Detection method, device, electronic equipment and medium for positive electrode sheet of square battery cell

Abstract

The present invention relates to the field of image processing, and provides a detection method, device, electronic device and medium for positive electrode sheets of square battery cells, the method comprising: extracting an area of ​​interest in an image of an electrode sheet of a positive electrode sheet of a square battery cell; determining a first dark area in the area of ​​interest; performing a difference operation on the first dark area and the area of ​​interest to obtain a first transition area; performing an open operation and a region scattering process on the first transition area to obtain a second transition area; extracting a second dark area in the second transition area, and performing a complement process on the second dark area to obtain a third dark area; combining and post-processing the first dark area and the third dark area to obtain an upper contour area containing a feed edge line. The scheme provided by the present invention can extract an upper contour area containing a feed edge line when the image grayscale is uneven and there are many transition pixels through the improvement of the processing flow, thereby improving the accuracy and reliability of feed edge detection.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to a detection method, device, electronic equipment and medium for a positive electrode sheet of a square battery cell. Background Art

[0002] During the winding process of square battery cells, it is necessary to detect the feeding angle of the positive electrode sheet of the square battery cell to detect whether the positive electrode sheet of the square battery cell is folded when entering the roller. The prerequisite for detecting the feeding angle is that the boundary of the electrode sheet feeding can be accurately extracted, that is, the feeding edge line.

[0003] In the related technology, due to the diaphragm covering the pole piece, the roller rotates at a high speed during the winding process, and a point light source is used during the winding process, resulting in uneven image illumination and more edge transition pixels. The traditional detection method directly uses grayscale gradient for edge extraction, which makes it difficult to accurately extract the edge line of the feed and the upper contour area where it is located. Summary of the invention

[0004] The present invention provides a method, device, electronic equipment and medium for detecting positive electrode sheets of square battery cells, which are used to solve the defect that it is difficult for traditional detection methods to accurately extract the edge line of the feed material and the upper contour area where it is located.

[0005] In one aspect, the present invention provides a method for detecting a positive electrode sheet of a square battery cell, comprising:

[0006] Extracting a region of interest from a pole piece image of a square battery cell positive pole piece; wherein the region of interest includes a feeding edge line of the square battery cell positive pole piece;

[0007] determining a first dark region in the region of interest;

[0008] Performing a difference operation on the first dark area and the region of interest to obtain a first transition area;

[0009] Performing an opening operation and a region scattering process on the first transition region to obtain a second transition region;

[0010] extracting a second dark area in the second transition area, and performing a completion process on the second dark area to obtain a third dark area;

[0011] The first dark area and the third dark area are combined and post-processed to obtain an upper contour area including the feeding edge line.

[0012] According to the detection method of the square battery cell positive electrode sheet provided by the present invention, determining the first dark area in the region of interest includes:

[0013] Performing compression processing on the region of interest to obtain a compressed region;

[0014] Determine the target dark area in the compressed area by a local threshold algorithm;

[0015] Amplifying the target dark area to obtain the first dark area;

[0016] The compression factor of the compression process is the same as the magnification factor of the magnification process.

[0017] According to the method for detecting the positive electrode sheet of a square battery cell provided by the present invention, after obtaining the first dark area, the method further includes:

[0018] The burrs and irregular areas around the first dark area are removed.

[0019] According to the detection method of the square battery cell positive electrode sheet provided by the present invention, the second dark area is supplemented to obtain the third dark area, including:

[0020] Determine the remaining dark area in the region of interest by using the position information prior condition;

[0021] The second dark area is complemented based on the remaining dark area to obtain a third dark area.

[0022] According to the detection method of the square battery cell positive electrode sheet provided by the present invention, the first dark area and the third dark area are combined and post-processed to obtain the upper contour area of ​​the square battery cell positive electrode sheet, including:

[0023] combining the first dark area and the third dark area to obtain a fourth dark area;

[0024] Performing gap filling processing on the fourth dark area to obtain a fifth dark area;

[0025] The fifth dark area is subjected to contour extraction and contour segmentation to obtain an upper contour area including the feeding edge line.

