WO2024016715A1 - 检测***的成像一致性的方法、装置和计算机存储介质 - Google Patents

检测***的成像一致性的方法、装置和计算机存储介质 Download PDF

Info

Publication number
WO2024016715A1
WO2024016715A1 PCT/CN2023/084549 CN2023084549W WO2024016715A1 WO 2024016715 A1 WO2024016715 A1 WO 2024016715A1 CN 2023084549 W CN2023084549 W CN 2023084549W WO 2024016715 A1 WO2024016715 A1 WO 2024016715A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
area
image information
target area
preset
Prior art date
Application number
PCT/CN2023/084549
Other languages
English (en)
French (fr)
Inventor
王智玉
王晞
江冠南
Original Assignee
宁德时代新能源科技股份有限公司
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 宁德时代新能源科技股份有限公司 filed Critical 宁德时代新能源科技股份有限公司
Priority to EP23733191.3A priority Critical patent/EP4332889A1/en
Priority to US18/474,262 priority patent/US20240029240A1/en
Publication of WO2024016715A1 publication Critical patent/WO2024016715A1/zh

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces

Definitions

  • the present application relates to the field of image processing, and more specifically, to a method, device and computer storage medium for detecting the imaging consistency of a system.
  • Embodiments of the present application provide a method, device and computer storage medium for detecting the imaging consistency of a system, which can effectively detect the imaging consistency of the system, thereby improving the accuracy of product detection.
  • a method for detecting imaging consistency of a system including: determining a target area in an image collected by the system, where the target area is a partial area in the image that includes a target object; and obtaining first image information of the target area; According to the first image information, the imaging consistency of the system is detected.
  • the imaging consistency of the system can be effectively detected based on the information of the target object. This improves the accuracy of product testing.
  • detecting the consistency of the system's imaging according to the first image information includes: if the first image information satisfies the first preset condition, determining that the system's imaging has consistency, or; if the first If an image information does not satisfy the first preset condition, it is determined that the imaging of the system is not consistent.
  • the target area is an area of interest in the image
  • the first image information includes the brightness, clarity, and position of the target area
  • the first image information satisfying the first preset condition includes: the brightness of the target area is at Within the first preset brightness range; the definition of the target area is greater than or equal to the first preset definition; and the position of the target area is within the preset position range.
  • the imaging consistency of the system can be effectively detected, but also the imaging consistency of the system can be effectively detected based on the brightness, clarity, and position of the region of interest.
  • the information determines the abnormality of the light source, light path adjustment equipment, image acquisition equipment and other components in the system.
  • determining the target area in the image collected by the system includes: processing the image based on a segmentation and positioning method to obtain the area of interest.
  • the image is processed through the segmentation and positioning method, which can effectively identify the target object and perform area segmentation according to the information of the target object, accurately determine the target area, and make the target object in the target area account for a higher proportion in the image. , so that the consistency of the system can be detected more effectively.
  • the target area is a line area composed of lines of the target object in the area of interest of the image
  • the first image information includes the brightness, sharpness, and line angle of the target area
  • the line angle is the line angle of the target object.
  • the angle of the line, the first image information satisfying the first preset condition includes: the brightness of the target area is within the second preset brightness range; the definition of the target area is greater than or equal to the second preset definition; the line angle of the target area is within the preset within the set angle range.
  • the imaging consistency of the system not only can the imaging consistency of the system be more effectively detected, but also the consistency of the line area can be detected based on the Information on brightness, sharpness, and line angle determines abnormalities in components such as light sources, light path adjustment equipment, and image acquisition equipment in the system.
  • determining the target area in the image collected by the system includes: processing the image based on a segmentation and positioning method to obtain the area of interest; performing semantic segmentation on the area of interest to obtain the target area.
  • the image is processed through the segmentation and positioning method to obtain the area of interest, and by performing semantic segmentation on the area of interest, the target object can be more effectively identified and segmented more accurately based on the information of the target object, which can accurately Determine the target area and make the target area almost only include the target object, so that the consistency of the system can be more effectively detected.
  • the first image information includes the brightness, sharpness and position of the target area and the brightness, sharpness and line angle of the line area in the target area, and the line area is the line formed by the target object in the target area.
  • the line angle is the angle of the line of the target object.
  • the first image information satisfies the first preset condition including: the brightness of the target area is within the first preset brightness range; the clarity of the target area is greater than or equal to the first preset condition.
  • the sharpness; the position of the target area is within the preset position range; the line in the target area
  • the brightness of the strip area is within the second preset brightness range; the definition of the line area in the target area is greater than or equal to the second preset sharpness; and the line angle of the line area in the target area is within the preset angle range.
  • the imaging consistency of the system can be accurately and quickly detected, but also the imaging consistency of the system can be accurately and quickly detected.
  • Abnormalities in components such as the light source, light path adjustment device, and image acquisition device in the system can be determined based on the information on the brightness, clarity, and position of the area of interest and the brightness, clarity, and line angle of the line area.
  • the method for detecting the consistency of the imaging of the system further includes: obtaining second image information of the images collected by the system; detecting the consistency of the imaging of the system includes: based on the second image information and the first image information. , to detect the imaging consistency of the system.
  • the imaging consistency of the system can be more comprehensively and effectively detected based on the image information collected by the system and the target object information, thereby improving the Product testing accuracy.
  • detecting the consistency of imaging of the system based on the second image information and the first image information includes: if the second image information satisfies the second preset condition and the first image information satisfies the first preset condition condition, it is determined that the imaging of the system is consistent, or; if the second image information does not meet the second preset condition or the first image information does not meet the first preset condition, it is determined that the imaging of the system is not consistent.
