CN116385423A

CN116385423A - Pole piece detection method and device, terminal equipment and storage medium

Info

Publication number: CN116385423A
Application number: CN202310429140.XA
Authority: CN
Inventors: 蔡翔; 徐建喜
Original assignee: Xiamen Hithium Energy Storage Technology Co Ltd
Current assignee: Xiamen Hithium Energy Storage Technology Co Ltd
Priority date: 2023-04-20
Filing date: 2023-04-20
Publication date: 2023-07-04

Abstract

The application provides a pole piece detection method and device, terminal equipment and storage medium. The pole piece detection method comprises the following steps: acquiring an initial image of a pole piece; performing color space transformation on the initial image after the filtering treatment to obtain an intermediate image, wherein the color space of the intermediate image is an HSV color space, and the HSV color space comprises HSV values corresponding to all pixel points of the intermediate image; performing binary processing on the intermediate image according to the HSV value of the intermediate image and a preset HSV threshold range to determine at least one abnormal region corresponding to an abnormal father type in the pole piece, wherein the preset HSV threshold ranges corresponding to different abnormal father types are different, and each abnormal father type comprises at least one abnormal subtype; performing rectangular template matching on at least one abnormal region to determine at least one rectangular region corresponding to the at least one abnormal region; and comparing according to the at least one rectangular area and the preset parameter value to determine the abnormal subtype of the at least one abnormal area.

Description

Pole piece detection method and device, terminal equipment and storage medium

Technical Field

The application relates to the technical field of energy storage batteries, in particular to a pole piece detection method and device, terminal equipment and a storage medium.

Background

Along with popularization of new energy, new energy batteries are increasingly widely used. The produced battery pole piece has a large number of defects, and the quality of the pole piece determines the performance and service life of the battery, so that the pole piece needs to be detected to remove the pole piece with abnormal severity. In general, when detecting an abnormality in a pole piece, the pole piece is photographed and detected to confirm the position and cause of the abnormality, but the problem of photographing light and resolution easily causes erroneous judgment of an abnormal area. Therefore, how to accurately and efficiently detect the abnormal situation of the pole piece becomes a problem to be solved.

Disclosure of Invention

The application provides a pole piece detection method and device, terminal equipment and storage medium, which are at least used for solving the problem of low determination accuracy of pole piece abnormal areas in the pole piece detection process.

In a first aspect, the present application provides a pole piece detection method. The pole piece detection method comprises the following steps: acquiring an initial image of a pole piece; performing color space transformation on the initial image after filtering treatment to obtain an intermediate image, wherein the color space of the intermediate image is an HSV color space which comprises HSV values corresponding to all pixel points of the intermediate image; performing binary processing on the intermediate image according to the HSV value of the intermediate image and a preset HSV threshold range to determine at least one abnormal region corresponding to an abnormal father type in the pole piece, wherein the preset HSV threshold range corresponding to the abnormal type is different, and each abnormal father type comprises at least one abnormal subtype; performing rectangular template matching on the at least one abnormal region to determine at least one rectangular region corresponding to the at least one abnormal region; and comparing according to the at least one rectangular area and the preset parameter value to determine the abnormal subtype of the at least one abnormal area.

In a possible implementation manner, the binary processing is performed on the intermediate image according to the HSV value of the intermediate image and the preset HSV threshold range, so as to determine at least one abnormal region corresponding to an abnormal parent type in the pole piece, which includes: determining an abnormal pixel point set according to the HSV values corresponding to the pixels of the intermediate image and the preset HSV threshold range, wherein one abnormal father type corresponds to one abnormal pixel point set, and the abnormal pixel point set comprises a plurality of pixel points belonging to the same abnormal father type; performing binary processing on the intermediate image according to the abnormal pixel point set to obtain a binary image, wherein one abnormal pixel point set corresponds to one binary image; and determining the at least one abnormal region corresponding to the abnormal father type according to the binary image and the abnormal pixel point set.

It can be seen that the abnormal parent types of pole pieces include a plurality of types, each abnormal parent type corresponding to a preset HSV threshold range. One or more exception regions corresponding to the exception parent type are determined for each exception parent type. For example, under the condition that one or more abnormal areas of an abnormal father type are determined, the HSV values corresponding to the pixels of the intermediate image can be compared with a preset HSV threshold range one by one, the pixels with the HSV values in the preset HSV threshold range are classified into an abnormal pixel point set of the abnormal father type, the intermediate image is subjected to binary processing according to each abnormal pixel point in the abnormal pixel point set to obtain a binary image, and at least one abnormal area is determined according to the binary image and the abnormal pixel point set. The initial image is converted into an intermediate image of an HSV color space, and abnormal pixel points can be accurately and efficiently distinguished according to HSV values of the pixel points, so that the accuracy and the efficiency of abnormal region identification are improved.

In one possible implementation manner, the preset HSV threshold range includes a first threshold range, a second threshold range, and a third threshold range, the HSV color space includes an H channel, an S channel, and a V channel, the first threshold range corresponds to the H channel, the second threshold range corresponds to the S channel, the third threshold range corresponds to the V channel, and the determining the abnormal pixel point set according to the HSV value corresponding to each pixel point of the intermediate image and the preset HSV threshold range includes: and acquiring pixel points of the intermediate image, wherein the H channel value is in the first threshold range, the S channel value is in the second threshold range and the V channel value is in the third threshold range, so as to form the abnormal pixel point set.

It can be seen that the HSV color space of the intermediate image is split into an H-channel, an S-channel and a V-channel, where the H-channel corresponds to a first threshold range of the preset HSV threshold ranges, the S-channel corresponds to a second threshold range of the preset HSV threshold ranges, and the V-channel corresponds to a third threshold range of the preset HSV threshold ranges, and for each pixel point of the intermediate image, it is determined whether the H-channel value, the S-channel value and the V-channel value are located within the respective corresponding threshold ranges, for example, the S-channel value at the pixel point (0, 0) satisfies the second threshold range, the V-channel value satisfies the third threshold range, and the H-channel value is located outside the first threshold range, so that the pixel point (0, 0) is not an abnormal pixel point. Whether the pixel points are abnormal pixel points or not is determined through different single channels of the HSV color space, so that the detection precision is higher, the accuracy is higher, and the possibility of misjudgment of an abnormal area is reduced.

In one possible implementation manner, the pixel values in the binary image include a first value and a second value, the first value and the second value are different, the binary processing is performed on the intermediate image according to the abnormal pixel point set to obtain a binary image, and the method includes: setting the pixel values of the pixel points belonging to the abnormal pixel point set in the intermediate image as the first numerical value; and setting the pixel values of the pixel points which do not belong to the abnormal pixel point set in the intermediate image as the second numerical value so as to obtain the binary image.