[0026] According to the method for detecting the positive electrode sheet of a square battery cell provided by the present invention, after obtaining the upper contour area including the feeding edge line, the method further comprises:

[0027] Determining a feeding angle of the positive electrode sheet of the square battery cell according to the upper contour area;

[0028] According to the feeding angle, the feeding discount detection result of the positive electrode sheet of the square battery cell is obtained.

[0029] According to the method for detecting the positive electrode sheet of a square battery cell provided by the present invention, obtaining the feed discount detection result of the positive electrode sheet of the square battery cell according to the feed angle, comprising:

[0030] If the feeding angle is greater than the preset angle threshold, the feeding discount detection result is that the feeding discount occurs in the positive electrode sheet of the square battery cell;

[0031] If the feeding angle is less than or equal to the preset angle threshold, the feeding discount detection result is that there is no feeding discount on the positive electrode sheet of the square battery cell.

[0032] On the other hand, the present invention also provides a detection device for a positive electrode sheet of a square battery cell, comprising:

[0033] An extraction module, used to extract a region of interest in the image of the positive electrode of the square battery cell; wherein the region of interest includes a feeding edge line of the positive electrode of the square battery cell;

[0034] A determination module, configured to determine a first dark area in the region of interest;

[0035] A calculation module, used for performing a difference operation on the first dark area and the region of interest to obtain a first transition area;

[0036] A first processing module, configured to perform an opening operation and a region scattering process on the first transition region to obtain a second transition region;

[0037] A second processing module is used to extract a second dark area in the second transition area, and perform a completion process on the second dark area to obtain a third dark area;

[0038] The third processing module is used to combine and post-process the first dark area and the third dark area to obtain an upper contour area including the feeding edge line.

[0039] On the other hand, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a method for detecting a positive electrode of a square battery cell as described above is implemented.

[0040] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method for detecting a positive electrode sheet of a square battery cell as described in any one of the above.

[0041] The detection method, device, electronic device and medium of the square battery cell positive electrode sheet provided by the present invention extract the region of interest in the electrode sheet image of the square battery cell positive electrode sheet, determine the first dark area in the region of interest, perform a difference set operation on the first dark area and the region of interest to obtain a first transition area, perform an open operation and regional scattering processing on the first transition area to obtain a second transition area, extract the second dark area in the second transition area, and perform a complement processing on the second dark area to obtain a third dark area, combine and post-process the first dark area with the third dark area to obtain an upper contour area containing the feed edge line. Through the improvement of the processing flow, the upper contour area containing the feed edge line can be extracted when the image grayscale is uneven and there are many transition pixels, thereby improving the accuracy and reliability of the feed edge detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0043] Figure 1 It is a schematic diagram of the flow of a method for detecting a positive electrode sheet of a square battery cell provided by an embodiment of the present invention;

[0044] Figure 2 It is a distribution diagram of the area of ​​interest;

[0045] Figure 3 is a schematic diagram of the distribution of the first dark area preliminarily determined in the region of interest;

[0046] Figure 4 It is a relatively accurate distribution diagram of the first dark area in the region of interest after removing burrs and irregular areas;

[0047] Figure 5 is a distribution diagram of the first transition area;

[0048] Figure 6 It is a distribution diagram of the second transition area after the opening operation and area scattering processing;

[0049] Figure 7 This is a schematic diagram of the distribution of the fourth dark area;

[0050] Figure 8 This is a schematic diagram of the distribution of the fifth dark area;

[0051] Fig. 9 It is a structural schematic diagram of a detection device for a positive electrode sheet of a square battery cell provided by an embodiment of the present invention;

[0052] Fig.10 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] Combine the following Figures 1 to 10 The invention describes the detailed scheme of the detection method, device, electronic equipment and medium of the positive electrode sheet of the square battery cell provided by the embodiment of the invention.

