Method, device, equipment, storage medium and program product for processing wound battery cell image

Abstract

The embodiment of the present application provides a method, device, equipment, storage medium and program product for processing a wound battery cell image, the method comprising taking a first image when a battery cell is wound on a winding machine and the battery cell includes a diaphragm with ceramic powder attached thereto; determining the size parameters of a ceramic powder area, the ceramic powder area being the area corresponding to the ceramic powder in the first image, the size parameters of the ceramic powder area including at least one of a ceramic powder width and a ceramic powder height, if there is a boundary line for grabbing an edge in the first image extending in the direction of the ceramic powder height, the size parameters include the ceramic powder height, if there is a boundary line for grabbing an edge in the first image extending in the direction of the ceramic powder width, the size parameters include the ceramic powder width; determining a target convolution kernel according to the size parameters of the ceramic powder area; filtering the first image according to the target convolution kernel to obtain a target image. In this way, a clearer target image can be obtained and the accuracy of image edge grabbing can be improved.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a method, device, equipment, storage medium and program product for processing a wound battery cell image. Background Art

[0002] With the widespread use of power batteries, in order to ensure the safety of batteries, the quality requirements in manufacturing are becoming more and more stringent. During the winding process of the battery cell, it is necessary to detect the alignment of the various materials of the battery cell to ensure the yield rate. At present, the alignment is usually detected by image edge processing, which means that the battery cell winding detection has high requirements for image clarity. However, in the actual winding process, the image may be disturbed by the material itself or the external shooting environment, resulting in poor image clarity, affecting the accuracy of subsequent image edge grabbing, and the robustness of battery cell winding detection is poor. Summary of the invention

[0003] The embodiments of the present application provide a method, device, equipment, storage medium and program product for processing a wound battery cell image to solve the technical problems of poor image clarity, affecting the accuracy of subsequent image edge capture, and poor robustness of battery cell winding detection.

[0004] In a first aspect, an embodiment of the present application provides a method for processing a wound battery cell image, comprising:

[0005] When a winding machine winds a battery cell, and the battery cell includes a separator with ceramic powder attached thereto, capturing a first image of the battery cell during winding;

[0006] Determine the size parameters of the ceramic powder area in the first image, the ceramic powder area being the area corresponding to the ceramic powder in the first image, the size parameters of the ceramic powder area including at least one of a ceramic powder width and a ceramic powder height, and in the case where there is at least one edge-grabbing boundary line extending in the direction of the ceramic powder height in the first image, the size parameters of the ceramic powder area include the ceramic powder height, and in the case where there is at least one edge-grabbing boundary line extending in the direction of the ceramic powder width in the first image, the size parameters of the ceramic powder area include the ceramic powder width;

[0007] Determine the target convolution kernel according to the size parameters of the ceramic powder area, wherein, when the size parameters of the ceramic powder area include the ceramic powder width, the ceramic powder width is determined as the width of the target convolution kernel, and when the size parameters of the ceramic powder area include the ceramic powder height, the ceramic powder height is determined as the height of the target convolution kernel;

[0008] The first image is filtered according to the target convolution kernel to obtain a target image.

[0009] In this embodiment, the size of the convolution kernel can be determined according to the size parameters of the ceramic powder area in the first image to obtain the target convolution kernel. The target convolution kernel is used for filtering processing to reduce the interference of the ceramic powder on the clarity of the first image and obtain a clearer target image, thereby improving the accuracy of subsequent image edge capture and ensuring the robustness of battery cell winding detection.

[0010] In some embodiments, when the size parameter of the ceramic powder region includes the height of the ceramic powder, determining the target convolution kernel according to the size parameter of the ceramic powder region includes:

[0011] When the edge-grabbing boundary line in the first image extends in the direction of the ceramic powder height, the ceramic powder height is determined as the height of the target convolution kernel, and the preset convolution kernel width is determined as the width of the target convolution kernel to obtain the target convolution kernel.

[0012] In this way, according to the different requirements of edge grasping directions, for the left and right edge grasping situations, the height of the ceramic powder can be selected to determine the target convolution kernel, thereby ensuring the rationality of the target convolution kernel and further improving the clarity of the target image after filtering processing.

[0013] In some embodiments, when the size parameter of the ceramic powder region includes the ceramic powder width, determining the target convolution kernel according to the size parameter of the ceramic powder region includes:

[0014] When the edge-grabbing boundary line in the first image extends in the direction of the ceramic powder width, the preset convolution kernel height is determined as the height of the target convolution kernel, and the ceramic powder width is determined as the width of the target convolution kernel to obtain the target convolution kernel.

[0015] In this way, according to the different requirements of edge grabbing directions, for the upper and lower edge grabbing situations, the width of the ceramic powder can be selected to determine the target convolution kernel, thereby ensuring the rationality of the target convolution kernel and further improving the clarity of the target image after filtering processing.

[0016] In some embodiments, when there are at least two edge-grabbing boundary lines in the first image, at least one boundary line extends in a direction of a ceramic powder height, and at least one boundary line extends in a direction of a ceramic powder width, the size parameters of the ceramic powder region include a ceramic powder width and a ceramic powder height, and the target convolution kernel includes a first convolution kernel and a second convolution kernel;

[0017] Performing filtering processing on the first image according to the target convolution kernel to obtain a target image, further comprising:

[0018] Performing filtering processing on the first image according to the first convolution kernel to obtain a first preliminary image, wherein the height of the first convolution kernel is the height of the ceramic powder, and the width of the first convolution kernel is the preset convolution kernel width;

[0019] The first preliminary image is filtered according to the second convolution kernel to obtain a target image, the height of the second convolution kernel is a preset convolution kernel height, and the width of the second convolution kernel is a ceramic powder width.

[0020] In this embodiment, two convolution kernels can be determined according to the height or width of the ceramic powder, and filtering is performed once using the two convolution kernels respectively, which can further improve the clarity of the target image and meet the edge capture requirements in different directions at the same time.

[0021] In some embodiments, when there are at least two edge-grabbing boundary lines in the first image, at least one boundary line extends in a direction of a ceramic powder height, and at least one boundary line extends in a direction of a ceramic powder width, the size parameters of the ceramic powder region include a ceramic powder width and a ceramic powder height, and the target convolution kernel includes a first convolution kernel and a second convolution kernel;

[0022] Performing filtering processing on the first image according to the target convolution kernel to obtain a target image, further comprising:

[0023] Performing filtering processing on the first image according to the second convolution kernel to obtain a second preliminary image, wherein the height of the second convolution kernel is a preset convolution kernel height, and the width of the second convolution kernel is a ceramic powder width;

[0024] The second primary image is filtered according to the first convolution kernel to obtain a target image, the height of the first convolution kernel is the height of the ceramic powder, and the width of the first convolution kernel is the preset convolution kernel width.

[0025] In this embodiment, two convolution kernels can be determined according to the height or width of the ceramic powder, and filtering is performed once using the two convolution kernels respectively, which can further improve the clarity of the target image and meet the edge capture requirements in different directions at the same time.

[0026] In some embodiments, when the first image includes at least two ceramic powder regions, determining the size parameters of the ceramic powder regions in the first image includes:

[0027] Determine the area of ​​each of the at least two ceramic powder regions;

[0028] Determine the ceramic powder region corresponding to the maximum area as the target ceramic powder region;

[0029] At least one of a ceramic powder width and a ceramic powder height corresponding to the target ceramic powder region is determined as a size parameter of the ceramic powder region in the first image.

[0030] In this way, the size parameters of the ceramic powder area can be determined according to the ceramic powder area with the largest area, so as to obtain a target convolution kernel of a more reasonable size to ensure the clarity of the filtered target image.

[0031] In some embodiments, when a first image of the battery cell winding is acquired, before determining the size parameter of the ceramic powder region in the first image, the method further includes:

[0032] Obtain the original image of the battery cell winding;

[0033] The original image is subjected to brightness adjustment processing to obtain a first image.

[0034] In this way, before eliminating the interference of uneven ceramic powder on image clarity, the brightness of the original image taken during the battery cell winding process can also be adjusted to further improve the accuracy of subsequent image edge capture and improve the robustness of battery cell winding detection.

