A battery vhb defect detection method and device and storage medium

Abstract

The application provides a battery VHB defect detection method and device and a storage medium. The method comprises the following steps: obtaining a target image; generating an object segmentation result in the target image, wherein the object segmentation result is used to represent a VHB head and a battery body in the target image; calculating a distance from an edge of each VHB head in the target image to the battery body in the target image according to the object segmentation result; and determining whether each VHB head in the target image has an out-of-body defect based on a first preset threshold. The technical scheme provided by the application can improve the accuracy of the battery defect detection result and improve the detection efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of battery defect detection, and particularly relates to a battery VHB defect detection method and device and a storage medium. BACKGROUND

[0002] With the development of science and technology, batteries have been widely applied. In the packaging stage of the battery, due to the complex manufacturing process, defects exist on the surface of the battery, and the existence of the defects will reduce the service life of the battery, cause short circuit of the battery and the like, and therefore, it is more and more necessary to detect the defects on the surface of the battery.

[0003] The lithium battery applied to electronic products such as mobile phones and tablets is mainly a soft package battery, and the VHB tape is usually used to wrap the outside of the battery to ensure the sealing and strength of the battery. Therefore, it is necessary to detect the defects of the VHB on the lithium battery. However, in the prior art, the defects of the VHB on the battery are usually detected by manual visual inspection, which is prone to miss detection and false detection, resulting in low accuracy of the detection result, and at the same time, unnecessary human resources are wasted, and the detection efficiency is low. SUMMARY

[0004] Therefore, the present application provides a battery VHB defect detection method and device and a storage medium to solve the technical problems of low accuracy and low efficiency of the detection result in the prior art.

[0005] In a first aspect, the present application provides a battery VHB defect detection method, comprising:

[0006] obtaining a target image;

[0007] generating an object segmentation result in the target image, the object segmentation result being used to represent a VHB head and a battery body in the target image;

[0008] According to the object segmentation result, the distance from the edge of each VHB head in the target image to the battery body in the target image is calculated.

[0009] Based on a first preset threshold, it is determined whether each VHB head in the target image has an out-of-body defect.

[0010] In an embodiment, the method further comprises:

[0011] Based on a second preset threshold, it is determined whether each VHB head in the target image has a deviation defect.

[0012] In an embodiment, the method further comprises:

[0013] determine whether the target image has a VHB head missing defect based on a third preset threshold and a total number of VHB heads in the target image.

[0014] In one embodiment, the target image includes a bright area and a dark area, which respectively correspond to two ends of a battery body in the target image.

[0015] In one embodiment, the calculating of the distance from the edge of each VHB head in the target image to the battery body in the target image according to the object segmentation result includes:

[0016] calculating the distance from the dark side edge of each VHB head in the dark area to the bright side edge of the battery body in the bright area according to the object segmentation result, and determining the distance from the dark side edge of each VHB head in the dark area to the battery body;

[0017] calculating the distance from the bright side edge of each VHB head in the dark area to the bright side edge of the battery body in the bright area according to the object segmentation result, and determining the distance from the bright side edge of each VHB head in the dark area to the battery body.

[0018] In one embodiment, the determining of whether each VHB head in the target image has an out-of-body defect based on the first preset threshold includes: determining whether each VHB head in the target image has an out-of-body defect according to the distance from the dark side edge of each VHB head in the dark area to the battery body and the first preset threshold;

[0019] The determining of whether each VHB head in the target image has a deviation defect based on the second preset threshold includes: determining whether each VHB head in the target image has a deviation defect according to the distance from the bright side edge of each VHB head in the dark area to the battery body and the second preset threshold.

[0020] In one embodiment, before the acquiring of the target image, the method further includes:

[0021] acquiring a first target image of a battery to be inspected under a first lighting scheme;

[0022] acquiring a second target image of the battery to be inspected under a second lighting scheme;

[0023] In the first lighting scheme, the bright area corresponds to a first end of the battery to be inspected, and the dark area corresponds to a second end of the battery to be inspected.