[0055] Figure 1 It is a schematic flow chart of a method for detecting a positive electrode sheet of a square battery cell provided in an embodiment of the present invention.

[0056] like Figure 1 As shown, the detection method of the positive electrode sheet of a square battery cell provided in an embodiment of the present invention can be performed by an electronic device having data receiving and sending and data processing functions. The method mainly includes the following steps:

[0057] Step 110: extracting a region of interest in the electrode piece image of the square battery cell positive electrode piece; wherein the region of interest includes the feeding edge line of the square battery cell positive electrode piece.

[0058] In this embodiment, the electrode image of the positive electrode of the square battery cell can be obtained by pre-shooting with an image acquisition device, and the region of interest is a rectangular region with a preset size. Figure 2 A region of interest 220 is shown as an example.

[0059] Step 120: Determine a first dark area in the region of interest.

[0060] In some embodiments, the first dark area may be obtained by using a local threshold segmentation method in the region of interest. Specifically, the first dark area may be determined by comparing the grayscale value of each pixel in the region of interest with the local threshold in the corresponding sub-region. Figure 3 The distribution of the first dark area in the region of interest is shown by way of example.

[0061] from Figure 3It can be seen that there are many burrs and irregular areas around the first dark area that is initially determined. In order to ensure the accuracy of subsequent processing, the burrs and irregular areas around the first dark area can be removed by opening and closing operations with rectangles as structural elements, thereby obtaining a more accurate first dark area. Figure 4 The relatively accurate first dark area after removing the burrs and irregular areas is shown as an example. The relatively accurate first dark area is subsequently used for difference set calculation to ensure the image processing accuracy.

[0062] Step 130: performing a difference operation on the first dark area and the region of interest to obtain a first transition area.

[0063] In this embodiment, the first transition area that does not include the first dark area can be obtained by using a difference set operation. Specifically, all the pixels in the first dark area can be taken as the first set, and all the pixels in the region of interest can be taken as the second set. After performing a difference set operation on the first set and the second set, all the pixels in the first transition area obtained belong to the second set but do not belong to the first set. Figure 5 The distribution of the first transition region is shown as an example.

[0064] Step 140: Perform an opening operation and a region scattering process on the first transition region to obtain a second transition region.

[0065] In this embodiment, after performing an opening operation on the first transition region using a rectangle as a structural element, the region is broken up, so that the unconnected regions can be dispersed into independent sub-regions. Figure 6 The distribution of the second transition area after the opening operation and area scattering is shown as an example.

[0066] Step 150: extracting the second dark area in the second transition area, and performing a completion process on the second dark area to obtain a third dark area.

[0067] It can be understood that since the second transition area contains both dark areas and bright areas, and the purpose of this embodiment is to determine the distribution of the entire dark area, it is necessary to extract the second dark area from the second transition area and fill in the vacant positions in the second dark area to obtain the third dark area. At this time, the third dark area does not include the first dark area.

[0068] Step 160: Combine and post-process the first dark area and the third dark area to obtain an upper contour area including the feed edge line.

[0069] In this embodiment, the first dark area is combined with the third dark area, and after a series of post-processing operations, the upper contour area of ​​the positive electrode sheet of the square battery cell can be determined from the area of ​​interest. At this time, the feeding edge line is the top boundary line of the upper contour area. In this way, even in the case of uneven image grayscale and a large number of transition pixels, the solution provided in this embodiment can still accurately extract the feeding edge line of the positive electrode sheet of the square battery cell.

[0070] In one embodiment, determining the first dark area in the region of interest specifically includes:

[0071] The first step is to compress the region of interest to obtain a compressed region.

[0072] It can be understood that by compressing the region of interest, the interference of edge transition pixels near the edge line of the feed material on the image processing process can be reduced, thereby improving the accuracy and reliability of the detection process.