[0035] In some embodiments, performing brightness adjustment processing on the original image to obtain the first image includes:

[0036] Extract the original image according to the preset extraction frame to obtain the target area;

[0037] Determine an average value of pixel information of the target area according to pixel information in the target area, where the pixel information is used to represent the brightness of the original image;

[0038] Determine the pixel information deviation value according to the pixel information average value and the preset pixel information standard value;

[0039] According to the pixel information deviation value, the pixel information in the target area is updated to obtain a first image.

[0040] In this way, the pixel information deviation value can be determined according to the pixel information average value in the preset extraction frame and the preset pixel information standard value, so that the image brightness can be compensated according to the pixel information deviation value to achieve the purpose of adjusting the image brightness.

[0041] In some embodiments, performing brightness adjustment processing on the original image to obtain the first image includes:

[0042] Performing brightness adjustment processing on the original image to obtain a second image;

[0043] Perform image enhancement processing on the second image to obtain the first image.

[0044] In this way, for the image after brightness adjustment, image enhancement processing can also be performed to enhance the edge contrast, further improve the subsequent image edge capture accuracy, and improve the robustness of battery cell winding detection.

[0045] In some embodiments, performing image enhancement processing on the second image to obtain the first image includes:

[0046] Acquiring pixel information of the second image;

[0047] According to a preset convolution kernel, filtering is performed on the pixel information of the second image to obtain filtered pixel information;

[0048] Determine a difference between pixel information of the second image and pixel information after filtering;

[0049] According to the difference, the pixel information of the second image is updated to obtain the first image.

[0050] In this way, the difference between the pixel information of the image and the pixel information after filtering can be calculated, and the pixel information can be enhanced according to the difference to achieve the purpose of enhancing the edge contrast.

[0051] In some embodiments, after filtering the first image according to the target convolution kernel to obtain the target image, the method further includes:

[0052] Perform grayscale processing on the target image to obtain a grayscale image;

[0053] Determine the grayscale average values ​​of a plurality of pixel groups according to the grayscale value of each pixel point in the grayscale image, wherein each pixel group includes pixels in the grayscale image that are located in the extension direction of the boundary line of the edge grabbing;

[0054] According to a preset derivative convolution kernel, a grayscale average value of multiple pixel groups is derivatized to obtain first-order derivatives of the multiple pixel groups;

[0055] Traversing the first-order derivatives of multiple pixel groups, determining a target pixel group whose absolute value of the first-order derivative is greater than a preset edge capture threshold;

[0056] Generate a grab bounding box based on the target pixel group.

[0057] In this way, the first-order derivative corresponding to the target image can be obtained by performing grayscale processing and then taking the derivative. Since the target image is clearer, the value of the first-order derivative is more accurate, so the accurate edge point can be determined based on the first-order derivative, thereby improving the edge capture accuracy.

[0058] In a second aspect, an embodiment of the present application further provides a device for processing a wound battery cell image, comprising:

[0059] A shooting module, used for shooting a first image of the battery cell during the winding process when the battery cell includes a diaphragm with ceramic powder attached thereto, when the battery cell is wound by a winding machine;

[0060] a first determination module, for determining size parameters of a ceramic powder region in a first image, the ceramic powder region being a region corresponding to ceramic powder in the first image, the size parameters of the ceramic powder region including at least one of a ceramic powder width and a ceramic powder height, and in a case where there is at least one edge-grabbing boundary line extending in a direction of the ceramic powder height in the first image, the size parameters of the ceramic powder region including the ceramic powder height, and in a case where there is at least one edge-grabbing boundary line extending in a direction of the ceramic powder width in the first image, the size parameters of the ceramic powder region including the ceramic powder width;

[0061] a second determination module, configured to determine a target convolution kernel according to a size parameter of the ceramic powder region, wherein when the size parameter of the ceramic powder region includes a ceramic powder width, the ceramic powder width is determined as the width of the target convolution kernel, and when the size parameter of the ceramic powder region includes a ceramic powder height, the ceramic powder height is determined as the height of the target convolution kernel;

[0062] The processing module is used to filter the first image according to the target convolution kernel to obtain the target image.

[0063] In this embodiment, the size of the convolution kernel can be determined according to the size parameters of the ceramic powder area in the first image to obtain the target convolution kernel. The target convolution kernel is used for filtering processing to reduce the interference of the ceramic powder on the clarity of the first image and obtain a clearer target image, thereby improving the accuracy of subsequent image edge capture and ensuring the robustness of battery cell winding detection.

[0064] In some embodiments, when the size parameter of the ceramic powder area includes the height of the ceramic powder, the second determining module is further configured to:

[0065] When the edge-grabbing boundary line in the first image extends in the direction of the ceramic powder height, the ceramic powder height is determined as the height of the target convolution kernel, and the preset convolution kernel width is determined as the width of the target convolution kernel to obtain the target convolution kernel.

[0066] In this way, according to the different requirements of edge grasping directions, for the left and right edge grasping situations, the height of the ceramic powder can be selected to determine the target convolution kernel, thereby ensuring the rationality of the target convolution kernel and further improving the clarity of the target image after filtering processing.

[0067] In some embodiments, when the size parameter of the ceramic powder region includes the ceramic powder width, the second determining module is further configured to:

[0068] When the edge-grabbing boundary line in the first image extends in the direction of the ceramic powder width, the preset convolution kernel height is determined as the height of the target convolution kernel, and the ceramic powder width is determined as the width of the target convolution kernel to obtain the target convolution kernel.

[0069] In this way, according to the different requirements of edge grabbing directions, for the upper and lower edge grabbing situations, the width of the ceramic powder can be selected to determine the target convolution kernel, thereby ensuring the rationality of the target convolution kernel and further improving the clarity of the target image after filtering processing.

[0070] In some embodiments, when there are at least two edge-grabbing boundary lines in the first image, at least one boundary line extends in a direction of a ceramic powder height, and at least one boundary line extends in a direction of a ceramic powder width, the size parameters of the ceramic powder region include a ceramic powder width and a ceramic powder height, and the target convolution kernel includes a first convolution kernel and a second convolution kernel;

[0071] The processing module is also used to:

[0072] Performing filtering processing on the first image according to the first convolution kernel to obtain a first preliminary image, wherein the height of the first convolution kernel is the height of the ceramic powder, and the width of the first convolution kernel is the preset convolution kernel width;

[0073] The first preliminary image is filtered according to the second convolution kernel to obtain a target image, the height of the second convolution kernel is a preset convolution kernel height, and the width of the second convolution kernel is a ceramic powder width.

[0074] In this embodiment, two convolution kernels can be determined according to the height or width of the ceramic powder, and filtering is performed once using the two convolution kernels respectively, which can further improve the clarity of the target image and meet the edge capture requirements in different directions at the same time.

[0075] In some embodiments, when there are at least two edge-grabbing boundary lines in the first image, at least one boundary line extends in a direction of a ceramic powder height, and at least one boundary line extends in a direction of a ceramic powder width, the size parameters of the ceramic powder region include a ceramic powder width and a ceramic powder height, and the target convolution kernel includes a first convolution kernel and a second convolution kernel;

[0076] The processing module is also used to:

[0077] Performing filtering processing on the first image according to the second convolution kernel to obtain a second preliminary image, wherein the height of the second convolution kernel is a preset convolution kernel height, and the width of the second convolution kernel is a ceramic powder width;

[0078] The second primary image is filtered according to the first convolution kernel to obtain a target image, the height of the first convolution kernel is the height of the ceramic powder, and the width of the first convolution kernel is the preset convolution kernel width.

[0079] In this embodiment, two convolution kernels can be determined according to the height or width of the ceramic powder, and filtering is performed once using the two convolution kernels respectively, which can further improve the clarity of the target image and meet the edge capture requirements in different directions at the same time.

[0080] In some embodiments, when the first image includes at least two ceramic powder regions, the second determining module is further configured to:

[0081] Determine the area of ​​each of the at least two ceramic powder regions;

[0082] Determine the ceramic powder region corresponding to the maximum area as the target ceramic powder region;

[0083] At least one of a ceramic powder width and a ceramic powder height corresponding to the target ceramic powder region is determined as a size parameter of the ceramic powder region in the first image.

[0084] In this way, the size parameters of the ceramic powder area can be determined according to the ceramic powder area with the largest area, so as to obtain a target convolution kernel of a more reasonable size to ensure the clarity of the filtered target image.

[0085] In some embodiments, the apparatus further comprises:

[0086] An acquisition module, for acquiring an original image of the winding of the battery cell before determining the size parameters of the ceramic powder area in the first image when the first image of the winding of the battery cell is acquired;

[0087] The processing module is further used to perform brightness adjustment processing on the original image to obtain a first image.