[0024] In the second lighting scheme, the bright area corresponds to a second end of the battery to be detected, and the dark area corresponds to a first end of the battery to be detected.

[0025] In a second aspect, the present application provides a battery VHB defect detection device, comprising:

[0026] An acquisition module is configured to acquire a target image.

[0027] A generation module is configured to generate an object segmentation result in the target image, the object segmentation result being used to represent a VHB head and a battery body in the target image.

[0028] A calculation module is configured to calculate, according to the object segmentation result, a distance from an edge of each VHB head in the target image to the battery body in the target image.

[0029] An out-of-body defect determination module is configured to determine, based on a first preset threshold, whether each VHB head in the target image has an out-of-body defect.

[0030] In a third aspect, the present application provides a computer device, comprising a memory and a processor, which are communicatively connected to each other, and the memory stores computer instructions, and the processor implements the battery VHB defect detection method of the first aspect by executing the computer instructions.

[0031] In a fourth aspect, the present application provides a computer readable storage medium, which stores computer instructions, and the computer instructions are executed by a processor to implement the battery VHB defect detection method of the first aspect.

[0032] The battery VHB defect detection method, device and storage medium provided by the present application have at least the following beneficial effects:

[0033] The technical solution provided by the present application can perform object recognition and segmentation on the VHB head and the battery body in the target image, calculate the distance from the edge of each VHB head to the battery body, and then calculate the gap between the VHB head and the short side of the battery, determine whether the VHB head has an out-of-body defect, and detect the sealing defect of the short side of the battery. Through the image recognition detection method, the waste of human resources is reduced, the accuracy of the detection result is improved, and the overall detection rate and detection efficiency are improved.

[0034] As can be seen, through the above-mentioned method, the accuracy of the battery defect detection result can be improved, and the detection efficiency can be improved. BRIEF DESCRIPTION OF DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the specific embodiments or the prior art of the present application, the drawings needed to be used in the description of the specific embodiments or the prior art will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings. It should be noted that the drawings in the following description are schematic and should not be understood as any limitation on the present application. In the drawings:

[0036] Figure 1 The battery surface collected image under a light mode in an embodiment of the present application is shown;

[0037] Figure 2 The battery surface collected image under another light mode in an embodiment of the present application is shown;

[0038] Figure 3 The schematic diagram of the battery VHB defect detection method in an embodiment of the present application is shown;

[0039] Figure 4 The schematic diagram of the battery VHB defect detection device in an embodiment of the present application is shown;

[0040] Figure 5 The schematic diagram of the computer device in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be clearly and completely described below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are some embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of the present application.

[0042] In the description of the present application, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the present application. In addition, the terms "first", "second", "third" are only for the purpose of description, and cannot be understood as indicating or implying relative importance.

[0043] In the description of the present application, it should be noted that unless specifically defined and limited, the terms "mounting", "connection", "connecting" should be understood broadly, for example, it can be fixed connection, or detachable connection, or integral connection; it can be mechanical connection, or electrical connection; it can be direct connection, or indirect connection through intermediate medium, or internal connection of two elements, it can be wireless connection, or wired connection. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0044] In addition, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as there is no conflict.

[0045] Although the processes described below include a plurality of operations appearing in a specific order, it should be clearly understood that these processes can also include more or less operations, which can be executed sequentially or in parallel.

[0046] Embodiment 1

[0047] The battery VHB defect detection method provided by the present application is suitable for detecting soft package lithium batteries, and can be used for mobile phone lithium batteries. Referring to Figure 1 The battery VHB defect detection method provided by the present application is suitable for detecting soft package lithium batteries, and can be used for mobile phone lithium batteries. Referring to Figure 1 The battery VHB defect detection method provided by the present application is mainly used for detecting the defects of the VHB head of the battery. Figure 1 The battery VHB defect detection method provided by the present application is mainly used for detecting the defects of the VHB head of the battery.