It can be seen that after determining an abnormal pixel point set corresponding to a certain abnormal parent type, the pixel values of the pixels in the abnormal pixel point set (i.e., the abnormal pixel points) are all set to be a first value, and the pixel values of the pixels not belonging to the abnormal pixel point set are set to be a second value, where the first value and the second value are different, for example, the first value is "0", the second value is "255", and in the binary image, the abnormal region appears black, and the non-abnormal region appears white, so that the abnormal region and the non-abnormal region can be intuitively distinguished through the binary image, and the efficiency of determining the abnormal region is effectively improved.

In a possible implementation manner, the determining the at least one abnormal region corresponding to the abnormal parent type according to the binary image and the abnormal pixel point set includes: and carrying out edge recognition on the binary image according to each pixel point in the abnormal pixel point set so as to obtain the at least one abnormal region.

It can be seen that in the binary image, the abnormal region and the non-abnormal region are in different colors, and the outline of the abnormal region is further detected through edge recognition, so that the area size of the abnormal region can be conveniently determined, the total area of the abnormal region corresponding to a certain abnormal father type in the initial image of the pole piece is counted, and the accuracy of recognition of the abnormal region is improved.

In one possible implementation manner, after the binary processing is performed on the intermediate image according to the HSV value of the intermediate image and the preset HSV threshold range to determine at least one abnormal region corresponding to an abnormal parent type in the pole piece, the method further includes: calculating a moment of the at least one anomaly region; determining centroid and area of the at least one anomaly region from the moment of the at least one anomaly region; and determining the number of the at least one abnormal region according to the mass center of the at least one abnormal region.

It can be seen that after determining at least one abnormal region, calculating the moment of each abnormal region to obtain the centroid and the area of the abnormal region, for example, calculating the zero-order moment and the first-order moment of the abnormal region to obtain the centroid of the abnormal region, and after calculating the centroid of the abnormal region, marking the centroid of each abnormal region into an initial image, and determining the abnormal condition of the pole piece through visual data. When the two abnormal areas are closer, the two abnormal areas can be rapidly distinguished through the center of mass marked by each abnormal area, and the situation that the number of the abnormal areas is misjudged is avoided. In addition, the distribution of the abnormal region is analyzed by the area of the abnormal region.

In one possible implementation manner, the performing rectangular template matching on the at least one abnormal region to determine at least one rectangular region corresponding to the at least one abnormal region includes: and performing rectangular template matching on the abnormal region according to the area of the abnormal region and the abnormal pixel point set, and determining a rectangular region corresponding to the abnormal region.

It can be seen that rectangular template matching is performed according to the positions of the abnormal regions corresponding to the abnormal pixel point sets and the areas of the abnormal regions, so as to determine rectangular regions of the abnormal regions, and then the abnormal sub-types of the abnormal regions are determined according to the rectangular regions.

In one possible embodiment, the electrode sheet includes a negative electrode sheet, and in the case that the electrode sheet is the negative electrode sheet, the preset parameter value includes a first parameter value, the first parameter value being an average value of differences between a width of a preset negative electrode sheet and a width of a preset positive electrode sheet; the comparing according to the at least one rectangular area and the preset parameter value to determine the abnormal subtype of the at least one abnormal area comprises the following steps: if the widths of the at least one rectangular area are all larger than the first parameter value, determining that the abnormal subtype of the at least one abnormal area is insufficient in lithium intercalation of the negative electrode sheet; if the widths of the at least one rectangular area are smaller than the first parameter value, determining that the abnormal subtype of the at least one abnormal area is insufficient in the negative electrode sheet clamping; and if at least one rectangular area with the width larger than the first parameter value and at least one rectangular area with the width smaller than the first parameter value exists, determining that the abnormal subtype of the at least one abnormal area is the dislocation of the negative electrode plate.

It can be seen that when the electrode sheet is a negative electrode sheet, the preset parameter value may be a first parameter value, and the first parameter value may be a design reference value of a standard positive and negative electrode sheet, that is, the preset negative electrode sheet is a standard negative electrode sheet, and the preset positive electrode sheet is a standard positive electrode sheet. And comparing the determined widths of the rectangular areas with the first parameter value respectively, if the widths of at least one rectangular area are larger than the first parameter value, indicating that the negative electrode plate is too wide, and the positive electrode plate is too narrow, indicating that the battery capacity is low at the moment, lithium ions move from the positive electrode plate to the negative electrode plate when the battery is charged, the distance is large, the resistance is large, the abnormal condition that lithium ions are not normally inserted into the negative electrode plate due to the fact that lithium ions are not inserted into the negative electrode plate normally can occur, and at the moment, determining the abnormal subtype of at least one abnormal area as the abnormal condition that lithium insertion of the negative electrode plate is insufficient. If the width of at least one rectangular area is larger than the first parameter value, the negative electrode plate is too narrow, namely the lithium ions are not enough in the block of the negative electrode plate, namely the lithium insertion space of the negative electrode plate is insufficient when the battery is charged, the abnormal condition that lithium is separated from the positive electrode plate due to the insufficient lithium insertion space of the negative electrode plate can occur, and at the moment, the abnormal subtype of at least one abnormal area is determined to be the insufficient block of the negative electrode plate. In view of the fact that the dislocation of the negative electrode plate can affect the moving path of lithium ions and cause the lithium ions on the negative electrode plate to have abnormal intercalation, if a plurality of rectangular areas exist, the width of at least one rectangular area is larger than a first parameter value, and the width of at least one rectangular area is smaller than the first parameter value, the dislocation of the negative electrode plate is indicated, and at the moment, the abnormal subtype of at least one abnormal area is determined to be abnormal dislocation of the negative electrode plate. In summary, the abnormal subtype of the abnormal region is further determined according to the first parameter value of the negative electrode plate, so that the negative electrode plate can be conveniently adjusted according to the abnormal subtype.

In one possible implementation manner, the preset parameter value further comprises a second parameter value, wherein the second parameter value is a dislocation threshold value of dislocation of the pole piece due to gravity sinking; and when the pole piece is a negative pole piece, comparing the at least one rectangular area with a preset parameter value to determine an abnormal subtype of the at least one abnormal area, wherein the method comprises the following steps: acquiring a difference value between the width of the rectangular region and the first parameter as a first difference value; and if the first difference value is larger than the second parameter value, determining that the abnormal subtype of the at least one abnormal region is the dislocation of the negative electrode plate.

