Inspection method and device for visual inspection system

Abstract

A kind of visual inspection system's point inspection method and device, comprising: obtaining multiple images to be detected (210);Multiple images to be detected are detected, to obtain the defect type and / or parameter (220) of target object in multiple images to be detected;According to defect type and / or the parameter, confirm the availability of visual inspection system (230).

Description

Technical Field

[0001] This application relates to the field of non-contact inspection, and in particular to an inspection method and apparatus for a visual inspection system. Background Technology

[0002] Visual inspection systems can replace manual inspection, improving production efficiency and product quality for factories and enterprises. Today, visual inspection systems are widely used across various industries, such as in the entire battery production process. The hardware of the visual inspection system acquires images of the battery, and then algorithms within the system detect defects in those images. However, the hardware and algorithms of visual inspection systems may experience various unexpected issues, necessitating regular availability and reliability checks to ensure the accuracy of the inspection results.

[0003] Therefore, there is an urgent need for a method to check the availability of visual inspection systems in order to ensure the accuracy of the inspection results. Summary of the Invention

[0004] This application provides a method and apparatus for inspecting a visual inspection system, which can detect whether the algorithm and hardware of the visual inspection system are available, so as to promptly remind or report errors when they are unavailable, thereby ensuring the accuracy of the inspection results of the visual inspection system.

[0005] In a first aspect, this application provides a method for inspecting a visual inspection system, comprising: acquiring multiple images to be inspected; inspecting the multiple images to be inspected to obtain the defect type and / or parameters of a target object in the multiple images to be inspected; and confirming the availability of the visual inspection system based on the defect type and / or the parameters.

[0006] In the technical solution of this application, a visual inspection system is used to detect the defect types and parameters of target objects in multiple images to be inspected, and the corresponding defect type detection results and parameter detection results are obtained. On the one hand, the accuracy or availability of the visual inspection system algorithm can be judged based on the defect type detection results, and on the other hand, the accuracy of the data provided by the visual inspection algorithm hardware to the algorithm can be judged based on the parameter detection results, thereby confirming the availability of the visual inspection system, so as to promptly remind or report errors when it is unavailable, and ensure the accuracy of the detection results.

[0007] In some embodiments, acquiring a plurality of images to be detected includes: acquiring the plurality of images to be detected from a sample image library, wherein the defect type of each image in the sample image library is known.

[0008] The above method of directly obtaining multiple images of known defect types from the sample image library can avoid the influence of the visual inspection system hardware on the inspection results and reduce the time for obtaining the images to be inspected, thereby improving the efficiency of the visual inspection system algorithm.

[0009] In some embodiments, detecting the plurality of images to be detected to obtain the defect type and / or parameters of the target object in the plurality of images to be detected includes: performing defect detection on each of the plurality of images to be detected using a defect detection algorithm in the visual inspection system to obtain the defect type of the target object in each image to be detected.

[0010] By detecting the defect type of each of the multiple images to be detected, the robustness of the defect detection algorithm can be comprehensively judged based on the detection results of the defect types of the multiple images to be detected, thereby improving the accuracy of the visual inspection system algorithm.

[0011] In some embodiments, confirming the availability of the visual inspection system based on the defect type and / or the parameters includes: if the defect type of the target object in each image to be inspected is the same as a known defect type, confirming that the defect detection algorithm of the visual inspection system is available.

[0012] In the above implementation, the defect detection algorithm of the visual inspection system is confirmed to be usable when the defect type detection results of all images to be inspected are the same as the known defect types, which can improve the accuracy and effectiveness of algorithm inspection.

[0013] In some embodiments, acquiring multiple images to be detected includes: running a standard target object detection process; acquiring an image of the target object captured by the visual detection system to obtain the multiple images to be detected.

[0014] When running a standard target object detection process, all cameras and light sources in the vision inspection system can be invoked. By detecting the parameters of the target object in multiple images to be detected captured by all cameras and light sources, the availability of each camera and light source can be determined based on the parameter detection results, thereby confirming the availability of the vision inspection system hardware.

[0015] In some embodiments, the target object is a battery cell or a film.

[0016] In some embodiments, the step of detecting the plurality of images to be detected by a visual inspection system to obtain the defect type and / or parameters of the target object in the plurality of images to be detected includes: measuring parameters of each of the plurality of images to be detected by the visual inspection system to obtain the parameters of the target object in each image to be detected.

[0017] By measuring the parameters of each image to be detected, the parameter measurement results of the target object in each image can be obtained. Based on the parameter measurement results of each image to be detected, the availability of the hardware corresponding to each image to be detected can be determined.

[0018] In some embodiments, the parameters include the size and grayscale of the target object.

[0019] By detecting the size and grayscale of the target object in each image to be inspected, it is possible to detect whether the camera and light source corresponding to each image to be inspected have changed, thereby confirming the availability of the visual inspection system hardware.

[0020] In some embodiments, confirming the availability of the visual inspection system based on the defect type and / or the parameters includes: if the parameters of the target object in each image to be inspected are consistent with the actual parameters, confirming that the hardware of the visual inspection system is available.

[0021] By comparing the parameters of the target object in each image to be detected with the actual parameters, it can be determined whether the hardware corresponding to each image to be detected is available, thus confirming the availability of the visual inspection system hardware.

[0022] In some embodiments, the hardware includes multiple cameras and multiple light sources.

[0023] By comparing the parameter detection results with the size and grayscale information in the actual parameters, it is possible to determine whether the camera position and the illumination conditions of the light source of the vision inspection system have changed, thus confirming the availability of the vision inspection system hardware.

[0024] In some embodiments, before acquiring multiple images to be detected, the method further includes: receiving a selection instruction from the camera; and setting the real parameters of the target object corresponding to the camera.

