A method and system for detecting defects in an industrial product

Abstract

The application provides a defect detection method and system of an industrial product. The method is applied to an edge computing device in a defect detection system of the industrial product. The defect detection system of the industrial product comprises a mobile device, an image acquisition device and the edge computing device. The method comprises the following steps: acquiring a first image. The first image is acquired by the image acquisition device when a first area of a film is moved to a collection range of the image acquisition device by the mobile device. The first image at least comprises an image of the first area of the film. The film is used to represent structural features of the industrial product.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of industrial detection, in particular to a defect detection method and system for industrial products. BACKGROUND

[0002] In the industrial field, the quality requirements for many industrial products are extremely high, and the defects of industrial products will affect their quality. Therefore, how to detect the defects of industrial products becomes a problem. SUMMARY

[0003] The present application provides the following technical solutions:

[0004] In one aspect, the present application provides a defect detection method for industrial products, which is applied to an edge computing device in a defect detection system for industrial products. The defect detection system for industrial products comprises a mobile device, an image acquisition device and the edge computing device. The method comprises the following steps:

[0005] Obtaining a first image, wherein the first image is acquired by the image acquisition device when a first area of a film is moved into the acquisition range of the image acquisition device by the mobile device, and the first image at least comprises an image of the first area of the film, and the film is used to represent the structural features of the industrial products.

[0006] Determining the defect features of the object to be detected in the first image.

[0007] The first image is obtained by the matrix-arranged multiple imaging elements of the image acquisition device when the first area of the film is moved into the acquisition range of the image acquisition device by the mobile device, and the first image is obtained by photographing the film.

[0008] The defect detection system for industrial products further comprises a light source, wherein the light source is located on the back of the film, and the back of the film is the side of the film that is not facing the image acquisition device.

[0009] Before obtaining the first image, the method further comprises the following steps:

[0010] Obtaining a second image, wherein the second image is acquired by the image acquisition device when the first area of the film is moved into the acquisition range of the image acquisition device by the mobile device, and the second image at least comprises an image of the first area of the film.

[0011] Calculating the gray scale distribution information of the second image.

[0012] Determining the difference between the gray scale distribution information of the second image and the set gray scale distribution threshold value of the second image.

[0013] set a brightness of the light source as a target luminous brightness based on the difference value;

[0014] wherein, under the target luminous brightness, the image acquisition device acquires a first image, and a gray scale distribution information of the first image satisfies a set gray scale distribution threshold of the first image.

[0015] The calculating the gray scale distribution information of the second image comprises:

[0016] calculating a first gray scale distribution information of at least one first part of the second image and a second gray scale distribution information of at least one second part of the second image, the first part containing information of interest in the second image, and the second part containing information of non-interest in the second image;

[0017] The determining the difference value between the gray scale distribution information of the second image and the set gray scale distribution threshold of the second image comprises:

[0018] determining a first difference value between the first gray scale distribution information of the first part of the second image and a first set gray scale distribution threshold of the first part, and a second difference value between the second gray scale distribution information of the second part of the second image and a second set gray scale distribution threshold of the second part;

[0019] The setting the brightness of the light source as the target luminous brightness based on the difference value comprises:

[0020] determining a gray scale compensation value based on the first difference value and a weight of the first part and the second difference value and a weight of the second part, and setting the brightness of the light source as the target luminous brightness based on the gray scale compensation value.

[0021] The method further comprises:

[0022] determining a first position of a defect feature of the object to be detected in the first image;

[0023] outputting a third image, the third image containing the first image, first prompt information corresponding to the defect feature of the object to be detected, and second prompt information corresponding to the first position.

[0024] The outputting the third image comprises:

[0025] determining a second position of a first area of the film included in the first image in the film;

[0026] determining a position of a defect feature of the object to be detected in the film based on the first position and the second position;

[0027] output a third image, the third image including an image of the film, and first prompt information corresponding to a defect feature of the object to be detected and third prompt information corresponding to a position of the defect feature of the object to be detected in the film.