[0088] In this way, before eliminating the interference of uneven ceramic powder on image clarity, the brightness of the original image taken during the battery cell winding process can also be adjusted to further improve the accuracy of subsequent image edge capture and improve the robustness of battery cell winding detection.

[0089] In some embodiments, the processing module is further configured to:

[0090] Extract the original image according to the preset extraction frame to obtain the target area;

[0091] Determine an average value of pixel information of the target area according to pixel information in the target area, where the pixel information is used to represent the brightness of the original image;

[0092] Determine the pixel information deviation value according to the pixel information average value and the preset pixel information standard value;

[0093] According to the pixel information deviation value, the pixel information in the target area is updated to obtain a first image.

[0094] In this way, the pixel information deviation value can be determined according to the pixel information average value in the preset extraction frame and the preset pixel information standard value, so that the image brightness can be compensated according to the pixel information deviation value to achieve the purpose of adjusting the image brightness.

[0095] In some embodiments, the processing module is further configured to:

[0096] Performing brightness adjustment processing on the original image to obtain a second image;

[0097] Perform image enhancement processing on the second image to obtain the first image.

[0098] In this way, for the image after brightness adjustment, image enhancement processing can also be performed to enhance the edge contrast, further improve the subsequent image edge capture accuracy, and improve the robustness of battery cell winding detection.

[0099] In some embodiments, the processing module is further configured to:

[0100] Acquiring pixel information of the second image;

[0101] According to a preset convolution kernel, filtering is performed on the pixel information of the second image to obtain filtered pixel information;

[0102] Determine a difference between pixel information of the second image and pixel information after filtering;

[0103] According to the difference, the pixel information of the second image is updated to obtain the first image.

[0104] In this way, the difference between the pixel information of the image and the pixel information after filtering can be calculated, and the pixel information can be enhanced according to the difference to achieve the purpose of enhancing the edge contrast.

[0105] In some embodiments, the processing module is further configured to:

[0106] After filtering the first image according to the target convolution kernel to obtain the target image, grayscale processing is performed on the target image to obtain a grayscale image;

[0107] The device also includes:

[0108] A third determination module is used to determine the grayscale average value of a plurality of pixel groups according to the grayscale value of each pixel point in the grayscale image, wherein each pixel group includes pixels in the grayscale image that are located in the extension direction of the boundary line of the edge grabbing;

[0109] A derivation module, used to perform derivation processing on the grayscale average values ​​of multiple pixel groups according to a preset derivation convolution kernel to obtain first-order derivatives of the multiple pixel groups;

[0110] A fourth determination module, configured to traverse the first-order derivatives of the plurality of pixel groups and determine a target pixel group whose absolute value of the first-order derivative is greater than a preset edge capture threshold;

[0111] The generation module is used to generate a grabbing border according to the target pixel group.

[0112] In this way, the first-order derivative corresponding to the target image can be obtained by performing grayscale processing and then taking the derivative. Since the target image is clearer, the value of the first-order derivative is more accurate, so the accurate edge point can be determined based on the first-order derivative, thereby improving the edge capture accuracy.

[0113] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor and a memory storing program instructions; when the processor executes the program instructions, the method of the first aspect is implemented.

[0114] In a fourth aspect, an embodiment of the present application provides a machine-readable storage medium having program instructions stored thereon, and the method of the first aspect is implemented when the program instructions are executed by a processor.

[0115] In a fifth aspect, an embodiment of the present application provides a computer program product. When instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the method of the first aspect.

[0116] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0117] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the drawings without paying creative work.

[0118] Figure 1 A schematic diagram of battery cell winding in a method for processing a wound battery cell image provided in an embodiment of the present application;

[0119] Figure 2 A schematic diagram of a process of a method for processing a wound battery cell image provided in an embodiment of the present application;

[0120] Figure 3 A schematic diagram of the size parameters of the ceramic powder area in the method for processing the wound battery core image provided in an embodiment of the present application;

[0121] Figure 4a One of the schematic diagrams of the target convolution kernel in the method for processing the wound battery cell image provided in the embodiment of the present application;

[0122] Figure 4bThis is one of the effect diagrams of the filtering processing in the method for processing the wound battery core image provided in the embodiment of the present application;

[0123] Figure 5a The second schematic diagram of the target convolution kernel in the method for processing the wound battery cell image provided in the embodiment of the present application;

[0124] Figure 5b This is a second effect diagram of the filtering process in the method for processing the wound battery cell image provided in an embodiment of the present application;

[0125] Figure 6a A schematic diagram of the grayscale value of the second image in the method for processing a wound battery cell image provided in an embodiment of the present application;

[0126] Figure 6b The gray value after filtering in the method for processing the wound battery cell image provided in the embodiment of the present application;

[0127] Figure 6c The difference between the grayscale value of the second image and the grayscale value after filtering in the method for processing the wound battery cell image provided in an embodiment of the present application;

[0128] Figure 6d The grayscale value after image enhancement in the method for processing the wound battery cell image provided in the embodiment of the present application;

[0129] Figure 7 An overall flow chart of a method for processing a wound battery cell image provided in an embodiment of the present application;

[0130] Figure 8 A schematic diagram of the structure of a device for processing a wound battery cell image provided in an embodiment of the present application;

[0131] Fig. 9 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0132] Reference numerals:

[0133] 100, winding needle; 101, diaphragm; 1011, ceramic powder; 102, anode sheet; 103, cathode sheet;

[0134] 401. Ceramic powder area; 402. Boundary line.

[0135] In the drawings, the drawings are not drawn to scale. DETAILED DESCRIPTION

[0136] The following detailed description and drawings of the embodiments of the present application are used to illustrate the principles of the present application, but cannot be used to limit the scope of the present application, that is, the present application is not limited to the described embodiments.

[0137] In the description of the present application, it should be noted that, unless otherwise specified, "multiple" means more than two; the terms "upper", "lower", "left", "right", "inside", "outside", etc., indicating the orientation or positional relationship, are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first", "second", "third", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. "Vertical" is not strictly vertical, but is within the allowable error range. "Parallel" is not strictly parallel, but is within the allowable error range.

[0138] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments.

[0139] In the related art, during the winding process of the battery cell, such as Figure 1 As shown, the diaphragm 101, the anode sheet 102, the diaphragm 101 and the cathode sheet 103 are arranged in sequence and then wound onto the winding needle 100. During the winding process, a charge coupled device (CCD) camera can be used to capture images, and the alignment between the diaphragm 101, the anode sheet 102 and the cathode sheet 103 can be detected by edge processing of the image.

[0140] The applicant found that due to the problem of uneven adhesion of the diaphragm coating, ceramic powder 1011 may exist on the diaphragm 101, which will cause the presence of ceramic powder areas in the captured image, resulting in poor image clarity and affecting the accuracy of subsequent image edge capture.

[0141] Based on this, the embodiments of the present application provide a method, device, equipment, storage medium and program product for processing a wound cell image to solve the above technical problems. The following first introduces the method for processing a wound cell image provided by the embodiments of the present application.

[0142] Please refer to Figure 2 , Figure 2 A method for processing a wound cell image is provided in an embodiment of the present application. The method for processing a wound cell image may include:

[0143] Step 201 : When a winding machine is used to wind a battery cell, and the battery cell includes a separator with ceramic powder attached thereto, a first image of the battery cell during the winding process is captured.

[0144] In step 201, as mentioned above, the separator of the battery cell may have ceramic powder on the separator due to uneven coating adhesion. For such a battery cell, when the battery cell is wound by a winding machine, a first image of the battery cell winding process can be captured. The first image can be an original image captured by a CCD camera, or an image preprocessed based on the original image captured by the CCD camera, which is not specifically limited here.

[0145] Step 202, determining the size parameters of the ceramic powder region in the first image, where the ceramic powder region is the region corresponding to the ceramic powder in the first image, and the size parameters of the ceramic powder region include at least one of a ceramic powder width and a ceramic powder height.

[0146] In step 201, since ceramic powder is attached to the diaphragm, there is an area corresponding to the ceramic powder in the first image, ie, a ceramic powder area, wherein the number of the ceramic powder areas may be one or more, which is not specifically limited here.

