WO2024044942A1 - 视觉检测系统的点检方法和装置 - Google Patents

视觉检测系统的点检方法和装置 Download PDF

Info

Publication number
WO2024044942A1
WO2024044942A1 PCT/CN2022/115748 CN2022115748W WO2024044942A1 WO 2024044942 A1 WO2024044942 A1 WO 2024044942A1 CN 2022115748 W CN2022115748 W CN 2022115748W WO 2024044942 A1 WO2024044942 A1 WO 2024044942A1
Authority
WO
WIPO (PCT)
Prior art keywords
detected
images
target object
parameters
visual inspection
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2022/115748
Other languages
English (en)
French (fr)
Inventor
吴倩
陈继伟
江冠南
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Contemporary Amperex Technology Co Ltd
Original Assignee
Contemporary Amperex Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Contemporary Amperex Technology Co Ltd filed Critical Contemporary Amperex Technology Co Ltd
Priority to CN202280006734.3A priority Critical patent/CN117980944A/zh
Priority to PCT/CN2022/115748 priority patent/WO2024044942A1/zh
Priority to EP22879633.0A priority patent/EP4358030B1/en
Priority to US18/296,995 priority patent/US12067710B2/en
Publication of WO2024044942A1 publication Critical patent/WO2024044942A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G06T7/001—Industrial image inspection using an image reference approach
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection

Definitions

  • the present application relates to the field of non-contact detection, and in particular to an inspection method and device for a visual inspection system.
  • the visual inspection system can replace manual inspection and improve production efficiency and product quality for factories and enterprises.
  • visual inspection systems have been widely used in various industries. For example, they can be used in the entire process of battery production. Images of batteries are obtained through the hardware of the visual inspection system, and then the algorithms in the visual inspection system are used to detect defects in the images.
  • various unexpected situations may occur in the hardware and algorithms of the visual inspection system, and it is necessary to conduct regular availability or reliability checks on the hardware and algorithms of the visual inspection system to ensure the accuracy of the visual inspection results.
  • This application provides an inspection method and device for 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.
  • this application provides an inspection method for a visual inspection system, which includes: acquiring multiple images to be detected; detecting the multiple images to be detected to obtain target objects in the multiple images to be detected Defect types and/or parameters; confirm the availability of the visual inspection system based on the defect types and/or parameters.
  • a visual detection system is used to detect the defect types and parameters of target objects in multiple images to be detected, and the corresponding defect type detection results and parameter detection results are obtained.
  • it can be judged based on the defect type detection results The accuracy or availability of the visual detection system algorithm.
  • it can be judged whether the data provided by the visual detection algorithm hardware for the algorithm is accurate, thereby confirming the availability of the visual detection system, so as to promptly remind or report errors when it is unavailable to ensure detection. accuracy of results.
  • obtaining the plurality of images to be detected includes: obtaining 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.
  • the above-mentioned method of obtaining multiple inspection images with known defect types directly from the sample image library can avoid the impact of the visual inspection system hardware equipment on the inspection results and reduce the acquisition time compared to images captured in real time using the hardware of the visual inspection system. The time of the image to be detected thereby improving the efficiency of the spot inspection visual inspection system algorithm.
  • detecting the multiple images to be detected to obtain the defect types and/or parameters of the target objects in the multiple images to be detected includes: detecting defects in the visual inspection system
  • the detection algorithm performs defect detection on each of the plurality of images to be detected to obtain the defect type of the target object in each of the 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 multiple images to be detected, thereby improving the performance of the point inspection visual inspection system algorithm. accuracy.
  • confirming the availability of the visual inspection system according to the defect type and/or the parameters includes: if the defect type of the target object in each to-be-inspected image is consistent with a known defect The types are the same, confirming that the defect detection algorithm of the visual inspection system is available.
  • the defect detection algorithm of the visual inspection system is available when the defect type detection results of all the images to be inspected are all the same as the known defect types, which can improve the accuracy and effectiveness of algorithm point inspection.
  • obtaining multiple images to be detected includes: running a standard target object detection process; and acquiring images of the target object captured by the visual detection system to obtain the multiple images to be detected.
  • all cameras and light sources in the visual inspection system can be called.
  • each parameter can be judged based on the parameter detection results.
  • the target object is a battery cell or a film.
  • the inspection of the plurality of images to be inspected by a visual inspection system to obtain the defect types and/or parameters of the target objects in the plurality of images to be inspected includes: The visual detection system performs parameter measurement on each image to be detected in the plurality of images to be detected, and obtains the parameters of the target object in each image to be detected.
  • the parameter measurement results of the target objects in each image to be detected 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 judged.
  • the parameters include size and grayscale of the target object.
  • confirming the availability of the visual inspection system according to the defect type and/or the parameters includes: if the parameters of the target object in each image to be inspected are consistent with real parameters, Confirm that the hardware of the vision inspection system is available.
  • the hardware includes multiple cameras and multiple light sources.
  • the method 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.
  • the parameters (real parameters) that the camera should obtain can be set so as to compare them with the parameter measurement results of the images to be detected captured by each camera, thereby determining the camera and the light source corresponding to the camera.
  • the method further includes: setting the number of inspections of the camera.
  • the above-mentioned selection of a camera to set or adjust the number of inspections of the camera and the light source corresponding to the camera can improve the accuracy of hardware inspection of the visual inspection system.
  • this application provides an inspection device for a visual inspection system, including: an acquisition unit for acquiring multiple images to be detected; and a processing unit for detecting the multiple images to be detected to obtain Defect types and/or parameters of target objects in the plurality of images to be detected; confirm the availability of the visual inspection system based on the defect types and/or parameters.
  • a visual detection system is used to detect the defect types and parameters of target objects in multiple images to be detected, and the corresponding defect type detection results and parameter detection results are obtained.
  • it can be judged based on the defect type detection results The accuracy or availability of the visual detection system algorithm.
  • it can be judged whether the data provided by the visual detection algorithm hardware for the algorithm is accurate, thereby confirming the availability of the visual detection system, so as to promptly remind or report errors when it is unavailable to ensure detection. accuracy of results.
  • the acquisition unit is configured 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.
  • the above-mentioned method of obtaining multiple inspection images with known defect types directly from the sample image library can avoid the impact of the visual inspection system hardware equipment on the inspection results and reduce the acquisition time compared with images captured in real time using the hardware of the visual inspection system. The time of the image to be detected thereby improving the efficiency of the spot inspection visual inspection system algorithm.
  • the processing unit is configured to: perform defect detection on each of the plurality of images to be detected through a defect detection algorithm in the visual inspection system to obtain each of the images to be detected. Detect the defect type of the target object in the image.
  • the robustness of the defect detection algorithm can be comprehensively judged based on the detection results of the defect types of multiple images to be detected, thereby improving the performance of the point inspection visual inspection system algorithm. accuracy.
  • 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.
  • the defect detection algorithm of the visual inspection system is available when the defect type detection results of all the images to be inspected are all the same as the known defect types, which can improve the accuracy and effectiveness of algorithm point inspection.
  • 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 detection system to obtain the multiple to-be-detected objects. image.
  • all cameras and light sources in the visual inspection system can be called.
  • each parameter can be judged based on the parameter detection results.
  • the target object is a battery cell or a film.
  • the processing unit is configured to: perform parameter measurement on each of the plurality of images to be detected through the visual detection system to obtain the target in each of the images to be detected. The parameters of the object.
  • the parameter measurement results of the target objects in each image to be detected 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 judged.
  • the parameters include size and grayscale of the target object.
  • the processing unit is configured to: if the parameters of the target object in each of the images to be detected are consistent with real parameters, confirm that the hardware of the visual detection system is available.
  • the hardware includes multiple cameras and multiple light sources.
  • the device further includes a receiving unit configured to receive a selection instruction from the camera; the processing unit is further configured to set the real parameters of the target object corresponding to the camera. .
  • the parameters (real parameters) that the camera should obtain can be set so as to compare them with the parameter measurement results of the images to be detected captured by each camera, thereby determining the camera and the light source corresponding to the camera.
  • the processing unit is also used to set the number of inspections of the camera.
  • the above-mentioned selection of a camera to set or adjust the number of inspections of the camera and the light source corresponding to the camera can improve the accuracy of hardware inspection of the visual inspection system.
  • embodiments of the present application provide an inspection device for a visual inspection system, including a processor and a memory.
  • the memory is used to store a program
  • the processor is used to call and run the program from the memory.
  • embodiments of the present application provide a computer-readable storage medium, including a computer program.
  • the computer program When the computer program is run on a computer, it causes the computer to execute the above-mentioned first aspect or any possibility of the first aspect.
  • the point inspection method of the visual inspection system in the implementation method is not limited to:
  • Figure 1 is a system architecture diagram of a visual inspection system applicable to the embodiment of the present application
  • Figure 2 is a schematic flow chart of an inspection method of a visual inspection system provided by an embodiment of the present application
  • Figure 3 is a schematic flow chart of a method for inspecting a visual inspection system algorithm provided by an embodiment of the present application
  • Figure 4 is a schematic flow chart of a method for inspecting hardware of a visual inspection system provided by an embodiment of the present application
  • Figure 5 is a schematic structural block diagram of a device for detecting the stability of a vision system according to an embodiment of the present application
  • Figure 6 is a schematic diagram of the hardware structure of a device for detecting the stability of a vision system according to an embodiment of the present application.
  • the industrial camera of the visual inspection system is used to collect image data instead of human eyes, and the intelligent equipment of the visual inspection system is used to replace the human brain to perform various operations on the image to extract the characteristics of the target, such as barcodes, defects, etc., and then Compare the detected image data with standard image data to determine whether the detected image data is abnormal or generate other detection results, thereby completing the entire process of automatic identification and detection.
  • the hardware and algorithms of the visual inspection system may cause inaccurate inspection results due to various unexpected situations, such as changes in the camera position during visual inspection, etc. Therefore, the availability of the visual inspection system needs to be checked regularly.
  • the hardware of the visual inspection system is mainly inspected manually. When the number of hardware in the visual inspection system is large, the inspection time is long and the accuracy is low.
  • embodiments of the present application provide a point inspection method of a visual inspection system, by detecting the defect type and/or parameters of the target object in multiple images to be inspected, and comparing it with the real defect type and/or real parameters. Whether they are consistent, confirm the availability of the visual inspection system to report an error in time when the visual inspection system is unavailable, thereby ensuring the accuracy of the inspection results.
  • Figure 1 shows a system architecture diagram of a visual inspection system 100 applicable to the embodiment of the present application.
  • the visual inspection system 100 may include a controller 110 , a camera 120 , and a light source 130 .
  • the control machine 110 can be connected to the camera 120 and the light source 130 .
  • the controller 110 may be configured with a control program for controlling the camera 120 and the light source 130 .
  • the control program may provide an interface for user interaction in the controller 110 , and the user can operate the interface to achieve relevant control of the camera 120 and the light source 130 .
  • the controller 110 can be a terminal, such as a mobile phone terminal, a tablet computer, a notebook computer, etc., or it can also be a server or cloud, etc.
  • the controller 110 may include a computing module 111 and a data storage module 112.
  • the computing module 111 may be used to process received input data (such as images to be processed). When the computing module 111 performs relevant processing, the controller 110 may call the data.
  • the data, codes, etc. in the storage module 112 are used for corresponding processing, and the data, instructions, etc. obtained by the corresponding processing can also be stored in the data storage module 112.
  • the light source 130 can be directly connected to the controller 110, or, in some other embodiments, the visual inspection system 100 can also include a light source controller, and the light source 130 can also be connected through the light source controller. Connected to controller 110.
  • the number of cameras 120 and light sources 130 may be multiple, and they may be distributed at different locations on a production line to collect images of products at different locations on the production line.
  • the camera 120 may include a line scan camera (or a line array camera), an area array camera, a monochrome camera, a color camera, and other types of industrial cameras.
  • the light source 130 may include a light emitting diode (LED), a light strip, or other types of light sources. The embodiment of the present application does not limit the specific types of the camera 120 and the light source 130 .
  • FIG. 1 is only a schematic diagram showing some of the equipment in the visual inspection system 100.
  • the visual inspection system 100 may also include related technologies.
  • the embodiment of the present application does not limit the specific architecture of the visual inspection system 100.
  • the above-mentioned camera 120 and light source 130 can be part of the visual detection equipment in the visual detection system 100.
  • the visual detection system 100 can also include other visual detection equipment, such as lenses and image capture cards. , image processing software, etc.
  • the visual inspection system 100 shown in FIG. 1 may be a visual inspection system for batteries.
  • the images collected by the above-mentioned camera 120 and the light source 130 can be used to detect battery products on the battery production line, for example, detecting foreign matter, scratches, indentations, poor tabs, pollution, corrosion, and dents on the battery products. Dots, pole ear burns, poor printing, blurred characters, etc.
  • the visual inspection system 100 shown in FIG. 1 may also be a visual inspection system for other types of products.
  • the visual inspection system 100 can be a visual inspection system for mechanical parts processing, a visual inspection system for circuit boards, a visual inspection system for electronic components, etc.
  • FIG. 2 shows a schematic flow chart of an inspection method 200 of a visual inspection system provided by an embodiment of the present application.
  • the method 200 for detecting the availability of visual inspection equipment includes the following steps:
  • the inspection device of the visual inspection system acquires multiple images to be inspected.
  • the multiple images to be inspected are multiple images obtained by using the visual inspection system to capture the target object during the inspection, or they may be images saved before the inspection of the visual inspection system.
  • the inspection device of the visual inspection system can serve as an interface for the upper layer (such as a user) to control the equipment on the visual inspection system.
  • the inspection device of the visual inspection system may include inspection software of the visual inspection system, and the inspection software may be installed in the controller 110 shown in FIG. 1 above.
  • the above-mentioned device is any device in the visual inspection system.
  • the device may be the camera 120 and the light source 130 shown in FIG. 1 above.
  • the inspection device of the visual inspection system detects the multiple images to be detected to obtain the defect types and/or parameters of the target objects in the multiple images to be detected.
  • the algorithm in the visual inspection system can be used to detect the image to be detected, and then obtain the defect information of the target object in the image to be detected, where the defect information can include defect type and defect location information; the parameter information of the target object in the image to be detected can also be obtained , where parameter information can include size information, grayscale information, position information, etc. of the target object.
  • the inspection device of the visual inspection system confirms the availability of the visual inspection system based on the defect type and/or parameters.
  • the availability of the 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
  • the hardware can include the camera and light source in the visual inspection system.
  • the detection results of the defect type of the target object in the image to be detected can be compared with the real defect type of the target object to know whether the algorithm of the visual inspection system is available.
  • the visual inspection system is used to detect the defect types and parameters of the target objects in multiple images to be inspected, and the corresponding defect type detection results and parameter detection results are obtained.
  • the visual inspection system can be judged according to the defect type detection results.
  • the accuracy or availability of the algorithm Based on the parameter detection results, it can be judged whether the data provided by the visual detection algorithm hardware for the algorithm is accurate, thereby confirming the availability of the visual detection system, so as to promptly remind or report errors when it is unavailable to ensure the accuracy of the detection results.
  • multiple images to be detected may be acquired from a sample image library, where the defect type of each image in the sample image library is known.
  • the visual inspection system includes a sample image library, which can be stored in the data storage module 112 of the controller 110.
  • the sample image library may be multiple folders including multiple defect images, and the defect types of the multiple defect images in each folder are the same.
  • the defect type of the first folder is poor pin extraction
  • the defect type of the second file is poor pin extraction.
  • the defect type of the folder is label foreign matter, that is, the defect type of all defective images in the first folder is poor pin extraction
  • the defect type of all defective images in the second folder is label foreign matter.
  • the defect types of the multiple defect images in each folder may also be different, which is not limited in this application. When acquiring multiple images to be detected, you can select one of the above multiple folders, and the multiple defect images in the folder can be used as multiple images to be detected.
  • multiple images to be inspected with known defect types can be obtained directly from the sample image library. Compared with images captured in real time using the hardware of the visual inspection system, it can avoid the impact of the visual inspection system hardware equipment. The impact of the inspection results is reduced, and the time to obtain the image to be inspected is reduced, thereby improving the efficiency of the spot inspection visual inspection system algorithm.