[0048] Referring to Figure 3 The battery VHB defect detection method provided by an embodiment of the present application can include the following steps.

[0049] S301, acquiring a target image;

[0050] S302, generating an object segmentation result in the target image, the object segmentation result being used to represent the VHB head and the battery body in the target image.

[0051] In the present embodiment, the target image can be an acquisition image containing a target surface of a battery acquired by an image acquisition device in a battery defect detection system. Specifically, the target image can be an acquisition image of the A surface of a lithium battery as shown in Figure 1 In actual application, for example, a camera for acquiring images can be arranged above a stage, a lithium battery is placed on the stage in a corresponding posture, and the A surface of the lithium battery is aligned with the camera. Under a corresponding lighting scheme, an acquisition image as shown in Figure 1The target image is shown. In the target image, the VHB head and the battery body may have different degrees of coincidence. In order to effectively identify the defects of the VHB head, the VHB head and the battery body need to be accurately segmented. In practical applications, an edge detection algorithm can be used to identify the contours of the VHB head and the battery body in the target image, thereby achieving the purpose of segmenting the VHB head and the battery body.

[0052] In one embodiment, to improve the segmentation efficiency of the VHB head and the battery body, a segmentation network can be used to segment the target image, thereby generating corresponding VHB head segmentation results and battery body segmentation results. The selected segmentation network can include Mask R-Cnn, solov2, Deep-Mask, U-Net, etc. In practical applications, the corresponding segmentation network can be flexibly selected according to different scene requirements.

[0053] S303, according to the object segmentation result, calculating the distance from the edge of each VHB head in the target image to the battery body in the target image;

[0054] S304, based on the first preset threshold, determining whether each VHB head in the target image has an out-of-body defect.

[0055] In this embodiment, after object segmentation of the target image, the object segmentation result obtained includes each VHB head segmentation area and battery body segmentation area. The distance from the edge of each VHB head to the battery body is calculated, that is, the distance from the edge contour of the VHB head segmentation area to the edge contour of the battery body segmentation area is calculated. It is judged whether the VHB head has an out-of-body defect, that is, whether the VHB head is in contact with the short side of the battery. By selecting the edge contour of the VHB head far away from the battery body side as the target edge, the distance from the edge contour of the VHB head segmentation area to the edge contour of the battery body segmentation area is calculated, thereby obtaining the distance from the edge contour of the VHB head to the short side of the battery. The first preset threshold is compared to determine whether the VHB head is in contact with the short side of the battery, and then determine whether the VHB head has an out-of-body defect.

[0056] In this embodiment, by object recognition and segmentation of the VHB head and the battery body in the target image, the distance from the edge of each VHB head to the battery body is calculated, and the gap between the VHB head and the short side of the battery can be calculated. It is determined whether the VHB head has an out-of-body defect, and the sealing defect of the short side of the battery can be detected. Through image recognition detection, the waste of human resources is reduced, the accuracy of the detection result is improved, and the overall detection rate and detection efficiency are improved.

[0057] In one embodiment, the method further comprises:

[0058] determining, based on a second preset threshold, whether each VHB head in the target image has a misalignment defect.

[0059] In the embodiment, the misalignment defect of the VHB head is mainly caused by the fact that the VHB is not closely adhered or is misaligned when wrapping the battery. The misalignment defect of the VHB head mainly manifests as the inclination of the VHB head or the shortage of the VHB head (shortage caused by the fact that the VHB head exceeds the body). Specifically, whether the VHB head has a misalignment defect is determined, i.e., whether the VHB head is inclined or the coincident part of the VHB head and the battery body is short. On the one hand, by selecting the edge profile of the coincident side of the VHB head as a target edge, the distance between the edge profile of the VHB head segmentation region obtained by calculation and the edge profile of the battery body segmentation region is calculated, thereby obtaining the distance between the edge profile of the coincident side of the VHB head and the short side of the battery, which is used for comparison with a second preset threshold to determine whether the coincident part of the VHB head and the battery body is short, and further determine whether the VHB head has a misalignment defect. On the other hand, by selecting the edge profile of the coincident side of the VHB head as a target edge and selecting a plurality of target points on the target edge, the distance between the plurality of target points and the edge profile of the battery body segmentation region is calculated, and by determining whether the distances of different points to the edge profile of the battery body segmentation region are the same, it can be determined whether the VHB head is inclined, and further determine whether the VHB head has a misalignment defect.