[0147] The size parameter of the ceramic powder area can be determined from the first image, and the size parameter of the ceramic powder area includes at least one of the ceramic powder width and the ceramic powder height. It is understood that in some examples, the height average of multiple ceramic powder areas in the first image can be calculated as the ceramic powder height, and the width average of multiple ceramic powder areas in the first image can be calculated as the ceramic powder width. In other words, the size parameter of the ceramic powder area in the first image can be obtained based on at least one of the height average and the width average.

[0148] In some embodiments, when the first image includes at least two ceramic powder regions, determining the size parameters of the ceramic powder regions in the first image may further include:

[0149] Determine the area of ​​each of the at least two ceramic powder regions;

[0150] Determine the ceramic powder region corresponding to the maximum area as the target ceramic powder region;

[0151] At least one of a ceramic powder width and a ceramic powder height corresponding to the target ceramic powder region is determined as a size parameter of the ceramic powder region in the first image.

[0152] For example, at least one of a ceramic powder width and a ceramic powder height corresponding to the largest ceramic powder region in the first image, that is, the target ceramic powder region, may be determined as the size parameter of the ceramic powder region in the first image.

[0153] For example, when only the boundary line of the grabbing edge extending in the direction of the ceramic powder width exists in the first image, the size parameters of the ceramic powder area may include the ceramic powder width corresponding to the target ceramic powder area. When only the boundary line of the grabbing edge extending in the direction of the ceramic powder height exists in the first image, the size parameters of the ceramic powder area may include the ceramic powder height corresponding to the target ceramic powder area. When both the boundary line of the grabbing edge extending in the direction of the ceramic powder width and the boundary line of the grabbing edge extending in the direction of the ceramic powder height exist in the first image, the size parameters of the ceramic powder area may include the ceramic powder width and the ceramic powder height corresponding to the target ceramic powder area.

[0154] In this way, the size parameters of the ceramic powder area can be determined according to the ceramic powder area with the largest area, so as to obtain a target convolution kernel of a more reasonable size to ensure the clarity of the filtered target image.

[0155] Step 203, determining a target convolution kernel according to the size parameters of the ceramic powder area.

[0156] In step 203, the size of the ceramic powder area can be determined as the size parameter of the convolution kernel to obtain the target convolution kernel, wherein, when the size parameter of the ceramic powder area includes the ceramic powder width, the ceramic powder width is determined as the width of the target convolution kernel, and when the size parameter of the ceramic powder area includes the ceramic powder height, the ceramic powder height is determined as the height of the target convolution kernel.

[0157] For example, the ceramic powder width can be set as the width of the target convolution kernel, and the ceramic powder height can be set as the height of the target convolution kernel. It is also possible to determine the width and height of the target convolution kernel according to the ceramic powder width and the preset convolution kernel height, or according to the preset convolution kernel width and ceramic powder height, based on the subsequent upper and lower edge grabbing and left and right edge grabbing requirements. It can be set specifically according to actual needs and is not specifically limited here.

[0158] Step 204: filter the first image according to the target convolution kernel to obtain a target image.

[0159] In step 204, each pixel in the first image can be scanned by a target convolution kernel of a specified size determined based on the size parameters of the ceramic powder area, and the pixel information of the pixel in the center of the neighborhood is replaced by the weighted average of the pixel information of all pixels in the neighborhood determined by the target convolution kernel to obtain a filtered target image.

[0160] It can be understood that the pixel information can be a pixel value, an RGB value, a grayscale value, etc., which can be set according to actual needs and is not specifically limited here.

[0161] In this embodiment, the size of the convolution kernel can be determined according to the size parameters of the ceramic powder area in the first image to obtain the target convolution kernel. The target convolution kernel is used for filtering processing to reduce the interference of the ceramic powder on the clarity of the first image and obtain a clearer target image, thereby improving the accuracy of subsequent image edge capture and ensuring the robustness of battery cell winding detection.

[0162] In some embodiments, when the size parameter of the ceramic powder region includes the height of the ceramic powder, determining the target convolution kernel according to the size parameter of the ceramic powder region includes:

[0163] When the edge-grabbing boundary line in the first image extends in the direction of the ceramic powder height, the ceramic powder height is determined as the height of the target convolution kernel, and the preset convolution kernel width is determined as the width of the target convolution kernel to obtain the target convolution kernel.

[0164] In this embodiment, the size parameter of the ceramic powder area may include the ceramic powder height. Figure 3 As shown, the ceramic powder width W corresponding to the ceramic powder area may be 60px, and the ceramic powder height H may be 20px.

[0165] When the boundary line of the edge grabbing in the first image extends along the direction of the ceramic powder height, that is, in order to meet the left and right edge grabbing requirements, it is necessary to reduce the interference of the ceramic powder area in the direction of the ceramic powder height. At this time, the ceramic powder height H can be determined as the height of the target convolution kernel, and the preset convolution kernel width can be determined as the width of the target convolution kernel to obtain the target convolution kernel.

[0166] Among them, the preset convolution kernel width can be set according to actual needs. For example, the side length of a common convolution kernel can be 1px, 3px, 5px, etc., which is not specifically limited here.

[0167] like Figure 4a As shown, the width of the target convolution kernel can be 3px and the height can be 20px. The first image is filtered by the target convolution kernel, and the filtering effect can be as follows Figure 4b As shown, after filtering by the target convolution kernel, the interference of the ceramic powder area 401 on the edge grabbing boundary line 402 extending along the height direction of the ceramic powder is reduced, making the boundary line 402 clearer.

[0168] In this way, according to the different requirements of edge grasping directions, for the upper and lower edge grasping situations, the height of the ceramic powder can be selected to determine the target convolution kernel, thereby ensuring the rationality of the target convolution kernel and further improving the clarity of the target image after filtering processing.

[0169] In some embodiments, when the size parameter of the ceramic powder region includes the ceramic powder width, determining the target convolution kernel according to the size parameter of the ceramic powder region includes:

[0170] When the edge-grabbing boundary line in the first image extends in the direction of the ceramic powder width, the preset convolution kernel height is determined as the height of the target convolution kernel, and the ceramic powder width is determined as the width of the target convolution kernel to obtain the target convolution kernel.

[0171] In this embodiment, the size parameter of the ceramic powder region may include the ceramic powder width. Figure 3 As shown, the ceramic powder width W corresponding to the ceramic powder area may be 60px, and the ceramic powder height H may be 20px.

[0172] When the edge grabbing boundary line in the first image extends along the direction of the ceramic powder width, that is, in order to meet the upper and lower edge grabbing requirements, it is necessary to reduce the interference of the ceramic powder area in the ceramic powder width direction. At this time, the ceramic powder width W can be determined as the width of the target convolution kernel, and the preset convolution kernel height can be determined as the height of the target convolution kernel to obtain the target convolution kernel.

[0173] Among them, the preset convolution kernel height can be set according to actual needs. For example, the side length of a common convolution kernel can be 1px, 3px, 5px, etc., which is not specifically limited here.

[0174] like Figure 5a As shown, the width of the target convolution kernel can be 60px and the height can be 3px. The first image is filtered by the target convolution kernel, and the filtering effect can be as follows Figure 5b As shown, after filtering by the target convolution kernel, the interference of the ceramic powder area 401 on the edge grabbing boundary line 402 extending along the width direction of the ceramic powder is reduced, making the boundary line 402 clearer.

[0175] In this way, according to the different requirements of edge grabbing directions, for the upper and lower edge grabbing situations, the width of the ceramic powder can be selected to determine the target convolution kernel, thereby ensuring the rationality of the target convolution kernel and further improving the clarity of the target image after filtering processing.

[0176] In some embodiments, when there are at least two edge-grabbing boundary lines in the first image, at least one boundary line extends in a direction of a ceramic powder height, and at least one boundary line extends in a direction of a ceramic powder width, the size parameters of the ceramic powder region include a ceramic powder width and a ceramic powder height, and the target convolution kernel includes a first convolution kernel and a second convolution kernel;

[0177] Performing filtering processing on the first image according to the target convolution kernel to obtain a target image, further comprising:

[0178] Performing filtering processing on the first image according to the first convolution kernel to obtain a first preliminary image, wherein the height of the first convolution kernel is the height of the ceramic powder, and the width of the first convolution kernel is the preset convolution kernel width;

[0179] The first preliminary image is filtered according to the second convolution kernel to obtain a target image, the height of the second convolution kernel is a preset convolution kernel height, and the width of the second convolution kernel is a ceramic powder width.