  • defect detection can be performed on each of the multiple to-be-detected images through a defect detection algorithm in the visual inspection system to obtain the defects of the target object in each of the to-be-detected images. type.
  • the defect detection algorithm can be stored in the data storage module 112 of the controller 110.
  • the image to be detected is first pre-processed through the calculation module 111 in the controller 110, such as binarization processing, so that Extract defect features of the target object in the image to be detected, and then compare the extracted defect features with known defect features through the defect detection algorithm in the data storage module 112 to obtain the defect type of the target object in the image to be detected.
  • the robustness of the defect detection algorithm can be comprehensively judged based on the detection results of the defect types of multiple images to be detected, thereby improving the performance of the point inspection visual inspection system algorithm. accuracy.
  • the defect type of the target object in each image to be detected is the same as the known defect type, it is confirmed that the defect detection algorithm of the visual inspection system is available.
  • the defect detection algorithm in the visual inspection system is accurate and available; if the defect type detection results in multiple images to be inspected are different from the known defect types, it is confirmed that the defect detection algorithm in the visual inspection system is less robust, that is, in the visual inspection system The defect detection algorithm is not available.
  • the vision is confirmed when the defect type detection results of all the images to be detected are all the same as the known defect types.
  • the defect detection algorithm of the inspection system is available, which can improve the accuracy and effectiveness of algorithm inspection.
  • step 210 when acquiring multiple images to be detected in step 210, you can first run a standard target object detection process, and then acquire images of the target object captured by the visual detection system to obtain multiple Image to be detected.
  • the visual inspection system includes multiple cameras, each of which has at least one corresponding light source, which can be distributed at different locations on a production line to collect images of target objects at different locations on the production line.
  • the standard target object detection process it is necessary to obtain multiple angles or multiple surface images of the standard target object, and shoot the standard target object through multiple cameras in the visual inspection system to obtain multiple angles or multiple surfaces. images of the surface to obtain multiple images to be detected.
  • the size and grayscale value of a standard target object under a fixed lighting environment are fixed.
  • the size and grayscale of the standard target object are recorded once, and then the hardware of the visual detection system is checked each time.
  • non-standard target objects to inspect hardware there can be countless types of non-standard target objects. Each inspection needs to record the parameters of the non-standard target objects used for that inspection, which increases the workload of hardware inspection and Reduced inspection efficiency.
  • all cameras and light sources in the visual inspection system can be called.
  • the camera can be judged based on the parameter detection results. and light source availability to confirm the availability of vision inspection system hardware.
  • the target object may be a battery cell or a film.
  • the above target object can be a battery cell that has been assembled and welded, or a battery diaphragm that makes up the battery cell. If the target object captured by some cameras is a component similar to a battery diaphragm, the detection of the film can be run. The process checks the availability of these cameras and corresponding light sources by comparing the parameter detection results of the film with the real parameters.
  • the visual detection system performs parameter measurement on each of the plurality of images to be detected to obtain the target object in each of the images to be detected. parameters.
  • the multiple images to be inspected are photos taken by all cameras of the visual inspection system.
  • the parameters of each image to be inspected can be obtained.
  • the availability of the camera and light source corresponding to each image to be detected can be checked.
  • the parameter measurement results of the target objects in each image to be detected 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 judged.
  • the parameters may include the size and grayscale of the target object.
  • the size of the target object will change.
  • the principle is that when measuring the length and width of a target object, it is calculated by measuring the number of pixels contained in the long or wide sides of the target object. Specifically, the length dimension is the width of each pixel multiplied by the long side of the target object. The number of pixels contained; the width dimension is the width of each pixel multiplied by the number of pixels contained in the short side of the target object.
  • the camera position when the camera position is closer to the target object at its station than the standard camera position, the more pixels the image contains, the measured size of the target object will be larger than the actual size; on the contrary, the camera position is different from the actual size.
  • the camera position is closer to the target object at its station than the standard camera position, the more pixels the image contains, the measured size of the target object will be larger than the actual size; on the contrary, the camera position is different from the actual size.
  • the camera position of the visual inspection system has changed through the size parameter information of the target object.
  • the illumination provided by the light source in the visual inspection system changes too much compared with the standard illumination, it will have a slight impact on the size measurement. For example, overexposure will cause the edge of the target object to shrink after imaging, and the measured size value will be too small, and the target can be passed.
  • the grayscale parameter information of the object is used to determine whether the light source of the visual inspection system has changed.
  • the parameters of the target object in each image to be detected are consistent with the real parameters, it is confirmed that the hardware of the visual detection system is available.
  • the parameters of the target object in each image to be detected are consistent with the real parameters, which can mean that the parameter measurement results are exactly the same as the real parameters, or that the difference between the parameter measurement results and the real parameters is less than a preset threshold.
  • preset thresholds Through the setting of preset thresholds, different customers' different accuracy requirements for measurement data can be met.
  • the parameter measurement results can be compared with the expected results to confirm the availability of the visual inspection system hardware, where the expected results can be the range formed by the real parameters and the preset threshold.
  • the hardware includes multiple cameras and multiple light sources.
  • the method further includes: receiving a selection instruction from a camera and setting real parameters of the target object corresponding to the camera.
  • the parameters (real parameters) that the camera should obtain can be set so as to compare them with the parameter measurement results of the images to be detected captured by each camera, thereby determining the camera and the light source corresponding to the camera.
  • the visual inspection system can also be used to detect the connection relationship between parts.
  • the battery visual inspection system includes a welding cathode camera to detect whether the welding position between the battery's cathode adapter and other components is correct
  • the parameters of the image to be inspected corresponding to the camera may also include standard cathode adapters. By detecting the corner position, solder spot area and other information of the standard cathode adapter piece, it can be determined whether the position of the welded cathode camera has changed. Therefore, according to the different functions of the camera of the visual inspection system, other parameters besides size and grayscale can be set for the camera, and the corresponding parameter information of the camera can be measured during inspection.
  • the number of detections of the camera is set.
  • the default number of inspections for each camera is set to 1, which can meet the basic inspection requirements.
  • FIG. 3 shows a schematic flow chart of an inspection method 300 of a visual inspection system algorithm provided by an embodiment of the present application.
  • the inspection method 300 of the visual inspection system algorithm includes the following steps:
  • the user can select a picture library through the interactive interface in the controller 110 to obtain multiple images to be detected.
  • the image library includes multiple images to be inspected, and the defect type of the target object in each image to be inspected is known.
  • the picture library may be a folder in the sample image library of the data storage module 112 .
  • the picture library can also be a default folder without user selection.
  • the controller 110 of the visual inspection system calls the code of the defect detection algorithm to detect multiple images in the image library. Defect detection is performed on the images to be inspected to obtain the defect type of the target object in each image to be inspected.
  • the image to be detected can also be pre-processed to more accurately extract defect features, thereby improving the accuracy of defect detection.
  • the defect type results of each target object in the image to be detected obtained in step 302 can be displayed on the interactive interface, or the known defect types (real defect types) of each image to be detected can be displayed correspondingly at the same time. on the interface so that users can view the defect type comparison results.
  • the availability of the visual inspection system algorithm is confirmed by whether the detected defect type is the same as the known defect type. If the detection result of each image to be detected is the same as the expected result, the visual detection system algorithm check is successful. At this time, the running permission of the visual detection system algorithm can be enabled. Otherwise, the visual detection system algorithm check fails and the visual detection system algorithm is prohibited from running. .
  • a warning signal can pop up on the interface so that the user can take corresponding actions based on the check failure result. For example, technicians can check whether there are problems with the algorithm code to ensure the accuracy of the algorithm detection results. .
  • the user only needs to select the image library and click the start detection button to realize automated inspection of the visual detection system algorithm.
  • FIG. 4 shows a schematic flow chart of a method 400 for inspecting hardware of a visual inspection system provided by an embodiment of the present application.
  • the inspection method 400 of the visual inspection system hardware includes the following steps:
  • the user can select the camera number on the interactive interface, set the number of detections for each camera and the real parameters of the target object under the camera.
  • the visual inspection system will take multiple images to be inspected through all cameras, then detect the parameters of the battery cells or films in the multiple images to be inspected, and then display the parameter inspection results on the interactive interface.
  • the real parameters of the target object of each image to be detected can also be displayed on the interactive interface at the same time, so that users can view the parameter detection and comparison results.
  • the data provided by the hardware of the visual detection system for the algorithm is accurate, that is, the hardware of the visual detection algorithm is available, and the inspection is successful at this time. Enable the running authority of the visual inspection system hardware. If the parameter detection results of the image to be detected are not within the expected range, the data provided by the camera and/or light source corresponding to the image to be detected for the algorithm is inaccurate or biased, that is, the vision If the hardware of the inspection system is unavailable and the inspection fails at this time, the hardware of the visual inspection system can be prohibited from running.
  • the results displayed on the interactive interface of hardware inspection are the overall inspection results of all cameras and corresponding light sources. You can also check the inspection results corresponding to a certain camera by selecting the camera number.
  • the user after configuring the real parameters corresponding to each camera, the user only needs to click the start inspection button to realize automated inspection of the hardware of the visual inspection system.
  • Figure 5 shows a schematic block diagram of the inspection device 500 of the visual inspection system according to an embodiment of the present application.
  • the inspection device 500 can perform the inspection method of the visual inspection system of the embodiment of the present application.
  • the inspection device 500 can be the aforementioned controller 110 .
  • the inspection device 500 includes:
  • the acquisition unit 510 is used to acquire multiple images to be detected.
  • the 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 confirm the performance of the visual inspection system according to the defect type and/or parameters.
  • the acquisition unit 510 is configured to acquire the plurality of images to be detected from a sample image library, where the defect type of each image in the sample image library is known.
  • the processing unit 520 is configured to perform defect detection on each of the plurality of images to be detected through a defect detection algorithm in the visual inspection system to obtain the Describe the defect type of the target object in each image to be detected.
  • the processing unit 520 is configured to confirm the defect of the visual inspection system Detection algorithms are available.
  • the processing unit 520 is configured to run a standard target object detection process; the acquisition unit 510 is configured to acquire the image of the target object captured by the visual detection system to obtain the Multiple images to be detected.
  • the target object is a battery cell or a film.
  • the processing unit 520 is configured to perform parameter measurement on each of the plurality of images to be detected through the visual detection system to obtain each of the images to be detected. parameters of the target object described in .
  • the parameters include the size and grayscale of the target object.
  • the processing unit 520 is used to confirm that the hardware of the visual detection system is available.
  • the hardware includes multiple cameras and multiple light sources.
  • the inspection device 500 also includes a receiving unit 530, the receiving unit 530 is used to receive the selection instruction of the camera; the processing unit 520 is also used to set the camera corresponding the real parameters of the target object.
  • the processing unit 520 is also used to set the number of detections of the camera.
  • FIG. 6 is a schematic diagram of the hardware structure of a device for detecting the availability of a visual inspection system according to an embodiment of the present application.
  • the device 600 for detecting the availability of the visual inspection system shown in FIG. 6 includes a memory 601, a processor 602, a communication interface 603 and a bus 604. Among them, the memory 601, the processor 602, and the communication interface 603 implement communication connections between each other through the bus 604.
  • the memory 601 may be a read-only memory (ROM), a static storage device, and a random access memory (RAM).
  • the memory 601 can store programs. 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 various steps of the inspection method of the visual inspection system according to the embodiment of the present application.
  • the processor 602 may be a general central processing unit (CPU), a microprocessor, an application specific integrated circuit (ASIC), a graphics processing unit (GPU), or one or more
  • the integrated circuit is used to execute relevant programs to implement the functions required to be performed by the units in the device for detecting the availability of the visual inspection system according to the embodiment of the present application, or to perform the inspection method of the visual inspection system according to the embodiment of the present application.
  • the processor 602 may also be an integrated circuit chip with signal processing capabilities. During the implementation process, each step of the inspection method of the visual inspection system in the embodiment of the present application can be completed by instructions in the form of hardware integrated logic circuits or software in the processor 602 .
  • the above-mentioned processor 602 can also be a general-purpose processor, a digital signal processor (digital signal processing, DSP), an ASIC, an off-the-shelf programmable gate array (field programmable gate array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.
  • DSP digital signal processing
  • ASIC application-specific integrated circuit
  • FPGA field programmable gate array
  • Each method, step and logical block diagram disclosed in the embodiment of this application can be implemented or executed.
  • a general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.
  • the steps of the methods disclosed in conjunction with the embodiments of the present application can be directly implemented by a hardware processor for execution, or can be executed by a combination of hardware and software modules in the processor.
  • the software module can be located in random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, registers and other mature storage media in this field.
  • the storage medium is located in the memory 601.
  • the processor 602 reads the information in the memory 601, and combines its hardware to complete the functions required to be performed by the units included in the device for detecting the availability of the visual inspection system in the embodiment of the present application, or to perform the embodiment of the present application. Point inspection method of visual inspection system.
  • the communication interface 603 uses a transceiver device such as but not limited to a transceiver to implement communication between the device 600 and other devices or communication networks. For example, the traffic data of the unknown device can be obtained through the communication interface 603.
  • a transceiver device such as but not limited to a transceiver to implement communication between the device 600 and other devices or communication networks.
  • the traffic data of the unknown device can be obtained through the communication interface 603.
  • Bus 604 may include a path that carries information between various components of device 600 (eg, memory 601, processor 602, communication interface 603).
  • the device 600 may also include other devices necessary for normal operation. At the same time, based on specific needs, those skilled in the art should understand that the device 600 may also include hardware devices that implement other additional functions. In addition, those skilled in the art should understand that the device 600 may only include components necessary to implement the embodiments of the present application, and does not necessarily include all components shown in FIG. 6 .
  • Embodiments of the present application also provide a computer-readable storage medium that stores program code for device execution.
  • the program code includes instructions for executing the steps in the inspection method of the visual inspection system.
  • Embodiments of the present application also provide a computer program product.
  • the computer program product includes a computer program stored on a computer-readable storage medium.
  • the computer program includes program instructions. When the program instructions are executed by a computer, The computer executes the inspection method of the above visual inspection system.
  • the above-mentioned computer-readable storage medium may be a transient computer-readable storage medium or a non-transitory computer-readable storage medium.
  • the device for detecting the availability of the visual inspection system can accept a user's control instruction for the device.
  • the host computer 110 has a display screen, and the device for detecting the availability of the visual inspection system can display a detection interface on the display screen of the host computer 110 , and the detection interface includes label options corresponding to multiple devices.
  • the user inputs multiple control instructions for the equipment into the host computer 110, thereby causing the detection device in the host computer 110 to receive the control instructions corresponding to the multiple devices.