[0060] In the embodiment, by performing object recognition segmentation on the VHB head and the battery body in the target image, the distance between the edge of each VHB head and the battery body (the edge profile of the coincident side of the VHB head as a target edge) is calculated, which can determine whether the VHB head and the battery are inclined, determine whether the coincident part of the VHB head and the battery body is short, and further determine whether the VHB head has a misalignment defect, and the VHB sealing defect on the battery can be detected. The detection range of the VHB head defect is expanded, the accuracy of the detection result is improved, and the overall detection rate and detection efficiency are further improved.

[0061] In one embodiment, the method further comprises:

[0062] determining, based on a third preset threshold and the total number of VHB heads in the target image, whether there is a VHB head missing defect in the target image.

[0063] In the embodiment, it is determined whether the VHB head is missing, that is, whether the number of VHB head segmentation regions in the object segmentation result is equal to the third preset threshold. If yes, it indicates that the VHB head is not missing, and if no, it indicates that the VHB head is missing. In actual application, the target image can also be divided into different regions, and it can be determined whether the VHB head is missing in the target image by judging whether the VHB head exists in the corresponding region. The specific implementation manner is not described herein again.

[0064] In the embodiment, the VHB head missing defect of the lithium battery can be effectively identified by comparing the total number of VHB heads with the third preset threshold, or by judging whether the VHB head exists in the corresponding region, thereby further expanding the detection range of the VHB defect of the battery and improving the detection efficiency of the VHB defect of the battery.

[0065] In one embodiment, the target image includes a bright area and a dark area, which correspond to two ends of the battery body in the target image, respectively.

[0066] In the embodiment, the target image includes a bright area and a dark area. Specifically, the bright area can better represent the inner edge contour of the battery body, so as to accurately segment the VHB head and the battery body and obtain a more accurate edge contour of the battery body. The dark area can better represent the outer edge contour of the VHB head.

[0067] In the embodiment, for example, referring to FIG. 1, Figure 1 , Figure 1 the left side of FIG. 1 is the dark area, and the right side is the bright area. In the right bright area, the battery body can be segmented according to the more clear edge contour of the battery body (corresponding to a section between the two VHB heads), and the overlapping part of the battery body and the two VHB heads is automatically filled, so that the edge contour of the right side of the battery body is more accurate. In actual application, when it is determined whether the left VHB head exceeds the battery body, the distance between the leftmost edge contour of the VHB head and the rightmost edge contour of the battery body can be compared, and it is necessary to note the length of the battery body. Therefore, the target image includes the bright area and the dark area, which is conducive to improving the accuracy of the detection result, thereby improving the overall detection rate and detection efficiency.

[0068] Referring to FIG. 1, in one embodiment, before the target image is acquired, the method further includes:

[0069] acquiring a first target image of the battery to be detected under a first lighting scheme;

[0070] collecting a second target image of the battery under a second lighting scheme;

[0071] In the first lighting scheme, the bright area corresponds to a first end of the battery, and the dark area corresponds to a second end of the battery.

[0072] In the second lighting scheme, the bright area corresponds to the second end of the battery, and the dark area corresponds to the first end of the battery.

[0073] In this embodiment, the VHB head is present at both ends of the battery. In order to ensure that the defects of the VHB head are detected completely, the target images under two lighting schemes need to be collected. The first target image is shown in FIG. 2A, and the second target image is shown in FIG. 2B. Figure 1 Figure 2 Figure 2 The left side of FIG. 2B is a bright area, and the right side is a dark area.