[0180] In this embodiment, if there is at least one boundary line in the first image extending in the direction of the ceramic powder height and at least one boundary line extending in the direction of the ceramic powder width, it means that the upper and lower edge grasping requirements and the left and right edge grasping requirements need to be met at the same time, that is, it is necessary to reduce the interference of the ceramic powder area in the ceramic powder width direction and the ceramic powder height direction.

[0181] At this time, the height of the ceramic powder can be determined as the height of the first convolution kernel, and the preset convolution kernel width can be determined as the width of the first convolution kernel to obtain the first convolution kernel. The width of the ceramic powder can be determined as the width of the second convolution kernel, and the preset convolution kernel height can be determined as the height of the second convolution kernel to obtain the second convolution kernel.

[0182] The first convolution kernel may be used to perform filtering processing first, and then the second convolution kernel may be used to perform filtering processing to obtain a target image.

[0183] In this embodiment, two convolution kernels can be determined according to the height or width of the ceramic powder, and filtering is performed once using the two convolution kernels respectively, which can further improve the clarity of the target image and meet the edge capture requirements in different directions at the same time.

[0184] In some embodiments, when there are at least two edge-grabbing boundary lines in the first image, at least one boundary line extends in a direction of a ceramic powder height, and at least one boundary line extends in a direction of a ceramic powder width, the size parameters of the ceramic powder region include a ceramic powder width and a ceramic powder height, and the target convolution kernel includes a first convolution kernel and a second convolution kernel;

[0185] Performing filtering processing on the first image according to the target convolution kernel to obtain a target image, further comprising:

[0186] Performing filtering processing on the first image according to the second convolution kernel to obtain a second preliminary image, wherein the height of the second convolution kernel is a preset convolution kernel height, and the width of the second convolution kernel is a ceramic powder width;

[0187] The second primary image is filtered according to the first convolution kernel to obtain a target image, the height of the first convolution kernel is the height of the ceramic powder, and the width of the first convolution kernel is the preset convolution kernel width.

[0188] In this embodiment, as mentioned above, if there is at least one boundary line in the first image extending in the direction of the ceramic powder height, and at least one boundary line extending in the direction of the ceramic powder width, then the ceramic powder height can be determined as the height of the first convolution kernel, and the preset convolution kernel width can be determined as the width of the first convolution kernel to obtain the first convolution kernel. The ceramic powder width can be determined as the width of the second convolution kernel, and the preset convolution kernel height can be determined as the height of the second convolution kernel to obtain the second convolution kernel.

[0189] The second convolution kernel may be used to perform filtering processing first, and then the first convolution kernel may be used to perform filtering processing to obtain a target image.

[0190] In this embodiment, two convolution kernels can be determined according to the height or width of the ceramic powder, and filtering is performed once using the two convolution kernels respectively, which can further improve the clarity of the target image and meet the edge capture requirements in different directions at the same time.

[0191] In some embodiments, when a first image of the battery cell winding is acquired, before determining the size parameter of the ceramic powder area in the first image, the method further includes:

[0192] Obtain the original image of the battery cell winding;

[0193] The original image is subjected to brightness adjustment processing to obtain a first image.

[0194] In this embodiment, when the CCD camera captures the original image of the battery cell winding, the original image may appear too dark or too bright due to low light or strong light during the shooting.

[0195] At this time, the original image can be subjected to brightness adjustment processing to obtain a first image. For example, the brightness adjustment processing can be to set a standard brightness value, calculate the deviation value between the current brightness value of the original image and the standard brightness value, and perform brightness compensation based on the deviation value to achieve the effect of brightness adjustment. It can also be to determine the ratio value of the brightness adjustment based on the current brightness value of the original image, and adjust the brightness of each pixel based on the ratio value. It can also be to input the original image into a pre-trained brightness adjustment model to obtain the first image after brightness adjustment output by the model. The specific adjustment method is not specifically limited here.

[0196] In this way, before eliminating the interference of uneven ceramic powder on image clarity, the brightness of the original image taken during the battery cell winding process can also be adjusted to further improve the accuracy of subsequent image edge capture and improve the robustness of battery cell winding detection.

[0197] In some embodiments, performing brightness adjustment processing on the original image to obtain the first image includes:

[0198] Extract the original image according to the preset extraction frame to obtain the target area;

[0199] Determine an average value of pixel information of the target area according to pixel information in the target area, where the pixel information is used to represent the brightness of the original image;

[0200] Determine the pixel information deviation value according to the pixel information average value and the preset pixel information standard value;

[0201] According to the pixel information deviation value, the pixel information in the target area is updated to obtain a first image.

[0202] In this embodiment, a preset extraction frame of a preset size may be set, and a pixel information standard value may also be preset, and the pixel information standard value may be used to represent the standard brightness of the image.

[0203] The original image can be extracted according to the preset extraction frame to obtain a target area of ​​a preset size. The average pixel information of the target area can be calculated based on the pixel information of each pixel in the target area. The pixel information can be used to characterize the brightness of the original image, for example, the pixel information can be a pixel value, an RGB value, a gray value, a brightness value, etc.

[0204] The difference between the pixel information average value and the preset pixel information standard value can be determined as the pixel information deviation value. And the pixel information in the target area can be updated according to the pixel information deviation value, and the calculation formula can be: g':=g*Mult+Add.

[0205] Among them, g' is the updated pixel information, g is the pixel information before updating, Mult is the proportional coefficient, which can be set according to actual needs, and Add is the pixel information deviation value.

[0206] The entire original image is traversed, and the pixel information of each pixel in the original image is updated to obtain a first image.

[0207] In this way, the pixel information deviation value can be determined according to the pixel information average value in the preset extraction frame and the preset pixel information standard value, so that the image brightness can be compensated according to the pixel information deviation value to achieve the purpose of adjusting the image brightness.

[0208] In some embodiments, performing brightness adjustment processing on the original image to obtain the first image includes:

[0209] Performing brightness adjustment processing on the original image to obtain a second image;

[0210] Perform image enhancement processing on the second image to obtain the first image.

[0211] In this embodiment, the original image may be first brightness adjusted to obtain a second image with appropriate brightness, and then the second image may be enhanced to enhance the contrast of the edge of the second image to obtain a first image with clearer and more prominent boundary lines.

[0212] In this way, for the image after brightness adjustment, image enhancement processing can also be performed to enhance the edge contrast, further improve the subsequent image edge capture accuracy, and improve the robustness of battery cell winding detection.

[0213] In some embodiments, performing image enhancement processing on the second image to obtain the first image includes:

[0214] Acquiring pixel information of the second image;

[0215] According to a preset convolution kernel, filtering is performed on the pixel information of the second image to obtain filtered pixel information;

[0216] Determine a difference between pixel information of the second image and pixel information after filtering;

[0217] According to the difference, the pixel information of the second image is updated to obtain the first image.

[0218] In this embodiment, the pixel information of the second image can be obtained, wherein the pixel information can be a pixel value, an RGB value, a gray value, a brightness value, etc., which is not specifically limited here. The following description will be made by taking the pixel information as a gray value as an example, wherein the gray value of the second image can be as follows: Figure 6a shown.

[0219] The second image can be filtered according to a preset convolution kernel. The preset convolution kernel can be set according to actual needs. In some examples, a 1×1, 3×3, or 5×5 convolution kernel can be selected for filtering according to needs. For example, taking the preset convolution kernel as a 3×3 convolution kernel as an example, the pixel information of the second image is filtered to obtain the filtered pixel information. The gray value after filtering can be as follows: Figure 6b shown.

[0220] The difference of each pixel can be calculated based on the pixel information of each pixel in the second image and the pixel information of each pixel after filtering. The difference of the gray value of each pixel can be calculated as follows: Figure 6c shown.

[0221] The pixel information of the second image can be updated according to the difference to obtain the first image. The calculation formula can be: res=(orig-mean)*Factor+orig.

[0222] Among them, res is the grayscale value of the first image, orig is the grayscale value of the second image, mean is the grayscale value after filtering, and Factor is the coefficient. The coefficient can be set according to actual needs and the value can be 0.8~1.2.

[0223] In some examples, taking the coefficient Factor as 1 as an example, the grayscale value of the first image can be as follows: Figure 6d As shown. Combined Figure 6a-6d As shown, in the second image, the grayscale value difference of pixels adjacent to the boundary line is 155, while after image enhancement processing, the grayscale value difference of pixels adjacent to the boundary line in the first image is 212, which effectively enhances the contrast of the boundary line.

