point located in a certain orientation from the center point of the pole piece can be selected as the target corner point.

[0069] In the above embodiments, since the positional relationship between the candidate corner points and the center point of the electrode is different, the target corner point can be determined at once from multiple candidate corner points through this positional relationship, thereby improving the efficiency of corner point detection.

[0070] Optionally, in some embodiments, determining the target corner point based on the positional relationship between multiple candidate corner points and the center point of the electrode can be done by determining the candidate corner point corresponding to the largest vertical distance among the vertical distances between the multiple candidate corner points and the center point of the electrode as the target corner point.

[0071] Optionally, in some embodiments, determining multiple corner points on the target contour may include: acquiring multiple corner points in a region of interest in the image to be detected.

[0072] A region of interest (ROI) can be a manually defined area, whose size and location can be predetermined. For example, it can be delineated using rectangles, circles, ellipses, irregular polygons, etc., to define the area to be processed. In a visual inspection station, the position of the tabs in each captured image is relatively fixed. Therefore, setting an ROI within the image narrows down the area that needs analysis and processing. For instance, it reduces the number of corner points acquired, allowing for more efficient processing and fewer iterations, thus improving corner detection efficiency.

[0073] Optionally, in some embodiments, step 120 may include: determining the target contour based on the contour of the electrode assembly; and using each vertex of the polygon corresponding to the target contour as the plurality of corner points.

[0074] In this embodiment, a target contour including the tab can be extracted from the outline of the electrode assembly using a rectangular bounding box of the region of interest. Then, a polygon approximation method is used to obtain the polygon corresponding to the target contour, and the vertices of the polygon are obtained to obtain multiple corner points.

[0075] Optionally, in some embodiments, at least one region of interest (ROI) may be determined in the image to be detected. Correspondingly, the above-described "determining the target contour based on the contour of the electrode assembly" may include: determining at least one ROI in the image to be detected; and determining the target contour in the at least one ROI.

[0076] In other words, multiple regions of interest (ROIs) can be set within the area to be detected to acquire corner points. When there are many corner points on the contour of the electrode assembly, setting multiple ROIs can further reduce the number of corner points acquired, thereby reducing the number of traversals and computational load, and improving the efficiency of corner point detection.

[0077] It should be noted that the embodiments of this application mainly focus on obtaining the target corner points of the electrodes when the position of the electrodes in the image to be detected is known. Therefore, the approximate position of the target corner points is determined, and the use of regions of interest can reduce the number of corner points that need to be analyzed. In the embodiments of this application, the number of regions of interest is the same as the number of target corner points, and only one target corner point needs to be determined for each region of interest.

[0078] Optionally, in some embodiments, determining multiple corner points may include: obtaining the outline of the electrode assembly in the region of interest to obtain a target outline, the target outline including the outline of the tab, and obtaining the corner points of the target outline to obtain the multiple corner points.

[0079] The image to be detected may include one or more regions of interest (ROIs). The outline of the electrode assembly includes not only the outline of the tab but also the outlines of other objects. The outline of the tab is extracted from the outline of the electrode assembly using the ROI to obtain the outline including the tab. Then, corner points are obtained on the outline including the tab. Compared with obtaining all corner points of the outline of the electrode assembly first and then using the ROI to obtain corner points on the outline including the tab, the number of corner points obtained is reduced, which helps to improve the efficiency of corner point detection.

[0080] Optionally, in some embodiments, the above-mentioned "taking each vertex of the polygon corresponding to the target contour as the plurality of corner points" includes: processing the target contours corresponding to the at least one region of interest respectively through a polygon approximation algorithm to obtain at least one polygon corresponding to the target contour respectively; and taking each vertex of the polygon corresponding to each target contour as the plurality of corner points.

[0081] In this embodiment of the application, the polygon corresponding to the target contour can be obtained by the polygon approximation method, and then the vertices of the polygon can be obtained to obtain multiple corner points.

[0082] When performing shape analysis on a contour, it is usually necessary to approximate the contour using polygons to reduce the number of vertices. The common OpenCV function approxPolyDP can achieve this, and other methods can also be used to obtain the polygon corresponding to the target contour. This application does not limit the specific methods used. Since the OpenCV function approxPolyDP is a commonly used polygon approximation method in the prior art, it will not be elaborated upon here.

[0083] By obtaining the polygon corresponding to the target contour through polygon approximation method, the number of corner points that need to be processed in the subsequent process can be reduced, thereby improving the efficiency of corner point detection.

[0084] Optionally, in some embodiments, step 110 may include: binarizing the image to be detected to obtain a binarized image of the image to be detected, and obtaining the contour of the electrode assembly based on the edge curve of the binarized image.