Landscapes

  • Engineering & Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)

Abstract

一种视觉检测系统的点检方法和装置，包括：获取多个待检测图像（210）；对多个待检测图像进行检测，以得到多个待检测图像中目标对象的缺陷类型和/或参数（220）；根据缺陷类型和/或所述参数，确认视觉检测系统的可用性（230）。

Description

视觉检测系统的点检方法和装置 技术领域
本申请涉及非接触式检测领域，特别是涉及一种视觉检测系统的点检方法和装置。
背景技术
视觉检测系统可以代替人工检测，为工厂和企业提升生产效率和产品质量。如今，视觉检测系统已经被广泛用于各个行业，例如可以用于电池生产的整个过程中，通过视觉检测系统的硬件获取电池的图像，再利用视觉检测系统中的算法对图像进行缺陷检测。但视觉检测系统的硬件和算法可能会出现各种意外情况，需要定期对视觉检测系统硬件和算法进行可用性或可靠性点检，以保证视觉检测结果的准确性。
因此，亟需一种能够点检视觉检测系统可用性的方法，以保证视觉检测系统检测结果的准确性。
发明内容
本申请提供了一种视觉检测系统的点检方法和装置，能够检测出视觉检测系统的算法和硬件是否可用，以便在不可用时及时提醒或报错，从而保证视觉检测系统检测结果的准确性。
第一方面，本申请提供了一种视觉检测系统的点检方法，包括：获取多个待检测图像；对所述多个待检测图像进行检测，以得到所述多个待检测图像中目标对象的缺陷类型和/或参数；根据所述缺陷类型和/或所述参数，确认视觉检测系统的可用性。
本申请的技术方案中，利用视觉检测系统对多个待检测图像中目标对象的缺陷类型以及参数进行检测，得出相应的缺陷类型检测结果以及参数检测结果，一方面根据缺陷类型检测结果可以判断视觉检测系统算法的准确性或可用性，一方面根据参数检测结果可以判断出视觉检测算法硬件为算法提供的数据是否准确，从而确认视 觉检测系统的可用性，以在不可用时及时提醒或报错，保证检测结果的准确性。
在一些实施例中，所述获取多个待检测图像包括：从样本图像库中获取所述多个待检测图像，其中，所述样本图像库中每个图像的缺陷类型已知。
上述直接从样本图像库中获取多个缺陷类型已知的待检测图像，相比使用视觉检测系统的硬件实时拍摄的图像，可以避免视觉检测系统硬件设备对点检结果的影响，并减少了获取待检测图像的时间，从而提高点检视觉检测系统算法的效率。
在一些实施例中，所述对所述多个待检测图像进行检测，以得到所述多个待检测图像中目标对象的缺陷类型和/或参数，包括：通过所述视觉检测系统中的缺陷检测算法对所述多个待检测图像中的每个待检测图像进行缺陷检测，以得到所述每个待检测图像中所述目标对象的缺陷类型。
通过对多个待检测图像中每个待检测图像的缺陷类型进行检测，可以根据多个待检测图像的缺陷类型检测结果综合判断缺陷检测算法的鲁棒性，从而提高点检视觉检测系统算法的准确性。
在一些实施例中，所述根据所述缺陷类型和/或所述参数，确认所述视觉检测系统的可用性包括：若所述每个待检测图像中所述目标对象的缺陷类型与已知缺陷类型相同，确认所述视觉检测系统的所述缺陷检测算法可用。
上述实施方式中，在所有待检测图像的缺陷类型检测结果与已知缺陷类型全部相同的情况下确认视觉检测系统的缺陷检测算法可用，可以提高算法点检的准确性和有效性。
在一些实施例中，所述获取多个待检测图像包括：运行标准的目标对象的检测流程；获取所述视觉检测系统拍摄的所述目标对象的图像，以得到所述多个待检测图像。
在运行标准的目标对象的检测流程时，可以调用视觉检测系统中所有的相机与光源，通过检测所有相机与光源拍摄的多个待检测图像中目标对象的参数，可以根据参数检测结果，判断每个相机与光源的可用性，以确认视觉检测系统硬件的可用性。
在一些实施例中，所述目标对象为电池单体或菲林片。
在一些实施例中，所述通过视觉检测系统对所述多个待检测图像进行检测，以得到所述多个待检测图像中所述目标对象的缺陷类型和/或参数，包括：通过所述视 觉检测系统对所述多个待检测图像中的每个待检测图像进行参数测量，得到所述每个待检测图像中所述目标对象的参数。
通过对每个待检测图像进行参数测量，可以获得每个待检测图像中目标对象的的参数测量结果，根据每个待检测图像的参数测量结果可以判断每个待检测图像对应的硬件的可用性。
在一些实施例中，所述参数包括所述目标对象的尺寸和灰度。
通过检测每个待检测图像中目标对象的尺寸和灰度，可以分别检测每个待检测图像所对应的相机和光源是否发生变化，以确认视觉检测系统硬件的可用性。
在一些实施例中，所述根据所述缺陷类型和/或所述参数，确认所述视觉检测系统的可用性包括：若所述每个待检测图像中所述目标对象的参数与真实参数一致，确认所述视觉检测系统的硬件可用。
通过比较每个待检测图像中目标对象的参数与真实参数是否一致，可以判断每个待检测图像所对应的硬件是否可用，以确认视觉检测系统硬件的可用性。
在一些实施例中，所述硬件包括多个相机和多个光源。
通过比较参数检测结果与真实参数中的尺寸和灰度信息，可以分别判断视觉检测系统的相机位置以及光源的光照条件是否发生变化，即可确认视觉检测系统硬件的可用性。
在一些实施例中，所述获取多个待检测图像之前，所述方法还包括：接收所述相机的选择指令；设置所述相机对应的所述目标对象的所述真实参数。
通过接收相机的选择指令，可以对相机应获取到的参数(真实参数)进行设置，以便与每个相机所拍摄的待检测图像的参数测量结果进行对比，从而判断该相机以及该相机对应的光源为算法提供的数据的准确性，以确认硬件的可用性。
在一些实施例中，所述方法还包括：设置所述相机的点检次数。
上述选择相机来设置或调整点检该相机以及该相机所对应的光源的次数，可以提高视觉检测系统硬件点检的准确性。
第二方面，本申请提供了一种视觉检测系统的点检装置，包括：获取单元，用于获取多个待检测图像；处理单元，用于对所述多个待检测图像进行检测，以得到所述多个待检测图像中目标对象的缺陷类型和/或参数；根据所述缺陷类型和/或所述参数，确认视觉检测系统的可用性。
本申请的技术方案中，利用视觉检测系统对多个待检测图像中目标对象的缺陷类型以及参数进行检测，得出相应的缺陷类型检测结果以及参数检测结果，一方面根据缺陷类型检测结果可以判断视觉检测系统算法的准确性或可用性，一方面根据参数检测结果可以判断出视觉检测算法硬件为算法提供的数据是否准确，从而确认视觉检测系统的可用性，以在不可用时及时提醒或报错，保证检测结果的准确性。
在一些实施例中，所述获取单元用于从样本图像库中获取所述多个待检测图像，其中，所述样本图像库中每个图像的缺陷类型已知。
上述直接从样本图像库中获取多个缺陷类型已知的待检测图像，相比使用视觉检测系统的硬件实时拍摄的图像，可以避免视觉检测系统硬件设备对点检结果的影响，并减少了获取待检测图像的时间，从而提高点检视觉检测系统算法的效率。
在一些实施例中，所述处理单元用于：通过所述视觉检测系统中的缺陷检测算法对所述多个待检测图像中的每个待检测图像进行缺陷检测，以得到所述每个待检测图像中所述目标对象的缺陷类型。
通过对多个待检测图像中每个待检测图像的缺陷类型进行检测，可以根据多个待检测图像的缺陷类型检测结果综合判断缺陷检测算法的鲁棒性，从而提高点检视觉检测系统算法的准确性。
在一些实施例中，所述处理单元用于：若所述每个待检测图像中所述目标对象的缺陷类型与已知缺陷类型相同，确认所述视觉检测系统的所述缺陷检测算法可用。
上述实施方式中，在所有待检测图像的缺陷类型检测结果与已知缺陷类型全部相同的情况下确认视觉检测系统的缺陷检测算法可用，可以提高算法点检的准确性和有效性。
在一些实施例中，所述处理单元用于运行标准的目标对象的检测流程；所述获取单元用于获取所述视觉检测系统拍摄的所述目标对象的图像，以得到所述多个待检测图像。
在运行标准的目标对象的检测流程时，可以调用视觉检测系统中所有的相机与光源，通过检测所有相机与光源拍摄的多个待检测图像中目标对象的参数，可以根据参数检测结果，判断每个相机与光源的可用性，以确认视觉检测系统硬件的可用性。
在一些实施例中，所述目标对象为电池单体或菲林片。
在一些实施例中，所述处理单元用于：通过所述视觉检测系统对所述多个待检测图像中的每个待检测图像进行参数测量，得到所述每个待检测图像中所述目标对象的参数。
通过对每个待检测图像进行参数测量，可以获得每个待检测图像中目标对象的的参数测量结果，根据每个待检测图像的参数测量结果可以判断每个待检测图像对应的硬件的可用性。
在一些实施例中，所述参数包括所述目标对象的尺寸和灰度。
通过检测每个待检测图像中目标对象的尺寸和灰度，可以分别检测每个待检测图像所对应的相机和光源是否发生变化，以确认视觉检测系统硬件的可用性。
在一些实施例中，所述处理单元用于：若所述每个待检测图像中所述目标对象的参数与真实参数一致，确认所述视觉检测系统的硬件可用。
通过比较每个待检测图像中目标对象的参数与真实参数是否一致，可以判断每个待检测图像所对应的硬件是否可用，以确认视觉检测系统硬件的可用性。
在一些实施例中，所述硬件包括多个相机和多个光源。
通过比较参数检测结果与真实参数中的尺寸和灰度信息，可以分别判断视觉检测系统的相机位置以及光源的光照条件是否发生变化，即可确认视觉检测系统硬件的可用性。
在一些实施例中，所述装置还包括接收单元，所述接收单元用于接收所述相机的选择指令；所述处理单元还用于设置所述相机对应的所述目标对象的所述真实参数。
通过接收相机的选择指令，可以对相机应获取到的参数(真实参数)进行设置，以便与每个相机所拍摄的待检测图像的参数测量结果进行对比，从而判断该相机以及该相机对应的光源为算法提供的数据的准确性，以确认硬件的可用性。
在一些实施例中，所述处理单元还用于设置所述相机的点检次数。
上述选择相机来设置或调整点检该相机以及该相机所对应的光源的次数，可以提高视觉检测系统硬件点检的准确性。
第三方面，本申请实施例提供了一种视觉检测系统的点检装置，包括处理器和存储器，所述存储器用于存储程序，所述处理器用于从所述存储器中调用并运行 所述程序以执行上述第一方面或第一方面的任一可能的实现方式中的视觉检测系统的点检方法。
第四方面，本申请实施例提供了一种计算机可读存储介质，包括计算机程序，当所述计算机程序在计算机上运行时，使得所述计算机执行上述第一方面或第一方面的任一可能的实现方式中的视觉检测系统的点检方法。
附图说明
为了更清楚地说明本申请实施例的技术方案，下面将对本申请实施例中所需要使用的附图作简单地介绍，显而易见地，下面所描述的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据附图获得其他的附图。
图1是本申请实施例适用的一种视觉检测系统系统的系统架构图；
图2是本申请实施例提供的一种视觉检测系统的点检方法的示意性流程框图；
图3是本申请实施例提供的一种视觉检测系统算法的点检方法的示意性流程图；
图4是本申请实施例提供的一种视觉检测系统硬件的点检方法的示意性流程图；
图5是根据本申请实施例的一种检测视觉系统稳定性装置的示意性结构框图；
图6是根据本申请实施例的一种检测视觉系统稳定性装置的硬件结构示意图。
在附图中，附图并未按照实际的比例绘制。
具体实施方式
下面结合附图和实施例对本申请的实施方式作进一步详细描述。以下实施例的详细描述和附图用于示例性地说明本申请的原理，但不能用来限制本申请的范围，即本申请不限于所描述的实施例。
在本申请的描述中，需要说明的是，除非另有说明，“多个”的含义是两个以上；术语“上”、“下”、“左”、“右”、“内”、“外”等指示的方位或位置关系仅是为了便 于描述本申请和简化描述，而不是指示或暗示所指的装置或元件必须具有特定的方位、以特定的方位构造和操作，因此不能理解为对本申请的限制。此外，术语“第一”、“第二”、“第三”等仅用于描述目的，而不能理解为指示或暗示相对重要性。“垂直”并不是严格意义上的垂直，而是在误差允许范围之内。“平行”并不是严格意义上的平行，而是在误差允许范围之内。
下述描述中出现的方位词均为图中示出的方向，并不是对本申请的具体结构进行限定。在本申请的描述中，还需要说明的是，除非另有明确的规定和限定，术语“安装”、“相连”、“连接”应做广义理解，例如，可以是固定连接，也可以是可拆卸连接，或一体地连接；可以是直接相连，也可以通过中间媒介间接相连。对于本领域的普通技术人员而言，可视具体情况理解上述术语在本申请中的具体含义。
在视觉检测中，利用视觉检测系统的工业相机代替人的眼睛采集图像数据，利用视觉检测系统的智能设备代替人的大脑对图像进行各种运算来提取目标的特征，如条码、缺陷等，再将检测到的图像数据与标准图像数据进行比较，从而判断检测到的图像数据是否异常或生成其他检测结果，进而完成自动识别和检测的整个流程。然而，视觉检测系统的硬件和算法可能会因为各种意外情况导致检测结果不准确，例如，视觉检测中的相机位置发生变化等，因此需要定期对视觉检测系统的可用性进行点检。目前视觉检测系统的硬件主要通过人工方式进行点检，当视觉检测系统中的硬件数量较多时，点检时间长且准确率低；另外，目前还没有视觉检测系统的算法还没有完善的点检方案。