[0224] In this way, the difference between the pixel information of the image and the pixel information after filtering can be calculated, and the pixel information can be enhanced according to the difference to achieve the purpose of enhancing the edge contrast.

[0225] In some embodiments, the pixel information is a grayscale value. In this way, brightness adjustment and image enhancement processing can be performed directly based on the grayscale value of the image after grayscale processing, which makes calculation more convenient and effectively saves computing resources.

[0226] In some embodiments, after filtering the first image according to the target convolution kernel to obtain the target image, the method may further include:

[0227] Perform grayscale processing on the target image to obtain a grayscale image;

[0228] Determine the grayscale average values ​​of a plurality of pixel groups according to the grayscale value of each pixel point in the grayscale image, wherein each pixel group includes pixels in the grayscale image that are located in the extension direction of the boundary line of the edge grabbing;

[0229] According to a preset derivative convolution kernel, a grayscale average value of multiple pixel groups is derivatized to obtain first-order derivatives of the multiple pixel groups;

[0230] Traversing the first-order derivatives of multiple pixel groups, determining a target pixel group whose absolute value of the first-order derivative is greater than a preset edge capture threshold;

[0231] Generate a grab bounding box based on the target pixel group.

[0232] In this embodiment, the target image may be gray-processed to obtain a gray-scale image, wherein the gray-scale value of each pixel in the gray-scale image may be as shown in Table 1:

[0233] Table 1

[0234]

[0235] It can be understood that each row in Table 1 represents pixels located in a direction of the width of the ceramic powder, and each column represents pixels located in a direction of the height of the ceramic powder.

[0236] The grayscale average values ​​of the plurality of pixel groups may be determined according to the grayscale values ​​of each pixel point in the grayscale image, wherein each pixel group includes pixels in the grayscale image that are located in the extension direction of the boundary line of the edge grabbing. Taking the extension direction of the boundary line of the edge grabbing as the direction of the height of the ceramic powder as an example, the plurality of pixel groups may include pixel group A, pixel group B to pixel group E, wherein pixel group A may include pixels A1 to A4.

[0237] The grayscale averages of multiple pixel groups can be shown in Table 2:

[0238] Table 2

[0239]

[0240] The grayscale average values ​​of multiple pixel groups can be derivatized according to the preset derivative convolution kernel to obtain the first-order derivatives of the multiple pixel groups. The size of the preset derivative convolution kernel can be set according to actual needs and is not specifically limited here. Taking the derivative convolution kernel of 1×1 as an example, the first-order derivatives of multiple pixel groups can be shown in Table 3:

[0241] Table 3:

[0242]

[0243] The first-order derivatives of multiple pixel groups can be traversed to determine a target pixel group whose absolute value of the first-order derivative is greater than a preset edge grabbing threshold. At this time, the pixels in the target pixel group can be considered as edge points, that is, all pixels in the target pixel group can be considered as pixels on the boundary line of edge grabbing, and a grabbing frame can be generated according to the target pixel group.

[0244] In this way, the first-order derivative corresponding to the target image can be obtained by performing grayscale processing and then taking the derivative. Since the target image is clearer, the value of the first-order derivative is more accurate, so the accurate edge point can be determined based on the first-order derivative, thereby improving the edge capture accuracy.

[0245] Figure 7 FIG. 1 shows an overall flow chart of a method for processing a wound cell image provided by an embodiment of the present application. Figure 7 As shown, the method for processing the wound battery cell image may include:

[0246] Step 701, brightness adjustment. The original image can be extracted according to a preset extraction frame to obtain a target area; the average grayscale value in the target area is calculated; the average grayscale value and a preset grayscale standard value are determined as a deviation value; and the grayscale value of the target area in the second image is calculated according to the deviation value.

[0247] Step 702, image enhancement. The grayscale value of the second image may be filtered according to a preset convolution kernel to obtain a filtered grayscale value; a difference may be calculated according to the grayscale value of the second image and the filtered grayscale value; and the sum of the difference and the grayscale value of the second image may be determined as the grayscale value of the first image.

[0248] Step 703, ceramic powder filtering: The size parameter of the largest ceramic powder area in the first image can be determined; according to the size parameter, a target convolution kernel of a specified size is determined; and the first image is filtered according to the target convolution kernel to obtain a target image.

[0249] like Figure 4b As shown, for the original image and the target image whose boundary lines extend along the height direction of the ceramic powder area, the pixel average values ​​in the vertical direction of the image can be calculated respectively, and the convolution operation can be performed using the preset derivative convolution kernel to obtain the first-order derivative value of the grayscale, that is, the first-order derivative.

[0250] right Figure 4b The original image and the target image shown in the above calculations show that the derivative peak of the original image is -1.91, and the derivative peak of the target image is -1.55. Compared with the original image, the peak of the derivative peak of the target image becomes slower and shorter. It can be understood that in the edge grabbing operation, if the corresponding value of the set edge grabbing threshold is above the absolute value of the number of abnormal peaks, there is no misgrab. If the corresponding value of the set edge grabbing threshold is below the absolute value of the number of abnormal peaks, there may be misgrab. Based on this, for the edge grabbing threshold of the same data, the risk of misgrabbing the target image is low, which effectively improves the edge grabbing accuracy.

[0251] Based on the method for processing a wound battery cell image provided in the above embodiment, the present application also provides an embodiment of a device for processing a wound battery cell image.

[0252] Figure 8 A schematic structural diagram of a device for processing a wound battery cell image provided in another embodiment of the present application is shown. For ease of explanation, only the portion related to the embodiment of the present application is shown.

[0253] Reference Figure 8 , the apparatus 1000 for processing the wound cell image may include:

[0254] A shooting module 1001 is used to shoot a first image of a battery cell during winding when a winding machine is used to wind a battery cell, and the battery cell includes a diaphragm with ceramic powder attached thereto;

[0255] A first determination module 1002 is used to determine a size parameter of a ceramic powder region in the first image, where the ceramic powder region is a region corresponding to the ceramic powder in the first image, and the size parameter of the ceramic powder region includes at least one of a ceramic powder width and a ceramic powder height;

[0256] The second determination module 1003 is used to determine the target convolution kernel according to the size parameter of the ceramic powder area, wherein when the size parameter of the ceramic powder area includes the ceramic powder width, the ceramic powder width is determined as the width of the target convolution kernel, and when the size parameter of the ceramic powder area includes the ceramic powder height, the ceramic powder height is determined as the height of the target convolution kernel;

[0257] The processing module 1004 is used to perform filtering processing on the first image according to the target convolution kernel to obtain a target image.

[0258] In this embodiment, the size of the convolution kernel can be determined according to the size parameters of the ceramic powder area in the first image to obtain the target convolution kernel. The target convolution kernel is used for filtering processing to reduce the interference of the ceramic powder on the clarity of the first image and obtain a clearer target image, thereby improving the accuracy of subsequent image edge capture and ensuring the robustness of battery cell winding detection.

[0259] In some embodiments, when the size parameter of the ceramic powder area includes the ceramic powder height, the second determining module 1003 is further configured to:

[0260] When the edge-grabbing boundary line in the first image extends in the direction of the ceramic powder height, the ceramic powder height is determined as the height of the target convolution kernel, and the preset convolution kernel width is determined as the width of the target convolution kernel to obtain the target convolution kernel.

[0261] In this way, according to the different requirements of edge grasping directions, for the left and right edge grasping situations, the height of the ceramic powder can be selected to determine the target convolution kernel, thereby ensuring the rationality of the target convolution kernel and further improving the clarity of the target image after filtering processing.

[0262] In some embodiments, when the size parameter of the ceramic powder region includes the ceramic powder width, the second determining module 1003 is further configured to:

[0263] When the edge-grabbing boundary line in the first image extends in the direction of the ceramic powder width, the preset convolution kernel height is determined as the height of the target convolution kernel, and the ceramic powder width is determined as the width of the target convolution kernel to obtain the target convolution kernel.

[0264] In this way, according to the different requirements of edge grabbing directions, for the upper and lower edge grabbing situations, the width of the ceramic powder can be selected to determine the target convolution kernel, thereby ensuring the rationality of the target convolution kernel and further improving the clarity of the target image after filtering processing.