[0085] The appropriate binarization method can be selected based on the brightness relationship between the foreground (electrode assembly or workpiece) and the background environment, such as ordinary binarization, big-law binarization, local binarization, adaptive binarization, etc. This can set the value of the foreground pixel to 1 and the value of the background pixel to 0, or set the value of the foreground pixel to 0 and the value of the background pixel to 1.

[0086] By performing edge analysis on the binarized image, the edge curves of the electrode assembly will appear in the binarized image, and the edge curves of the electrode assembly can form the contour curve of the electrode assembly.

[0087] Depending on the number and shape of the objects in the electrode assembly, the electrode assembly may have one or more contour curves.

[0088] In the above embodiments, after binarizing the image to be detected, the entire image can present a clear black and white effect to highlight the outline of the electrode assembly, so as to quickly extract the outline of the electrode assembly through the edge curve of the binarized image.

[0089] Optionally, in some embodiments, the binarized image may be denoised before the outline of the electrode assembly is obtained from the edges of the binarized image.

[0090] After binarization, the outlines of objects in the image are rough and uneven. For example, median filtering can be used to denoise binary images. Median filtering is a non-linear smoothing technique that sets the gray value of each pixel to the median of the gray values ​​of all pixels within a neighborhood window, making the surrounding pixel values ​​closer to the true value, thus eliminating isolated noise points. Specifically, a two-dimensional sliding template with a certain structure can be used, sorting the pixels within the template according to their pixel values ​​to generate a monotonically increasing (or decreasing) two-dimensional data sequence. The two-dimensional template is usually a 3*3 or 5*5 area, but it can also be of different shapes, such as lines, circles, crosses, or rings. Median filtering is a commonly used denoising method in existing technology and will not be elaborated further here; of course, other denoising methods can also be used.

[0091] Optionally, in some embodiments, the predetermined region can be circular. Setting the predetermined region as circular facilitates the rapid determination of the area ratio of the electrode assembly within the predetermined region, and also avoids the need to consider the influence of angle on the area ratio, as with other angled images, thereby improving the accuracy of corner detection.

[0092] Optionally, in some embodiments, the radius of the circle can be 10 pixels. Setting the radius of the predetermined area of ​​the circle to 10 pixels can avoid the problem that an excessively large radius value may include other corner points in the predetermined area, affecting the calculation of the area ratio of the current corner point, while an excessively small radius value may cause low accuracy. This value can more reasonably and effectively calculate the area ratio, thereby improving the accuracy of corner point detection.

[0093] Optionally, in some embodiments, the predetermined value can be 0.6. Setting the predetermined value to 0.6 can exclude corner points on approximately straight lines, which is beneficial for quickly obtaining target corner points and improving the efficiency of corner point detection.

[0094] Optionally, in some embodiments, the process of detecting the target corner point of the electrode can be described with reference to the following description and Figure 3 , Figure 4 .

[0095] According to some embodiments of this application, see Figures 3 to 4 This application provides a schematic flowchart of a method 300 for detecting the corner points of a tab, which may include at least some of the following: Figure 4 This is a schematic diagram illustrating the process of detecting the target corner point of the electrode.

[0096] 301, Obtain the image to be detected. For example... Figure 2 As shown, when detecting the corner of the tab 12 on the battery assembly, the image to be detected includes not only the tab 12, but also the cell body 11 and the adapter plate 12, wherein the tab 12 is welded to the adapter plate 13.

[0097] 302, binarize the image to be detected. Figure 4 (a) is a Figure 2 The image has been binarized, where the black portion represents the electrode assembly, including the battery cell 11, tab 12, and adapter 13; the white portion represents the background.

[0098] S303, Obtain the outline of the electrode assembly. The outline of the electrode assembly can be extracted from the edges of the binarized image, i.e., the intersection of black and white. Figure 4 (b) is to obtain Figure 4 The outline of the electrode assembly is obtained by considering the edges of the electrode assembly in (a). The outline of the electrode assembly consists of three curves, representing the edges of three white areas. The outline of the electrode assembly includes a portion of the tab's outline.

[0099] S304, Obtain the outline including the electrode. Specifically, obtain the outline including the electrode through the region of interest. Figure 4 In (c), the outline including the tabs is extracted using a rectangular bounding box over the region of interest to obtain the target outline. It should be noted that... Figure 4 (c) only shows the bounding box of one region of interest, but in fact there are 8 bounding boxes of regions of interest. The other 7 are not shown. Each bounding box needs to detect one target corner point. The image needs to detect a total of 8 target corner points of the electrode.