[0028] determine a second position of a first region of the film included in the first image in the film, including:

[0029] obtain a moving distance of the first region of the film moved by the moving device;

[0030] determine the second position of the first region of the film included in the first image in the film based on the moving distance.

[0031] determine a defect feature of an object to be detected in the first image, including:

[0032] perform image segmentation on the first image to obtain at least one sub-image;

[0033] input the sub-image into a defect detection model to obtain a defect feature of a target part in the first image determined by the defect detection model, the target part belonging to the object to be detected.

[0034] Another aspect of the present application provides a defect detection system for an industrial product, including: a moving device, an image acquisition device, an edge computing device;

[0035] The moving device is configured to move the film.

[0036] The image acquisition device is configured to acquire a first image when a first region of the film moved by the moving device moves to a capture range of the image acquisition device, and transmit the first image to the edge computing device, the first image including at least an image of the first region of the film, the film being used to represent a structural feature of the industrial product.

[0037] The edge computing device is configured to execute the defect detection method for the industrial product according to any one of the above.

[0038] The defect detection system for the industrial product further includes:

[0039] A fixing device is configured to fix the film on the moving device.

[0040] And / or,

[0041] A dark box is installed with the image acquisition device.

[0042] The image acquisition device acquires a first image in the dark box when the film is moved into the dark box by the mobile device and the first area of the film is within the acquisition range of the image acquisition device.

[0043] In the present application, in combination with the mobile device, the film and the image acquisition device are moved by the mobile device, and the first image is acquired when the first area of the film is moved into the acquisition range of the image acquisition device. The first image is acquired automatically, and on this basis, the edge computing device can acquire the first image, determine the defect features of the to-be-detected object in the first image, and automatically detect the defects of the industrial product, thereby ensuring the efficiency and accuracy. BRIEF DESCRIPTION OF DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0045] Figure 1 is a flowchart of an industrial product defect detection method provided by Embodiment 1 of the present application;

[0046] Figure 2 is a schematic diagram of an implementation scenario of an industrial product defect detection method provided by Embodiment 1 of the present application;

[0047] Figure 3 is a flowchart of an industrial product defect detection method provided by Embodiment 2 of the present application;

[0048] Figure 4 is a schematic diagram of an implementation scenario of an industrial product defect detection method provided by Embodiment 2 of the present application;

[0049] Figure 5 is a schematic diagram of the relative position relationship between the light source and the film provided by Embodiment 2 of the present application;

[0050] Figure 6 is a flowchart of an industrial product defect detection method provided by Embodiment 3 of the present application;

[0051] Figure 7 is a flowchart of an industrial product defect detection method provided by Embodiment 4 of the present application;

[0052] Figure 8 is a structural schematic diagram of an industrial product defect detection system provided by the present application. DETAILED DESCRIPTION

[0053] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all the other embodiments obtained by those skilled in the art without creative effort belong to the scope of the present application.

[0054] In order to make the above objectives, characteristics and advantages of the present application more obvious and easy to understand, the present application will be further described in detail below with reference to the drawings and specific embodiments.

[0055] Referring to Figure 1 A flowchart of a defect detection method of an industrial product provided by Embodiment 1 of the present application, the method can be applied to an edge computing device in a defect detection system of an industrial product, the defect detection system of the industrial product includes a mobile device, an image acquisition device and an edge computing device, as shown in Figure 1 The method can include but is not limited to the following steps:

[0056] Step S101, acquiring a first image, the first image is acquired by the image acquisition device when the first area of the film is moved into the acquisition range of the image acquisition device by the mobile device, the first image at least includes the image of the first area of the film, and the film is used to represent the structural features of the industrial product.

[0057] Specifically, the image acquisition device can include but is not limited to a plurality of imaging elements arranged in a matrix.

[0058] As shown in Figure 2 The plurality of imaging elements arranged in a matrix of the image acquisition device can take a photo of the film to obtain the first image when the first area of the film is moved into the acquisition range of the image acquisition device by the mobile device, which can ensure the speed of taking a photo of the film, shorten the time of acquiring the first image and improve the efficiency of acquiring the first image.