[0025] By receiving the camera's selection command, the parameters (real parameters) that the camera should acquire can be set, so as to compare them with the parameter measurement results of the image to be detected captured by each camera, thereby judging the accuracy of the data provided by the camera and the light source corresponding to the camera to the algorithm, and confirming the availability of the hardware.

[0026] In some embodiments, the method further includes setting the number of times the camera is inspected.

[0027] The above-mentioned selection of camera settings or adjustment of the number of times the camera and its corresponding light source are inspected can improve the accuracy of hardware inspection in the vision inspection system.

[0028] Secondly, this application provides an inspection device for a visual inspection system, comprising: an acquisition unit for acquiring multiple images to be inspected; a processing unit for inspecting the multiple images to be inspected to obtain the defect type and / or parameters of a target object in the multiple images to be inspected; and confirming the availability of the visual inspection system based on the defect type and / or the parameters.

[0029] In the technical solution of this application, a visual inspection system is used to detect the defect types and parameters of target objects in multiple images to be inspected, and the corresponding defect type detection results and parameter detection results are obtained. On the one hand, the accuracy or availability of the visual inspection system algorithm can be judged based on the defect type detection results, and on the other hand, the accuracy of the data provided by the visual inspection algorithm hardware to the algorithm can be judged based on the parameter detection results, thereby confirming the availability of the visual inspection system, so as to promptly remind or report errors when it is unavailable, and ensure the accuracy of the detection results.

[0030] In some embodiments, the acquisition unit is used to acquire the plurality of images to be detected from a sample image library, wherein the defect type of each image in the sample image library is known.

[0031] The above method of directly obtaining multiple images of known defect types from the sample image library can avoid the influence of the visual inspection system hardware on the inspection results and reduce the time for obtaining the images to be inspected, thereby improving the efficiency of the visual inspection system algorithm.

[0032] In some embodiments, the processing unit is configured to: perform defect detection on each of the plurality of images to be detected using a defect detection algorithm in the visual inspection system, so as to obtain the defect type of the target object in each image to be detected.

[0033] By detecting the defect type of each of the multiple images to be detected, the robustness of the defect detection algorithm can be comprehensively judged based on the detection results of the defect types of the multiple images to be detected, thereby improving the accuracy of the visual inspection system algorithm.

[0034] In some embodiments, the processing unit is configured to: if the defect type of the target object in each image to be detected is the same as a known defect type, confirm that the defect detection algorithm of the visual inspection system is available.

[0035] In the above implementation, the defect detection algorithm of the visual inspection system is confirmed to be usable when the defect type detection results of all images to be inspected are the same as the known defect types, which can improve the accuracy and effectiveness of algorithm inspection.

[0036] In some embodiments, the processing unit is used to run a standard target object detection process; the acquisition unit is used to acquire images of the target object captured by the visual inspection system to obtain the plurality of images to be detected.

[0037] When running a standard target object detection process, all cameras and light sources in the vision inspection system can be invoked. By detecting the parameters of the target object in multiple images to be detected captured by all cameras and light sources, the availability of each camera and light source can be determined based on the parameter detection results, thereby confirming the availability of the vision inspection system hardware.

[0038] In some embodiments, the target object is a battery cell or a film.

[0039] In some embodiments, the processing unit is configured to: measure parameters of each of the plurality of images to be detected using the visual inspection system, and obtain parameters of the target object in each image to be detected.

[0040] By measuring the parameters of each image to be detected, the parameter measurement results of the target object in each image can be obtained. Based on the parameter measurement results of each image to be detected, the availability of the hardware corresponding to each image to be detected can be determined.

[0041] In some embodiments, the parameters include the size and grayscale of the target object.

[0042] By detecting the size and grayscale of the target object in each image to be inspected, it is possible to detect whether the camera and light source corresponding to each image to be inspected have changed, thereby confirming the availability of the visual inspection system hardware.

[0043] In some embodiments, the processing unit is configured to: confirm that the hardware of the visual detection system is available if the parameters of the target object in each image to be detected are consistent with the actual parameters.

[0044] By comparing the parameters of the target object in each image to be detected with the actual parameters, it can be determined whether the hardware corresponding to each image to be detected is available, thus confirming the availability of the visual inspection system hardware.

[0045] In some embodiments, the hardware includes multiple cameras and multiple light sources.

[0046] By comparing the parameter detection results with the size and grayscale information in the actual parameters, it is possible to determine whether the camera position and the illumination conditions of the light source of the vision inspection system have changed, thus confirming the availability of the vision inspection system hardware.

[0047] In some embodiments, the apparatus further includes a receiving unit for receiving a selection instruction from the camera; the processing unit is further configured to set the actual parameters of the target object corresponding to the camera.

[0048] By receiving the camera's selection command, the parameters (real parameters) that the camera should acquire can be set, so as to compare them with the parameter measurement results of the image to be detected captured by each camera, thereby judging the accuracy of the data provided by the camera and the light source corresponding to the camera to the algorithm, and confirming the availability of the hardware.

[0049] In some embodiments, the processing unit is further configured to set the number of times the camera is inspected.

[0050] The above-mentioned selection of camera settings or adjustment of the number of times the camera and its corresponding light source are inspected can improve the accuracy of hardware inspection in the vision inspection system.

[0051] Thirdly, embodiments of this application provide an inspection apparatus for a visual inspection system, including a processor and a memory. The memory is used to store a program, and the processor is used to call and run the program from the memory to perform the inspection method of the visual inspection system in the first aspect or any possible implementation of the first aspect.