鉴于此，本申请实施例提供了一种视觉检测系统的点检方法，通过检测多个待检测图像中目标对象的缺陷类型和/或参数，与真实的缺陷类型和/或真实的参数相比是否一致，确认视觉检测系统的可用性，以在视觉检测系统不可用时及时报错，从而保证检测结果的准确性。
图1示出了本申请实施例适用的一种视觉检测系统100的系统架构图。
如图1所示，该视觉检测系统100可包括控制器110、相机120、光源130。
如图1所示，控制机110可以连接于相机120、光源130。该控制器110中可配置有用于控制该相机120、光源130的控制程序。可选地，该控制程序可在控制器110中提供与用户交互的界面，用户通过操作该界面，以实现对相机120和光源130的相关控制。控制器110可以是终端，如手机终端，平板电脑，笔记本电脑等，还可以 是服务器或者云端等。控制器110可以包括计算模块111和数据存储模块112，计算模块111可以用于对接收到的输入数据(例如待处理图像)进行处理，在计算模块111执行相关处理时，控制器110可以调用数据存储模块112中的数据、代码等以用于相应的处理，也可以将相应处理得到的数据、指令等存入数据存储模块112中。
可选地，在一些实施方式中，光源130可以直接连接于控制器110，或者，在一些其他实施方式中，该视觉检测系统100还可以包括光源控制器，该光源130也可以通过光源控制器连接于控制器110。
具体地，在该视觉检测系统中，相机120和光源130的数量可以为多个，其可以分布设置在一个生产产线的不同位置，以采集产线不同位置处产品的图像。可选地，该相机120可以包括线扫相机(或者也可呈线阵相机)和面阵相机、单色相机、彩色相机等多种类型的工业相机。光源130可以包括发光二极管(light emitting diode，LED)、发光条，或其他类型的光源。本申请实施例对相机120和光源130的具体类型不作限定。
可以理解的是，图1仅作为示意示出了视觉检测系统100中的部分设备，除了图1中所示的控制器110、相机120以及光源130以外，该视觉检测系统100还可以包括相关技术中的其它部件，本申请实施例对该视觉检测系统100的具体架构不做限定。
另外，上述相机120和光源130可以为视觉检测系统100中的部分视觉检测设备，除了该相机120和光源130以外，该视觉检测系统100还可以包括其它视觉检测设备，例如：镜头、图像采集卡、图像处理软件等等。
作为示例而非限定，该图1中所示的视觉检测系统100可以为电池的视觉检测系统。上述相机120和光源130相互配合采集得到的图像可以用于电池生产产线上的电池产品的检测，例如，检测该电池产品上异物、划痕、压痕、极耳不良、污染、腐蚀、凹点、极耳烧伤、喷码不良、字符模糊等等。
或者，在其它实施例中，该图1中所示的视觉检测系统100还可以为其它类型产品的视觉检测系统。例如，该视觉检测系统100可以为机械零件加工的视觉检测系统、电路板的视觉检测系统、电子元器件的视觉检测系统等。
图2示出了本申请实施例提供的一种视觉检测系统的点检方法200的示意性流程框图。
如图2所示，该检测视觉检测设备可用性的方法200包括以下步骤：
210，视觉检测系统的点检装置获取多个待检测图像。
多个待检测图像是在点检时使用视觉检测系统拍摄目标对象所得到的多个图像，也可以是在点检视觉检测系统之前保存好的图像。
视觉检测系统的点检装置可以作为上层(例如用户)用于控制视觉检测系统上设备的接口。可选地，该视觉检测系统的点检装置可包括视觉检测系统的点检软件，该点检软件可安装于上文图1所示的控制器110中。可选地，上述设备为视觉检测系统中的任意设备，例如，该设备可以是上文图1中所示的相机120、光源130。
220，视觉检测系统的点检装置对所述多个待检测图像进行检测，以得到所述多个待检测图像中目标对象的缺陷类型和/或参数。
利用视觉检测系统中的算法可以对待检测图像进行检测，然后得到待检测图像中目标对象的缺陷信息，其中缺陷信息可以包括缺陷类型以及缺陷位置信息；还可以得到待检测图像中目标对象的参数信息，其中参数信息可以包括目标对象的尺寸信息、灰度信息、位置信息等。
230，视觉检测系统的点检装置根据缺陷类型和/或参数，确认视觉检测系统的可用性。
其中，视觉检测系统的可用性包括视觉检测系统算法的可用性和视觉检测系统硬件的可用性，算法可以是缺陷检测算法，硬件可以包括视觉检测系统中的相机与光源。
为了检测视觉检测系统中算法的可用性，可以根据待检测图像中目标对象的缺陷类型的检测结果，与目标对象的真实缺陷类型相对比，即可得知视觉检测系统的算法是否可用。为了检测视觉检测系统中硬件的可用性，可以先使用视觉检测系统硬件拍摄的待检测图像，然后根据待检测图像中目标对象的参数检测结果，与目标对象的真实参数相对比，即可得知视觉检测系统的硬件是否可用。
本申请实施例中，利用视觉检测系统对多个待检测图像中目标对象的缺陷类型以及参数进行检测，得出相应的缺陷类型检测结果以及参数检测结果，根据缺陷类型检测结果可以判断视觉检测系统算法的准确性或可用性，根据参数检测结果可以判断出视觉检测算法硬件为算法提供的数据是否准确，从而确认视觉检测系统的可用性，以在不可用时及时提醒或报错，保证检测结果的准确性。
根据本申请的一些实施例，可选地，在步骤210获取多个待检测图像时，可以从样本图像库中获取多个待检测图像，其中样本图像库中每个图像的缺陷类型已知。
视觉检测系统中包括样本图像库，该样本图像库可以存储在上述控制器110的数据存储模块112中。示例性的，样本图像库可以是包括多个缺陷图像的多个文件夹，每个文件夹中多个缺陷图像的缺陷类型相同，例如第一文件夹的缺陷类型为拔针不良，第二文件夹的缺陷类型为标签异物，即该第一文件夹中所有缺陷图像的缺陷类型为拔针不良，该第二文件夹中所有缺陷图像的缺陷类型为标签异物。当然每个文件夹中多个缺陷图像的缺陷类型也可以不同，本申请对此不作限定。当获取多个待检测图像时，可以选择上述多个文件夹中的一个文件夹，该文件夹中的多个缺陷图像可以作为多个待检测图像。
为了检测视觉检测系统的算法的可用性，可以直接从样本图像库中获取多个缺陷类型已知的待检测图像，相比使用视觉检测系统的硬件实时拍摄的图像，可以避免视觉检测系统硬件设备对检测结果的影响，并减少了获取待检测图像的时间，从而提高点检视觉检测系统算法的效率。
根据本申请的一些实施例，可选地，可以通过视觉检测系统中的缺陷检测算法对多个待检测图像中每个待检测图像进行缺陷检测，以得到每个待检测图像中目标对象的缺陷类型。
缺陷检测算法可以存储在控制器110的数据存储模块112中，当需要对待检测图像进行缺陷检测时，首先通过控制器110中的计算模块111对待检测图像进行预处理，例如二值化处理，以便提取待检测图像中目标对象的缺陷特征，进而通过数据存储模块112中的缺陷检测算法将提取的缺陷特征与已知缺陷特征进行特征对比，从而得出待检测图像中目标对象的缺陷类型。
通过对多个待检测图像中每个待检测图像的缺陷类型进行检测，可以根据多个待检测图像的缺陷类型检测结果综合判断缺陷检测算法的鲁棒性，从而提高点检视觉检测系统算法的准确性。
根据本申请的一些实施例，可选地，若每个待检测图像中目标对象的缺陷类型与已知缺陷类型相同，确认视觉检测系统的缺陷检测算法可用。
将每个待检测图像中目标对象的缺陷类型与相应的已知缺陷类型相比，其中已知缺陷类型指待检测图像中目标对象的真实缺陷类型，若两者相同，则可以确认视觉检测系统中的缺陷检测算法准确且可用；若多个待检测图像中存在缺陷类型检测结果与已知缺陷类型不同的情况，则确认视觉检测系统中缺陷检测算法鲁棒性较差，即视觉检测系统中的缺陷检测算法不可用。
上述通过对比多个待检测图像中每个待检测图像中目标对象的缺陷类型检测结果与已知缺陷类型，在所有待检测图像的缺陷类型检测结果与已知缺陷类型全部相同的情况下确认视觉检测系统的缺陷检测算法可用，可以提高算法点检的准确性和有效性。
根据本申请的一些实施例，可选地，在步骤210获取多个待检测图像时，可以先运行标准的目标对象的检测流程，然后获取视觉检测系统拍摄的目标对象的图像，以得到多个待检测图像。
应理解，视觉检测系统中包括多个相机，每个相机均有对应的至少一个光源，其可以分布设置在一个生产产线的不同位置，以采集生产产线不同位置处目标对象的图像。当运行标准的目标对象的检测流程时，需要获取标准的目标对象多个角度或多个表面的图像，通过视觉检测系统中的多个相机对标准目标对象进行拍摄，从而获取多个角度或多个表面的图像，以得到多个待检测图像。
还应理解，标准的目标对象其尺寸以及在固定光照环境下的灰度值是固定的，本申请实施例，将标准目标对象的尺寸与灰度记录一次，然后每次对视觉检测系统的硬件进行点检时，只需运行一次标准的目标对象的检测流程，将检测结果与记录的信息进行对比即可得出硬件的点检结果，这样可以提高硬件点检的速度与效率。而使用非标准的目标对象点检硬件时，非标准的目标对象可以由无数种，每次点检需要记录该次点检使用的非标准目标对象的参数，增加了硬件点检的工作量并降低了点检效率。
在运行标准的目标对象的检测流程时，可以调用视觉检测系统中所有的相机与光源，通过检测所有相机与光源拍摄的多个待检测图像中目标对象的参数，可以根据参数检测结果，判断相机与光源的可用性，以确认视觉检测系统硬件的可用性。
根据本申请的一些实施例，可选地，目标对象可以是电池单体或菲林片。
应理解，在某种产品的生产过程中，不仅需要对成品进行尺寸或缺陷等进行检测，可能还需要组成该产品的零部件进行检测。例如上述目标对象可以是组装及焊接完成的电池单体，也可以是组成电池单体的电池膜片，若某些相机拍摄目标对象为类似电池膜片的零部件时，可以运行菲林片的检测流程，通过对比菲林片的参数检测结果与真实参数，检测这些相机以及对应光源的可用性。
应理解，标准的电池单体或标准的菲林片的参数是固定的，当检测出的参数与标准的电池单体或标准的菲林片的参数不同或相差较大，则可以确认视觉检测系统硬件不可用。
根据本申请的一些实施例，可选地，通过所述视觉检测系统对所述多个待检测图像中的每个待检测图像进行参数测量，得到所述每个待检测图像中所述目标对象的参数。
应理解，在对视觉检测系统的硬件进行点检时，所使用的多个待检测图像是通过视觉检测系统的所有相机拍摄的照片，对每个待检测图像进行参数测量，可以得到每个待检测图像中目标对象的参数检测结果。根据每个待检测图像的参数检测结果，可以对每个待检测图像所对应的相机和光源进行可用性点检。
通过对每个待检测图像进行参数测量，可以获得每个待检测图像中目标对象的的参数测量结果，根据每个待检测图像的参数测量结果可以判断每个待检测图像对应的硬件的可用性。
根据本申请的一些实施例，可选地，参数可以包括目标对象的尺寸和灰度。
当视觉检测系统的某一相机位置发生改变，对该相机拍摄的目标对象的待检测图像进行尺寸测量，目标对象的尺寸会发生变化。其中的原理是，测量目标对象的长宽尺寸时是通过测量目标对象的长边或宽边所包含的像素个数进行计算，具体地，长度尺寸为每个像素的宽度乘以目标对象长边所包含的像素个数；宽度尺寸为每个像素的宽度乘以目标对象短边所包含的像素个数。因此当相机位置与标准相机位置相比，越接近其工位上的目标对象，其图像内包含的像素个数越多，则测量出目标对象的尺寸会比实际尺寸大；相反，相机位置与标准相机位置相比，越远离其工位上的目标对象，其图像内包含的像素个数越少，测量出目标对象的尺寸会比实际尺寸小。因此可以通过目标对象的尺寸参数信息，判断视觉检测系统的相机位置是否发生变化。
视觉检测系统中光源提供的光照与标准光照相比变化过大时，会对尺寸测量有轻微影响，例如过曝时会导致目标对象成像后边缘内缩，测量的尺寸值偏小，可以通过目标对象的灰度参数信息，判断视觉检测系统的光源是否发生变化。
通过检测每个待检测图像中目标对象的尺寸和灰度，可以分别检测每个待检测图像所对应的相机和光源是否发生变化，以确认视觉检测系统硬件的可用性。
根据本申请的一些实施例，可选地，若每个待检测图像中目标对象的参数与真实参数一致，确认视觉检测系统的硬件可用。
每个待检测图像中目标对象的参数与真实参数一致可以是指参数测量结果与真实参数完全相同，也可以是参数测量结果与真实参数的差值小于预设阈值。通过预设阈值的设置，可以满足不同客户对测量数据的不同准确度需求。在实际实现时，可以将参数测量结果与预期结果进行比对，以确认视觉检测系统硬件的可用性，其中，预期结果可以是真实参数与预设阈值形成的范围。
上述通过比较每个待检测图像中目标对象的参数与真实参数是否一致，可以判断每个待检测图像所对应的硬件是否可用，以确认视觉检测系统硬件的可用性。