[0074] In practical applications, the rotation of the large battery on the platform or the opening and closing of the light source at different positions can achieve different lighting schemes for the battery. That is, when the light source does not change, the battery can be rotated horizontally by 180° to switch to another lighting scheme. When the position of the battery does not change, the opening and closing of the light source at different positions can switch to another lighting scheme. Two target images are obtained under two lighting schemes, which is conducive to the comprehensive and accurate detection of the defects of the VHB head on the battery according to the two target images, and is conducive to improving the accuracy of the detection results, thereby improving the overall detection rate and detection efficiency.

[0075] In one embodiment, the distance from the edge of each VHB head in the target image to the battery body in the target image is calculated according to the object segmentation result, comprising:

[0076] According to the object segmentation result, the distance from the dark side edge of each VHB head in the dark area to the bright side edge of the battery body in the bright area is calculated, and the distance from the dark side edge of each VHB head in the dark area to the battery body is determined.

[0077] In this embodiment, the distance from the dark side edge of the VHB head to the bright side edge of the battery body is calculated, and then the length of the battery body is subtracted, so that the distance from the dark side edge of the VHB head to the battery body is obtained.

[0078] ​​In one embodiment, the determining whether each VHB head in the target image has the out-of-body defect based on the first preset threshold value comprises: determining whether each VHB head in the target image has the out-of-body defect according to a distance from a dark side edge of each VHB head in the dark area to the battery body, and the first preset threshold value.

[0079] In the embodiment, whether each VHB head has the out-of-body defect can be determined by comparing the distance from the dark side edge of the VHB head to the battery body with the first preset threshold value. This is advantageous to improve the accuracy of the detection result, and further improve the overall detection rate and detection efficiency.

[0080] In one embodiment, the calculating the distance from the edge of each VHB head in the target image to the battery body in the target image according to the object segmentation result comprises:

[0081] The distance from the bright side edge of each VHB head in the dark area to the bright side edge of the battery body in the bright area is calculated according to the object segmentation result, and the distance from the bright side edge of each VHB head in the dark area to the battery body is determined.

[0082] In the embodiment, when the VHB head does not have the out-of-body defect, the VHB head can also have a deviation defect. The distance from the dark side edge of the VHB head to the bright side edge of the battery body can be calculated, and the distance from the dark side edge of the VHB head to the battery body, i.e. the distance by which the VHB head covers the battery body, can be obtained by subtracting the distance from the length of the battery body.

[0083] In one embodiment, the determining whether each VHB head in the target image has the deviation defect based on the second preset threshold value comprises: determining whether each VHB head in the target image has the deviation defect according to a distance from a bright side edge of each VHB head in the dark area to the battery body, and the second preset threshold value.

[0084] In the embodiment, whether each VHB head has the deviation defect can be determined by comparing the distance from the bright side edge of the VHB head to the battery body with the second preset threshold value. For example, the deviation defect caused by the skew of the VHB head, or the VHB head (shortage or overlength) deviation defect caused by the mispositioning of the VHB large plane. This improves the defect detection range, improves the accuracy of the defect detection result, and further improves the overall detection rate and detection efficiency.

[0085] Embodiment 2

[0086] The embodiment provides a battery VHB defect detection device for the battery VHB defect detection method provided in the embodiment 1. Figure 4 As shown in the figure, the battery VHB defect detection device provided by one embodiment of the application can include the following modules.

[0087] The acquisition module is configured to acquire a target image.

[0088] The generation module is configured to generate an object segmentation result in the target image, and the object segmentation result is used to represent a VHB head and a battery body in the target image.

[0089] The calculation module is configured to calculate distances from edges of each VHB head in the target image to the battery body in the target image according to the object segmentation result.

[0090] The out-of-body defect determination module is configured to determine whether each VHB head in the target image has an out-of-body defect based on a first preset threshold.