It can be seen that the second parameter value may be a maximum misalignment threshold for misalignment of the pole piece due to gravitational sag. Wherein the pole piece is a negative pole piece. When the electrode plate is the negative electrode plate, a difference value between the rectangular area and the first parameter value is obtained and is used as a first difference value, the first difference value represents the dislocation size of the negative electrode plate, if the first difference value is larger than the second parameter value, the dislocation size of the negative electrode plate exceeds the maximum dislocation threshold value for dislocation due to gravity sinking, the dislocation of the negative electrode plate is indicated, and the abnormal subtype of at least one abnormal area is determined to be the dislocation of the negative electrode plate. In conclusion, whether the negative plate has the dislocation abnormality or not can be accurately determined according to the first difference value and the second parameter value of the negative plate.

In a second aspect, embodiments of the present application further provide a pole piece detection device. The pole piece detection device comprises an acquisition unit, a filtering unit, a transformation unit, a first determination unit, a second determination unit and a third determination unit. The acquisition unit is used for acquiring an initial image of the pole piece. The transformation unit is used for carrying out color space transformation on the initial image after the filtering processing to obtain an intermediate image, wherein the color space of the intermediate image is an HSV color space, and the HSV color space comprises HSV values corresponding to all pixel points of the intermediate image. The first determining unit is configured to perform binary processing on the intermediate image according to an HSV value of the intermediate image and a preset HSV preset range, so as to determine an abnormal region corresponding to an abnormal father type in the pole piece, where the preset HSV threshold ranges corresponding to different abnormal father types are different, and each abnormal father type includes at least one abnormal subtype; the second determining unit is used for performing rectangular template matching on the at least one abnormal region to determine at least one rectangular region corresponding to the at least one abnormal region; the third determining unit is used for comparing the at least one rectangular area with a preset parameter value to determine the abnormal subtype of the at least one abnormal area.

In a third aspect, embodiments of the present application further provide a terminal device. The terminal device comprises a processor and a memory, the processor and the memory being interconnected, wherein the memory is adapted to store a computer program comprising program instructions, the processor being configured to invoke the program instructions to perform the pole piece detection method according to the first aspect.

In a fourth aspect, embodiments of the present application also provide a computer-readable storage medium. The computer readable storage medium stores a computer program comprising program instructions which, when executed by a processor, cause the processor to perform the pole piece detection method according to the first aspect.

According to the pole piece detection method, the pole piece detection device, the terminal equipment and the computer readable storage medium, the initial image after filtering is subjected to color space transformation to obtain the intermediate image of the HSV color space, for each abnormal father type, abnormal pixel points are determined according to HSV values of all pixel points in the intermediate image and a preset HSV threshold range, the intermediate image after the abnormal pixel points are determined is subjected to binary processing, at least one abnormal area corresponding to one abnormal father type in the pole piece can be accurately and efficiently determined, at least one rectangular area is determined by performing rectangular template matching on the at least one abnormal area, the rectangular area and preset parameters are utilized for comparison, and the abnormal subtype of the at least one abnormal area is determined, so that targeted adjustment can be conveniently performed according to the abnormal subtype in the follow-up process.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below.

Fig. 1 is a schematic flow chart of a pole piece detection method provided in an embodiment of the present application;

fig. 2 is a schematic diagram of an initial image of a pole piece detection method according to an embodiment of the present application;

fig. 3 is a schematic diagram of a binary image of a pole piece detection method according to an embodiment of the present application;

fig. 4 is a schematic diagram of an initial image and a target image of a pole piece detection method according to an embodiment of the present application;

fig. 5 is a schematic diagram of a pole piece detection device provided in an embodiment of the present application;

fig. 6 is a schematic diagram of a composition of a terminal device according to an embodiment of the present application.

Reference numerals:

the pole piece detection device 500, the acquisition unit 501, the transformation unit 502, the first determination unit 503, the second determination unit 504, the third determination unit 505, the calculation unit 506, the fourth determination unit 507, and the fifth determination unit 508;

terminal device 600, bus 10, processor 30, memory 50, communication interface 70.

Detailed Description

The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all, of the embodiments of the present application. All other embodiments, based on the embodiments herein, which would be apparent to one of ordinary skill in the art without undue burden are within the scope of the present application.

The following description of the embodiments refers to the accompanying drawings, which illustrate specific embodiments that can be used to practice the present application. Directional terms referred to in this application, such as "upper", "lower", "front", "rear", "left", "right", "inner", "outer", "side", etc., are merely directions referring to the attached drawings, and thus, directional terms are used for better, more clear description and understanding of the present application, rather than indicating or implying that the apparatus or element being referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present application.

Furthermore, the numbering of the components itself, e.g., "first," "second," etc., herein is merely used to distinguish between the described objects and does not have any sequential or technical meaning. The terms "coupled" and "connected," as used herein, are intended to encompass both direct and indirect coupling (coupling), unless otherwise indicated.

In order to solve the above problems, an embodiment of the present application provides a method for detecting a pole piece. According to the pole piece detection method, the color space of the filtered initial image is transformed to obtain an intermediate image of the HSV color space, for each abnormal father type, abnormal pixel points are determined according to HSV values of all pixel points in the intermediate image and a preset HSV threshold range, the intermediate image after the abnormal pixel points are determined is subjected to binary processing, at least one abnormal area corresponding to one abnormal father type in the pole piece can be accurately and efficiently determined, then at least one rectangular area is determined by performing rectangular template matching on the at least one abnormal area, the rectangular area is compared with preset parameters, and the abnormal subtype of the at least one abnormal area is determined, so that targeted adjustment can be conveniently performed according to the abnormal subtype in the follow-up process.

Referring to fig. 1, fig. 1 is a flow chart of a pole piece detection method according to an embodiment of the present application. The pole piece detection method comprises the following steps S101-S104, wherein:

s101: an initial image of the pole piece is obtained.

The battery cell is formed by winding a plurality of pole pieces. For example, after the battery cell is disassembled, the initial images of the plurality of pole pieces can be obtained by arranging the inner pole pieces, the middle pole pieces and the outer pole pieces, performing panoramic photographing on the plurality of pole pieces arranged and placed by utilizing the pole piece detection device, photographing the plurality of pole pieces at one time, reducing different photographing time, influencing the initial image quality by light, and further reducing the misjudgment of an abnormal area.

After the battery cell is disassembled, the number of the anomalies is usually judged by a disassembling person through experience, a large number of words, a small number of words and the like are usually used when the anomaly condition of the pole piece is described, the analysis and judgment of the position and the reason of the anomaly of the pole piece are not facilitated, and the severity of the anomaly of the pole piece cannot be clarified.

