Protection film anomaly detection method and device, computer equipment and storage medium

Abstract

The invention relates to a protective film anomaly detection method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring a target image for a protective film of the explosion-proof valve; based on the target position of the liquid injection hole in the target image, determining the corresponding reference position of the protective film of the explosion-proof valve in the target image; based on the brightness value of the pixel point in the target image in the target color channel, determining the corresponding coverage position of the protective film of the explosion-proof valve in the target image; the color of the target color channel is the same as that of a protective film of the anti-explosion valve; and determining an anomaly detection result of the protective film of the explosion-proof valve based on the reference position and the coverage position. By adopting the method, the accuracy of the abnormal detection result of the protective film of the explosion-proof valve can be improved.

Description

Technical Field

[0001] The present application relates to the field of automation technology, and in particular to a protective film abnormality detection method, device, computer equipment and storage medium. Background Art

[0002] With the rapid development of new energy technology, new energy batteries, as the core components of new energy equipment, are widely used in various new energy equipment. The new energy top cover is the top cover of the new energy battery. Usually, a protective film is covered on the explosion-proof valve of the new energy top cover to improve the sealing and safety of the new energy top cover.

[0003] In the traditional technology, a neural network model is used to detect abnormalities on the protective film of the explosion-proof valve. Since the position of the explosion-proof valve has no obvious features, the accuracy of the abnormality detection results obtained by the neural network model is low. Summary of the invention

[0004] Based on this, it is necessary to provide a protective film abnormality detection method, device, computer equipment, computer readable storage medium and computer program product to address the above technical problems, which can improve the accuracy of protective film abnormality detection of explosion-proof valves.

[0005] In a first aspect, the present application provides a method for detecting an abnormality of a protective film, comprising:

[0006] Acquire a target image of a protective film of an explosion-proof valve;

[0007] Based on the target position of the injection hole in the target image, determining the reference position where the protective film of the explosion-proof valve should be located in the target image;

[0008] Based on the brightness value of the pixel point in the target image in the target color channel, determine the corresponding covering position of the protective film of the explosion-proof valve in the target image; the color of the target color channel is the same as the color of the protective film of the explosion-proof valve;

[0009] Based on the reference position and the covering position, an abnormality detection result of the protection film of the explosion-proof valve is determined.

[0010] In a second aspect, the present application also provides a protective film abnormality detection device, comprising:

[0011] An acquisition module, used for acquiring a target image of a protective film of an explosion-proof valve;

[0012] A reference position determination module, used to determine a reference position corresponding to the protective film of the explosion-proof valve in the target image based on the target position of the injection hole in the target image;

[0013] A covering position determination module is used to determine the corresponding covering position of the protective film of the explosion-proof valve in the target image based on the brightness value of the pixel point in the target image in the target color channel; the color of the target color channel is the same as the color of the protective film of the explosion-proof valve;

[0014] The detection module is used to determine an abnormal detection result of the protective film of the explosion-proof valve based on a reference position and a covering position.

[0015] In a third aspect, the present application provides a computer device, the computer device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the steps in the above method when executing the computer program.

[0016] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the steps in the above method when executed by a processor.

[0017] In a fifth aspect, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps in the above method are implemented.

[0018] The above-mentioned protective film abnormality detection method, device, computer equipment, computer-readable storage medium and computer program product determine the reference position of the explosion-proof valve's protective film in the target image by the target position of the injection hole in the target image, that is, the injection hole has obvious geometric features, and the target position of the injection hole in the target image can be accurately determined. The injection hole is near the explosion-proof valve, the relative position of the explosion-proof valve's protective film and the injection hole is fixed, and the size of the protective film is fixed. Therefore, according to the target position of the injection hole, the reference position of the protective film in the target image can be accurately determined. The reference position can be understood as the protective film in The theoretical position in the target image; the corresponding covering position of the explosion-proof valve protective film in the target image is determined by the brightness value corresponding to the target color channel of the pixel point in the target image. Since the protective film is a colored protective film, the corresponding covering position of the protective film in the target image can be accurately determined according to the brightness value corresponding to the target color channel of the pixel point in the target image with the same color as the protective film. The covering position can be understood as the actual position of the protective film in the target image, and then the abnormal detection result of the protective film is determined according to the reference position and the covering position, thereby improving the accuracy of the abnormal detection result of the explosion-proof valve protective film. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A diagram of an application environment of a protective film abnormality detection method provided in an embodiment of the present application;

[0020] Figure 2A schematic diagram of a process for detecting anomalies of a protective film provided in an embodiment of the present application;

[0021] Figure 3 A partial schematic diagram of a new energy top cover provided in an embodiment of the present application;

[0022] Figure 4 A schematic diagram of a process for determining a target position provided in an embodiment of the present application;

[0023] Figure 5 A flowchart of an abnormality detection result determination step provided in an embodiment of the present application;

[0024] Figure 6 A schematic diagram of a protective film deviation provided in an embodiment of the present application;

[0025] Figure 7 A schematic diagram of a protective film perforation provided in an embodiment of the present application;

[0026] Figure 8 A structural block diagram of a protective film abnormality detection device provided in an embodiment of the present application;

[0027] Fig. 9 An internal structure diagram of a computer device provided in an embodiment of the present application;

[0028] Fig.10 An internal structure diagram of a readable storage medium provided in an embodiment of the present application. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0030] The protective film abnormality detection method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. Among them, the terminal 102 can be but is not limited to various personal computers, laptops, smart phones, tablets, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented with an independent server or a server cluster consisting of multiple servers.