根据本申请的一些实施例，可选地，硬件包括多个相机和多个光源。
应理解，视觉检测系统中的硬件一般会发生变化的是相机的位置，与光源的光照条件。通过比较参数检测结果与真实参数中的尺寸和灰度信息，可以分别判断视觉检测系统的相机位置以及光源的光照条件是否发生变化，即可确认视觉检测系统硬件的可用性。
根据本申请的一些实施例，可选地，在获取多个待检测图像之前，所述方法还包括：接收相机的选择指令，设置该相机对应的目标对象的真实参数。
应理解，在第一次对视觉检测系统的硬件进行点检时，需要记录或设置标准视觉检测系统硬件条件下，每个相机应获取到的真实参数。通过接收相机的选择指令，可以对相机应获取到的参数(真实参数)进行设置，以便与每个相机所拍摄的待检测图像的参数测量结果进行对比，从而判断该相机以及该相机对应的光源为算法提供的数据的准确性，以确认硬件的可用性。
还应理解，当对视觉检测系统的硬件进行非首次点检时，即每个相机对应的真实参数已经被记录或设置，且硬件未发生调整，此时不需要设置参数；若发生调整，则需要设置该相机对应的真实参数，以便保证点检的准确性。
需要说明的是，视觉检测系统还可以用于检测零部件之间的连接关系。例如，电池视觉检测系统中包括焊接阴极相机，用于检测电池的阴极转接片与其他部件间的焊接位置是否正确，则该相机所对应的待检测图像的参数还可以包括标准阴极转接片的角点位置、焊点面积等信息，通过检测标准阴极转接片的角点位置、焊点面积等参数，可以判断该焊接阴极相机的位置是否发生变化。因此，可以根据视觉检测系统相机功能的不同，为该相机设置除了尺寸与灰度外其他的参数，以及在点检时测量该相机下对应的参数信息。
根据本申请的一些实施例，可选地，设置所述相机的检测次数。
一般情况下，对每个相机的点检次数默认设置为1，即可达到基本的点检需求。为了提高点检的准确性，可以选择相机来设置或调整点检该相机以及该相机所对应的光源的检测次数。
图3示出了本申请实施例提供的一种视觉检测系统算法的点检方法300的示意性流程图。
如图3所示，该视觉检测系统算法的点检方法300包括以下步骤：
301，选择图片库。
具体地，用户可以通过控制器110中的交互界面选择图片库，以获取多个待检测图像。该图片库中包括多个待检测图像，每个待检测图像中目标对象的缺陷类型已知。该图片库可以是数据存储模块112的样本图像库中的一个文件夹。当然，该图片库也可以是默认文件夹，不需要用户选择。
302，运行检测流程。
具体地，在用户选择图片库后，可以点击交互界面上的“开始检测”按钮，视觉检测系统的控制器110接收到该开始检测的指令后，调用缺陷检测算法的代码对图片库中的多个待检测图像进行缺陷检测，从而得出每个待检测图像中目标对象的缺陷类型。
可选地，在调用缺陷检测算法的代码对待检测图像进行缺陷检测前，还可以对待检测图像进行预处理，以便更准确提取缺陷特征，从而提高缺陷检测的准确性。
303，显示检测结果。
具体地，可以将302步骤得出的每个待检测图像中目标对象的缺陷类型结果显示在交互界面上，也可以同时将每个待检测图像的已知缺陷类型(真实缺陷类型)对应地显示在界面上，以便用户查看缺陷类型对比结果。
304，判断算法检测出的缺陷类型与预期结果是否相同。
具体地，通过检测出的缺陷类型与已知缺陷类型是否相同，确认视觉检测系统算法的可用性。若每个待检测图像的检测结果与预期结果相同，则视觉检测系统算法点检成功，此时可以开启视觉检测系统算法的运行权限，否则视觉检测系统算法点检失败，禁止视觉检测系统算法运行。可选地，可以在算法点检失败的同时，在界面上弹出警示信号，以便用户根据点检失败结果作出相应动作，例如，技术人员排查算法代码是否出现问题，从而保证算法检测结果的准确性。
通过上述实施方式，用户只需选择图片库，点击开始检测按钮，即可实现对视觉检测系统算法的自动化点检。
图4示出了本申请实施例提供的一种视觉检测系统硬件的点检方法400的示意性流程图。
如图4所示，该视觉检测系统硬件的点检方法400包括以下步骤：
401，选择相机号。
具体地，用户可以在交互界面上选择相机号，设置每个相机的检测次数以及该相机下目标对象的真实参数。
402，配置参数。
具体地，选择好相机号后，可以设置该相机下目标对象的真实参数。将标准位置的相机与光照条件下目标对象的尺寸和灰度设置为真实参数。
403，运行检测流程。
具体地，当设置好每个相机下目标对象的真实参数后，运行标准的电池单体或菲林片的检测流程。
404，显示检测结果。
具体地，在运行检测流程后，视觉检测系统会通过所有相机拍摄多个待检测图像，然后检测多个待检测图像中电池单体或菲林片的参数，然后将参数检测结果显示在交互界面上，也可以同时将每个待检测图像的目标对象的真实参数显示在交互界面上，以便用户查看参数检测对比结果。
405，判断参数检测结果是否在预期结果范围内。
具体地，若每个待检测图像的参数检测结果在预期范围内，则视觉检测系统的硬件为算法提供的数据是准确的，即视觉检测算法的硬件是可用的，此时点检成功，可以开启视觉检测系统硬件的运行权限，若存在待检测图像的参数检测结果不在预期范围内，则该待检测图像对应的相机和/或光源为算法提供的数据是不准确或存在偏差的，即视觉检测系统的硬件不可用，此时点检失败，可以禁止视觉检测系统硬件运行。
可选地，硬件点检的交互界面上显示的结果为所有相机以及对应的光源的整体点检结果，还可以通过选择相机号，查阅某一相机对应的点检结果。
通过上述实施方式，用户在配置好每个相机对应的真实参数的情况下，只需点击开始检测按钮，即可实现对视觉检测系统的硬件的自动化点检。
上文详细地描述了本申请实施例的方法实施例，下面描述本申请实施例的装置实施例，装置实施例与方法实施例相互对应，因此未详细描述的部分可参见前面方法实施例，装置可以实现上述方法中任意可能实现的方式。
图5示出了本申请一个实施例的视觉检测系统的点检装置500的示意性框图。该点检装置500可以执行上述本申请实施例的视觉检测系统的点检方法，例如，该点检装置500可以为前述控制器110。
如图5所示，该点检装置500包括：
获取单元510，用于获取多个待检测图像。
处理单元520，用于对所述多个待检测图像进行检测，以得到所述多个待检测图像中目标对象的缺陷类型和/或参数；根据缺陷类型和/或参数，确认视觉检测系统的可用性
根据本申请的一些实施例，可选地，获取单元510用于从样本图像库中获取所述多个待检测图像，其中，所述样本图像库中每个图像的缺陷类型已知。
根据本申请的一些实施例，可选地，处理单元520用于通过所述视觉检测系统中的缺陷检测算法对所述多个待检测图像中的每个待检测图像进行缺陷检测，以得到所述每个待检测图像中所述目标对象的缺陷类型。
根据本申请的一些实施例，可选地，若所述每个待检测图像中所述目标对象的缺陷类型与已知缺陷类型相同，处理单元520用于确认所述视觉检测系统的所述缺陷检测算法可用。
根据本申请的一些实施例，可选地，处理单元520用于运行标准的目标对象的检测流程；获取单元510用于获取所述视觉检测系统拍摄的所述目标对象的图像，以得到所述多个待检测图像。
根据本申请的一些实施例，可选地，目标对象为电池单体或菲林片。
根据本申请的一些实施例，可选地，处理单元520用于通过所述视觉检测系统对所述多个待检测图像中的每个待检测图像进行参数测量，得到所述每个待检测图像中所述目标对象的参数。
根据本申请的一些实施例，可选地，所述参数包括所述目标对象的尺寸和灰度。
根据本申请的一些实施例，可选地，若所述每个待检测图像中所述目标对象的参数与真实参数一致，处理单元520用于确认所述视觉检测系统的硬件可用。
根据本申请的一些实施例，可选地，硬件包括多个相机和多个光源。
根据本申请的一些实施例，可选地，点检装置500还包括接收单元530，所述接收单元530用于接收所述相机的选择指令；所述处理单元520还用于设置所述相机对应的所述目标对象的所述真实参数。
根据本申请的一些实施例，可选地，处理单元520还用于设置所述相机的检测次数。
图6是本申请实施例的检测视觉检测系统可用性的装置的硬件结构示意图。图6所示的检测视觉检测系统可用性的装置600包括存储器601、处理器602、通信接口603以及总线604。其中，存储器601、处理器602、通信接口603通过总线604实现彼此之间的通信连接。
存储器601可以是只读存储器(read-only memory，ROM)，静态存储设备和随机存取存储器(random access memory，RAM)。存储器601可以存储程序，当存储器601中存储的程序被处理器602执行时，处理器602和通信接口603用于执行本申请实施例的视觉检测系统的点检方法的各个步骤。
处理器602可以采用通用的中央处理器(central processing unit，CPU)，微处理器，应用专用集成电路(application specific integrated circuit，ASIC)，图形处理器(graphics processing unit，GPU)或者一个或多个集成电路，用于执行相关程序，以实现本申请实施例的检测视觉检测系统可用性的装置中的单元所需执行的功能，或者执行本申请实施例的视觉检测系统的点检方法。
处理器602还可以是一种集成电路芯片，具有信号的处理能力。在实现过程中，本申请实施例的视觉检测系统的点检方法的各个步骤可以通过处理器602中的硬件的集成逻辑电路或者软件形式的指令完成。
上述处理器602还可以是通用处理器、数字信号处理器(digital signal processing，DSP)、ASIC、现成可编程门阵列(field programmable gate array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。可以实现或者执行本申请实施例中的公开的各方法、步骤及逻辑框图。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。结合本申请实施例所公开的方法的步骤可以直接体现为硬件处理器执行完成，或者用处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器，闪存、只读存储器，可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器601，处理器602读取存储器601中的信息，结合其硬件完成本申请实施例的检测视觉检测系统可用性的装置中包括的单元所需执行的功能，或者执行本申请实施例的视觉检测系统的点检方法。
通信接口603使用例如但不限于收发器一类的收发装置，来实现装置600与其他设备或通信网络之间的通信。例如，可以通过通信接口603获取未知设备的流量数据。
总线604可包括在装置600各个部件(例如，存储器601、处理器602、通信接口603)之间传送信息的通路。
应注意，尽管上述装置600仅仅示出了存储器、处理器、通信接口，但是在具体实现过程中，本领域的技术人员应当理解，装置600还可以包括实现正常运行所必须的其他器件。同时，根据具体需要，本领域的技术人员应当理解，装置600还可包括实现其他附加功能的硬件器件。此外，本领域的技术人员应当理解，装置600也可仅仅包括实现本申请实施例所必须的器件，而不必包括图6中所示的全部器件。
本申请实施例还提供了一种计算机可读存储介质，存储用于设备执行的程序代码，程序代码包括用于执行上述视觉检测系统的点检方法中的步骤的指令。
本申请实施例还提供了一种计算机程序产品，所述计算机程序产品包括存储在计算机可读存储介质上的计算机程序，所述计算机程序包括程序指令，当所述程序指令被计算机执行时，使所述计算机执行上述视觉检测系统的点检方法。
上述的计算机可读存储介质可以是暂态计算机可读存储介质，也可以是非暂态计算机可读存储介质。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的装置的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在步骤210之前，检测视觉检测系统可用性的装置可接受用户对设备的控制指令。在一些实施例中，上位机110中具有显示屏，该检测视觉检测系统可用性的装置可在上位机110的显示屏中显示检测界面，该检测界面中包括对应于多个设备的标签选项。用户通过对该检测界面中多个标签选项进行操作，从而向上位机110中输入多个对设备的控制指令，进而使该上位机110中的检测装置接收该对应于多个设备的控制指令。
虽然已经参考优选实施例对本申请进行了描述，但在不脱离本申请的范围的情况下，可以对其进行各种改进并且可以用等效物替换其中的部件。尤其是，只要不存在结构冲突，各个实施例中所提到的各项技术特征均可以任意方式组合起来。本申请并不局限于文中公开的特定实施例，而是包括落入权利要求的范围内的所有技术方案。