[0073] In the second step, the target dark area in the compressed area is determined by a local threshold algorithm.

[0074] In practical applications, the local threshold used in the local threshold algorithm generally divides the compressed area into several sub-image areas during the selection process, and determines the corresponding local threshold for each sub-image area. Then, according to the local thresholds corresponding to different sub-image areas, the dark pixels in different sub-image areas are determined respectively. Finally, the target dark area can be obtained based on all the determined dark pixels.

[0075] In some embodiments, a relatively classic local threshold algorithm such as the Bernsen algorithm or the Niblack algorithm may be used to determine the target dark area.

[0076] In the third step, the target dark area is enlarged to obtain a first dark area; wherein the compression multiple of the compression process is the same as the magnification multiple of the amplification process.

[0077] It is understandable that, since the target dark area is extracted from the compressed area, it needs to be enlarged to restore the image size, so the processing multiples corresponding to the compression processing and the enlargement processing should be consistent.

[0078] In one embodiment, after obtaining the first dark area, the method may further include:

[0079] The burrs and irregular areas around the first dark area are removed.

[0080] In this embodiment, the extracted first dark area may be subjected to an opening operation and a closing operation using a rectangle as a structural element, so as to remove burrs and irregular areas around the first dark area, thereby making the first dark area more accurate.

[0081] It can be understood that opening and closing are two commonly used processing operations in morphological image processing. Opening is usually used to eliminate small objects or separate touching objects, while closing is usually used to fill small holes or connect broken objects. The two processing operations can be used to complement each other to achieve image enhancement, segmentation and denoising functions.

[0082] In one embodiment, the second dark area is complemented to obtain the third dark area, which specifically includes:

[0083] First, the remaining dark area in the region of interest is determined by the position information prior condition. It can be understood that the position information prior condition can be determined based on key information such as the size and placement position of the square battery cell positive electrode. The remaining dark area can be understood as the dark area composed of dark pixels in the region of interest except the second dark area and the first dark area.

[0084] Then, the second dark area is complemented based on the remaining dark area to obtain a third dark area.

[0085] It can be understood that after the completion processing, the second dark area will be more complete and accurate, thereby being able to improve the accuracy of the upper contour area determined subsequently.

[0086] In one embodiment, the first dark area and the third dark area are combined and post-processed to obtain the upper contour area of ​​the positive electrode sheet of the square battery cell, which specifically includes:

[0087] In the first step, the first dark area is combined with the third dark area to obtain a fourth dark area.

[0088] It can be understood that after combining the first dark area with the third dark area, all dark areas in the region of interest, namely the fourth dark area, can be obtained. Figure 7 The distribution of the fourth dark area is shown as an example.

[0089] In the second step, gap-filling processing is performed on the fourth dark area to obtain the fifth dark area.

[0090] In this embodiment, the fourth dark area may be opened and closed to achieve gap filling processing, thereby obtaining a more accurate dark area, namely, the fifth dark area. Figure 8 The distribution of the fifth dark area is shown as an example. It can be understood that the fifth dark area is a partial area of ​​the positive electrode plate of the square battery cell.

[0091] The third step is to extract and segment the contour of the fifth dark area to obtain the upper contour area containing the edge line of the feed material.

[0092] It can be understood that the top boundary line of the upper contour area is the feeding edge line of the positive electrode sheet of the square battery cell, so the position of the feeding edge line can be determined according to the upper contour area, thereby realizing the precise extraction function of the feeding edge line.

[0093] In one embodiment, after obtaining the upper contour area including the feeding edge line, the method may further include:

[0094] First, determine the feeding angle of the positive electrode sheet of the square battery cell based on the upper contour area.