[0031] like Figure 2 As shown, the embodiment of the present application provides a protective film abnormality detection method, which is applied to Figure 1 The terminal 102 or the server 104 in the example is used for explanation. It is understandable that the computer device may include at least one of the terminal and the server. The method comprises the following steps:

[0032] Step 202: Acquire a target image of the protective film of the explosion-proof valve.

[0033] Among them, the target image refers to the image data used to detect abnormalities on the protective film of the explosion-proof valve. The target image can be a whole image or a partial image in a whole image. The image content in the target image is a fixed area including the explosion-proof valve and the injection hole in the new energy top cover. It can be understood that the objects captured by different target images are fixed areas including the explosion-proof valve and the injection hole in different new energy top covers. The explosion-proof valve refers to a safety device on the new energy top cover, which is used to prevent dangerous events such as explosions when the new energy battery is under high pressure or overheating. The explosion-proof valve usually releases pressure by rupturing the film or opening a special valve. In order to prevent dust or pollutants from clogging the outlet of the explosion-proof valve, a protective film will be covered on the explosion-proof valve. The protective film refers to a thin film covering the explosion-proof valve. The color and material of the protective film are not limited here.

[0034] Exemplarily, the computer device acquires the image to be detected from the photographing device, and determines the target image for the protective film of the explosion-proof valve from the image to be detected.

[0035] Step 204 : Based on the target position of the injection hole in the target image, determine the reference position where the protective film of the explosion-proof valve should be located in the target image.

[0036] Among them, the new energy top cover refers to the top cover of the new energy battery, which is used to seal and protect the internal structure of the new energy battery. There is an explosion-proof valve and an injection hole on the new energy top cover. The injection hole refers to a small hole in the new energy top cover, which is used to inject electrolyte into the new energy battery. The injection hole is usually small, located near the explosion-proof valve, and has obvious geometric features. For example, a partial schematic diagram of the new energy top cover is shown in Figure 3 As shown, 302 is an explosion-proof valve and 304 is a liquid injection hole.

[0037] The target position refers to the position of the injection hole in the target image. The target position can be the position of the center point of the injection hole in the target image. The target position can be represented by two-dimensional coordinates. The reference position refers to the position of the protective film in the target image according to the design. It can be understood as the theoretical position of the protective film in the target image. The reference position can be represented as the position of multiple pixel points, that is, multiple two-dimensional coordinates.

[0038] Exemplarily, the computer device determines a reference position in the target image where the protective film of the explosion-proof valve should correspond based on the positions of the pixels in the reference coverage area.

[0039] In some embodiments, before determining that the protective film of the explosion-proof valve should be at a corresponding reference position in the target image based on the target position of the injection hole in the target image, the method further includes:

[0040] Determine the injection hole area in the target image through a neural network model;

[0041] The position of the center point of the injection hole area in the target image is determined as the target position of the injection hole in the target image.

[0042] Step 206, based on the brightness value of the pixel point in the target image in the target color channel, determine the corresponding covering position of the explosion-proof valve protective film in the target image; the color of the target color channel is the same as the color of the explosion-proof valve protective film.

[0043] Among them, pixel refers to the smallest unit that constitutes the target image. The target color channel refers to the color channel with the same color as the color of the protective film. The brightness value refers to the value that characterizes the brightness of the color corresponding to the target color channel. The coverage position refers to the position of the protective film in the target image. The coverage position can be expressed as the positions of multiple pixel points, that is, multiple two-dimensional coordinates.

[0044] Exemplarily, the computer device obtains the brightness value corresponding to each pixel in the target image in the target color channel, and determines the corresponding covering position of the protective film of the explosion-proof valve in the target image based on the relationship between the brightness value corresponding to each pixel and the brightness value range.

[0045] Step 208: determining an abnormality detection result of the protective film of the explosion-proof valve based on the reference position and the covering position.

[0046] Among them, the abnormal detection results include but are not limited to at least one of whether it is abnormal and the type of abnormality, for example, the abnormal detection results are divided into normal and abnormal, or the abnormal detection results are divided into protective film missing, protective film perforation and protective film offset, etc.