According to the method and the device, the abnormal areas corresponding to different abnormal father types in the pole piece are obtained through obtaining the initial image of the pole piece, the naked eye identification difference of different dismantling personnel can be eliminated, the abnormal areas are accurately defined through the information obtained through obtaining the initial image, and the accuracy of the abnormal area identification is improved. And under the abnormal condition of analyzing a plurality of pole pieces, only one initial image is needed to be analyzed, so that the analysis speed is high, and the efficiency of judging an abnormal area can be effectively improved.

S102: and carrying out color space transformation on the initial image after the filtering treatment to obtain an intermediate image, wherein the color space of the intermediate image is an HSV color space, and the HSV color space comprises HSV values corresponding to all pixel points of the intermediate image.

For example, when the initial image is subjected to filtering, at least one of the following filtering modes may be adopted: gaussian filtering, median filtering, mean filtering and direction filtering (sobel filtering), and one or more filtering modes can be selected according to actual requirements.

It can be seen that the gaussian filtering is adopted to perform filtering processing on the initial image, so that details of the edge part of the initial image are not damaged, and the accuracy of identifying the abnormal region is ensured under the condition that the abnormal region easily appears in the edge region. When the median filtering is adopted to carry out filtering processing on the initial image, details of edge parts (namely peripheral edge parts of the initial image) of the initial image can be effectively protected, when an abnormal region of the edge parts of the initial image is obtained, for example, when the abnormal parent type of the lithium deficiency is obtained and identified, the abnormal region of the lithium deficiency is generally distributed on the edge parts of the pole pieces, the median filtering is adopted to denoise the initial image, the details of the edge parts of the initial image can be reserved, and the accuracy of the abnormal region of the edge parts is ensured to be determined subsequently. When the average filtering is adopted to carry out filtering processing on the initial image, the efficiency of the filtering processing can be improved, and the efficiency of determining the abnormal region is further improved. The initial image is subjected to filtering processing by adopting direction filtering (namely sobel filtering), edges can be extracted in the filtering processing process, and the efficiency of identifying the edges of the abnormal region can be effectively improved.

After the initial image filtering processing, the image noise in the initial image can be removed, and the image quality of the initial image is ensured. The HSV color space consists of three parts, namely Hue, saturation and brightness Value, the color space is an intermediate image of the HSV color space, and the pixel Value of the pixel point is determined by HSV values. In general, an initial image obtained by photographing is an RGB color space image, and the RGB image is greatly affected by light, and the direct analysis of an abnormal area by adopting the initial image in an RGB image format is easy to cause erroneous judgment.

S103: performing binary processing on the intermediate image according to the HSV value of the intermediate image and a preset HSV threshold range to determine at least one abnormal region corresponding to the abnormal father type in the pole piece, wherein the preset HSV threshold ranges corresponding to different abnormal father types are different, and each abnormal father type comprises at least one abnormal subtype.

In the application, when determining the abnormal areas of different abnormal father types, the target images corresponding to different abnormal father types corresponding to the same pole piece are respectively output so as to avoid the possibility of overlapping or misjudging the abnormal areas of different abnormal father types. One or more abnormal areas belonging to one abnormal parent type are marked in one target image, and differences exist between marked abnormal parent types in corresponding different target images.

In one possible implementation, S103: the method for determining the abnormal region corresponding to the abnormal father type in the pole piece by performing binary processing on the intermediate image according to the HSV value of the intermediate image and the preset HSV threshold range comprises the following steps:

determining an abnormal pixel point set according to HSV values corresponding to all pixel points of the intermediate image and a preset HSV threshold range, wherein one abnormal father type corresponds to one abnormal pixel point set, and the abnormal pixel point set comprises a plurality of pixel points belonging to the same abnormal father type;

Performing binary processing on the intermediate image according to the abnormal pixel point set to obtain a binary image, wherein one abnormal pixel point set corresponds to one frame of binary image;

and determining at least one abnormal region corresponding to the abnormal parent type according to the binary image and the abnormal pixel point set.

Under the condition that an abnormal region of a certain abnormal father type is determined, comparing the HSV value of each pixel point of the intermediate image with a preset HSV threshold range corresponding to the abnormal father type, marking the pixel point with the HSV value of the pixel point in the preset SHV threshold range as an abnormal pixel point, and putting the abnormal pixel point into an abnormal pixel point set.

It will be appreciated that an outlier pixel set includes all outlier pixels belonging to the outlier parent type, and that outlier pixels in the outlier pixel set may constitute one or more outlier regions.

It can be seen that whether the pixel points belong to abnormal pixel points is judged through HSV values of the pixel points of the intermediate image, so that the abnormal pixel points can be accurately and efficiently distinguished, and the accuracy and the efficiency of abnormal region identification are improved.

In a possible implementation manner, the preset HSV threshold range includes a first threshold range, a second threshold range and a third threshold range, the HSV color space includes an H channel, an S channel and a V channel, the first threshold range corresponds to the H channel, the second threshold range corresponds to the S channel, the third threshold range corresponds to the V channel, and the implementation method for determining the abnormal pixel point set according to the HSV value corresponding to each pixel point of the intermediate image and the preset HSV threshold range may be:

And acquiring pixels of the intermediate image, wherein the H channel value is in the first threshold range, the S channel value is in the second threshold range and the V channel value is in the third threshold range, so as to form an abnormal pixel point set.

In one possible implementation manner, the pixel values in the binary image include a first value and a second value, the first value and the second value are different, and the binary processing is performed on the intermediate image according to the abnormal pixel point set, so as to obtain the binary image, which may be implemented by:

Setting the pixel values of the pixels belonging to the abnormal pixel point set in the intermediate image as a first numerical value;

and setting the pixel values of the pixel points which do not belong to the abnormal pixel point set in the intermediate image as a second numerical value so as to obtain a binary image.

For example, assuming that the initial image is an image with a size of 8×8, as shown in fig. 2, fig. 2 is a schematic diagram of the initial image of the pole piece detection method provided in the embodiment of the present application, (0, 0) represents a pixel point at a first column of a first row, (0, 4) represents a pixel point at a fifth column of the first row, (1, 0) represents a pixel point at a first column of a second row, … …, and (7, 7) represents a pixel point at an eighth column of an eighth row. Assuming that the abnormal pixel point set is { (0, 0), (0, 1), (1, 0), (1, 1), (2, 0), (3, 4), (3, 5), (4, 4), (4, 5) }, after the intermediate image is binary-processed according to the abnormal pixel point set, the pixel values of the pixel points in the abnormal pixel point set are all a first value (e.g. the first value is "0"), the pixel values of the pixel points in the non-abnormal pixel point set are all a second value (e.g. the second value is "255"), so as to obtain a binary image, as shown in fig. 3, fig. 3 is a schematic diagram of a binary image of a pole piece detection method provided in the embodiment of the present application, the pixel points (0, 0), (0, 1), (1, 0), (1, 1) and (2, 0) in fig. 3 may form an abnormal region, and the pixel points (3, 4), (3, 5), (4, 4) and (4, 5) in fig. 3 may form another abnormal region.