[0059] It should be noted that Figure 2 The moving direction of the mobile device is shown, the structure of the mobile device is not shown, and the moving direction of the mobile device is not limited to the direction shown in Figure 2 . Figure 2 The defect detection system of the industrial product shown is only an example, which does not limit the defect detection system of the industrial product.

[0060] It can be understood that the plurality of imaging elements arranged in a matrix of the image acquisition device take a photo of the film to obtain an image which can include a plurality of rows of pixels, and the plurality of rows of pixels at least include the pixels included in the image of the first area of the film.

[0061] The structural features of the industrial product for characterization by the film can include, but are not limited to, surface structural features of the industrial product, and / or internal structural features.

[0062] In this embodiment, obtaining the first image can include, but is not limited to:

[0063] S1011, receiving the first image, the first image being sent by the image acquisition device to the edge computing device in real time in the case of acquiring the first image.

[0064] In this embodiment, the image acquisition device can also send a signal to the mobile device after acquiring the first image, and the mobile device moves by a set distance and drives the first film to move when receiving the signal.

[0065] Obtaining the first image can also include:

[0066] S1012, sending an image acquisition instruction to the image acquisition device, so that the image acquisition device sends the first image to the edge computing device in response to the image acquisition instruction.

[0067] The edge computing device can send an image acquisition instruction to the image acquisition device, but is not limited to the case where the set condition is met. For example, the edge computing device can send an image acquisition instruction to the image acquisition device in the case where its performance meets the performance threshold.

[0068] Of course, the edge computing device can also send an image acquisition instruction to the image acquisition device in response to a trigger instruction input by the user, so as to realize defect feature detection triggered by the user.

[0069] S1013, receiving the first image.

[0070] Step S102, determining the defect feature of the object to be detected in the first image.

[0071] Determining the defect feature of the object to be detected in the first image can include:

[0072] S1021, inputting the first image into the defect detection model to obtain the defect feature of the object to be detected in the first image determined by the defect detection model.

[0073] In this embodiment, another embodiment for determining the defect feature of the object to be detected in the first image is also provided, which can specifically include:

[0074] S1022, image segmentation is performed on the first image to obtain at least one sub-image.

[0075] The manner of image segmentation of the first image is not limited in the present application.

[0076] Specifically, the sub-image can at least contain at least part of the information of interest in the first image, and the information of interest is related to the industrial product.

[0077] S1023, input the sub-image into the defect detection model to obtain a defect feature of a target part in the first image determined by the defect detection model, and the target part belongs to the to-be-detected object.

[0078] In this embodiment, the defect detection model can be determined in the following manner:

[0079] S10231, obtain an image of the industrial product, perform image segmentation on the image of the industrial product, and obtain at least one sub-training image;

[0080] S10232, label the defect feature in the sub-training image to obtain a sub-training image labeled with the defect feature;

[0081] S10233, input at least one sub-training image labeled with the defect feature into the defect detection model to train the defect detection model.

[0082] It should be noted that the edge computing device can have the function of image edge detection. Specifically, the defect feature of the to-be-detected object in the first image can be determined by performing edge detection on the first image.

[0083] The to-be-detected object can be understood as at least one part of the industrial product, which can include but is not limited to at least one part of the surface of the industrial product and / or at least one part of the interior of the industrial product.

[0084] In this embodiment, in combination with the mobile device, the first image including the image of the first area of the film is automatically collected by driving the film and the image acquisition device by the mobile device to move the first area of the film driven by the mobile device to the acquisition range of the image acquisition device. On this basis, the edge computing device can obtain the first image, determine the defect feature of the to-be-detected object in the first image, and automatically detect the defect of the industrial product, thereby ensuring the efficiency and accuracy.

[0085] As another optional embodiment of the present application, referring to Figure 3 A flowchart of an embodiment 2 of a defect detection method of an industrial product provided by the present application is shown. The method can be applied to an edge computing device in an industrial product defect detection system, which includes a mobile device, an image acquisition device, an edge computing device, and a light source. This embodiment is mainly an extension of the defect detection method of the industrial product described in the above embodiment 1. The method can include but is not limited to the following steps:

[0086] In step S201, a second image is acquired. The second image is acquired by the image acquisition device when the first area of the film is moved to the acquisition range of the image acquisition device by the moving device. The second image at least includes the image of the first area of the film.