[0047] Exemplarily, the computer device determines a reference binary matrix based on the reference position, determines a covering binary matrix based on the covering position, and determines an abnormality detection result of the protective film based on the reference binary matrix and the covering binary matrix.

[0048] In this embodiment, the reference position of the explosion-proof valve's protective film in the target image is determined by the target position of the injection hole in the target image, that is, the injection hole has obvious geometric features, and the target position of the injection hole in the target image can be accurately determined. The injection hole is near the explosion-proof valve, the relative position of the explosion-proof valve's protective film and the injection hole is fixed, and the size of the protective film is fixed. Therefore, the reference position of the explosion-proof valve's protective film in the target image can be accurately determined according to the target position of the injection hole. The reference position can be understood as the theoretical position of the protective film in the target image; the covering position of the explosion-proof valve's protective film in the target image is determined by the brightness value corresponding to the target color channel of the pixel point in the target image. Since the protective film is a colored protective film, the covering position of the protective film in the target image can be accurately determined according to the brightness value corresponding to the target color channel of the pixel point in the target image with the same color as the protective film. The covering position can be understood as the actual position of the protective film in the target image, and then the abnormal detection result of the protective film is determined according to the reference position and the covering position, thereby improving the accuracy of the abnormal detection result of the explosion-proof valve's protective film.

[0049] In some embodiments, the flowchart of the target location determination step is as follows: Figure 4 As shown, including:

[0050] Step 402: convert the target image into a grayscale image.

[0051] Among them, grayscale image refers to image data with only brightness information but no color information. Grayscale image represents the brightness and darkness through the grayscale value of each pixel. The amount of grayscale image data is smaller than that of the target image, but it effectively retains the image features.

[0052] Exemplarily, the computer device determines the grayscale value corresponding to each pixel in the target image based on the brightness value corresponding to each color channel of each pixel, and obtains a grayscale image corresponding to the target image based on the grayscale value corresponding to each pixel.

[0053] Step 404 , based on the grayscale image and the grayscale value interval, determine a grayscale binary image corresponding to the grayscale image; the grayscale value of the pixel point corresponding to the injection hole in the grayscale image is within the grayscale value interval.

[0054] The gray value interval refers to the interval in which the gray value representing the injection hole is located. The pixel value of the pixel point in the gray binary image is a first identifier or a second identifier, the first identifier represents that the pixel point is a pixel point constituting the injection hole in the target image, and the second identifier represents that the pixel point is not a pixel point constituting the injection hole in the target image.

[0055] Exemplarily, a computer device determines the identifier of a pixel point in a grayscale image whose grayscale value is within a grayscale value interval as a first identifier, and determines the identifier of a pixel point in the grayscale image whose grayscale value is outside the grayscale value interval as a second identifier; based on the identifier corresponding to each pixel point, a grayscale binary image corresponding to the grayscale image is obtained.

[0056] Step 406: Determine a plurality of target pixel points of the injection hole in the target image based on the grayscale binary image.

[0057] The target pixel point refers to the pixel point representing the injection hole in the target image.

[0058] Exemplarily, the computer device determines a plurality of adjacent pixel points in the target image and corresponding to the first identifier in the grayscale binary image as a plurality of target pixel points.

[0059] Step 408: Determine the target position of the center point of the injection hole in the target image based on the multiple target pixel points.

[0060] Exemplarily, the computer device determines the minimum bounding rectangle of the multiple target pixels, and determines the position of the center point of the minimum bounding rectangle in the target image as the target position of the center point of the injection hole in the target image. The minimum bounding rectangle is a rectangle that surrounds the multiple target pixels and has the smallest area.

[0061] In this embodiment, by converting the target image into a grayscale image, and then converting the grayscale image into a grayscale binary image, the target position of the center point of the injection hole in the target image is determined according to the grayscale binary image, thereby providing accurate basic data for the subsequent determination of the reference position where the protective film of the explosion-proof valve should correspond in the target image.

[0062] In some embodiments, based on the target position of the injection hole in the target image, determining the reference position where the protective film of the explosion-proof valve should be located in the target image includes:

[0063] Obtaining the relative position of the explosion-proof valve and the injection hole, and the preset size of the protective film of the explosion-proof valve;

[0064] Based on the target position, relative position and preset size of the injection hole in the target image, a reference position corresponding to the protective film of the explosion-proof valve in the target image is determined.

[0065] The relative position refers to the position of the explosion-proof valve on the new energy top cover relative to the injection hole. The relative position can be the offset of the center point of the explosion-proof valve on the new energy top cover relative to the center point of the injection hole on the new energy top cover. The offset can be represented by a vector. The preset size refers to the design size of the protective film, which can be understood as the theoretical size of the protective film.