In one possible implementation, determining at least one anomaly region corresponding to an anomaly parent type from the binary image and the anomaly pixel point set includes:

and carrying out edge recognition on the binary image according to each pixel point in the abnormal pixel point set so as to obtain at least one abnormal region.

It can be seen that the pixel gray values between the abnormal region and the non-abnormal region in the binary image change, the abnormal region and the non-abnormal region are in different colors, and the outline of the abnormal region is further detected through edge recognition, so that the area size of the abnormal region can be conveniently determined, the total area of the abnormal region corresponding to a certain abnormal father type in the initial image of the pole piece is counted, and the accuracy of the abnormal region recognition is improved.

In one possible implementation, after performing binary processing on the intermediate image according to the HSV value of the intermediate image and the preset HSV threshold range to determine at least one abnormal region corresponding to the abnormal parent type in the pole piece, the method further includes:

calculating a moment of at least one abnormal region;

determining centroid and area of at least one anomaly region based on moment of at least one anomaly region;

the number of the at least one abnormal region is determined according to the mass center of the at least one abnormal region.

It can be seen that after the abnormal region is determined, the centroid and the area of the abnormal region are obtained by calculating the moment of each abnormal region, for example, the centroid of the abnormal region is obtained by calculating the zero-order moment and the first-order moment of the abnormal region, and after the centroid of the abnormal region is obtained by calculation, the centroid of each abnormal region can be marked in the initial image, wherein when the centroid is marked for each abnormal region, the marked centroid is marked at the centroid position in the abnormal region, and the abnormal condition of the pole piece is determined by visual data. Under the condition that the two abnormal areas are closer, the two abnormal areas can be rapidly distinguished through the mass center calibrated by each abnormal area, and the situation that the number of the abnormal areas is misjudged is avoided. In addition, the distribution of the abnormal region is analyzed by the area of the abnormal region.

After calculating the moment of the abnormal region, the value of the centroid and the value of the area of the abnormal region may be marked in the target image. Wherein the target image may be an image of the same image format as the initial image, such as an RGB image.

Here, the abnormal father type is not limited to the conditions of abnormal lithium ion intercalation, high water content, abnormal pole piece coating, and the like, and multiple abnormal father types may exist in the same pole piece, and correspondingly, multiple target images corresponding to the multiple abnormal father types may be output; exemplary, as shown in fig. 4, fig. 4 is a schematic diagram of an initial image and a target image of a pole piece detection method according to an embodiment of the present application. In fig. 4, the left image is an initial image, the right image is a target image, and the abnormal region identified in the target image is a lithium ion intercalation abnormal region; here, the abnormal region identified in the target image may be other abnormality parent type such as high water content, abnormal pole piece coating, or the like.

In each target image, the value of the centroid and the value of the area may be marked by fonts of different colors. In the target image corresponding to the lithium ion intercalation abnormality shown in fig. 4, the abnormal region of the edge portion is continuous and has an excessively large area, and when the area value is marked, the width value of the abnormal region having an excessively large area can be used to calculate the width of the rectangle by matching the abnormal region of the edge portion with the rectangle, for example. Specifically:

S104: rectangular template matching is performed on the at least one abnormal region to determine at least one rectangular region corresponding to the at least one abnormal region.

In one possible implementation, S104: the method for implementing rectangular template matching on at least one abnormal region to determine at least one rectangular region corresponding to the at least one abnormal region may be: and carrying out rectangular template matching on the abnormal region according to the area of the abnormal region and the abnormal pixel point set, and determining a rectangular region corresponding to the abnormal region.

And for each abnormal region, performing rectangular template matching according to the position of the abnormal region corresponding to the abnormal pixel point set and the area of the abnormal region to determine a rectangular region of the abnormal region, so that the abnormal subtype of the abnormal region is determined according to the rectangular region.

After determining the rectangular areas of the abnormal areas, the rectangular areas of each abnormal area may be marked and framed in the target image, such as rectangular area A1, rectangular area A2, and rectangular area A3 of the right image in fig. 4.

It can be appreciated that, when rectangular template matching is performed according to the position of the abnormal region and the area of the abnormal region determined by the abnormal pixel point set, the matching can be performed by a least square method or other matching methods, which is not limited thereto.

S105: and comparing according to the at least one rectangular area and the preset parameter value to determine the abnormal subtype of the at least one abnormal area.

In one possible embodiment, the pole piece comprises a negative pole piece, and in the case that the pole piece is a negative pole piece, the preset parameter value comprises a first parameter value, the first parameter value being an average value of a difference between a width of the preset pole piece and a width of the preset pole piece; comparing according to the at least one rectangular area and the preset parameter value to determine an abnormal subtype of the at least one abnormal area, wherein the method comprises the following steps: if the widths of the at least one rectangular area are all larger than the first parameter value, determining that the abnormal subtype of the at least one abnormal area is insufficient in lithium intercalation of the negative electrode sheet; if the widths of the at least one rectangular area are smaller than the first parameter value, determining that the abnormal subtype of the at least one abnormal area is insufficient in negative plate clamping; if the width of the at least one rectangular area is larger than the first parameter value and the width of the at least one rectangular area is smaller than the first parameter value, determining that the abnormal subtype of the at least one abnormal area is the dislocation of the negative plate.

It can be seen that when the electrode sheet is a negative electrode sheet, the preset parameter value may be a first parameter value, and the first parameter value may be a design reference value of a standard positive and negative electrode sheet, that is, the preset negative electrode sheet is a standard negative electrode sheet, and the preset positive electrode sheet is a standard positive electrode sheet. And comparing the determined widths of the rectangular areas with the first parameter value respectively, if the widths of at least one rectangular area are larger than the first parameter value, indicating that the negative electrode plate is too wide, and the positive electrode plate is too narrow, indicating that the battery capacity is low at the moment, lithium ions move from the positive electrode plate to the negative electrode plate when the battery is charged, the distance is large, the resistance is large, the abnormal condition that lithium ions are not normally inserted into the negative electrode plate due to the fact that lithium ions are not inserted into the negative electrode plate normally can occur, and at the moment, determining the abnormal subtype of at least one abnormal area as the abnormal condition that lithium insertion of the negative electrode plate is insufficient. If the width of at least one rectangular area is larger than the first parameter value, the negative electrode plate is too narrow, namely the lithium ions are not enough in the block of the negative electrode plate, namely the lithium insertion space of the negative electrode plate is insufficient when the battery is charged, the abnormal condition that lithium is separated from the positive electrode plate due to the insufficient lithium insertion space of the negative electrode plate can occur, and at the moment, the abnormal subtype of at least one abnormal area is determined to be the insufficient block of the negative electrode plate. If the number of rectangular areas is multiple, the width of at least one rectangular area is larger than the first parameter value, and the width of at least one rectangular area is smaller than the first parameter value, the negative electrode piece is indicated to be misplaced, and at the moment, the abnormal subtype of at least one abnormal area is determined to be misplaced. In summary, the abnormal subtype of the abnormal region is further determined according to the first parameter value of the negative electrode plate, so that the negative electrode plate can be conveniently adjusted according to the abnormal subtype.