[0095] In some embodiments, the pixel information of each target pixel point on the edge line of the feed material and the pixel information of the associated pixel points adjacent to the feed material boundary line in the upper contour area can be first extracted, and the feed material angle can be determined according to the difference in pixel information between the target pixel point and the associated pixel point. Specifically, the corresponding relationship between the pixel difference value of the target pixel point and the associated pixel point and the feed material angle can be established in advance, and then after determining the pixel information difference value, the feed material angle can be directly determined according to the corresponding relationship.

[0096] Then, according to the feeding angle, the feeding discount detection result of the positive electrode piece of the square battery cell is obtained.

[0097] In this embodiment, after the feeding angle is determined, it is possible to determine whether the feeding positive electrode sheet of the square battery cell is folded by threshold comparison, thereby obtaining a feeding folding detection result.

[0098] In one embodiment, according to the feeding angle, the feeding folding detection result of the positive electrode sheet of the square battery cell is obtained, which specifically includes:

[0099] If the feeding angle is greater than the preset angle threshold, the feeding discount detection result is that the positive electrode of the square battery cell is broken;

[0100] If the feeding angle is less than or equal to the preset angle threshold, the feeding discount detection result is that there is no feeding discount on the positive electrode of the square battery cell.

[0101] In actual applications, the preset angle threshold can be reasonably set according to actual detection needs. For example, in scenarios with high detection accuracy requirements, the preset angle threshold can be set slightly smaller. In scenarios with low detection accuracy requirements, the preset angle threshold can be set slightly larger to meet specific scenario requirements.

[0102] In some embodiments, after detecting that the positive electrode of the square battery cell is broken, the detection result can be pushed to a management terminal, which can be a fixed monitoring terminal for supervision or a mobile monitoring terminal carried by the management personnel.

[0103] Based on the same general inventive concept, the present invention also protects a detection device for a square battery cell positive electrode sheet. The detection device for a square battery cell positive electrode sheet provided by the present invention is described below. The detection device for a square battery cell positive electrode sheet described below and the detection method for a square battery cell positive electrode sheet described above can be referenced to each other.

[0104] Fig. 9 It is a structural schematic diagram of a detection device for a positive electrode sheet of a square battery cell provided in an embodiment of the present invention.

[0105] like Fig. 9 As shown, the detection device for the positive electrode sheet of a square battery cell provided by the embodiment of the present invention specifically includes:

[0106] The extraction module 310 is used to extract the region of interest in the electrode piece image of the square battery cell positive electrode piece; wherein the region of interest includes the feeding edge line of the square battery cell positive electrode piece.

[0107] The determination module 320 is configured to determine a first dark area in the region of interest.

[0108] The operation module 330 is used to perform a difference operation on the first dark area and the region of interest to obtain a first transition area.

[0109] The first processing module 340 is used to perform an opening operation and a region scattering process on the first transition region to obtain a second transition region.

[0110] The second processing module 350 is used to extract the second dark area in the second transition area and perform a completion process on the second dark area to obtain a third dark area.

[0111] The third processing module 360 ​​is used to combine and post-process the first dark area and the third dark area to obtain an upper contour area including a feed edge line.

[0112] In one embodiment, the determination module 320 specifically includes:

[0113] A compression unit, used for compressing the region of interest to obtain a compressed region;

[0114] A computing unit, used for determining a target dark area in the compression area by a local threshold algorithm;

[0115] The amplification unit is used to amplify the target dark area to obtain a first dark area; wherein the compression multiple of the compression process is the same as the amplification multiple of the amplification process.

[0116] In one embodiment, the determination module 320 further includes:

[0117] The elimination unit is used to eliminate burrs and irregular areas around the first dark area.

[0118] In one embodiment, the second processing module 350 performs a completion process on the second dark area to obtain a third dark area through the following process, including:

[0119] Determine the remaining dark area in the region of interest through the location information prior;

[0120] The second dark area is complemented based on the remaining dark area to obtain a third dark area.