[0066] Exemplarily, a computer device obtains the relative position of the explosion-proof valve and the injection hole, as well as a preset size of the protective film of the explosion-proof valve from a design drawing, and determines the target relative position corresponding to the relative position in the target image, and the target size corresponding to the preset size in the target image based on the shooting parameters of the target image; determines the reference pixel point in the target image to which the protective film of the explosion-proof valve should correspond based on the target position, the target relative position and the target size of the injection hole in the target image, and determines the position of the reference pixel point in the target image as the reference position to which the protective film should correspond in the target image.

[0067] In some embodiments, the computer device obtains the target relative position of the explosion-proof valve and the injection hole in the target image, and the target size of the protective film of the explosion-proof valve in the target image; based on the target position, target relative position and target size of the injection hole in the target image, the reference position corresponding to the protective film of the explosion-proof valve in the target image is determined. That is, the target relative position and target size are directly obtained, thereby reducing the amount of calculation for determining the reference position and improving the efficiency of determining the reference position.

[0068] In the present embodiment, the relative position of the explosion-proof valve and the injection hole in the same new energy top cover, as well as the preset size of the protective film of the explosion-proof valve are fixed. Therefore, the relative position of the explosion-proof valve and the injection hole and the preset size of the protective film of the explosion-proof valve can be obtained. According to the target position, relative position and preset size of the injection hole in the target image, the reference position where the protective film of the explosion-proof valve should be located in the target image can be accurately determined, thereby improving the accuracy of the determined reference position.

[0069] In some embodiments, based on the brightness value of the pixel point in the target image in the target color channel, determining the corresponding covering position of the protective film of the explosion-proof valve in the target image includes:

[0070] For each pixel in the target image, obtain the brightness value corresponding to the pixel in the target color channel;

[0071] The pixel points corresponding to the brightness values ​​in the brightness value interval are determined as the pixel points that the protective film of the explosion-proof valve should cover in the target image;

[0072] The position of the covering pixel point in the target image is determined as the corresponding covering position where the protective film of the explosion-proof valve should be in the target image.

[0073] The brightness interval value refers to the interval in which the brightness value representing the protective film is located. The coverage pixel point refers to the pixel points constituting the protective film in the target image.

[0074] Exemplarily, for each pixel in the target image, the computer device obtains the brightness value corresponding to the pixel in the target color channel, and determines whether the brightness value is within the brightness value range. If so, the pixel corresponding to the brightness value is determined as the covering pixel, and the position of the covering pixel in the target image is determined as the corresponding covering position where the protective film of the explosion-proof valve should be in the target image.

[0075] In this embodiment, the corresponding covering position of the explosion-proof valve protective film in the target image is determined by the relationship between the brightness value corresponding to the pixel point in the target image in the target color channel and the brightness value range. Since the protective film is a colored protective film, the covering pixel point of the explosion-proof valve protective film in the target image can be accurately determined according to the brightness value corresponding to the target color channel in which the pixel point in the target image has the same color as the protective film, and then the corresponding covering position of the explosion-proof valve protective film in the target image is determined according to the position of the covering pixel point in the target image, thereby improving the accuracy of the covering position.

[0076] In some embodiments, Figure 5 As shown, based on the reference position and the covering position, the abnormal detection result of the protective film of the explosion-proof valve is determined, including:

[0077] Step 502: Determine a reference binary matrix corresponding to the target image based on the reference position.

[0078] Among them, the reference binary matrix refers to a binary matrix that represents the reference position of the protective film, the number of elements in the reference binary matrix is ​​the same as the number of pixels in the target image, and the elements in the reference binary matrix correspond one-to-one to the pixels in the target image.

[0079] Exemplarily, the computer device determines the elements corresponding to the reference positions in the reference binary matrix as the first identifiers, and determines the remaining elements as the second identifiers, to obtain the reference binary matrix.

[0080] Step 504: determine the coverage binary matrix corresponding to the target image based on the coverage position.

[0081] Among them, the coverage binary matrix refers to a binary matrix that represents the coverage position, the number of elements in the coverage binary matrix is ​​the same as the number of pixels in the target image, and the elements in the coverage binary matrix correspond one-to-one to the pixels in the target image.

[0082] Exemplarily, the computer device determines the elements corresponding to the covering positions in the covering binary matrix as the first identifiers, and determines the remaining elements as the second identifiers, to obtain the covering binary matrix.

[0083] Step 506, performing an XOR operation on the reference binary matrix and the cover binary matrix to obtain an operation binary matrix.

[0084] Among them, the XOR operation is a logical operation. When the two input values ​​are different, the output is 1; when the two input values ​​are the same, the output is 0.

[0085] Step 508: Determine the abnormality detection result of the protective film of the explosion-proof valve based on the binary matrix operation.

[0086] Exemplarily, the computer device determines an abnormality detection result of the protective film of the explosion-proof valve based on the operation binary matrix and the reference position; the abnormality detection result is one of normal or abnormal.