In one possible implementation, the preset parameter values further include a second parameter value, where the second parameter value is a misalignment threshold value at which the pole piece is misaligned due to gravity sinking; under the condition that the pole piece is a negative pole piece, comparing according to at least one rectangular area and a preset parameter value to determine an abnormal subtype of at least one abnormal area, wherein the method comprises the following steps: acquiring a difference value between the width of the rectangular area and a first parameter as a first difference value; if the first difference value is larger than the second parameter value, determining that the abnormal subtype of at least one abnormal region is negative plate dislocation.

It can be seen that the second parameter value may be a maximum misalignment threshold for misalignment of the pole piece due to gravitational sag. Wherein the pole piece is a negative pole piece. When the electrode plate is the negative electrode plate, a difference value between the rectangular area and the first parameter value is obtained and is used as a first difference value, the first difference value represents the dislocation size of the negative electrode plate, if the first difference value is larger than the second parameter value, the dislocation size of the negative electrode plate exceeds the maximum dislocation threshold value for dislocation due to gravity sinking, the dislocation abnormality of the negative electrode plate is indicated, and the abnormal subtype of at least one abnormal area is determined to be the dislocation of the negative electrode plate.

It is understood that when the electrode sheet is a negative electrode sheet, the second parameter value may be a maximum misalignment threshold at which the negative electrode sheet is misaligned due to gravity sinking.

In the application, after determining the abnormal subtype corresponding to the abnormal region, design adjustment or process correction can be performed for different abnormal subtypes. For example, when it is determined that the abnormal subtype of the abnormal region is the anode sheet misalignment abnormality according to the width of the rectangular region and the first parameter, the machine winding apparatus may be corrected, or the width dimension of the anode sheet may be corrected. When the abnormal subtype of the abnormal region is determined to be the dislocation of the negative electrode plate according to the first difference value and the second parameter of the negative electrode plate, the negative electrode plate is considered to be abnormal due to gravity, the winding time when the winding core is wound is adjusted, and the abnormal condition of the negative electrode plate due to the influence of the gravity is reduced.

For example, when the abnormal subtype of the abnormal region is abnormal in lithium precipitation of the negative electrode sheet or insufficient lithium intercalation of the negative electrode sheet, the design parameters of the positive electrode sheet and/or the negative electrode sheet can be adjusted, so that the design parameters of the positive electrode sheet and the negative electrode sheet are ensured to meet the standard.

The method designed by the embodiment of the application is described in detail, and the pole piece detection device designed by the embodiment of the application is provided below.

Referring to fig. 5, fig. 5 is a schematic diagram of a pole piece detection device 500 according to an embodiment of the present application. The pole piece detection method provided by the application is applied to the pole piece detection device 500. The pole piece detection device 500 includes an acquisition unit 501, a transformation unit 502, a first determination unit 503, a second determination unit 504, and a third determination unit 505. The acquisition unit 501 is used to acquire an initial image of the pole piece. The transforming unit 502 is configured to perform color space transformation on the filtered initial image to obtain an intermediate image, where the color space of the intermediate image is an HSV color space, and the HSV color space includes HSV values of each pixel point of the intermediate image. The first determining unit 503 is configured to perform binary processing on the intermediate image according to the HSV value of the intermediate image and a preset HSV threshold range, so as to determine an abnormal region corresponding to an abnormal parent type in the pole piece, where the preset HSV threshold ranges corresponding to different abnormal parent types are different, and each abnormal parent type includes at least one abnormal child type. The second determining unit 504 is configured to perform rectangular template matching on the at least one abnormal region to determine at least one rectangular region corresponding to the at least one abnormal region. The third determining unit 505 is configured to perform a comparison according to the at least one rectangular area and a preset parameter value, so as to determine an abnormal subtype of the at least one abnormal area.

In a possible implementation manner, the first determining unit 503 is further configured to: determining an abnormal pixel point set according to HSV values corresponding to all pixel points of the intermediate image and a preset HSV threshold range, wherein one abnormal father type corresponds to one abnormal pixel point set, and the abnormal pixel point set comprises a plurality of pixel points belonging to the same abnormal father type; performing binary processing on the intermediate image according to the abnormal pixel point set to obtain a binary image, wherein one abnormal pixel point set corresponds to one binary image; and determining at least one abnormal region corresponding to the abnormal parent type according to the binary image and the abnormal pixel point set.

In a possible implementation manner, the preset HSV threshold range includes a first threshold range, a second threshold range, and a third threshold range, the HSV color space includes an H-channel, an S-channel, and a V-channel, the first threshold range corresponds to the H-channel, the second threshold range corresponds to the S-channel, the third threshold range corresponds to the V-channel, and the first determining unit 503 is further configured to: and acquiring pixels of the intermediate image, wherein the H channel value is in the first threshold range, the S channel value is in the second threshold range and the V channel value is in the third threshold range, so as to form an abnormal pixel point set.

In a possible implementation, the pixel values in the binary image include a first value and a second value, the first value and the second value being different, and the first determining unit 503 is further configured to: setting the pixel values of the pixels belonging to the abnormal pixel point set in the intermediate image as a first numerical value; and setting the pixel values of the pixel points which do not belong to the abnormal pixel point set in the intermediate image as a second numerical value so as to obtain a binary image.

In a possible implementation manner, the first determining unit 503 is further configured to: and carrying out edge recognition on the binary image according to each pixel point in the abnormal pixel point set so as to obtain an abnormal region.

In a possible embodiment, the pole piece detection device 500 further comprises a calculation unit 506, a fourth determination unit 507 and a fifth determination unit 508. The calculation unit 506 is used to calculate the moment of the abnormal region. The fourth determination unit 507 is configured to determine the centroid and the area of the abnormal region from the moment of the abnormal region. The fifth determining unit 508 is configured to determine the number of abnormal regions according to the centroid of the abnormal region.