[0265] In some embodiments, when there are at least two edge-grabbing boundary lines in the first image, at least one boundary line extends in a direction of a ceramic powder height, and at least one boundary line extends in a direction of a ceramic powder width, the size parameters of the ceramic powder region include a ceramic powder width and a ceramic powder height, and the target convolution kernel includes a first convolution kernel and a second convolution kernel;

[0266] The processing module 1004 is further configured to:

[0267] Performing filtering processing on the first image according to the first convolution kernel to obtain a first preliminary image, wherein the height of the first convolution kernel is the height of the ceramic powder, and the width of the first convolution kernel is the preset convolution kernel width;

[0268] The first preliminary image is filtered according to the second convolution kernel to obtain a target image, the height of the second convolution kernel is a preset convolution kernel height, and the width of the second convolution kernel is a ceramic powder width.

[0269] In this embodiment, two convolution kernels can be determined according to the height or width of the ceramic powder, and filtering is performed once using the two convolution kernels respectively, which can further improve the clarity of the target image and meet the edge capture requirements in different directions at the same time.

[0270] In some embodiments, when there are at least two edge-grabbing boundary lines in the first image, at least one boundary line extends in a direction of a ceramic powder height, and at least one boundary line extends in a direction of a ceramic powder width, the size parameters of the ceramic powder region include a ceramic powder width and a ceramic powder height, and the target convolution kernel includes a first convolution kernel and a second convolution kernel;

[0271] The processing module 1004 is further configured to:

[0272] Performing filtering processing on the first image according to the second convolution kernel to obtain a second preliminary image, wherein the height of the second convolution kernel is a preset convolution kernel height, and the width of the second convolution kernel is a ceramic powder width;

[0273] The second primary image is filtered according to the first convolution kernel to obtain a target image, the height of the first convolution kernel is the height of the ceramic powder, and the width of the first convolution kernel is the preset convolution kernel width.

[0274] In this embodiment, two convolution kernels can be determined according to the height or width of the ceramic powder, and filtering is performed once using the two convolution kernels respectively, which can further improve the clarity of the target image and meet the edge capture requirements in different directions at the same time.

[0275] In some embodiments, when the first image includes at least two ceramic powder regions, the second determining module 1003 is further configured to:

[0276] Determine the area of ​​each of the at least two ceramic powder regions;

[0277] Determine the ceramic powder region corresponding to the maximum area as the target ceramic powder region;

[0278] At least one of a ceramic powder width and a ceramic powder height corresponding to the target ceramic powder region is determined as a size parameter of the ceramic powder region in the first image.

[0279] In this way, the size parameters of the ceramic powder area can be determined according to the ceramic powder area with the largest area, so as to obtain a target convolution kernel of a more reasonable size to ensure the clarity of the filtered target image.

[0280] In some embodiments, the apparatus 1000 for processing the wound cell image further includes:

[0281] An acquisition module, for acquiring an original image of the winding of the battery cell before determining the size parameters of the ceramic powder area in the first image when the first image of the winding of the battery cell is acquired;

[0282] The processing module 1004 is further used to perform brightness adjustment processing on the original image to obtain a first image.

[0283] In this way, before eliminating the interference of uneven ceramic powder on image clarity, the brightness of the original image taken during the battery cell winding process can also be adjusted to further improve the accuracy of subsequent image edge capture and improve the robustness of battery cell winding detection.

[0284] In some embodiments, the processing module 1004 is further configured to:

[0285] Extract the original image according to the preset extraction frame to obtain the target area;

[0286] Determine an average value of pixel information of the target area according to pixel information in the target area, where the pixel information is used to represent the brightness of the original image;

[0287] Determine the pixel information deviation value according to the pixel information average value and the preset pixel information standard value;

[0288] According to the pixel information deviation value, the pixel information in the target area is updated to obtain a first image.

[0289] In this way, the pixel information deviation value can be determined according to the pixel information average value in the preset extraction frame and the preset pixel information standard value, so that the image brightness can be compensated according to the pixel information deviation value to achieve the purpose of adjusting the image brightness.

[0290] In some embodiments, the processing module 1004 is further configured to:

[0291] Performing brightness adjustment processing on the original image to obtain a second image;

[0292] Perform image enhancement processing on the second image to obtain the first image.

[0293] In this way, for the image after brightness adjustment, image enhancement processing can also be performed to enhance the edge contrast, further improve the subsequent image edge capture accuracy, and improve the robustness of battery cell winding detection.

[0294] In some embodiments, the processing module 1004 is further configured to:

[0295] Acquiring pixel information of the second image;

[0296] According to a preset convolution kernel, filtering is performed on the pixel information of the second image to obtain filtered pixel information;

[0297] Determine a difference between pixel information of the second image and pixel information after filtering;

[0298] According to the difference, the pixel information of the second image is updated to obtain the first image.

[0299] In this way, the difference between the pixel information of the image and the pixel information after filtering can be calculated, and the pixel information can be enhanced according to the difference to achieve the purpose of enhancing the edge contrast.

[0300] In some embodiments, the processing module 1004 is further configured to:

[0301] After filtering the first image according to the target convolution kernel to obtain the target image, grayscale processing is performed on the target image to obtain a grayscale image;

[0302] The device 1000 for processing the wound cell image further includes:

[0303] A third determination module is used to determine the grayscale average value of a plurality of pixel groups according to the grayscale value of each pixel point in the grayscale image, wherein each pixel group includes pixels in the grayscale image that are located in the extension direction of the boundary line of the edge grabbing;

[0304] A derivation module, used to perform derivation processing on the grayscale average values ​​of multiple pixel groups according to a preset derivation convolution kernel to obtain first-order derivatives of the multiple pixel groups;

[0305] A fourth determination module, configured to traverse the first-order derivatives of the plurality of pixel groups and determine a target pixel group whose absolute value of the first-order derivative is greater than a preset edge capture threshold;

[0306] The generation module is used to generate a grabbing border according to the target pixel group.

[0307] In this way, the first-order derivative corresponding to the target image can be obtained by performing grayscale processing and then taking the derivative. Since the target image is clearer, the value of the first-order derivative is more accurate, so the accurate edge point can be determined based on the first-order derivative, thereby improving the edge capture accuracy.

[0308] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application, and are devices corresponding to the above-mentioned method for processing the wound battery cell image. All implementation methods in the above-mentioned method embodiment are applicable to the embodiment of the device. Its specific functions and technical effects can be found in the method embodiment part, which will not be repeated here.

[0309] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0310] Fig. 9 A schematic diagram of the hardware structure of an electronic device provided in yet another embodiment of the present application is shown.

[0311] The electronic device 1100 may include a processor 1101 and a memory 1102 storing programs or instructions. When the processor 1101 executes the program, the steps in any of the above method embodiments are implemented.

[0312] Exemplarily, the program may be divided into one or more modules / units, one or more modules / units are stored in the memory 1102, and executed by the processor 1101 to complete the present application. One or more modules / units may be a series of program instruction segments capable of completing a specific function, and the instruction segments are used to describe the execution process of the program in the device.

[0313] Specifically, the processor 1101 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0314] The memory 1102 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 1102 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 1102 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 1102 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 1102 is a non-volatile solid-state memory.

[0315] The memory may include read-only memory (ROM), random access memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical or other physical / tangible memory storage devices. Thus, typically, the memory includes one or more tangible (non-transitory) readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to an aspect of the present disclosure.

[0316] The processor 1101 implements any one of the methods in the above embodiments by reading and executing the program or instruction stored in the memory 1102 .

[0317] In one example, the electronic device may further include a communication interface 1103 and a bus 1104. The processor 1101, the memory 1102, and the communication interface 1103 are connected via the bus 1104 and communicate with each other.

[0318] The communication interface 1103 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0319] Bus 1104 includes hardware, software or both, and couples the components of online data traffic billing equipment to each other. For example, but not limitation, the bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front-side bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnect (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. Where appropriate, bus 1104 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the present application considers any suitable bus or interconnection.

[0320] In addition, in combination with the method in the above embodiment, the embodiment of the present application may provide a machine-readable storage medium for implementation. The machine-readable storage medium stores a program or instruction; when the program or instruction is executed by a processor, any one of the methods in the above embodiment is implemented. The machine-readable storage medium can be read by a machine such as a computer.

[0321] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0322] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0323] An embodiment of the present application provides a computer program product, which is stored in a machine-readable storage medium. The program product is executed by at least one processor to implement the various processes of the above-mentioned method embodiment and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0324] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0325] The functional modules shown in the structural block diagram described above can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application-specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier. "Machine-readable medium" may include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROMs, flash memories, erasable ROMs (EROMs), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer grid such as the Internet, an intranet, etc.