[0087] In some embodiments, based on the binary matrix and the reference position, determining the abnormality detection result of the protective film of the explosion-proof valve includes:

[0088] If the elements corresponding to the reference positions in the binary matrix are all zero, the abnormal detection result of the explosion-proof valve protective film is normal; if the elements corresponding to at least one reference position in the binary matrix are all one, the abnormal detection result of the explosion-proof valve protective film is abnormal. That is, if the elements corresponding to the reference positions in the binary matrix are all zero, the covering positions are the same as the reference positions, indicating that the explosion-proof valve protective film is intact and the position of the explosion-proof valve protective film has not shifted, and the abnormal detection result of the explosion-proof valve protective film is normal.

[0089] In this embodiment, a reference binary matrix corresponding to the target image is determined based on the reference position, and a covering binary matrix corresponding to the target image is determined based on the covering position. An operation binary matrix is ​​obtained by performing an XOR operation on the reference binary matrix and the covering binary matrix. The operation speed is fast and the operation result is accurate, thereby saving the computing resources of the computer equipment and improving the accuracy of the operation binary matrix. The abnormality detection result of the protective film of the explosion-proof valve is determined based on the operation binary matrix, thereby improving the accuracy of the abnormality detection of the protective film of the explosion-proof valve.

[0090] In some embodiments, based on the binary matrix operation, determining the abnormality detection result of the protective film of the explosion-proof valve includes:

[0091] If the elements corresponding to each reference position in the operation binary matrix are all first identifiers, then the abnormal detection result of the protective film of the explosion-proof valve is determined to be the absence of the protective film; the first identifier indicates that the elements corresponding to the reference position in the reference binary matrix and the covering binary matrix are different; or,

[0092] If the element corresponding to at least one reference position in the binary matrix is ​​the first identifier, and there is an overlap position identical to the reference position, then it is determined that the abnormal detection result of the protective film of the explosion-proof valve is a perforation of the protective film; or,

[0093] If the element corresponding to at least one reference position in the binary matrix is ​​the first identifier, and there is no overlapping position identical to the reference position, then it is determined that the abnormal detection result of the protective film of the explosion-proof valve is protective film deviation.

[0094] Among them, elements refer to the values ​​in the matrix. The first mark is zero, and the corresponding elements of the reference position in the reference binary matrix and the covering binary matrix are different. Protective film missing means that the explosion-proof valve is not covered with protective film. Protective film perforation means that holes appear in the protective film. Protective film offset means that the protective film covers part of the explosion-proof valve. For example, the schematic diagram of protective film offset is as follows Figure 6 As shown, 602 is an explosion-proof valve, 604 is a liquid injection hole, 606 is a protective film, and the protective film 606 does not completely cover the explosion-proof valve 602. The abnormal detection result of the protective film 606 of the explosion-proof valve is that the protective film is offset; the schematic diagram of the protective film perforation is as shown in Figure 7 As shown, 702 is a protective film, 704 is a liquid injection hole, and a hole 706 appears on the protective film 702. Then, the abnormal detection result of the protective film 702 of the explosion-proof valve is that the protective film is perforated.

[0095] Exemplarily, the computer device determines the element corresponding to each reference position in the operational binary matrix. If the elements corresponding to each reference position in the operational binary matrix are all first identifiers, then the abnormal detection result of the protective film of the explosion-proof valve is determined to be the missing protective film; if there is one or more reference positions whose corresponding elements in the operational binary matrix are the first identifiers, then it is further determined whether there is an overlapping position identical to the above-mentioned reference position. If there is an overlapping position identical to the reference position, then the abnormal detection result of the protective film of the explosion-proof valve is determined to be the perforation of the protective film; otherwise, then the abnormal detection result of the protective film of the explosion-proof valve is determined to be the offset of the protective film.

[0096] In this embodiment, by operating the binary matrix, the reference position and the covering position, not only whether the protective film is abnormal can be determined, but also the type of abnormality of the protective film of the explosion-proof valve can be determined.

[0097] In some embodiments, acquiring a target image of a protective film of an explosion-proof valve includes:

[0098] Control the manipulator to move the top cover of the new energy battery to be inspected to the target shooting area;

[0099] Controlling the target shooting device to shoot the top cover of the new energy battery in the target shooting area to obtain an image to be detected;

[0100] The region of interest in the image to be detected is determined as a target image for the protective film of the explosion-proof valve.

[0101] In fact, the manipulator is a mechanical device in industrial automation, which is used to imitate the movements of human arms, to grab and move the top cover of new energy batteries, and to move the top cover of new energy batteries to the target shooting area. The target shooting area refers to a pre-set area for placing the top cover of new energy batteries for shooting. The target shooting device refers to a device used to shoot the image to be detected. The image to be detected refers to the image obtained by shooting the top cover of the new energy battery in the target shooting area. The region of interest refers to the area of ​​concern in the image to be detected, and the region of interest can be preset according to actual needs.