[0087] In step S202, the gray scale distribution information of the second image is calculated.

[0088] In the embodiment, the calculation of the gray scale distribution information of the second image can include but is not limited to the following.

[0089] In S2021, the first gray scale distribution information of at least one first part of the second image is calculated.

[0090] The at least one first part is a part of the second image. The first part can include the information of interest in the second image.

[0091] The information of interest can include information related to an industrial product.

[0092] The calculation of the first gray scale distribution information of the at least one first part of the second image can include but is not limited to the following.

[0093] The gray scale histogram of the at least one first part of the second image is calculated.

[0094] The embodiment further provides another implementation of the calculation of the gray scale distribution information of the second image, which can include but is not limited to the following.

[0095] In S2022, the first gray scale distribution information of at least one first part of the second image and the second gray scale distribution information of at least one second part of the second image are calculated. The first part includes the information of interest in the second image, and the second part includes the information of no interest in the second image.

[0096] The at least one first part and the at least one second part constitute the second image.

[0097] The detailed process of the calculation of the first gray scale distribution information of the at least one first part of the second image can be referred to the related description of step S2021, which is not described herein again.

[0098] The calculation of the second gray scale distribution information of the at least one second part of the second image can include but is not limited to the following.

[0099] The gray scale histogram of the at least one second part of the second image is calculated.

[0100] In step S203, the difference between the gray scale distribution information of the second image and the set gray scale distribution threshold of the second image is determined.

[0101] Corresponding to the embodiment of step S2021, this step can include but is not limited to:

[0102] S2031, determining a first difference between the first gray scale distribution information of the first part of the second image and the first set gray scale threshold of the first part.

[0103] Corresponding to the embodiment of step S2022, this step can include but is not limited to:

[0104] S2032, determining a first difference between the first gray scale distribution information of the first part of the second image and the first set gray scale distribution threshold of the first part, and a second difference between the second gray scale distribution information of the second part of the second image and the second set gray scale distribution threshold of the second part.

[0105] The first set gray scale distribution threshold of the first part is different from the second set gray scale distribution threshold of the second part.

[0106] Step S204, based on the difference, setting the brightness of the light source to the target luminous brightness.

[0107] As shown in Figure 4 , the light source is located on the back of the film, and the back of the film is the side of the film not facing the image acquisition device. Among them, the top view capable of representing the relative position relationship between the light source and the film can be seen from Figure 5 , as shown in Figure 5 , the light source is located on the back of the film.

[0108] Based on the difference, the adjustment range of the brightness of the light source can be determined, and based on the adjustment range of the brightness, the brightness of the light source is set to the target luminous brightness.

[0109] It can be understood that the adjustment of the brightness of the light source can at least affect the change of the gray scale distribution information of the image collected by the image acquisition device.

[0110] Among them, the light source can radiate light of a set wavelength to meet the requirement of highlighting the information of interest in the film. The set wavelength can be determined based on at least the material characteristics of the film, and the set wavelength can be but not limited to: 515nm single wavelength.

[0111] Corresponding to the embodiments of steps S2021 and S2031, this step can include but is not limited to:

[0112] S2041, determining a gray scale compensation value based on the first difference, and setting the brightness of the light source to the target luminous brightness based on the gray scale compensation value.

[0113] Based on the first difference, determining the gray scale compensation value can include: determining the first difference as the gray scale compensation value.

[0114] The brightness of the light source is set to the target luminous brightness based on the gray scale compensation value, so that the gray scale distribution information of the image collected by the image collection device under the target luminous brightness is the gray scale distribution information compensated based on the gray scale compensation value.