[0052] Fourthly, embodiments of this application provide a computer-readable storage medium including a computer program that, when run on a computer, causes the computer to perform the inspection method of the visual inspection system in the first aspect or any possible implementation thereof. Attached Figure Description

[0053] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the embodiments of this application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on the drawings without creative effort.

[0054] Figure 1 This is a system architecture diagram of a visual inspection system applicable to the embodiments of this application;

[0055] Figure 2 This is a schematic flowchart of an inspection method for a visual inspection system provided in an embodiment of this application;

[0056] Figure 3 This is a schematic flowchart of a visual inspection system algorithm inspection method provided in an embodiment of this application;

[0057] Figure 4 This is a schematic flowchart of a method for inspecting hardware of a visual inspection system provided in an embodiment of this application;

[0058] Figure 5 This is a schematic structural block diagram of a device for detecting the stability of a vision system according to an embodiment of this application;

[0059] Figure 6 This is a schematic diagram of the hardware structure of a device for detecting the stability of a vision system according to an embodiment of this application.

[0060] The accompanying drawings are not drawn to scale. Detailed Implementation

[0061] The embodiments of this application will be described in further detail below with reference to the accompanying drawings and examples. The detailed description of the following embodiments and the accompanying drawings are used to illustrate the principles of this application by way of example, but should not be used to limit the scope of this application, that is, this application is not limited to the described embodiments.

[0062] In the description of this application, it should be noted that, unless otherwise stated, "a plurality of" means two or more; the terms "upper," "lower," "left," "right," "inner," and "outer," etc., indicating orientation or positional relationships, are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation on this application. Furthermore, the terms "first," "second," and "third," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. "Vertical" is not vertical in the strict sense, but within the allowable tolerance range. "Parallel" is not parallel in the strict sense, but within the allowable tolerance range.

[0063] The directional terms used in the following description refer to the directions shown in the figures and are not intended to limit the specific structure of this application. It should also be noted in the description of this application that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "joining" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a direct connection or an indirect connection through an intermediate medium. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0064] In visual inspection, industrial cameras in a visual inspection system replace human eyes to collect image data. Intelligent devices within the system then perform various calculations on the images, replacing the human brain, to extract features of the target, such as barcodes and defects. The detected image data is then compared with standard image data to determine if it is abnormal or to generate alternative detection results, thus completing the entire process of automatic identification and inspection. However, the hardware and algorithms of a visual inspection system may produce inaccurate results due to various unforeseen circumstances, such as changes in camera position. Therefore, regular checks on the availability of the visual inspection system are necessary. Currently, the hardware of visual inspection systems is mainly checked manually. When there are many hardware components in the system, the check is time-consuming and inaccurate. Furthermore, there is currently no perfect check solution for the algorithms used in visual inspection systems.

[0065] In view of this, embodiments of this application provide a visual inspection system inspection method, which confirms the availability of the visual inspection system by detecting whether the defect types and / or parameters of target objects in multiple images to be inspected are consistent with the actual defect types and / or actual parameters, so as to promptly report errors when the visual inspection system is unavailable, thereby ensuring the accuracy of the inspection results.

[0066] Figure 1 A system architecture diagram of a visual inspection system 100 applicable to embodiments of this application is shown.

[0067] like Figure 1 As shown, the visual inspection system 100 may include a controller 110, a camera 120, and a light source 130.

[0068] like Figure 1 As shown, the controller 110 can be connected to the camera 120 and the light source 130. The controller 110 can be configured with a control program for controlling the camera 120 and the light source 130. Optionally, the control program can provide a user interface in the controller 110, allowing the user to control the camera 120 and the light source 130. The controller 110 can be a terminal, such as a mobile terminal, tablet computer, or laptop computer, or it can be a server or cloud service. The controller 110 can include a computing module 111 and a data storage module 112. The computing module 111 can process received input data (e.g., an image to be processed). When the computing module 111 performs related processing, the controller 110 can call data, code, etc., in the data storage module 112 for corresponding processing, or it can store the processed data, instructions, etc., into the data storage module 112.

[0069] Optionally, in some embodiments, the light source 130 can be directly connected to the controller 110, or in some other embodiments, the visual inspection system 100 may also include a light source controller, and the light source 130 may also be connected to the controller 110 through the light source controller.

[0070] Specifically, in this vision inspection system, there can be multiple cameras 120 and light sources 130, which can be distributed and set at different locations on a production line to acquire images of products at different locations on the production line. Optionally, the camera 120 can include various types of industrial cameras such as line scan cameras (or line array cameras), area scan cameras, monochrome cameras, and color cameras. The light source 130 can include light emitting diodes (LEDs), light strips, or other types of light sources. This application embodiment does not limit the specific types of cameras 120 and light sources 130.

[0071] Understandable, Figure 1 This is only an illustration of a portion of the equipment in the vision inspection system 100, excluding... Figure 1 In addition to the controller 110, camera 120 and light source 130 shown, the visual inspection system 100 may also include other components from related technologies. The specific architecture of the visual inspection system 100 is not limited in this application embodiment.

[0072] In addition, the camera 120 and the light source 130 mentioned above can be some of the visual inspection devices in the visual inspection system 100. Besides the camera 120 and the light source 130, the visual inspection system 100 may also include other visual inspection devices, such as: lens, image acquisition card, image processing software, etc.

[0073] As an example rather than a limitation, Figure 1 The visual inspection system 100 shown can be a visual inspection system for batteries. The images acquired by the camera 120 and the light source 130 can be used for the inspection of battery products on the battery production line, for example, to detect foreign objects, scratches, indentations, defective tabs, contamination, corrosion, dents, tab burns, defective coding, blurred characters, etc. on the battery product.