[0091] The battery VHB defect detection device provided by the embodiment of the application can be applied to the battery VHB defect detection method provided in the embodiment 1, and the related details refer to the method provided in the embodiment 1, and the implementation principle and technical effects are similar, and will not be described here.

[0092] It should be noted that the battery VHB defect detection device provided in the embodiment of the application is used for battery VHB defect detection, and only the division of the above functional modules / functional units is used as an example for illustration, and in actual application, the above functions can be distributed by different functional modules / functional units according to needs, that is, the internal structure of the battery VHB defect detection device is divided into different functional modules / functional units to complete all or part of the functions described above. In addition, the implementation manner of the battery VHB defect detection method provided in the method embodiment 1 is the same as the implementation manner of the battery VHB defect detection device provided in the embodiment 2, and the specific implementation process of the battery VHB defect detection device provided in the embodiment 2 is described in the method embodiment 1, which will not be described here.

[0093] Embodiment 3

[0094] As shown in the figure, the battery VHB defect detection device provided by one embodiment of the application can include the following modules. Figure 5 As shown in the figure, the battery VHB defect detection device provided by one embodiment of the application can include the following modules.

[0095] The processor can be a central processing unit (CPU). The processor can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, graphics processing units (GPU), embedded neural-network processing units (NPU) or other dedicated deep learning co-processors, discrete gate or transistor logic devices, discrete hardware components, or combinations thereof.

[0096] The memory is a non-transitory computer-readable storage medium, and can be used to store non-transitory software programs, non-transitory computer-executable programs and modules, such as program instructions / modules corresponding to the methods in the above embodiments of the present application. The processor executes various functions and data processing of the processor by running the non-transitory software programs, instructions and modules stored in the memory, that is, implements the methods in the above method embodiments.

[0097] The memory can include a program storage area and a data storage area. The program storage area can store an operating system and at least one application required by a function. The data storage area can store data created by the processor and the like. In addition, the memory can include a high-speed random access memory, and can also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state memory device. In some embodiments, the memory can optionally include a memory remotely disposed relative to the processor, and these remote memories can be connected to the processor through a network. Examples of the network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0098] An embodiment of the present application further provides a computer-readable storage medium for storing a computer program, wherein the computer program is executed by a processor to implement the method in the above method embodiments.

[0099] The technical scheme provided in the application can detect the sealing defect of the short side of the battery by performing object recognition segmentation on the VHB head and the battery body in the target image, calculating the distance from the edge of each VHB head to the battery body, and then calculating the gap between the VHB head and the short side of the battery, and determining whether the VHB head has a defect that exceeds the body. The sealing defect of the short side of the battery can be detected. Through the image recognition detection mode, the waste of human resources is reduced, the accuracy of the detection result is improved, and the overall detection rate and detection efficiency are improved.

[0100] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments of the application can be completed by a computer program instructing related hardware, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments of each method. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD), etc. The storage medium can also include a combination of the above-mentioned types of memories.

[0101] The technical features of the above embodiments can be combined in any way. To make the description concise, not all possible combinations of the technical features in the above embodiments are described, but as long as the combinations of the technical features do not contradict, they should be considered within the scope of the present application.

[0102] Although the embodiments of the application are described in conjunction with the drawings, it should not be understood as limiting the scope of the application. It should be noted that for those skilled in the art, other different forms of changes or variations can be made on the basis of the above description without departing from the concept of the application. Here, it is not necessary or possible to exhaust all the embodiments. The obvious changes or variations derived therefrom are still within the protection scope of the application. Therefore, the protection scope of the patent of the application should be subject to the appended claims.