[0115] Corresponding to the embodiments of steps S2022 and S2032, this step can include but is not limited to:

[0116] S2042, determining a gray scale compensation value based on the first difference value and the weight of the first part and the second difference value and the weight of the second part, and setting the brightness of the light source to the target luminous brightness based on the gray scale compensation value.

[0117] Determining the gray scale compensation value based on the first difference value and the weight of the first part and the second difference value and the weight of the second part can include but is not limited to:

[0118] Adding the product of the first difference value and the weight of the first part to the product of the second difference value and the weight of the second part to obtain the gray scale compensation value.

[0119] Similarly, the brightness of the light source is set to the target luminous brightness based on the gray scale compensation value, so that the gray scale distribution information of the image collected by the image collection device under the target luminous brightness is the gray scale distribution information compensated based on the gray scale compensation value.

[0120] Step S205, acquiring a first image, the first image being collected by the image collection device when the first region of the film is moved to the collection range of the image collection device and the brightness of the light source is the target luminous brightness, the first image including at least the image of the first region of the film, the film being used to represent the structural features of the industrial product.

[0121] Wherein, under the target luminous brightness, the image collection device collects the first image, and the gray scale distribution information of the first image meets the set gray scale distribution threshold of the first image.

[0122] It can be understood that the set gray scale distribution threshold of the first image is the same as the set gray scale distribution threshold of the second image. The brightness of the light source is the target luminous brightness, which will affect the gray scale distribution information of the image collected by the image collection device, and accordingly, the gray scale distribution information of the first image is different from the gray scale distribution information of the second image.

[0123] Step S206, determining the defect feature of the to-be-detected object in the first image.

[0124] In this embodiment, by acquiring a second image collected by the image collection device when the first area of the film driven by the moving device moves to the collection range of the image collection device, calculating the gray scale distribution information of the second image, determining the difference between the gray scale distribution information of the second image and the set gray scale distribution threshold of the second image, and setting the brightness of the light source as the target luminous brightness based on the difference, the brightness of the light source is adjusted, and on this basis, the image collection device can at least collect the first image at the target luminous brightness. Under the target luminous brightness, the gray scale distribution information of the first image meets the set gray scale distribution threshold of the first image, ensuring the uniformity of the gray scale distribution of the first image, and further improving the accuracy of defect feature detection.

[0125] As another optional embodiment of the present application, referring to Figure 6 The flowchart of an embodiment 3 of a defect detection method for an industrial product provided by the present application, which can be applied to an edge computing device in an industrial product defect detection system. The industrial product defect detection system includes a moving device, an image collection device, and an edge computing device. The embodiment mainly extends the defect detection method for the industrial product described in the above embodiment 1. The method can include but is not limited to the following steps:

[0126] Step S301: Acquire a first image. The first image is collected by the image collection device when the first area of the film driven by the moving device moves to the collection range of the image collection device. The first image at least includes the image of the first area of the film, and the film is used to represent the structural features of the industrial product.

[0127] Step S302: Determine the defect feature of the to-be-detected object in the first image.

[0128] The detailed processes of steps S301-S302 can be referred to the related introduction of steps S101-S102 in embodiment 1, which will not be repeated here.

[0129] Step S303: Determine the first position of the defect feature of the to-be-detected object in the first image.

[0130] In this embodiment, the first position of the defect feature of the to-be-detected object in the first image can be determined based on the position of the defect feature of the to-be-detected object in the to-be-detected object and the position of the to-be-detected object in the first image.

[0131] Step S304: Output a third image. The third image includes the first image, the first prompt information corresponding to the defect feature of the to-be-detected object, and the second prompt information corresponding to the first position.

[0132] The outputting the third image can include but is not limited to:

[0133] The third image is displayed.

[0134] Alternatively, the outputting the third image can include:

[0135] The third image is sent to the display device so that the display device displays the third image.

[0136] In this embodiment, in combination with the mobile device, the first image including the image of the first area of the film is automatically collected by driving the film and the image collection device by the mobile device to move the first area of the film driven by the mobile device to the collection range of the image collection device. On this basis, the edge computing device can obtain the first image, determine the defect feature of the to-be-detected object in the first image, and realize automatic detection of defects of the industrial product, thereby ensuring efficiency and accuracy.