[0326] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0327] Aspects of the present disclosure are described above with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and program products according to the embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by a computer program or instruction. These programs or instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the functions / actions specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0328] Although the present application has been described with reference to preferred embodiments, various modifications may be made thereto and parts thereof may be replaced with equivalents without departing from the scope of the present application. In particular, the various technical features mentioned in the various embodiments may be combined in any manner as long as there is no structural conflict. The present 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 processing a wound battery cell image, characterized in that: include: When a winding machine winds a battery cell, and the battery cell includes a separator with ceramic powder attached thereto, capturing a first image of the battery cell during the winding process; Determine size parameters of a ceramic powder region in the first image, the ceramic powder region being a region corresponding to the ceramic powder in the first image, the size parameters of the ceramic powder region including at least one of a ceramic powder width and a ceramic powder height, and in the case where there is at least one edge-grabbing boundary line extending in a direction of the ceramic powder height in the first image, the size parameters of the ceramic powder region include the ceramic powder height, and in the case where there is at least one edge-grabbing boundary line extending in a direction of the ceramic powder width in the first image, the size parameters of the ceramic powder region include the ceramic powder width; Determine a target convolution kernel according to the size parameters of the ceramic powder area, wherein, when the size parameters of the ceramic powder area include the ceramic powder width, the ceramic powder width is determined as the width of the target convolution kernel, and when the size parameters of the ceramic powder area include the ceramic powder height, the ceramic powder height is determined as the height of the target convolution kernel; The first image is filtered according to the target convolution kernel to obtain a target image.

2. The method according to claim 1, characterized in that In a case where the size parameter of the ceramic powder area includes the height of the ceramic powder, determining the target convolution kernel according to the size parameter of the ceramic powder area includes: When the edge-grabbing boundary line in the first image extends along the direction of the ceramic powder height, the ceramic powder height is determined as the height of the target convolution kernel, and the preset convolution kernel width is determined as the width of the target convolution kernel to obtain the target convolution kernel.

3. The method according to claim 1, characterized in that In a case where the size parameter of the ceramic powder region includes the ceramic powder width, determining the target convolution kernel according to the size parameter of the ceramic powder region includes: When the edge-grabbing boundary line in the first image extends along the direction of the ceramic powder width, the preset convolution kernel height is determined as the height of the target convolution kernel, and the ceramic powder width is determined as the width of the target convolution kernel to obtain the target convolution kernel.

4. The method according to claim 1, characterized in that: In the case where there are at least two edge-grabbing boundary lines in the first image, at least one boundary line extends along the direction of the ceramic powder height, and at least one boundary line extends along the direction of the ceramic powder width, the size parameters of the ceramic powder area include the ceramic powder width and the ceramic powder height, and the target convolution kernel includes a first convolution kernel and a second convolution kernel; The filtering process is performed on the first image according to the target convolution kernel to obtain a target image, and further includes: Performing filtering processing on the first image according to the first convolution kernel to obtain a first preliminary image, wherein the height of the first convolution kernel is the height of the ceramic powder, and the width of the first convolution kernel is a preset convolution kernel width; The first preliminary image is filtered according to the second convolution kernel to obtain a target image, the height of the second convolution kernel is a preset convolution kernel height, and the width of the second convolution kernel is the width of the ceramic powder.

5. The method according to claim 1, characterized in that In the case where there are at least two edge-grabbing boundary lines in the first image, at least one boundary line extends along the direction of the ceramic powder height, and at least one boundary line extends along the direction of the ceramic powder width, the size parameters of the ceramic powder area include the ceramic powder width and the ceramic powder height, and the target convolution kernel includes a first convolution kernel and a second convolution kernel; The filtering process is performed on the first image according to the target convolution kernel to obtain a target image, and further includes: Performing filtering processing on the first image according to the second convolution kernel to obtain a second preliminary image, wherein the height of the second convolution kernel is a preset convolution kernel height, and the width of the second convolution kernel is the width of the ceramic powder; The second primary image is filtered according to the first convolution kernel to obtain a target image, the height of the first convolution kernel is the height of the ceramic powder, and the width of the first convolution kernel is a preset convolution kernel width.

6. The method according to claim 1, characterized in that In a case where the first image includes at least two ceramic powder regions, determining size parameters of the ceramic powder regions in the first image includes: Determine the area of ​​each of the at least two ceramic powder regions; Determine the ceramic powder region corresponding to the maximum area as the target ceramic powder region; At least one of a ceramic powder width and a ceramic powder height corresponding to the target ceramic powder area is determined as a size parameter of the ceramic powder area in the first image.

7. The method according to claim 1, characterized in that Before determining the size parameter of the ceramic powder area in the first image, the method further includes: Acquire an original image of the battery cell winding; Perform brightness adjustment processing on the original image to obtain the first image.

8. The method according to claim 7, characterized in that The step of performing brightness adjustment processing on the original image to obtain the first image includes: Extract the original image according to a preset extraction frame to obtain a target area; Determine an average value of pixel information of the target area according to pixel information in the target area, wherein the pixel information is used to represent the brightness of the original image; Determining a pixel information deviation value according to the pixel information average value and a preset pixel information standard value; According to the pixel information deviation value, the pixel information in the target area is updated to obtain the first image.

9. The method according to claim 7, characterized in that: The step of performing brightness adjustment processing on the original image to obtain the first image includes: Performing brightness adjustment processing on the original image to obtain a second image; Perform image enhancement processing on the second image to obtain the first image.

10. The method according to claim 9, characterized in that The performing image enhancement processing on the second image to obtain the first image includes: Acquire pixel information of the second image; According to a preset convolution kernel, filtering is performed on the pixel information of the second image to obtain filtered pixel information; Determine a difference between pixel information of the second image and the filtered pixel information; According to the difference, pixel information of the second image is updated to obtain the first image.

11. The method according to any one of claims 1 to 10, characterized in that After filtering the first image according to the target convolution kernel to obtain the target image, the method further includes: Performing grayscale processing on the target image to obtain a grayscale image; Determine the grayscale average values ​​of a plurality of pixel groups according to the grayscale value of each pixel point in the grayscale image, wherein each pixel group includes pixels in the grayscale image that are located in the extension direction of the boundary line of the edge grabbing; According to a preset derivative convolution kernel, a grayscale average value of the plurality of pixel groups is derivatized to obtain first-order derivatives of the plurality of pixel groups; Traversing the first-order derivatives of the plurality of pixel groups, and determining a target pixel group whose absolute value of the first-order derivative is greater than a preset edge capture threshold; A grabbing frame is generated according to the target pixel group.

12. A device for processing a wound battery cell image, characterized in that: include: A shooting module, used for shooting a first image of a battery cell during a winding process when a winding machine is used to wind a battery cell, wherein the battery cell includes a diaphragm with ceramic powder attached thereto; a first determination module, configured to determine size parameters of a ceramic powder region in the first image, the ceramic powder region being a region corresponding to the ceramic powder in the first image, the size parameters of the ceramic powder region including at least one of a ceramic powder width and a ceramic powder height, and in the case where there is at least one edge-grabbing boundary line extending in a direction of the ceramic powder height in the first image, the size parameters of the ceramic powder region including the ceramic powder height, and in the case where there is at least one edge-grabbing boundary line extending in a direction of the ceramic powder width in the first image, the size parameters of the ceramic powder region including the ceramic powder width; a second determination module, configured to determine a target convolution kernel according to a size parameter of the ceramic powder area, wherein, when the size parameter of the ceramic powder area includes the ceramic powder width, the ceramic powder width is determined as the width of the target convolution kernel, and when the size parameter of the ceramic powder area includes the ceramic powder height, the ceramic powder height is determined as the height of the target convolution kernel; A processing module is used to filter the first image according to the target convolution kernel to obtain a target image.

13. An electronic device, characterized in that: The device comprises: a processor and a memory storing programs or instructions; When the processor executes the program or instruction, the method according to any one of claims 1 to 11 is implemented.

14. A machine-readable storage medium, characterized in that: The machine-readable storage medium stores a program or instruction, and when the program or instruction is executed by a processor, the method according to any one of claims 1 to 11 is implemented.

15. A computer program product, characterized in that When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the method according to any one of claims 1 to 11.

Images