[0100] S305: Obtain multiple corner points and calculate the area proportion of each corner point. Specifically, obtain the polygon corresponding to the target contour through a polygon approximation method, and obtain the vertices of the polygon to obtain multiple corner points. Figure 4 (e) shows the multiple corner points acquired. When calculating the area proportion of each corner point, a predetermined area can be drawn centered on each corner point, and the area proportion of the electrode assembly within that predetermined area can be calculated. For example... Figure 4 (f) is a diagram showing the area proportion of the corner points, with the predetermined area being a circle as an example.

[0101] S306, among multiple corner points, obtain at least one candidate corner point whose area proportion is greater than a predetermined value. Determine whether the area proportion corresponding to each corner point is greater than the predetermined value; if it is, the corner point is listed as a candidate corner point.

[0102] S307, determine if there are multiple candidate corner points. If not, it means that all interfering points have been eliminated through the predetermined value and area proportion, and the listed candidate corner point is the target corner point. If yes, it means that not all interfering points have been eliminated through the predetermined value and area proportion, then among the multiple candidate corner points, the candidate corner point with the largest perpendicular distance to the center point of the electrode is determined as the target corner point, such as... Figure 4When the predetermined value of (g) is 0.6, the target corner point of the electrode is finally detected.

[0103] It should also be noted that the above only uses one region of interest as an example. The target node corner points in the other 7 regions of interest can be detected by referring to the steps after step 304.

[0104] The method embodiments of this application have been described in detail above. The device embodiments of this application are described below. The device embodiments correspond to the method embodiments. Therefore, for any part not described in detail, please refer to the preceding method embodiments. The device can implement any possible implementation of the above methods.

[0105] Figure 5 This is a schematic diagram of the hardware structure of the corner detection device for the tabs according to an embodiment of this application. Figure 5 The corner detection device 500 shown includes a memory 501 and a processor 502. The memory 501 stores instructions, which, when executed by the processor, cause the device 500 to perform the method described in any of the above embodiments.

[0106] The memory 501 can be a read-only memory (ROM), a static storage device, or a random access memory (RAM).

[0107] The processor 502 may be a general-purpose central processing unit (CPU), microprocessor, application-specific integrated circuit (ASIC), graphics processing unit (GPU), or one or more integrated circuits, used to execute relevant programs to achieve the functions required by the units in the tab corner detection device of this application embodiment, or to execute the tab corner detection method of this application embodiment.

[0108] The processor 502 can also be an integrated circuit chip with signal processing capabilities. In implementation, each step of the corner detection method for the tabs in this embodiment can be completed by the integrated logic circuitry in the processor 502 or by software instructions.

[0109] The processor 502 described above can also be a general-purpose processor, a digital signal processor (DSP), an ASIC, a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly implemented by the hardware processor, or implemented by a combination of hardware and software modules in the processor. The software modules can be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory 501. The processor 502 reads the information in memory 501 and, in conjunction with its hardware, completes the functions required by the units included in the tab corner detection device of the embodiments of this application, or executes the tab corner detection method of the embodiments of this application.

[0110] This application also provides a computer-readable storage medium storing program code for device execution, the program code including instructions for performing the steps in the above-described method for detecting the corner points of the tab.

[0111] This application also provides a computer program product, which includes a computer program stored on a computer-readable storage medium. The computer program includes program instructions, which, when executed by a computer, cause the computer to perform the aforementioned method for detecting the corner points of the tabs.

[0112] The aforementioned computer-readable storage medium may be a transient computer-readable storage medium or a non-transitory computer-readable storage medium.

[0113] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the device described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0114] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0115] The terms used in this application are for describing embodiments only and are not intended to limit the claims. As used in the description of embodiments and claims, the singular forms “a” and “described” are intended to include the plural forms as well, unless the context clearly indicates otherwise. Similarly, the term “and / or” as used herein means including one or more of the associated listed items and all possible combinations thereof. Additionally, when used in this application, the term “comprising” refers to the presence of stated features, integrals, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof.

[0116] The aspects, implementations, or features of the described embodiments can be used individually or in any combination. The aspects of the described embodiments can be implemented by software, hardware, or a combination of both. The described embodiments can also be embodied in a computer-readable medium storing computer-readable code, including instructions executable by at least one computing device. The computer-readable medium can be associated with any data storage device capable of storing data readable by a computer system. Examples of computer-readable media include read-only memory, random access memory, compact disc read-only memory (CD-ROM), hard disk drive (HDD), digital video disc (DVD), magnetic tape, and optical data storage devices. The computer-readable medium can also be distributed across a network-connected computer system, allowing the computer-readable code to be distributed for storage and execution.