[0137] Moreover, by determining the first position of the defect feature of the to-be-detected object in the first image, the third image containing the first image, the first prompt information corresponding to the defect feature of the to-be-detected object, and the second prompt information corresponding to the first position is outputted, which can intuitively display the first image, the defect feature of the to-be-detected object, and the position of the defect feature of the to-be-detected object in the first image, thereby facilitating personnel maintenance.

[0138] As another optional embodiment of the present application, referring to Figure 7 A flowchart of an embodiment 4 of a method for detecting defects of an industrial product is provided in the present application. The method can be applied to an edge computing device in an industrial product defect detection system, which includes a mobile device, an image collection device, and an edge computing device. The embodiment mainly describes a detailed scheme of the method for detecting defects of an industrial product described in the above embodiment 3. The method can include but is not limited to the following steps:

[0139] In step S401, a first image is obtained. The first image is collected by the image collection device when the first area of the film driven by the mobile device moves to the collection range of the image collection device. The first image at least includes the image of the first area of the film, and the film is used to represent the structural features of the industrial product.

[0140] In step S402, a defect feature of a to-be-detected object in the first image is determined.

[0141] In step S403, a first position of the defect feature of the to-be-detected object in the first image is determined.

[0142] In this embodiment, the pixel value of the defect feature of the to-be-detected object in the first image can be determined based on the defect detection algorithm, and the first position of the defect feature of the to-be-detected object in the first image can be determined based on the pixel value of the defect feature of the to-be-detected object in the first image and the size of the first image.

[0143] The detailed processes of steps S401-S403 can refer to the related descriptions of steps S301-S303 in Embodiment 3, which will not be repeated here.

[0144] Step S404, determining the second position of the first area of the film included in the first image in the film.

[0145] In this embodiment, the target area in the film that matches the first area of the film included in the first image can be determined by comparing the first area of the film included in the first image with the area in the film, and the position of the target area in the film is determined as the second position of the first area of the film included in the first image in the film.

[0146] Of course, this step can also include but is not limited to:

[0147] S4041, obtaining the moving distance of the first area of the film moved by the moving device.

[0148] S4042, determining the second position of the first area of the film included in the first image in the film based on the moving distance.

[0149] In the case that the moving device moves the film, the position of the first image in the film can be determined based on the moving distance and the size of each frame of image collected by the image collection device, and the position of the first image in the film is determined as the second position of the first area of the film included in the first image in the film.

[0150] The second position can be

[0151] Step S405, determining the position of the defect feature of the to-be-detected object in the film based on the first position and the second position.

[0152] Based on the first position and the second position, the relative positional relationship between the defect feature of the to-be-detected object and the film can be determined, and the position of the defect feature of the to-be-detected object in the film can be determined. Specifically, the position of the defect feature of the to-be-detected object in the film can be determined through the following relationship:

[0153] Lc=(lc1+u*p, v*k)

[0154] Wherein, Lc represents the position of the defect feature of the to-be-detected object in the film, lc1 represents the second position, (u, v) represents the first position, lc1 = m * (n-1), m represents the size of each frame of image, n represents the total number of frames of the multi-frame images collected by the image collection device, (p, k) represents the pixel and the size of each frame of image, and (p, k) is determined based on the performance parameters of the image collection device.

[0155] In the embodiment, the pixel value of the defect feature of the to-be-detected object in the first image can be determined based on the defect detection algorithm, and the pixel region to which the pixel value of the defect feature of the to-be-detected object in the first image belongs can be determined in combination with the performance parameters of the image collection device. The first position of the defect feature of the to-be-detected object in the first image is determined based on the pixel region to which the pixel value of the defect feature of the to-be-detected object in the first image belongs.

[0156] In step S406, the third image is output, and the third image contains the image of the film, the first prompt information corresponding to the defect feature of the to-be-detected object, and the third prompt information corresponding to the position of the defect feature of the to-be-detected object in the film.

[0157] Steps S404-S406 are a specific implementation of step S304 in Embodiment 3.