[0074] Alternatively, in other embodiments, the Figure 1 The vision inspection system 100 shown can also be a vision inspection system for other types of products. For example, the vision inspection system 100 can be a vision inspection system for machining mechanical parts, a vision inspection system for circuit boards, a vision inspection system for electronic components, etc.

[0075] Figure 2 A schematic flowchart of an inspection method 200 for a visual inspection system provided in an embodiment of this application is shown.

[0076] like Figure 2 As shown, the method 200 for detecting the availability of a visual inspection device includes the following steps:

[0077] 210. The inspection device of the visual inspection system acquires multiple images to be inspected.

[0078] Multiple images to be inspected are multiple images of the target object captured by the visual inspection system during the inspection, or images saved before the visual inspection system is installed.

[0079] The inspection device of the vision inspection system can serve as an interface for upper-level (e.g., user) control of devices on the vision inspection system. Optionally, the inspection device of the vision inspection system may include the inspection software of the vision inspection system, which can be installed on the aforementioned... Figure 1 In the controller 110 shown. Optionally, the above-mentioned device can be any device in the vision inspection system; for example, the device can be the one described above. Figure 1 The camera 120 and light source 130 are shown in the diagram.

[0080] 220, the inspection device of the visual inspection system inspects the plurality of images to be inspected to obtain the defect type and / or parameters of the target object in the plurality of images to be inspected.

[0081] Algorithms in a visual inspection system can be used to detect images and obtain defect information of target objects in the images. The defect information can include defect type and defect location information. The system can also obtain parameter information of target objects in the images, which can include the size information, grayscale information, and position information of the target objects.

[0082] 230. The inspection device of the vision inspection system confirms the availability of the vision inspection system based on the defect type and / or parameters.

[0083] The availability of a visual inspection system includes the availability of the visual inspection system algorithm and the availability of the visual inspection system hardware. The algorithm can be a defect detection algorithm, and the hardware can include the camera and light source in the visual inspection system.

[0084] To test the usability of an algorithm in a vision inspection system, the detection results of defect types in the target object within the image to be inspected can be compared with the actual defect types of the target object. Similarly, to test the usability of the hardware in a vision inspection system, the image to be inspected can be captured using the system's hardware. Then, the detection results of the target object's parameters within the image can be compared with the actual parameters of the target object.

[0085] In this embodiment, a visual inspection system is used to detect the defect types and parameters of target objects in multiple images to be inspected, and corresponding defect type detection results and parameter detection results are obtained. Based on the defect type detection results, the accuracy or availability of the visual inspection system algorithm can be determined. Based on the parameter detection results, it can be determined whether the data provided by the visual inspection algorithm hardware to the algorithm is accurate, thereby confirming the availability of the visual inspection system, so as to promptly remind or report errors when it is unavailable, and ensure the accuracy of the detection results.

[0086] According to some embodiments of this application, optionally, when acquiring multiple images to be detected in step 210, multiple images to be detected can be acquired from a sample image library, wherein the defect type of each image in the sample image library is known.

[0087] The visual inspection system includes a sample image library, which can be stored in the data storage module 112 of the controller 110. For example, the sample image library can be multiple folders containing multiple defect images, where the defect types of the multiple defect images in each folder are the same. For instance, the first folder might contain images of "needle removal failure," and the second folder might contain images of "label foreign objects." That is, all images in the first folder might contain images of "needle removal failure," and all images in the second folder might contain images of "label foreign objects." Of course, the defect types of the multiple defect images in each folder can also be different, and this application does not limit this. When acquiring multiple images to be inspected, one of the multiple folders can be selected, and the multiple defect images in that folder can be used as multiple images to be inspected.

[0088] To test the usability of the visual inspection system's algorithm, multiple images with known defect types can be directly obtained from the sample image library. Compared to using images captured in real time by the visual inspection system's hardware, this avoids the influence of the hardware on the inspection results and reduces the time required to acquire the images, thereby improving the efficiency of the visual inspection system's algorithm.

[0089] According to some embodiments of this application, optionally, defect detection can be performed on each of the multiple images to be detected by a defect detection algorithm in a visual inspection system to obtain the defect type of the target object in each image to be detected.

[0090] The defect detection algorithm can be stored in the data storage module 112 of the controller 110. When it is necessary to perform defect detection on the image to be detected, the calculation module 111 in the controller 110 first performs preprocessing on the image to be detected, such as binarization, in order to extract the defect features of the target object in the image to be detected. Then, the defect detection algorithm in the data storage module 112 compares the extracted defect features with the known defect features to obtain the defect type of the target object in the image to be detected.

[0091] By detecting the defect type of each of the multiple images to be detected, the robustness of the defect detection algorithm can be comprehensively judged based on the detection results of the defect types of the multiple images to be detected, thereby improving the accuracy of the visual inspection system algorithm.

[0092] Optionally, according to some embodiments of this application, if the defect type of the target object in each image to be detected is the same as the known defect type, the defect detection algorithm of the visual inspection system is confirmed to be usable.

[0093] The defect type of the target object in each image to be detected is compared with the corresponding known defect type, where the known defect type refers to the actual defect type of the target object in the image to be detected. If the two are the same, it can be confirmed that the defect detection algorithm in the visual inspection system is accurate and usable. If there are cases where the defect type detection results in multiple images to be detected are different from the known defect types, it is confirmed that the defect detection algorithm in the visual inspection system has poor robustness, that is, the defect detection algorithm in the visual inspection system is unusable.

[0094] The above method compares the defect type detection results of the target object in each of the multiple images to be detected with the known defect types. When the defect type detection results of all the images to be detected are the same as the known defect types, it is confirmed that the defect detection algorithm of the visual inspection system is usable, which can improve the accuracy and effectiveness of the algorithm inspection.