Claims (22)

  1. 一种视觉检测系统的点检方法，其特征在于，包括：
    获取多个待检测图像；
    对所述多个待检测图像进行检测，以得到所述多个待检测图像中目标对象的缺陷类型和/或参数；
    根据所述缺陷类型和/或所述参数，确认视觉检测系统的可用性。
  2. 根据权利要求1所述的点检方法，其特征在于，所述获取多个待检测图像包括：
    从样本图像库中获取所述多个待检测图像，其中，所述样本图像库中每个图像的缺陷类型已知。
  3. 根据权利要求1或2所述的点检方法，其特征在于，所述对所述多个待检测图像进行检测，以得到所述多个待检测图像中目标对象的缺陷类型和/或参数，包括：
    通过所述视觉检测系统中的缺陷检测算法对所述多个待检测图像中的每个待检测图像进行缺陷检测，以得到所述每个待检测图像中所述目标对象的缺陷类型。
  4. 根据权利要求1至3中任一项所述的点检方法，其特征在于，所述根据所述缺陷类型和/或所述参数，确认所述视觉检测系统的可用性包括：
    若所述每个待检测图像中所述目标对象的缺陷类型与已知缺陷类型相同，确认所述视觉检测系统的所述缺陷检测算法可用。
  5. 根据权利要求1所述的点检方法，其特征在于，所述获取多个待检测图像包括：
    运行标准的目标对象的检测流程；
    获取所述视觉检测系统拍摄的所述目标对象的图像，以得到所述多个待检测图像。
  6. 根据权利要求5所述的点检方法，其特征在于，所述目标对象为电池单体或菲林片。
  7. 根据权利要求5或6所述的点检方法，其特征在于，所述通过视觉检测系统对所述多个待检测图像进行检测，以得到所述多个待检测图像中所述目标对象的缺陷类型和/或参数，包括：
    通过所述视觉检测系统对所述多个待检测图像中的每个待检测图像进行参数测量，得到所述每个待检测图像中所述目标对象的参数。
  8. 根据权利要求7所述的点检方法，其特征在于，所述参数包括所述目标对象的尺寸和灰度。
  9. 根据权利要求5至8中任一项所述的点检方法，其特征在于，所述根据所述缺陷类型和/或所述参数，确认所述视觉检测系统的可用性包括：
    若所述每个待检测图像中所述目标对象的参数与真实参数一致，确认所述视觉检测系统的硬件可用。
  10. 根据权利要求9所述的点检方法，其特征在于，所述硬件包括多个相机和多个光源。
  11. 根据权利要求10所述的点检方法，其特征在于，所述获取多个待检测图像之前，所述方法还包括：
    接收所述相机的选择指令；
    设置所述相机对应的所述目标对象的所述真实参数。
  12. 根据权利要求11所述的点检方法，其特征在于，所述方法还包括：
    设置所述相机的点检次数。
  13. 一种视觉检测系统的点检装置，其特征在于，所述装置包括：
    获取单元，用于获取多个待检测图像；
    处理单元，用于对所述多个待检测图像进行检测，以得到所述多个待检测图像中目标对象的缺陷类型和/或参数；根据所述缺陷类型和/或所述参数，确认视觉检测系统的可用性。
  14. 根据权利要求13所述的点检装置，其特征在于，所述获取单元用于从样本图像库中获取所述多个待检测图像，其中，所述样本图像库中每个图像的缺陷类型已知。
  15. 根据权利要求13或14所述的点检装置，其特征在于，所述处理单元用于：
    通过所述视觉检测系统中的缺陷检测算法对所述多个待检测图像中的每个待检测图像进行缺陷检测，以得到所述每个待检测图像中所述目标对象的缺陷类型。
  16. 根据权利要求13至15中任一项所述的点检装置，其特征在于，所述处理单元用于：
    若所述每个待检测图像中所述目标对象的缺陷类型与已知缺陷类型相同，确认所述视觉检测系统的所述缺陷检测算法可用。
  17. 根据权利要求13所述的点检装置，其特征在于，
    所述处理单元用于运行标准的目标对象的检测流程；
    所述获取单元用于获取所述视觉检测系统拍摄的所述目标对象的图像，以得到所述多个待检测图像。
  18. 根据权利要求17所述的点检装置，其特征在于，所述处理单元用于：
    通过所述视觉检测系统对所述多个待检测图像中的每个待检测图像进行参数测量，得到所述每个待检测图像中所述目标对象的参数。
  19. 根据权利要求18所述的点检装置，其特征在于，所述参数包括所述目标对象的尺寸和灰度。
  20. 根据权利要求16至19中任一项所述的点检装置，其特征在于，所述处理单元用于：
    若所述每个待检测图像中所述目标对象的参数与真实参数一致，确认所述视觉检测系统的硬件可用。
  21. 一种视觉检测系统的点检装置，其特征在于，包括处理器和存储器，所述存储器用于存储程序，所述处理器用于从所述存储器中调用并运行所述程序以执行权利要求1至12中任一项所述的视觉检测系统的点检方法。
  22. 一种计算机可读存储介质，其特征在于，包括计算机程序，当所述计算机程序在计算机上运行时，使得所述计算机执行权利要求1至12中任一项所述的视觉检测系统的点检方法。
PCT/CN2022/115748 2022-08-30 2022-08-30 视觉检测系统的点检方法和装置 Ceased WO2024044942A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
CN202280006734.3A CN117980944A (zh) 2022-08-30 2022-08-30 视觉检测系统的点检方法和装置
PCT/CN2022/115748 WO2024044942A1 (zh) 2022-08-30 2022-08-30 视觉检测系统的点检方法和装置
EP22879633.0A EP4358030B1 (en) 2022-08-30 2022-08-30 Computer-implemented method and apparatus for spot- checking visual inspection system
US18/296,995 US12067710B2 (en) 2022-08-30 2023-04-07 Method and apparatus for spot-checking visual inspection system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2022/115748 WO2024044942A1 (zh) 2022-08-30 2022-08-30 视觉检测系统的点检方法和装置