[0158] In the embodiment, the first image is collected by the mobile device, and the film and the image collection device are driven by the mobile device to move the first area of the film to the collection range of the image collection device, so that the first image containing the image of the first area of the film is automatically collected. On this basis, the edge computing device can obtain the first image, determine the defect feature of the to-be-detected object in the first image, and automatically detect the defect of the industrial product, thereby ensuring the efficiency and accuracy.

[0159] In addition, by determining the first position of the defect feature of the to-be-detected object in the first image and the second position of the defect feature of the to-be-detected object in the film, the third image is output, and the third image contains the image of the film, the first prompt information corresponding to the defect feature of the to-be-detected object, and the third prompt information corresponding to the position of the defect feature of the to-be-detected object in the film. The image of the film, the defect feature of the to-be-detected object, and the position of the defect feature of the to-be-detected object in the film can be intuitively displayed, thereby facilitating personnel maintenance.

[0160] Next, an industrial product defect detection system provided by the present application is introduced. The industrial product defect detection system introduced below can be correspondingly referred to the industrial product defect detection method introduced above.

[0161] Please refer to Figure 8The defect detection system of the industrial product comprises a mobile device 100, an image acquisition device 200, and an edge computing device 300.

[0162] The mobile device 100 is used to drive the film to move.

[0163] The image acquisition device 200 is used to acquire a first image when the first area of the film driven by the mobile device moves to the acquisition range of the image acquisition device, and transmit the first image to the edge computing device, wherein the first image at least comprises an image of the first area of the film, and the film is used to represent the structural features of the industrial product.

[0164] The edge computing device 300 is used to execute the defect detection method of the industrial product as introduced in the method embodiment 1 or 3 or 4.

[0165] In this embodiment, the defect detection system of the industrial product can further comprise a light source.

[0166] The light source is located on the back of the film, and the back of the film is the side of the film not facing the image acquisition device.

[0167] Correspondingly, the edge computing device 300 is used to execute the defect detection method of the industrial product as introduced in the method embodiment 2.

[0168] In this embodiment, the defect detection system of the industrial product can further comprise:

[0169] The fixing device is used to fix the film on the mobile device.

[0170] And / or,

[0171] The dark box is installed with the image acquisition device 200.

[0172] The image acquisition device 200 specifically acquires the first image in the dark box when the film driven by the mobile device 100 moves to the dark box and is in the acquisition range of the image acquisition device 200.

[0173] It should be noted that each embodiment mainly explains the difference from other embodiments, and the same and similar parts between the embodiments can be referred to each other. For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the related parts can be referred to the part of the method embodiment.

[0174] Finally, it is to be understood that the phraseology or terminology employed herein, such as "first" and "second", etc. for example, is for the purpose of differentiating one from another instantiation but is not intended to imply any actual relationship or order between such entities or acts. Also, the use of "including" and "comprising" and variations thereof as terms of inclusion in a claim are not used as limitations but to game that any process, method, article, or apparatus that incorporates one or more of features of a claim is within the scope of the claim, and is used the same manner as the term "comprising" as defined above. Additionally, the use of "first", "second", "third", etc. are not used to connote any ordering such as in a first step before a second step or vice versa, but are used for the purpose of naming various elements.

[0175] For the purpose of clarity, the above apparatus is described in terms of various modules performing various functions. Of course, the functionality of the various modules can be implemented in one or more software and / or hardware components.

[0176] From the above description of the embodiments, it is apparent that a person skilled in the art can clearly know that the present application can be implemented by means of software plus necessary universal hardware platforms. Based on such an understanding, the technical solutions of the present application can be embodied in the form of a software product, and the computer software product can be stored in a storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in the various embodiments or some parts of the embodiments of the present application.

[0177] The above provides a detailed description of the defect detection method and system of an industrial product provided by the present application. The principles and implementation manners of the present application are described by applying specific examples in this paper. The above description of the embodiments is only used to help understand the method of the present application and its core idea; at the same time, for those skilled in the art, according to the idea of the present application, the specific implementation manner and application range will be changed; in view of the above, the content of the specification should not be understood as a limitation of the present application.