[0095] According to some embodiments of this application, optionally, when acquiring multiple images to be detected in step 210, a standard target object detection process can be run first, and then images of the target object captured by the visual inspection system can be acquired to obtain multiple images to be detected.

[0096] It should be understood that a vision inspection system includes multiple cameras, each with at least one corresponding light source. These cameras can be distributed and positioned at different locations on a production line to acquire images of target objects at different locations on the production line. When running a standard target object inspection process, it is necessary to acquire images of the standard target object from multiple angles or on multiple surfaces. This is achieved by using multiple cameras in the vision inspection system to capture images of the standard target object from multiple angles or on multiple surfaces, thereby obtaining multiple images to be inspected.

[0097] It should also be understood that the size and grayscale value of a standard target object are fixed under fixed lighting conditions. In this embodiment, the size and grayscale of the standard target object are recorded once. Then, each time the hardware of the vision inspection system is inspected, the inspection process of the standard target object only needs to be run once, and the inspection result is compared with the recorded information to obtain the hardware inspection result. This can improve the speed and efficiency of hardware inspection. However, when using non-standard target objects to inspect hardware, there can be countless types of non-standard target objects. Each inspection requires recording the parameters of the non-standard target object used in that inspection, which increases the workload of hardware inspection and reduces inspection efficiency.

[0098] When running a standard target object detection process, all cameras and light sources in the vision inspection system can be invoked. By detecting the parameters of the target object in multiple images captured by all cameras and light sources, the availability of the cameras and light sources can be determined based on the parameter detection results, thereby confirming the availability of the vision inspection system hardware.

[0099] According to some embodiments of this application, the target object may optionally be a battery cell or a film.

[0100] It should be understood that during the production process of a product, it is necessary not only to inspect the finished product for dimensions or defects, but also to inspect the components that make up the product. For example, the target object mentioned above could be an assembled and welded battery cell, or a battery film that makes up the battery cell. If certain cameras are photographing components similar to battery films, a film inspection process can be run. By comparing the parameter inspection results of the film with the actual parameters, the usability of these cameras and their corresponding light sources can be checked.

[0101] It should be understood that the parameters of a standard battery cell or a standard film are fixed. If the detected parameters are different from or significantly different from the parameters of a standard battery cell or a standard film, it can be confirmed that the vision inspection system hardware is unusable.

[0102] According to some embodiments of this application, optionally, the visual inspection system measures the parameters of each of the plurality of images to be inspected to obtain the parameters of the target object in each image to be inspected.

[0103] It should be understood that when inspecting the hardware of a vision inspection system, the multiple images to be inspected are photographs taken by all cameras of the vision inspection system. By measuring the parameters of each image, the parameter detection results of the target object in each image can be obtained. Based on the parameter detection results of each image, the availability of the corresponding camera and light source can be inspected.

[0104] By measuring the parameters of each image to be detected, the parameter measurement results of the target object in each image can be obtained. Based on the parameter measurement results of each image to be detected, the availability of the hardware corresponding to each image to be detected can be determined.

[0105] According to some embodiments of this application, the parameters may optionally include the size and grayscale of the target object.

[0106] When the position of a camera in a vision inspection system changes, the size of the target object captured by that camera will change when its dimensions are measured. The principle behind this is that the length and width of the target object are calculated by measuring the number of pixels contained in its longer or shorter side. Specifically, the length is calculated as the width of each pixel multiplied by the number of pixels contained in the longer side of the target object; the width is calculated as the width of each pixel multiplied by the number of pixels contained in the shorter side of the target object. Therefore, compared to the standard camera position, the closer the camera is to the target object at its workstation, the more pixels it contains in the image, resulting in a larger measured size than the actual size. Conversely, the farther the camera is from the target object at its workstation, the fewer pixels it contains in the image, resulting in a smaller measured size than the actual size. Therefore, the size parameters of the target object can be used to determine whether the camera position of the vision inspection system has changed.

[0107] When the illumination provided by the light source in a visual inspection system changes too much compared to the standard illumination, it will have a slight impact on the size measurement. For example, overexposure will cause the edges of the target object to shrink after imaging, resulting in a smaller measured size value. The grayscale parameter information of the target object can be used to determine whether the light source of the visual inspection system has changed.

[0108] By detecting the size and grayscale of the target object in each image to be inspected, it is possible to detect whether the camera and light source corresponding to each image to be inspected have changed, thereby confirming the availability of the visual inspection system hardware.

[0109] According to some embodiments of this application, optionally, if the parameters of the target object in each image to be detected are consistent with the actual parameters, the hardware of the visual inspection system is confirmed to be usable.

[0110] For each image to be inspected, the parameters of the target object being consistent with the true parameters can mean either that the measured parameters are exactly the same as the true parameters, or that the difference between the measured parameters and the true parameters is less than a preset threshold. By setting the preset threshold, different customers can be satisfied with the varying accuracy requirements of the measurement data. In practical implementation, the measured parameters can be compared with the expected results to confirm the usability of the visual inspection system hardware. The expected results can be the range formed by the true parameters and the preset threshold.

[0111] By comparing the parameters of the target object in each image to be detected with the actual parameters, it is possible to determine whether the hardware corresponding to each image to be detected is available, thereby confirming the availability of the visual inspection system hardware.

[0112] According to some embodiments of this application, the hardware may optionally include multiple cameras and multiple light sources.

[0113] It should be understood that the hardware in a vision inspection system that typically changes includes the camera position and the lighting conditions of the light source. By comparing the measured parameters with the actual dimensions and grayscale information, it is possible to determine whether the camera position and lighting conditions of the light source have changed, thus confirming the availability of the vision inspection system hardware.