[0102] In this embodiment, the manipulator is controlled to move the new energy battery top cover to be inspected to the target shooting area, and the target shooting device is controlled to shoot the new energy battery top cover in the target shooting area to obtain the image to be inspected, and the area of ​​interest in the image to be inspected is determined as the target image, ensuring that the image content in the target image is a fixed area in the new energy top cover including the explosion-proof valve and the injection hole, thereby laying a foundation for subsequent protective film abnormality detection.

[0103] In an exemplary embodiment, a protective film abnormality detection method for detecting abnormality of a protective film of an explosion-proof valve of a new energy top cover includes:

[0104] (1) The computer device controls the manipulator to move the top cover of the new energy battery to be inspected to the target shooting area, controls the target shooting device to shoot the top cover of the new energy battery in the target shooting area, obtains the image to be inspected, and determines the area of ​​interest in the image to be inspected as the target image.

[0105] (2) The computer device converts the target image into a grayscale image, determines the identifiers of the pixel points in the grayscale image whose grayscale values ​​are within the grayscale value interval as the first identifier, determines the identifiers of the pixel points in the grayscale image whose grayscale values ​​are outside the grayscale value interval as the second identifier, and obtains a grayscale binary image corresponding to the grayscale image based on the identifiers corresponding to the respective pixel points; determines multiple adjacent pixel points in the target image and the corresponding identifiers in the grayscale binary image as the first identifier as multiple target pixel points; determines the minimum circumscribed rectangle of the multiple target pixel points, and determines the position of the center point of the minimum circumscribed rectangle in the target image as the target position of the center point of the injection hole in the target image.

[0106] (3) The computer device obtains the relative position of the explosion-proof valve and the injection hole, as well as the preset size of the protective film of the explosion-proof valve from the design drawing, and determines the target relative position corresponding to the relative position in the target image, and the target size corresponding to the preset size in the target image based on the shooting parameters of the target image; based on the target position, target relative position and target size of the injection hole in the target image, the computer device determines the reference pixel point corresponding to the protective film of the explosion-proof valve in the target image, and determines the position of the reference pixel point in the target image as the reference position that the protective film should correspond to in the target image.

[0107] (4) For each pixel in the target image, the computer device obtains the brightness value corresponding to the pixel in the target color channel and determines whether the brightness value is within the brightness value interval. If the brightness value is within the brightness value interval, the pixel corresponding to the brightness value is determined as the covering pixel. The position of the covering pixel in the target image is used to determine the corresponding covering position of the explosion-proof valve protective film in the target image.

[0108] (5) The computer device determines the elements corresponding to the reference positions in the reference binary matrix as 0 and the remaining elements as 1 to obtain a reference binary matrix; determines the elements corresponding to the covering positions in the covering binary matrix as 0 and the remaining elements as 1 to obtain a covering binary matrix; performs an XOR operation on the reference binary matrix and the covering binary matrix to obtain an operation binary matrix.

[0109] (6) The computer device determines the element corresponding to each reference position in the binary matrix. If the elements corresponding to each reference position in the binary matrix are all 0, the abnormal detection result of the protective film of the explosion-proof valve is determined to be the missing protective film. If there is one or more reference positions whose corresponding elements in the binary matrix are 0, it is further determined whether there is an overlapping position identical to the above reference position. If there is an overlapping position identical to the reference position, it is determined that the abnormal detection result of the protective film of the explosion-proof valve is the perforation of the protective film. If there is no overlapping position identical to the reference position, it is determined that the abnormal detection result of the protective film of the explosion-proof valve is the offset of the protective film.

[0110] In this embodiment, the reference position of the explosion-proof valve's protective film in the target image is determined by the target position of the injection hole in the target image, that is, the injection hole has obvious geometric features, and the target position of the injection hole in the target image can be accurately determined. The injection hole is near the explosion-proof valve, the relative position of the explosion-proof valve's protective film and the injection hole is fixed, and the size of the protective film is fixed. Therefore, the reference position of the explosion-proof valve's protective film in the target image can be accurately determined according to the target position of the injection hole. The reference position can be understood as the theoretical position of the protective film in the target image; the covering position of the explosion-proof valve's protective film in the target image is determined by the brightness value corresponding to the target color channel of the pixel point in the target image. Since the protective film is a colored protective film, the covering position of the protective film in the target image can be accurately determined according to the brightness value corresponding to the target color channel of the pixel point in the target image with the same color as the protective film. The covering position can be understood as the actual position of the protective film in the target image, and then the abnormal detection result of the protective film is determined according to the reference position and the covering position, thereby improving the accuracy of the abnormal detection result of the explosion-proof valve's protective film. Furthermore, by operating the binary matrix, the reference position and the covering position, not only the abnormality of the protective film can be determined, but also the type of the abnormality of the protective film can be determined.