[0117] The above technical description is illustrated with reference to the accompanying drawings, which form part of this application, and which show implementations according to the described embodiments. While these embodiments are described in sufficient detail to enable those skilled in the art to implement them, they are not limiting; thus, other embodiments can be used, and variations can be made without departing from the scope of the described embodiments. For example, the order of operations described in the flowcharts is not limiting, and the order of two or more operations illustrated and described in the flowcharts may be changed according to several embodiments. As another example, in several embodiments, one or more operations illustrated and described in the flowcharts are optional or can be deleted. Additionally, certain steps or functions may be added to the disclosed embodiments, or the order of two or more steps may be interchanged. All such variations are considered to be included in the disclosed embodiments and the claims.

[0118] Furthermore, terminology is used in the above technical description to provide a thorough understanding of the described embodiments. However, excessive detail is not required to implement the described embodiments. Therefore, the above description of the embodiments is presented for illustrative and descriptive purposes. The embodiments presented in the above description, as well as the examples disclosed according to these embodiments, are provided separately to add context and aid in understanding the described embodiments. The above specification is not intended to be exhaustive or to limit the described embodiments to the precise form of this application. Based on the above teachings, several modifications, choices of application, and variations are possible. In some cases, well-known processing steps have not been described in detail to avoid unnecessarily affecting the described embodiments. Although this application has been described with reference to preferred embodiments, various modifications can be made thereto and components can be replaced with equivalents without departing from the scope of this application. In particular, the various technical features mentioned in the various embodiments can be combined in any manner, provided there is no structural conflict. This application is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims

1. A method for detecting the corner points of an electrode, characterized in that, The method includes: The outline of the electrode assembly in the image to be detected is determined; the electrode assembly includes a single cell, a tab connected to the single cell, and an adapter piece welded to the tab; Based on the outline of the electrode assembly, multiple corner points are determined on the target outline; the target outline is the outline of the electrode assembly that includes a portion of the outline of the tab. Determine the area proportion corresponding to each of the plurality of corner points, wherein the area proportion is the proportion of the area of ​​the electrode assembly within a predetermined area centered on the corner point; Based on the area proportions corresponding to the plurality of corner points, the target corner point of the electrode is determined among the plurality of corner points; the target corner point is the corner point of the electrode adjacent to the background of the image to be detected, and the background refers to the area in the image to be detected other than the electrode assembly; The step of determining the target corner point of the electrode among the plurality of corner points based on the area proportions corresponding to the plurality of corner points includes: determining at least one candidate corner point among the plurality of corner points whose area proportion is greater than a predetermined value; and determining the target corner point among the at least one candidate corner point. The step of determining multiple corner points on a target contour based on the contour of the electrode assembly includes: determining the target contour based on the contour of the electrode assembly; and using each vertex of the polygon corresponding to the target contour as the multiple corner points.

2. The method according to claim 1, characterized in that, Determining the target corner point from the at least one candidate corner point includes: When there are multiple candidate corner points, the target corner point is determined based on the positional relationship between the multiple candidate corner points and the center point of the electrode.

3. The method according to claim 2, characterized in that, The positional relationship includes the distance between the candidate corner point and the center point of the electrode; determining the target corner point based on the positional relationship between the multiple candidate corner points and the center point of the electrode includes: The candidate corner point corresponding to the largest distance among the multiple distances is determined as the target corner point.

4. The method according to claim 1, characterized in that, Determining the target contour based on the contour of the electrode assembly includes: Identify at least one region of interest in the image to be detected; The target contour is determined in the at least one region of interest.

5. The method according to claim 4, characterized in that, The step of using each vertex of the polygon corresponding to the target contour as the plurality of corner points includes: The target contours corresponding to the at least one region of interest are processed by a polygon approximation algorithm to obtain at least one polygon corresponding to the target contours. Each vertex of the polygon corresponding to each target contour is taken as the plurality of corner points.

6. The method according to any one of claims 1 to 5, characterized in that, Determining the contour of the electrode assembly in the image to be detected includes: The image to be detected is binarized to obtain a binarized image of the image to be detected; The outline of the electrode assembly is determined based on the edge curves of the electrode assembly in the binarized image.

7. A device for detecting the corner points of an electrode tab, characterized in that, It includes a processor and a memory, the memory being used to store a program, and the processor being used to call and run the program from the memory to perform the method for detecting the corner points of the tabs according to any one of claims 1 to 6.

8. A computer-readable storage medium, characterized in that, The method includes a computer program that, when run on a computer, causes the computer to perform the method for detecting the corner points of the tabs according to any one of claims 1 to 6.

Images