[0114] According to some embodiments of this application, optionally, before acquiring multiple images to be detected, the method further includes: receiving a selection instruction from a camera and setting the real parameters of the target object corresponding to the camera.

[0115] It should be understood that during the initial hardware inspection of the vision inspection system, it is necessary to record or set the actual parameters that each camera should acquire under standard vision inspection system hardware conditions. By receiving camera selection instructions, the parameters (actual parameters) that the camera should acquire can be set, so as to compare them with the parameter measurement results of the images to be inspected captured by each camera. This allows for the determination of the accuracy of the data provided by the camera and its corresponding light source to the algorithm, thereby confirming the availability of the hardware.

[0116] It should also be understood that when performing a non-first inspection on the hardware of a vision inspection system, that is, when the actual parameters corresponding to each camera have been recorded or set and the hardware has not been adjusted, there is no need to set the parameters at this time; if adjustments have been made, then the actual parameters corresponding to that camera need to be set in order to ensure the accuracy of the inspection.

[0117] It should be noted that vision inspection systems can also be used to detect the connections between components. For example, a battery vision inspection system includes a welding cathode camera to detect whether the welding position of the battery's cathode adapter piece with other components is correct. The parameters of the image to be inspected corresponding to this camera can also include information such as the corner positions and weld area of ​​the standard cathode adapter piece. By detecting parameters such as the corner positions and weld area of ​​the standard cathode adapter piece, it can be determined whether the position of the welding cathode camera has changed. Therefore, depending on the different functions of the camera in the vision inspection system, parameters other than size and grayscale can be set for the camera, and the corresponding parameter information under the camera can be measured during inspection.

[0118] According to some embodiments of this application, optionally, the number of detections by the camera is set.

[0119] In general, the default inspection count for each camera is set to 1, which is sufficient for basic inspection requirements. To improve the accuracy of the inspection, you can select a camera to set or adjust the inspection count for that camera and its corresponding light source.

[0120] Figure 3 A schematic flowchart of a visual inspection system algorithm inspection method 300 provided in an embodiment of this application is shown.

[0121] like Figure 3 As shown, the inspection method 300 of the visual inspection system algorithm includes the following steps:

[0122] 301, Select Image Gallery.

[0123] Specifically, the user can select an image library through the interactive interface in controller 110 to obtain multiple images to be detected. This image library includes multiple images to be detected, and the defect type of the target object in each image is known. This image library can be a folder within the sample image library of data storage module 112. Alternatively, the image library can be a default folder, requiring no user selection.

[0124] 302, Run the testing process.

[0125] Specifically, after the user selects an image library, they can click the "Start Detection" button on the interactive interface. After receiving the start detection instruction, the controller 110 of the visual inspection system calls the code of the defect detection algorithm to perform defect detection on multiple images to be detected in the image library, thereby determining the defect type of the target object in each image to be detected.

[0126] Optionally, before the code that calls the defect detection algorithm performs defect detection on the image to be detected, the image to be detected can be preprocessed to extract defect features more accurately, thereby improving the accuracy of defect detection.

[0127] 303 indicates the test results.

[0128] Specifically, the defect type results of the target object in each image to be detected obtained from step 302 can be displayed on the interactive interface. Alternatively, the known defect type (true defect type) of each image to be detected can be displayed on the interface at the same time, so that users can view the defect type comparison results.

[0129] 304, determine whether the defect type detected by the algorithm is the same as the expected result.

[0130] Specifically, the usability of the visual inspection system algorithm is confirmed by comparing the detected defect types with known defect types. If the detection result for each image matches the expected result, the visual inspection system algorithm is considered successfully inspected, and its execution permission can be granted. Otherwise, the algorithm fails to run and is prohibited from operation. Optionally, a warning signal can be displayed on the interface upon algorithm failure, allowing users to take appropriate actions based on the failure result. For example, technicians can check the algorithm code for problems, thereby ensuring the accuracy of the algorithm's detection results.

[0131] With the above implementation method, users only need to select the image library and click the start detection button to realize the automated inspection of the visual inspection system algorithm.

[0132] Figure 4 A schematic flowchart of a visual inspection system hardware inspection method 400 provided in an embodiment of this application is shown.

[0133] like Figure 4 As shown, the inspection method 400 for the hardware of the vision inspection system includes the following steps:

[0134] 401, Select camera number.

[0135] Specifically, users can select a camera number on the interactive interface, set the number of detections for each camera, and the actual parameters of the target object under that camera.

[0136] 402, Configuration Parameters.

[0137] Specifically, after selecting the camera number, you can set the actual parameters of the target object under that camera. This sets the size and grayscale of the target object under standard lighting conditions and the camera's position to the actual parameters.

[0138] 403, Run the detection process.

[0139] Specifically, after setting the actual parameters of the target object under each camera, the standard battery cell or film inspection process is run.

[0140] 404 indicates the test result.

[0141] Specifically, after running the inspection process, the visual inspection system will take multiple images to be inspected through all cameras, then detect the parameters of the battery cells or film in the multiple images to be inspected, and then display the parameter detection results on the interactive interface. Alternatively, the actual parameters of the target object in each image to be inspected can be displayed on the interactive interface at the same time, so that users can view the parameter detection comparison results.

[0142] 405, Determine whether the parameter detection result is within the expected range.

[0143] Specifically, if the parameter detection results of each image to be detected are within the expected range, then the data provided by the hardware of the vision inspection system to the algorithm is accurate, that is, the hardware of the vision inspection algorithm is usable. At this time, the inspection is successful, and the running permission of the hardware of the vision inspection system can be enabled. If the parameter detection results of an image to be detected are not within the expected range, then the data provided by the camera and / or light source corresponding to the image to be detected to the algorithm is inaccurate or has deviation, that is, the hardware of the vision inspection system is unusable. At this time, the inspection fails, and the operation of the hardware of the vision inspection system can be prohibited.