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/296,995 Continuation US12067710B2 (en) 2022-08-30 2023-04-07 Method and apparatus for spot-checking visual inspection system

Publications (1)

Publication Number Publication Date
WO2024044942A1 true WO2024044942A1 (zh) 2024-03-07

Family

ID=89997368

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/115748 Ceased WO2024044942A1 (zh) 2022-08-30 2022-08-30 视觉检测系统的点检方法和装置

Country Status (4)

Country Link
US (1) US12067710B2 (zh)
EP (1) EP4358030B1 (zh)
CN (1) CN117980944A (zh)
WO (1) WO2024044942A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN119380169A (zh) * 2024-12-27 2025-01-28 杭州海康机器人股份有限公司 一种视觉检测配置方法、装置及视觉检测系统

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118988750B (zh) * 2024-10-24 2025-02-21 杭州领策科技有限公司 集成电路测试系统的点检方法、装置、设备及存储介质

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109978875A (zh) * 2019-04-03 2019-07-05 无锡立赫智能科技有限公司 一种电容器外观缺陷识别方法及识别装置
CN111640091A (zh) * 2020-05-14 2020-09-08 阿丘机器人科技(苏州)有限公司 产品缺陷的检测方法及计算机存储介质
US20220092359A1 (en) * 2020-09-21 2022-03-24 Boe Technology Group Co., Ltd. Image data classification method, device and system
CN114359253A (zh) * 2022-01-12 2022-04-15 盛泰光电科技股份有限公司 基于卷积神经网络的影像脏污检测方法及系统
WO2022101909A1 (en) * 2020-11-11 2022-05-19 B. G. Negev Technologies And Applications Ltd., At Ben-Gurion University Methods and systems for trusted unknown malware detection and classification in linux cloud environments
US20220172483A1 (en) * 2020-12-02 2022-06-02 PatriotOne Technologies System and method social distancing recognition in cctv surveillance imagery
CN115147363A (zh) * 2022-06-24 2022-10-04 深圳市纳研科技有限公司 一种基于深度学习算法的影像缺陷检测和分类方法及系统

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH01145553A (ja) * 1987-12-02 1989-06-07 Hitachi Ltd パターン検査装置
JP5780936B2 (ja) * 2011-12-06 2015-09-16 株式会社ニューフレアテクノロジー 検査装置
CN203778357U (zh) * 2014-01-27 2014-08-20 河南科技大学 锂电池极片表面缺陷在线检测分拣系统
CN109239075B (zh) * 2018-08-27 2021-11-30 北京百度网讯科技有限公司 电池检测方法及装置
CN110554053B (zh) * 2019-08-12 2025-03-21 超音速人工智能科技股份有限公司 一种电池涂布缺陷检测设备
CN110599484B (zh) * 2019-09-19 2023-01-10 京东方科技集团股份有限公司 缺陷检测方法、装置及存储介质
KR102261757B1 (ko) * 2020-06-22 2021-06-08 (주) 인텍플러스 배터리 전극 검사 시스템
CN113092489B (zh) * 2021-05-20 2024-08-23 鲸朵(上海)智能科技有限公司 一种电池外观缺陷的检测系统及方法
US11978197B2 (en) * 2021-10-28 2024-05-07 Hilti Aktiengesellschaft Inspection method for inspecting an object and machine vision system
US11657494B1 (en) * 2022-01-14 2023-05-23 GM Global Technology Operations LLC Method to detect defects in battery pouch cells using angled flash thermography
US12203880B2 (en) * 2022-02-07 2025-01-21 GM Global Technology Operations LLC Image processing and detection of discontinuities in battery cells

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109978875A (zh) * 2019-04-03 2019-07-05 无锡立赫智能科技有限公司 一种电容器外观缺陷识别方法及识别装置
CN111640091A (zh) * 2020-05-14 2020-09-08 阿丘机器人科技(苏州)有限公司 产品缺陷的检测方法及计算机存储介质
US20220092359A1 (en) * 2020-09-21 2022-03-24 Boe Technology Group Co., Ltd. Image data classification method, device and system
WO2022101909A1 (en) * 2020-11-11 2022-05-19 B. G. Negev Technologies And Applications Ltd., At Ben-Gurion University Methods and systems for trusted unknown malware detection and classification in linux cloud environments
US20220172483A1 (en) * 2020-12-02 2022-06-02 PatriotOne Technologies System and method social distancing recognition in cctv surveillance imagery
CN114359253A (zh) * 2022-01-12 2022-04-15 盛泰光电科技股份有限公司 基于卷积神经网络的影像脏污检测方法及系统
CN115147363A (zh) * 2022-06-24 2022-10-04 深圳市纳研科技有限公司 一种基于深度学习算法的影像缺陷检测和分类方法及系统

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4358030A4 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN119380169A (zh) * 2024-12-27 2025-01-28 杭州海康机器人股份有限公司 一种视觉检测配置方法、装置及视觉检测系统

Also Published As

Publication number Publication date
EP4358030A1 (en) 2024-04-24
US20240070849A1 (en) 2024-02-29
CN117980944A (zh) 2024-05-03
EP4358030A4 (en) 2024-11-27
EP4358030B1 (en) 2026-04-22
US12067710B2 (en) 2024-08-20

Similar Documents

Publication Publication Date Title
US11587219B2 (en) Method and apparatus for detecting pixel defect of optical module, and device
US12499577B2 (en) Method and apparatus for testing stability of vision system
CN115147370A (zh) 一种电池顶盖焊接缺陷检测方法、装置、介质及电子设备
US12067710B2 (en) Method and apparatus for spot-checking visual inspection system
KR20130126370A (ko) 비아홀을 검사하는 방법 및 장치
CN115731165A (zh) 一种锂电池在线尺寸点检的检测系统及方法
CN117589770A (zh) Pcb贴片板检测方法、装置、设备及介质
CN111951210A (zh) 数据的处理方法、装置及设备
WO2024016715A1 (zh) 检测系统的成像一致性的方法、装置和计算机存储介质
CN116337412A (zh) 屏幕检测方法、设备及存储介质
CN117115233B (zh) 一种基于机器视觉的尺寸测量方法、装置及电子设备
CN117455887A (zh) 基于机器视觉的pcb来料检测方法、装置、设备及介质
CN116524334A (zh) 一种表计的读数检测方法、系统、存储介质和电子设备
CN109712115B (zh) 一种pcb板自动检测方法及系统
CN111780675B (zh) 螺钉浮高检测方法、装置、电子装置及存储介质
CN116993654B (zh) 摄像头模组缺陷检测方法、装置、设备、存储介质及产品
JP2016217872A (ja) 検査装置、検査方法、プログラム、記録媒体
CN116977302A (zh) 图像处理方法、装置、设备及存储介质
CN117689660B (zh) 基于机器视觉的保温杯温度质检方法
CN117834997B (zh) 一种黑屏异常检测方法、装置、计算机设备及存储介质
CN119555697B (zh) 铜箔表面缺陷检测方法、装置、计算机设备及存储介质
US20250191162A1 (en) Method to detect camera blemishes
KR102028196B1 (ko) 영상 처리를 이용한 엘이디 모듈 검사 장치
CN117676122A (zh) 图像采集装置的检测方法、装置、电子设备及存储介质
CN119762425A (zh) 设备一致性的检测方法、装置、设备及存储介质

Legal Events

Date Code Title Description
WWE Wipo information: entry into national phase

Ref document number: 202280006734.3

Country of ref document: CN

ENP Entry into the national phase

Ref document number: 2022879633

Country of ref document: EP

Effective date: 20230427

NENP Non-entry into the national phase

Ref country code: DE

WWG Wipo information: grant in national office

Ref document number: 2022879633

Country of ref document: EP