[0111] It should be understood that, although the steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indications of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear description in this article, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0112] Based on the same inventive concept, the embodiment of the present application also provides a protective film abnormality detection device. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above method, so the specific limitations in one or more protective film abnormality detection device embodiments provided below can refer to the limitations of the protective film abnormality detection method above, and will not be repeated here.

[0113] like Figure 8 As shown, an embodiment of the present application provides a protective film abnormality detection device, comprising:

[0114] An acquisition module 802 is used to acquire a target image of a protective film of an explosion-proof valve;

[0115] A reference position determination module 804 is used to determine a reference position corresponding to the protective film of the explosion-proof valve in the target image based on the target position of the injection hole in the target image;

[0116] A covering position determination module 806 is used to determine the corresponding covering position of the protective film of the explosion-proof valve in the target image based on the brightness value of the pixel point in the target image in the target color channel; the color of the target color channel is the same as the color of the protective film of the explosion-proof valve;

[0117] The detection module 808 is used to determine the abnormal detection result of the protective film of the explosion-proof valve based on the reference position and the covering position.

[0118] In some embodiments, the reference location determination module 804 is further configured to:

[0119] Convert the target image to a grayscale image;

[0120] Based on the grayscale image and the grayscale value interval, a grayscale binary image corresponding to the grayscale image is determined; the grayscale value of the pixel point corresponding to the injection hole in the grayscale image is within the grayscale value interval;

[0121] Based on the grayscale binary image, a plurality of target pixel points of the injection hole in the target image are determined;

[0122] Based on the multiple target pixel points, a target position of a center point of the injection hole in the target image is determined.

[0123] In some embodiments, in determining the reference position corresponding to the protective film of the explosion-proof valve in the target image based on the target position of the injection hole in the target image, the reference position determination module 804 is specifically used to:

[0124] Obtaining the relative position of the explosion-proof valve and the injection hole, and the preset size of the protective film of the explosion-proof valve;

[0125] Based on the target position, relative position and preset size of the injection hole in the target image, a reference position corresponding to the protective film of the explosion-proof valve in the target image is determined.

[0126] In some embodiments, in determining the corresponding covering position of the protective film of the explosion-proof valve in the target image based on the brightness value of the pixel point in the target color channel in the target image, the covering position determining module 806 is specifically used to:

[0127] For each pixel in the target image, obtain the brightness value of the pixel in the target color channel;

[0128] The pixel points corresponding to the brightness values ​​in the brightness value interval are determined as the pixel points that the protective film of the explosion-proof valve should cover in the target image;

[0129] The position of the covering pixel point in the target image is determined as the corresponding covering position where the protective film of the explosion-proof valve should be in the target image.

[0130] In some embodiments, in determining the abnormal detection result of the protective film of the explosion-proof valve based on the reference position and the covering position, the detection module 808 is specifically used to:

[0131] Based on the reference position, determine a reference binary matrix corresponding to the target image;

[0132] Based on the coverage position, determine the coverage binary matrix corresponding to the target image;

[0133] Performing an XOR operation on the reference binary matrix and the covering binary matrix to obtain an operation binary matrix;

[0134] Based on the operation binary matrix, the abnormality detection result of the protective film of the explosion-proof valve is determined.

[0135] In some embodiments, in determining the abnormal detection result of the protective film of the explosion-proof valve based on the binary matrix operation, the detection module 808 is specifically used to:

[0136] If the elements corresponding to each reference position in the operation binary matrix are all first identifiers, then the abnormal detection result of the protective film of the explosion-proof valve is determined to be the absence of the protective film; the first identifier indicates that the elements corresponding to the reference position in the reference binary matrix and the covering binary matrix are different; or,

[0137] If the element corresponding to at least one reference position in the binary matrix is ​​the first identifier, and there is an overlap position identical to the reference position, then it is determined that the abnormal detection result of the protective film of the explosion-proof valve is a perforation of the protective film; or,

[0138] If the element corresponding to at least one reference position in the binary matrix is ​​the first identifier, and there is no overlapping position identical to the reference position, then it is determined that the abnormal detection result of the protective film of the explosion-proof valve is protective film deviation.

[0139] In some embodiments, in acquiring a target image of a protective film of an explosion-proof valve, the acquisition module 802 is specifically used to:

[0140] Control the manipulator to move the top cover of the new energy battery to be inspected to the target shooting area;

[0141] Controlling the target shooting device to shoot the top cover of the new energy battery in the target shooting area to obtain an image to be detected;

[0142] The region of interest in the image to be detected is determined as a target image for the protective film of the explosion-proof valve.

[0143] Each module in the above protective film abnormality detection device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module.

[0144] In some embodiments, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Fig. 9 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, the steps in the above-mentioned protective film abnormality detection method are implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0145] Those skilled in the art will understand that Fig. 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0146] In some embodiments, a computer device is provided. The computer device includes a memory and a processor. The memory stores a computer program. When the processor executes the computer program, the steps in the above method embodiments are implemented.