[0121] In one embodiment, the third processing module 360 ​​specifically includes:

[0122] A combining unit, used for combining the first dark area with the third dark area to obtain a fourth dark area;

[0123] A filling unit, used for performing gap filling processing on the fourth dark area to obtain a fifth dark area;

[0124] The extraction and segmentation unit is used to extract and segment the contour of the fifth dark area to obtain an upper contour area containing the edge line of the input material.

[0125] In one embodiment, the detection device for the positive electrode sheet of a square battery cell provided by the present invention may further include:

[0126] The fourth processing module is used to determine the feeding angle of the positive electrode sheet of the square battery cell according to the upper contour area;

[0127] The fold detection module is used to obtain the fold detection result of the positive electrode sheet of the square battery cell according to the feeding angle.

[0128] In one embodiment, the discount detection module specifically includes:

[0129] The first detection unit is used to determine that the feed-in angle is greater than a preset angle threshold, and the feed-in angle detection result is that the positive electrode sheet of the square battery cell is broken;

[0130] The second detection unit is used to determine that the feed discount detection result is that the square battery cell positive electrode sheet has no feed discount when the feed angle is less than or equal to a preset angle threshold.

[0131] In summary, the detection device for the positive electrode sheet of a square battery cell provided by an embodiment of the present invention extracts a region of interest in the electrode sheet image of the positive electrode sheet of a square battery cell through an extraction module, determines a first dark region in the region of interest through a determination module, performs a difference operation on the first dark region and the region of interest through a calculation module to obtain a first transition region, performs an opening operation and region breaking-up processing on the first transition region through a first processing module to obtain a second transition region, extracts a second dark region in the second transition region through a second processing module, and completes the second dark region to obtain a third dark region, combines and post-processes the first dark region and the third dark region through a third processing module to obtain an upper contour region containing a feed edge line, and can extract the upper contour region containing a feed edge line when the image grayscale is uneven and there are many transition pixels, thereby improving the accuracy and reliability of feed edge detection.

[0132] Fig.10 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention.

[0133] like Fig.10 As shown, the electronic device may include: a processor 410, a communication interface 420, a memory 430 and a communication bus 440, wherein the processor 410, the communication interface 420 and the memory 430 communicate with each other through the communication bus 440. The processor 410 may call the logic instructions in the memory 430 to execute the detection method of the square cell positive electrode sheet provided in the above embodiments, the method comprising: extracting the region of interest in the electrode sheet image of the square cell positive electrode sheet; wherein the region of interest includes the feeding edge line of the square cell positive electrode sheet; determining the first dark region in the region of interest; performing a difference operation on the first dark region and the region of interest to obtain a first transition region; performing an open operation and a region scattering process on the first transition region to obtain a second transition region; extracting the second dark region in the second transition region, and completing the second dark region to obtain a third dark region; combining and post-processing the first dark region and the third dark region to obtain an upper contour region including the feeding edge line.

[0134] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0135] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the detection method of the square battery cell positive electrode sheet provided in the above-mentioned embodiments, the method including: extracting a region of interest in the electrode sheet image of the square battery cell positive electrode sheet; wherein the region of interest includes the feeding edge line of the square battery cell positive electrode sheet; determining a first dark area in the region of interest; performing a difference operation on the first dark area and the region of interest to obtain a first transition area; performing an opening operation and region breaking up processing on the first transition area to obtain a second transition area; extracting the second dark area in the second transition area, and completing the second dark area to obtain a third dark area; combining and post-processing the first dark area with the third dark area to obtain an upper contour area including the feeding edge line.

[0136] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for detecting the square battery cell positive electrode sheet provided in the above-mentioned embodiments, the method comprising: extracting a region of interest in the electrode sheet image of the square battery cell positive electrode sheet; wherein the region of interest includes the feeding edge line of the square battery cell positive electrode sheet; determining a first dark area in the region of interest; performing a difference operation on the first dark area and the region of interest to obtain a first transition area; performing an open operation and region breakup processing on the first transition area to obtain a second transition area; extracting the second dark area in the second transition area, and completing the second dark area to obtain a third dark area; combining and post-processing the first dark area with the third dark area to obtain an upper contour area including the feeding edge line.