In a possible implementation manner, the second determining unit 504 is further configured to: and carrying out rectangular template matching on the abnormal region according to the area of the abnormal region and the abnormal pixel point set, and determining a rectangular region corresponding to the abnormal region.

In one possible embodiment, the pole piece comprises a negative pole piece, and in case the pole piece is a negative pole piece, the preset parameter value comprises a first parameter value, the first parameter value being an average value of differences between a width of the preset negative pole piece and a width of the preset positive pole piece. The third determining unit 505 is further configured to: if the widths of the at least one rectangular area are all larger than the first parameter value, determining that the abnormal subtype of the at least one abnormal area is insufficient in lithium intercalation of the negative electrode sheet; if the widths of the at least one rectangular area are smaller than the first parameter value, determining that the abnormal subtype of the at least one abnormal area is insufficient in negative plate clamping; if the width of the at least one rectangular area is larger than the first parameter value and the width of the at least one rectangular area is smaller than the first parameter value, determining that the abnormal subtype of the at least one abnormal area is the dislocation of the negative plate.

In one possible embodiment, the preset parameter values further include a second parameter value, where the second parameter value is a misalignment threshold for misalignment of the pole piece due to gravitational dip. In case the pole piece is a negative pole piece, the third determining unit 505 is further configured to: acquiring a difference value between the width of the rectangular area and a first parameter as a first difference value; if the first difference value is larger than the second parameter value, determining that the abnormal subtype of at least one abnormal region is negative plate dislocation.

The implementation of each unit of the pole piece detection device 500 may also correspond to the corresponding description of the pole piece detection method embodiment described in any embodiment of the present application.

Referring to fig. 6, fig. 6 is a schematic diagram illustrating a composition of a terminal device 600 according to an embodiment of the present application. The terminal device 600 may comprise a processor 30, a memory 50 and a communication interface 70, wherein the processor 30, the memory 50 and the communication interface 70 are interconnected by a bus 10, the memory 50 being adapted to store a computer program comprising program instructions, the processor 30 being configured to invoke the program instructions to perform a pole piece detection method as in any of the embodiments of the present application.

As an implementation, the functions of the communication interface 70 may be considered to be implemented by a transceiving circuit or a dedicated chip for transceiving. Processor 30 may be considered to be implemented by a dedicated processing chip, a processing circuit, a processor, or a general-purpose chip.

The concepts related to the technical solutions provided in the embodiments of the present application, explanation, detailed description and other steps related to the terminal device refer to the foregoing methods or descriptions of the contents of the method steps executed by the apparatus in other embodiments, which are not repeated herein.

As another implementation of this embodiment, a computer-readable storage medium is provided, on which instructions are stored that when executed perform a method as described in any of the implementations of the application.

As another implementation of this embodiment, a computer program product is provided that contains instructions that, when executed, perform the method described in any of the implementations of the application.

Those skilled in the art will appreciate that only one memory 50 and processor 30 is shown in fig. 6 for ease of illustration. In an actual terminal or server, there may be multiple processors 30 and memories 50. The memory 50 may also be referred to as a storage medium or storage device, etc., and the embodiments of the present application are not limited thereto.

It should be appreciated that in embodiments of the present application, the processor 30 may be a central processing unit (Central Processing Unit, CPU for short), the processor 30 may also be other general purpose processors, digital signal processors (Digital Signal Processing, DSP for short), application specific integrated circuits (Application Specific Integrated Circuit, ASIC for short), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA for short) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like.

It should also be appreciated that the memory 50 referred to in the embodiments of the present application may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The nonvolatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an electrically Erasable ROM (Electrically EPROM, EEPROM), or a flash Memory. The volatile memory may be a random access memory (Random Access Memory, RAM for short) which acts as an external cache. By way of example, and not limitation, many forms of RAM are available, such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (Double Data Rate SDRAM), enhanced SDRAM (ESDRAM), synchronous DRAM (SLDRAM), and direct memory bus RAM (Direct Rambus RAM, DR RAM).

It should be noted that when the processor 30 is a general-purpose processor, DSP, ASIC, FPGA or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component, the memory (storage module) is integrated into the processor.

It should be noted that the memory 50 described herein is intended to comprise, without being limited to, these and any other suitable types of memory.

The bus 10 may include a power bus, a control bus, a status signal bus, and the like in addition to a data bus. But for clarity of illustration the various buses are labeled as bus 10 in the figures.

It should also be understood that the first, second, third, fourth, and various numerical numbers referred to herein are merely descriptive convenience and are not intended to limit the scope of the present application.

It should be understood that the term "and/or" is merely an association relationship describing the associated object, and means that three relationships may exist, for example, a and/or B may mean: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship.

In implementation, the steps of the above method may be performed by integrated logic circuitry in hardware or instructions in software in the processor 30. The steps of a method disclosed in connection with the embodiments of the present application may be embodied directly in hardware processor execution or in a combination of hardware and software modules in the processor 30. The software modules may be located in a random access memory 50, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in the memory 50 and the processor 30 reads the information in the memory 50 and in combination with its hardware performs the steps of the method described above. To avoid repetition, a detailed description is not provided herein.

In various embodiments of the present application, the sequence number of each process does not mean the sequence of execution, and the execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

Those of ordinary skill in the art will appreciate that the various illustrative logical blocks (illustrative logical block, abbreviated ILBs) and steps described in connection with the embodiments disclosed herein can be implemented in electronic hardware, or in combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods may be implemented in other ways. For example, the above-described device embodiments are merely illustrative, e.g., the division of modules is merely a logical function division, and there may be additional divisions of actual implementation, e.g., multiple modules or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some interface, indirect coupling or communication connection of devices or modules, electrical, mechanical, or other form.

The modules described above as separate components may or may not be physically separate, and components shown as modules may or may not be physical modules, i.e., may be located in one place, or may be distributed over a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist alone physically, or two or more modules may be integrated into one module.

In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present application, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by a wired (e.g., coaxial cable, fiber optic, digital subscriber line), or wireless (e.g., infrared, wireless, microwave, etc.). Computer readable storage media can be any available media that can be accessed by a computer or data storage devices, such as servers, data centers, etc., that contain an integration of one or more available media. Usable media may be magnetic media (e.g., floppy disks, hard disks, magnetic tape), optical media (e.g., DVD), or semiconductor media (e.g., solid state disk), among others.

The foregoing is a partial embodiment of the present application and it should be noted that, for a person skilled in the art, several improvements and modifications can be made without departing from the principle of the present application, and these improvements and modifications are also considered as the protection scope of the present application.