Claims

1. A method for defect detection of an industrial product, applied to an edge computing device in a defect detection system for the industrial product, the defect detection system for the industrial product comprising: The mobile device, the image acquisition device, the light source located at the back of the film, the back of the film being the side of the film not facing the image acquisition device, and the edge computing device, the method comprising: calculating first gray scale distribution information of at least one first part of the acquired second image and second gray scale distribution information of at least one second part of the second image, the first part containing information of interest in the second image, and the second part containing information of no interest in the second image; determining a first difference between the first gray scale distribution information of the first part of the second image and a first set gray scale distribution threshold of the first part, and a second difference between the second gray scale distribution information of the second part of the second image and a second set gray scale distribution threshold of the second part; based on the determined difference, setting the brightness of the light source to a target luminous brightness; wherein under the target luminous brightness, the image acquisition device acquires a first image, and the gray scale distribution information of the first image meets a set gray scale distribution threshold of the first image; acquiring a first image, the first image being acquired by the image acquisition device when the first area of the film is moved to the acquisition range of the image acquisition device by the mobile device, the first image comprising at least an image of the first area of the film, the film being used to represent the structural features of the industrial product; determining the defect feature of the to-be-detected object in the first image.

2. The method of claim 1, wherein the first image is obtained by the image acquisition device when a plurality of imaging elements arranged in a matrix of the image acquisition device take a picture of the film, the first image comprising at least an image of the first area of the film.

3. The method of claim 1, wherein the second image is acquired by the image acquisition device when the first area of the film is moved to the acquisition range of the image acquisition device by the mobile device, the second image comprising at least an image of the first area of the film.

4. The method of claim 1, wherein based on the determined difference, the brightness of the light source is set to a target luminous brightness, comprising: based on the first difference and the weight of the first part and the second difference and the weight of the second part, determining a gray scale compensation value, and based on the gray scale compensation value, setting the brightness of the light source to a target luminous brightness.

5. The method of claim 1, further comprising: determining a first position of the defect feature of the to-be-detected object in the first image; outputting a third image, the third image comprising the first image, first prompt information corresponding to the defect feature of the to-be-detected object, and second prompt information corresponding to the first position.

6. The method of claim 5, wherein outputting a third image comprises: determining a second position of the first area of the film included in the first image in the film; based on the first position and the second position, determining the position of the defect feature of the to-be-detected object in the film. Output a third image, the third image including an image of the film, first prompt information corresponding to a defect feature of the object to be detected, and third prompt information corresponding to a position of the defect feature of the object to be detected in the film.

7. The method of claim 6, determining a second position of the first region of the film included in the first image in the film comprises: obtaining a movement distance of the first region of the film moved by the moving device; determining the second position of the first region of the film included in the first image in the film based on the movement distance.

8. The method of claim 1, determining a defect feature of an object to be detected in the first image comprises: performing image segmentation on the first image to obtain at least one sub-image; inputting the sub-image into a defect detection model to obtain a defect feature of a target part in the first image determined by the defect detection model, the target part belonging to the object to be detected.

9. A system for defect detection of an industrial product, comprising: a moving device, an image acquisition device, a light source, and an edge computing device; the moving device is configured to move the film; the image acquisition device is configured to acquire a first image when a first region of the film moved by the moving device is within a capture range of the image acquisition device, and transmit the first image to the edge computing device, the first image at least including an image of the first region of the film, the film being used to represent a structural feature of an industrial product; the light source is located on a back of the film, the back of the film being a side of the film not facing the image acquisition device; the edge computing device is configured to perform the defect detection method of the industrial product according to any one of claims 1-8.

10. The defect detection system of the industrial product of claim 9, further comprising: a fixing device configured to fix the film on the moving device; and / or, a dark box, the dark box being installed with the image acquisition device; the image acquisition device is specifically configured to acquire a first image in the dark box when the film moved by the moving device is within the dark box and within a capture range of the image acquisition device.

Images