Claims

1. A battery VHB defect detection method, characterized in that: include: Acquire the target image; generating an object segmentation result in the target image, wherein the object segmentation result is used to characterize the VHB head and the battery body in the target image; Calculating the distance between the edge of each VHB head in the target image and the battery body in the target image according to the object segmentation result; Based on a first preset threshold, determining whether each VHB head in the target image has a defect exceeding the body; Calculating the distance from the edge of each VHB head in the target image to the battery body in the target image according to the object segmentation result includes: calculating the distance from the dark side edge of each VHB head in the dark area to the bright side edge of the battery body in the bright area according to the object segmentation result, and determining the distance from the dark side edge of each VHB head in the dark area to the battery body; The determining, based on the first preset threshold, whether each VHB head in the target image has a defect of exceeding the battery body includes: determining whether each VHB head in the target image has a defect of exceeding the battery body according to the distance from the dark side edge of each VHB head in the dark area to the battery body and the first preset threshold; The target image includes a bright area and a dark area, which respectively correspond to the two ends of the battery body in the target image; Before acquiring the target image, the method further includes: Acquire a first target image of the battery to be inspected under a first lighting scheme; Acquiring a second target image of the battery to be inspected under a second lighting scheme; Wherein, under the first lighting scheme, the bright area corresponds to the first end of the battery to be inspected, and the dark area corresponds to the second end of the battery to be inspected; In the second lighting scheme, the bright area corresponds to the second end of the battery to be inspected, and the dark area corresponds to the first end of the battery to be inspected.

2. The battery VHB defect detection method according to claim 1, characterized in that: Also includes: Based on a second preset threshold, it is determined whether each VHB header in the target image has an offset defect.

3. The battery VHB defect detection method according to claim 1, characterized in that: Also includes: Based on a third preset threshold and the total number of VHB headers in the target image, it is determined whether a VHB header missing defect exists in the target image.

4. The battery VHB defect detection method according to claim 1, characterized in that: Calculating the distance from the edge of each VHB head in the target image to the battery body in the target image according to the object segmentation result includes: According to the object segmentation result, the distance from the bright side edge of each VHB head in the dark area to the bright side edge of the battery body in the bright area is calculated, and the distance from the bright side edge of each VHB head in the dark area to the battery body is determined.

5. The battery VHB defect detection method according to claim 1, characterized in that: Based on a second preset threshold, determining whether each VHB head in the target image has an offset defect, including: determining whether each VHB head in the target image has an offset defect based on the distance from the bright side edge of each VHB head in the dark area to the battery body and the second preset threshold.

6. A battery VHB defect detection device, characterized in that: include: An acquisition module, used to acquire a target image; A generating module, configured to generate an object segmentation result in the target image, wherein the object segmentation result is used to characterize the VHB head and the battery body in the target image; a calculation module, configured to calculate, based on the object segmentation result, a distance from an edge of each VHB head in the target image to a battery body in the target image; the calculating, based on the object segmentation result, the distance from the edge of each VHB head in the target image to the battery body in the target image, comprising: calculating, based on the object segmentation result, a distance from a dark side edge of each VHB head in a dark region to a bright side edge of the battery body in a bright region, and determining the distance from the dark side edge of each VHB head in the dark region to the battery body; an exceeding defect determining module, configured to determine, based on a first preset threshold, whether each VHB head in the target image has an exceeding body defect; the determining, based on the first preset threshold, whether each VHB head in the target image has an exceeding body defect, comprising: determining, based on the distance from the dark side edge of each VHB head in the dark area to the battery body and the first preset threshold, whether each VHB head in the target image has an exceeding body defect; The target image includes a bright area and a dark area, which respectively correspond to the two ends of the battery body in the target image; Before acquiring the target image, the method further includes: Acquire a first target image of the battery to be inspected under a first lighting scheme; Acquiring a second target image of the battery to be inspected under a second lighting scheme; Wherein, under the first lighting scheme, the bright area corresponds to the first end of the battery to be inspected, and the dark area corresponds to the second end of the battery to be inspected; In the second lighting scheme, the bright area corresponds to the second end of the battery to be inspected, and the dark area corresponds to the first end of the battery to be inspected.

7. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor implements the battery VHB defect detection method according to any one of claims 1 to 5 by executing the computer instructions.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the battery VHB defect detection method according to any one of claims 1 to 5 is implemented.

Images