Claims

1. The pole piece detection method is characterized by comprising the following steps of:

acquiring an initial image of a pole piece;

performing color space transformation on the initial image after filtering treatment to obtain an intermediate image, wherein the color space of the intermediate image is an HSV color space which comprises HSV values corresponding to all pixel points of the intermediate image;

performing binary processing on the intermediate image according to the HSV value of the intermediate image and a preset HSV threshold range to determine at least one abnormal region corresponding to an abnormal father type in the pole piece, wherein the preset HSV threshold range corresponding to the abnormal father type is different, and each abnormal father type comprises at least one abnormal subtype;

performing rectangular template matching on the at least one abnormal region to determine at least one rectangular region corresponding to the at least one abnormal region;

and comparing according to the at least one rectangular area and the preset parameter value to determine the abnormal subtype of the at least one abnormal area.

2. The pole piece detection method according to claim 1, wherein the performing binary processing on the intermediate image according to the HSV value of the intermediate image and the preset HSV threshold range to determine at least one abnormal region corresponding to an abnormal parent type in the pole piece includes:

determining an abnormal pixel point set according to the HSV values corresponding to the pixels of the intermediate image and the preset HSV threshold range, wherein one abnormal father type corresponds to one abnormal pixel point set, and the abnormal pixel point set comprises a plurality of pixel points belonging to the same abnormal father type;

performing binary processing on the intermediate image according to the abnormal pixel point set to obtain a binary image, wherein one abnormal pixel point set corresponds to one frame of the binary image;

and determining the at least one abnormal region corresponding to the abnormal father type according to the binary image and the abnormal pixel point set.

3. The pole piece detection method according to claim 2, wherein the preset HSV threshold range includes a first threshold range, a second threshold range, and a third threshold range, the HSV color space includes an H-channel, an S-channel, and a V-channel, the first threshold range corresponds to the H-channel, the second threshold range corresponds to the S-channel, the third threshold range corresponds to the V-channel, and the determining the abnormal pixel point set according to the HSV value corresponding to each pixel point of the intermediate image and the preset HSV threshold range includes:

And acquiring pixel points of the intermediate image, wherein the H channel value is in the first threshold range, the S channel value is in the second threshold range and the V channel value is in the third threshold range, so as to form the abnormal pixel point set.

4. The pole piece detection method according to claim 2, wherein the pixel values in the binary image include a first value and a second value, the first value and the second value being different, the binary processing is performed on the intermediate image according to the abnormal pixel point set to obtain a binary image, including:

setting the pixel values of the pixel points belonging to the abnormal pixel point set in the intermediate image as the first numerical value;

and setting the pixel values of the pixel points which do not belong to the abnormal pixel point set in the intermediate image as the second numerical value so as to obtain the binary image.

5. The pole piece detection method according to claim 2, wherein the determining the at least one anomaly region corresponding to the anomaly parent type from the binary image and the anomaly pixel point set includes:

and carrying out edge recognition on the binary image according to each pixel point in the abnormal pixel point set so as to obtain the at least one abnormal region.

6. The pole piece detection method according to claim 2, further comprising, after the performing binary processing on the intermediate image according to the HSV value of the intermediate image and a preset HSV threshold range to determine at least one abnormal region corresponding to an abnormal parent type in the pole piece:

calculating a moment of the at least one anomaly region;

determining centroid and area of the at least one anomaly region from the moment of the at least one anomaly region;

and determining the number of the at least one abnormal region according to the mass center of the at least one abnormal region.

7. The pole piece detection method of claim 6, wherein the rectangular template matching the at least one abnormal region to determine at least one rectangular region corresponding to the at least one abnormal region comprises:

and performing rectangular template matching on the abnormal region according to the area of the abnormal region and the abnormal pixel point set, and determining a rectangular region corresponding to the abnormal region.

8. The pole piece detection method according to claim 1, wherein the pole piece includes a negative pole piece, and the preset parameter value includes a first parameter value that is an average value of differences between a width of a preset negative pole piece and a width of a preset positive pole piece in a case where the pole piece is the negative pole piece;

The comparing according to the at least one rectangular area and the preset parameter value to determine the abnormal subtype of the at least one abnormal area comprises the following steps:

if the widths of the at least one rectangular area are all larger than the first parameter value, determining that the abnormal subtype of the at least one abnormal area is insufficient in lithium intercalation of the negative electrode sheet;

if the widths of the at least one rectangular area are smaller than the first parameter value, determining that the abnormal subtype of the at least one abnormal area is insufficient in the negative electrode sheet clamping;

and if at least one rectangular area with the width larger than the first parameter value and at least one rectangular area with the width smaller than the first parameter value exists, determining that the abnormal subtype of the at least one abnormal area is abnormal due to dislocation of the negative electrode plate.

9. The method of claim 8, wherein the predetermined parameter value further comprises a second parameter value, the second parameter value being a misalignment threshold at which the pole piece is misaligned due to gravity dip;

and when the pole piece is a negative pole piece, comparing the at least one rectangular area with a preset parameter value to determine an abnormal subtype of the at least one abnormal area, wherein the method comprises the following steps:

Acquiring a difference value between the width of the rectangular region and the first parameter as a first difference value;

and if the first difference value is larger than the second parameter value, determining that the abnormal subtype of the at least one abnormal region is the dislocation of the negative electrode plate.

10. A pole piece detection device, comprising:

the acquisition unit is used for acquiring an initial image of the pole piece;

the transformation unit is used for carrying out color space transformation on the initial image after the filtering processing to obtain an intermediate image, wherein the color space of the intermediate image is an HSV color space which comprises HSV values of all pixel points of the intermediate image;

the first determining unit is used for carrying out binary processing on the intermediate image according to the HSV value of the intermediate image and a preset HSV threshold range so as to determine at least one abnormal region corresponding to an abnormal father type in the pole piece, wherein the preset HSV threshold ranges corresponding to different abnormal father types are different, and each abnormal father type comprises at least one abnormal subtype;

a second determining unit, configured to perform rectangular template matching on the at least one abnormal region, so as to determine at least one rectangular region corresponding to the at least one abnormal region;

And the third determining unit is used for comparing the at least one rectangular area with a preset parameter value to determine the abnormal subtype of the at least one abnormal area.

11. A terminal device comprising a processor and a memory, the processor and the memory being interconnected, wherein the memory is adapted to store a computer program comprising program instructions, the processor being configured to invoke the program instructions to perform the pole piece detection method according to any of claims 1 to 9.

12. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program comprising program instructions which, when executed by a processor, cause the processor to perform the pole piece detection method as claimed in any one of claims 1 to 9.