[0144] Optionally, the hardware inspection interface displays the overall inspection results for all cameras and their corresponding light sources. Users can also select a camera number to view the inspection results for a specific camera.

[0145] With the above implementation method, once the user has configured the actual parameters corresponding to each camera, they only need to click the start inspection button to achieve automated inspection of the hardware of the visual inspection system.

[0146] The method embodiments of this application have been described in detail above. The device embodiments of this application are described below. The device embodiments correspond to the method embodiments. Therefore, for any part not described in detail, please refer to the preceding method embodiments. The device can implement any possible implementation of the above methods.

[0147] Figure 5 A schematic block diagram of an inspection device 500 for a visual inspection system according to an embodiment of this application is shown. The inspection device 500 can perform the inspection method of the visual inspection system described in the embodiment of this application. For example, the inspection device 500 can be the aforementioned controller 110.

[0148] like Figure 5 As shown, the inspection device 500 includes:

[0149] The acquisition unit 510 is used to acquire multiple images to be detected.

[0150] Processing unit 520 is configured to detect the plurality of images to be detected to obtain the defect type and / or parameters of the target object in the plurality of images to be detected; and to confirm the availability of the visual inspection system based on the defect type and / or parameters.

[0151] According to some embodiments of this application, optionally, the acquisition unit 510 is used to acquire the plurality of images to be detected from a sample image library, wherein the defect type of each image in the sample image library is known.

[0152] According to some embodiments of this application, optionally, the processing unit 520 is used to perform defect detection on each of the plurality of images to be detected by using a defect detection algorithm in the visual inspection system, so as to obtain the defect type of the target object in each image to be detected.

[0153] According to some embodiments of this application, optionally, if the defect type of the target object in each image to be detected is the same as the known defect type, the processing unit 520 is used to confirm that the defect detection algorithm of the visual inspection system is available.

[0154] According to some embodiments of this application, optionally, the processing unit 520 is used to run a standard target object detection process; the acquisition unit 510 is used to acquire the image of the target object captured by the vision detection system to obtain the plurality of images to be detected.

[0155] According to some embodiments of this application, optionally, the target object is a battery cell or a film.

[0156] According to some embodiments of this application, optionally, the processing unit 520 is used to perform parameter measurement on each of the plurality of images to be detected by the visual inspection system to obtain the parameters of the target object in each image to be detected.

[0157] According to some embodiments of this application, optionally, the parameters include the size and grayscale of the target object.

[0158] According to some embodiments of this application, optionally, if the parameters of the target object in each image to be detected are consistent with the actual parameters, the processing unit 520 is used to confirm that the hardware of the visual detection system is available.

[0159] According to some embodiments of this application, the hardware may optionally include multiple cameras and multiple light sources.

[0160] According to some embodiments of this application, optionally, the inspection device 500 further includes a receiving unit 530, which is used to receive the selection command of the camera; the processing unit 520 is also used to set the real parameters of the target object corresponding to the camera.

[0161] According to some embodiments of this application, optionally, the processing unit 520 is also configured to set the number of detections by the camera.

[0162] Figure 6 This is a schematic diagram of the hardware structure of an apparatus for detecting the availability of a visual inspection system according to an embodiment of this application. Figure 6 The apparatus 600 for detecting the availability of a visual inspection system, as shown, includes a memory 601, a processor 602, a communication interface 603, and a bus 604. The memory 601, processor 602, and communication interface 603 are interconnected via the bus 604.

[0163] The memory 601 may be a read-only memory (ROM), a static storage device, or a random access memory (RAM). The memory 601 may store a program, and when the program stored in the memory 601 is executed by the processor 602, the processor 602 and the communication interface 603 are used to execute the various steps of the inspection method of the vision inspection system of the present application embodiment.

[0164] The processor 602 may be a general-purpose central processing unit (CPU), microprocessor, application-specific integrated circuit (ASIC), graphics processing unit (GPU), or one or more integrated circuits, for executing related programs to achieve the functions required by the units in the apparatus for detecting the availability of the visual inspection system according to the embodiments of this application, or to execute the inspection method of the visual inspection system according to the embodiments of this application.

[0165] The processor 602 can also be an integrated circuit chip with signal processing capabilities. In implementation, each step of the inspection method of the visual inspection system in this embodiment can be completed by the integrated logic circuitry in the processor 602 or by software instructions.

[0166] The processor 602 described above can also be a general-purpose processor, a digital signal processor (DSP), an ASIC, a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly implemented by the hardware processor, or implemented by a combination of hardware and software modules in the processor. The software modules can be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory 601. The processor 602 reads the information in memory 601 and, in conjunction with its hardware, completes the functions required by the units included in the apparatus for detecting the availability of the visual inspection system in the embodiments of this application, or executes the inspection method of the visual inspection system in the embodiments of this application.

[0167] The communication interface 603 uses transceiver devices, such as, but not limited to, transceivers, to enable communication between the device 600 and other devices or communication networks. For example, traffic data from unknown devices can be obtained through the communication interface 603.

[0168] Bus 604 may include a pathway for transmitting information between various components of device 600 (e.g., memory 601, processor 602, communication interface 603).

[0169] It should be noted that although the above-described device 600 only shows a memory, processor, and communication interface, those skilled in the art should understand that in specific implementations, device 600 may also include other devices necessary for normal operation. Furthermore, depending on specific needs, those skilled in the art should understand that device 600 may also include hardware devices for implementing other additional functions. Moreover, those skilled in the art should understand that device 600 may only include the devices necessary for implementing the embodiments of this application, and may not necessarily include... Figure 6 All the devices shown.