[0137] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0138] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0139] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for detecting a positive electrode of a square battery cell, characterized in that: include: Extracting a region of interest from a pole piece image of a square battery cell positive pole piece; wherein the region of interest includes a feeding edge line of the square battery cell positive pole piece; determining a first dark region in the region of interest; Performing a difference operation on the first dark area and the region of interest to obtain a first transition area; Performing an opening operation and a region scattering process on the first transition region to obtain a second transition region; extracting a second dark area in the second transition area, and performing a completion process on the second dark area to obtain a third dark area; The first dark area and the third dark area are combined and post-processed to obtain an upper contour area including the feeding edge line.

2. The method for detecting the positive electrode of a square battery cell according to claim 1, characterized in that: Determining a first dark area in the region of interest includes: Performing compression processing on the region of interest to obtain a compressed region; Determine the target dark area in the compressed area by a local threshold algorithm; Amplifying the target dark area to obtain the first dark area; The compression factor of the compression process is the same as the magnification factor of the magnification process.

3. The method for detecting the positive electrode of a square battery cell according to claim 2, characterized in that: After obtaining the first dark area, the method further includes: The burrs and irregular areas around the first dark area are removed.

4. The method for detecting the positive electrode of a square battery cell according to claim 1, characterized in that: The second dark area is complemented to obtain a third dark area, including: Determine the remaining dark area in the region of interest by using the position information prior condition; The second dark area is complemented based on the remaining dark area to obtain a third dark area.

5. The method for detecting the positive electrode of a square battery cell according to claim 1, characterized in that: The first dark area and the third dark area are combined and post-processed to obtain an upper contour area of ​​the positive electrode sheet of the square battery cell, including: combining the first dark area and the third dark area to obtain a fourth dark area; Performing gap filling processing on the fourth dark area to obtain a fifth dark area; The fifth dark area is subjected to contour extraction and contour segmentation to obtain an upper contour area including the feeding edge line.

6. The method for detecting the positive electrode of a square battery cell according to claim 1, characterized in that: After obtaining the upper contour area including the feeding edge line, the method further comprises: Determining a feeding angle of the positive electrode sheet of the square battery cell according to the upper contour area; According to the feeding angle, the feeding discount detection result of the positive electrode sheet of the square battery cell is obtained.

7. The method for detecting the positive electrode of a square battery cell according to claim 6, characterized in that: According to the feeding angle, the feeding discount detection result of the positive electrode sheet of the square battery cell is obtained, including: If the feeding angle is greater than the preset angle threshold, the feeding discount detection result is that the feeding discount occurs in the positive electrode sheet of the square battery cell; If the feeding angle is less than or equal to the preset angle threshold, the feeding discount detection result is that there is no feeding discount on the positive electrode sheet of the square battery cell.

8. A detection device for a positive electrode of a square battery cell, characterized in that: include: An extraction module, used to extract a region of interest in the image of the positive electrode of the square battery cell; wherein the region of interest includes a feeding edge line of the positive electrode of the square battery cell; A determination module, configured to determine a first dark area in the region of interest; A calculation module, used for performing a difference operation on the first dark area and the region of interest to obtain a first transition area; A first processing module, configured to perform an opening operation and a region scattering process on the first transition region to obtain a second transition region; A second processing module is used to extract a second dark area in the second transition area, and perform a completion process on the second dark area to obtain a third dark area; The third processing module is used to combine and post-process the first dark area and the third dark area to obtain an upper contour area including the feeding edge line.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method for detecting the positive electrode sheet of a square battery cell as described in any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for detecting the positive electrode sheet of a square battery cell as claimed in any one of claims 1 to 7 is implemented.

Images