[0147] In some embodiments, a computer-readable storage medium 1000 is provided on which a computer program 1002 is stored. When the computer program 1002 is executed by a processor, the steps in the above-mentioned method embodiments are implemented. The internal structure diagram thereof can be as follows: Fig.10 shown.

[0148] In some embodiments, a computer program product is provided. The computer program product includes a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0149] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0150] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0151] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0152] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for detecting abnormality of a protective film, characterized in that: include: Acquire a target image of a protective film of an explosion-proof valve; Based on the target position of the injection hole in the target image, determining a reference position in the target image where the protective film of the explosion-proof valve should correspond; Based on the brightness value of the pixel point in the target image in the target color channel, determining the corresponding covering position of the protective film of the explosion-proof valve in the target image; the color of the target color channel is the same as the color of the protective film of the explosion-proof valve; Based on the reference position and the covering position, an abnormality detection result of the protection film of the explosion-proof valve is determined.

2. The method according to claim 1, characterized in that Before determining, based on the target position of the injection hole in the target image, that the protective film of the explosion-proof valve should be at a corresponding reference position in the target image, the method further includes: Converting the target image into a grayscale image; Based on the grayscale image and the grayscale value interval, a grayscale binary image corresponding to the grayscale image is determined; the grayscale value of the pixel point corresponding to the injection hole in the grayscale image is within the grayscale value interval; Based on the grayscale binary image, determining a plurality of target pixel points of the injection hole in the target image; Based on the multiple target pixel points, a target position of the center point of the injection hole in the target image is determined.

3. The method according to claim 1, characterized in that The step of determining a reference position in the target image where the protective film of the explosion-proof valve should correspond based on the target position of the injection hole in the target image includes: Obtaining the relative position of the explosion-proof valve and the liquid injection hole, and the preset size of the protective film of the explosion-proof valve; Based on the target position of the injection hole in the target image, the relative position and the preset size, a reference position in the target image where the protective film of the explosion-proof valve should correspond is determined.

4. The method according to claim 1, characterized in that: The step of determining the corresponding covering position of the protective film of the explosion-proof valve in the target image based on the brightness value of the pixel point in the target color channel in the target image includes: For each pixel in the target image, obtain the brightness value of the pixel in the target color channel; Determine the pixel points corresponding to the brightness values ​​in the brightness value interval as the pixel points that the protective film of the explosion-proof valve should cover in the target image; The position of the covering pixel point in the target image is determined as the corresponding covering position of the protective film of the explosion-proof valve in the target image.

5. The method according to claim 1, characterized in that The determining, based on the reference position and the covering position, an abnormality detection result of the protective film of the explosion-proof valve comprises: Based on the reference position, determining a reference binary matrix corresponding to the target image; Based on the coverage position, determining a coverage binary matrix corresponding to the target image; Performing an XOR operation on the reference binary matrix and the covering binary matrix to obtain an operation binary matrix; Based on the operational binary matrix, an abnormality detection result of the protective film of the explosion-proof valve is determined.

6. The method according to claim 5, characterized in that The step of determining the abnormality detection result of the protective film of the explosion-proof valve based on the binary matrix operation includes: If the elements corresponding to each of the reference positions in the operation binary matrix are all first identifiers, it is determined that the abnormal detection result of the protective film of the explosion-proof valve is the absence of the protective film; the first identifier indicates that the elements corresponding to the reference position in the reference binary matrix and the covering binary matrix are different; or, If the element corresponding to at least one of the reference positions in the binary matrix is ​​a first identifier and there is an overlap position identical to the reference position, then it is determined that the abnormal detection result of the protective film of the explosion-proof valve is a perforation of the protective film; or, If the element corresponding to at least one of the reference positions in the binary operation matrix is ​​a first identifier and there is no overlapping position identical to the reference position, it is determined that the abnormal detection result of the protective film of the explosion-proof valve is protective film deviation.

7. The method according to claim 1, characterized in that The step of acquiring a target image of a protective film of the explosion-proof valve comprises: Control the manipulator to move the top cover of the new energy battery to be inspected to the target shooting area; Controlling the target shooting device to shoot the new energy battery top cover in the target shooting area to obtain an image to be detected; The region of interest in the image to be detected is determined as a target image for the protective film of the explosion-proof valve.

8. A protective film abnormality detection device, characterized in that: include: An acquisition module, used for acquiring a target image of a protective film of an explosion-proof valve; A reference position determination module, used to determine a reference position of the protective film of the explosion-proof valve in the target image based on the target position of the injection hole in the target image; A covering position determination module, used to determine the corresponding covering position of the protective film of the explosion-proof valve in the target image based on the brightness value of the pixel point in the target image in the target color channel; the color of the target color channel is the same as the color of the protective film of the explosion-proof valve; The detection module is used to determine an abnormal detection result of the protective film of the explosion-proof valve based on the reference position and the covering position.

9. A computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images