[0170] This application also provides a computer-readable storage medium storing program code for execution by a device, the program code including instructions for performing the steps in the inspection method of the above-described visual inspection system.

[0171] This application also provides a computer program product, which includes a computer program stored on a computer-readable storage medium. The computer program includes program instructions, which, when executed by a computer, cause the computer to perform the inspection method of the above-described visual inspection system.

[0172] The aforementioned computer-readable storage medium may be a transient computer-readable storage medium or a non-transitory computer-readable storage medium.

[0173] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the device described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0174] Prior to step 210, the device for detecting the availability of the vision inspection system may accept user control commands for the devices. In some embodiments, the host computer 110 has a display screen, on which the device for detecting the availability of the vision inspection system may display a detection interface, which includes label options corresponding to multiple devices. By operating on the multiple label options in the detection interface, the user inputs multiple control commands for the devices into the host computer 110, thereby causing the detection device in the host computer 110 to receive the control commands corresponding to the multiple devices.

[0175] Although this application has been described with reference to preferred embodiments, various modifications can be made thereto and components can be replaced with equivalents without departing from the scope of this application. In particular, the technical features mentioned in the various embodiments can be combined in any manner, provided there is no structural conflict. This application is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims

1. A method for spot inspection of a visual inspection system, characterized in that, include: Acquire multiple images to be detected; The plurality of images to be detected are inspected to obtain the defect type and / or parameters of the target object in the plurality of images to be detected; the parameters include the size and grayscale of the target object; The availability of the visual inspection system is confirmed based on the defect type and / or the parameters.

2. The inspection method according to claim 1, characterized in that, The acquisition of multiple images to be detected includes: The plurality of images to be detected are obtained from a sample image library, wherein the defect type of each image in the sample image library is known.

3. The inspection method according to claim 1 or 2, characterized in that, The step of detecting the plurality of images to be detected to obtain the defect type and / or parameters of the target object in the plurality of images to be detected includes: The defect detection algorithm in the visual inspection system is used to perform defect detection on each of the plurality of images to be inspected, so as to obtain the defect type of the target object in each image to be inspected.

4. The inspection method according to claim 3, characterized in that, The step of confirming the availability of the visual inspection system based on the defect type and / or the parameters includes: If the defect type of the target object in each image to be detected is the same as the known defect type, the defect detection algorithm of the visual inspection system is confirmed to be usable.

5. The inspection method according to claim 1, characterized in that, The acquisition of multiple images to be detected includes: The standard target object detection process is implemented. The visual inspection system captures images of the target object to obtain the plurality of images to be inspected.

6. The inspection method according to claim 5, characterized in that, The target object is a single battery cell or a film.

7. The inspection method according to claim 5 or 6, characterized in that, The plurality of images to be inspected are inspected using a visual inspection system to obtain the defect type and / or parameters of the target object in the plurality of images to be inspected, including: The visual inspection system measures the parameters of each of the plurality of images to be inspected to obtain the parameters of the target object in each image to be inspected.

8. The inspection method according to any one of claims 5 to 7, characterized in that, The step of confirming the availability of the visual inspection system based on the defect type and / or the parameters includes: If the parameters of the target object in each image to be detected are consistent with the actual parameters, the hardware of the visual detection system is confirmed to be usable.

9. The inspection method according to claim 8, characterized in that, The hardware includes multiple cameras and multiple light sources.

10. The inspection method according to claim 9, characterized in that, Before acquiring multiple images to be detected, the method further includes: Receive the camera selection command; Set the actual parameters of the target object corresponding to the camera.

11. The inspection method according to claim 10, characterized in that, The method further includes: Set the number of times the camera is inspected.

12. An inspection device for a visual inspection system, characterized in that, The device includes: The acquisition unit is used to acquire multiple images to be detected; A processing unit is configured to detect the plurality of images to be detected in order to obtain the defect type and / or parameters of the target object in the plurality of images to be detected; the parameters include the size and grayscale of the target object; and to confirm the availability of the visual inspection system based on the defect type and / or the parameters.

13. The inspection device according to claim 12, characterized in that, The acquisition unit is used to acquire the plurality of images to be detected from the sample image library, wherein the defect type of each image in the sample image library is known.

14. The inspection device according to claim 12 or 13, characterized in that, The processing unit is used for: The defect detection algorithm in the visual inspection system is used to perform defect detection on each of the plurality of images to be inspected, so as to obtain the defect type of the target object in each image to be inspected.

15. The inspection device according to claim 14, characterized in that, The processing unit is used for: If the defect type of the target object in each image to be detected is the same as the known defect type, the defect detection algorithm of the visual inspection system is confirmed to be usable.

16. The inspection device according to claim 12, characterized in that, The processing unit is used to run a standard target object detection process; The acquisition unit is used to acquire the image of the target object captured by the visual inspection system to obtain the plurality of images to be detected.

17. The inspection device according to claim 16, characterized in that, The processing unit is used for: The visual inspection system measures the parameters of each of the plurality of images to be inspected to obtain the parameters of the target object in each image to be inspected.

18. The inspection device according to any one of claims 15 to 17, characterized in that, The processing unit is used for: If the parameters of the target object in each image to be detected are consistent with the actual parameters, the hardware of the visual detection system is confirmed to be usable.

19. An inspection device for a visual inspection system, characterized in that, It includes a processor and a memory, the memory being used to store a program, and the processor being used to call and run the program from the memory to perform the inspection method of the visual inspection system according to any one of claims 1 to 11.

20. A computer-readable storage medium, characterized in that, Includes a computer program that, when run on a computer, causes the computer to perform the inspection method of the visual inspection system according to any one of claims 1 to 11.

Images