  • the cause of inconsistent imaging of the detection system can also be determined based on the information that does not satisfy the first preset condition and the second preset condition.
  • the second image information includes detecting the brightness, clarity and similarity of the image, and the second image information satisfying the second preset condition includes: the brightness of the image is within the third preset brightness range; The definition is greater than or equal to the third preset definition; the similarity of the image is within the preset similarity range.
  • the imaging consistency of the system can be more comprehensively and effectively detected, but also the imaging consistency of the system can be detected based on the brightness, clarity and similarity of the image.
  • the degree of information determines the abnormality of the light source, light path adjustment equipment, image acquisition equipment and other components in the system.
  • the target object is the pole
  • the target area is a partial area in the image that includes the pole, or the target area is a line area in the image composed of pole lines of the pole.
  • the target area as a partial area in the image that includes the tabs, or by setting the target area as a line area composed of the tab lines of the tabs in the image, it is possible to target the information or tabs of the tabs.
  • the ear line information effectively detects the imaging consistency of the system and improves the accuracy of product detection.
  • a device for detecting imaging consistency of a system including a determination module, an acquisition module and a detection module, wherein the determination module is used to determine the target area in the image collected by the system, and the target area is included in the image.
  • a partial area of the target object an acquisition module, used to obtain the first image information of the target area; and a detection module, used to detect the consistency of the imaging of the system based on the first image information.
  • the detection module is configured to: if the first image information satisfies the first preset condition, determine that the imaging of the system is consistent, or; if the first image information does not satisfy the first preset condition, then Determine whether the system's imaging is consistent.
  • the target area is an area of interest in the image
  • the first image information includes the brightness, clarity, and position of the target area
  • the first image information satisfying the first preset condition includes: the brightness of the target area is at Within the first preset brightness range; the definition of the target area is greater than or equal to the first preset definition; and the position of the target area is within the preset position range.
  • the imaging consistency of the system can be effectively detected, but also the imaging consistency of the system can be effectively detected based on the brightness, clarity, and position of the region of interest.
  • the information determines the abnormality of the light source, light path adjustment equipment, image acquisition equipment and other components in the system.
  • the determination module is configured to: process the image based on a segmentation and positioning method to obtain the region of interest.
  • the image is processed through the segmentation and positioning method, which can effectively identify the target object and perform area segmentation according to the information of the target object, accurately determine the target area, and make the target object in the target area account for a higher proportion in the image. , so that the consistency of the system can be detected more effectively.
  • the target area is a line area composed of lines of the target object in the area of interest of the image
  • the first image information includes the brightness, sharpness, and line angle of the target area
  • the line angle is the line angle of the target object.
  • the angle of the line, the first image information satisfying the first preset condition includes: the brightness of the target area is within the second preset brightness range; the definition of the target area is greater than or equal to the second preset definition; the line angle of the target area is within the preset within the set angle range.
  • the imaging consistency of the system not only can the imaging consistency of the system be more effectively detected, but also the consistency of the line area can be detected based on the Information on brightness, sharpness, and line angle determines abnormalities in components such as light sources, light path adjustment equipment, and image acquisition equipment in the system.
  • the determination module is used to: process the image based on the segmentation and positioning method to obtain the area of interest; perform semantic segmentation on the area of interest to obtain the target area.
  • the image is processed by the segmentation and positioning method to obtain the area of interest, and by performing semantic segmentation on the area of interest, the target object can be identified more effectively and segmented more accurately based on the information of the target object, and the target object can be accurately determined.
  • the target area makes the target area almost only include the target object, so that the consistency of the system can be detected more effectively.
  • the first image information includes the brightness, sharpness, and position of the target area and the brightness, sharpness, and line angle of the line area in the target area
  • the line area is the The line area is composed of the lines of the target object.
  • the line angle is the angle of the line of the target object.
  • the first image information satisfies the first preset condition including: the brightness of the target area is within the first preset brightness range; the clarity of the target area Greater than or equal to the first preset definition; the position of the target area is within the preset position range; the brightness of the line area in the target area is within the second preset brightness range; the clarity of the line area in the target area is greater than or equal to the second Default sharpness; the line angle of the line area in the target area is within the preset angle range.
  • the imaging consistency of the system can be effectively detected, but also the imaging consistency of the system can be effectively detected.
  • Abnormalities in components such as the light source, light path adjustment device, and image acquisition device in the system are determined based on the information on the brightness, sharpness, and position of the area of interest and the brightness, sharpness, and line angle of the line area.
  • the acquisition module is also used to acquire the second image information of the image collected by the system; the detection module is used to detect the consistency of the imaging of the system based on the second image information and the first image information.
  • the imaging consistency of the system can be more comprehensively and effectively detected based on the image information collected by the system and the target object information, thereby improving the Product testing accuracy.
  • the detection module is configured to: if the second image information satisfies the second preset condition and the first image information satisfies the first preset condition, determine that the imaging of the system is consistent, or; if the second If the image information does not satisfy the second preset condition or the first image information does not satisfy the first preset condition, it is determined that the imaging of the system does not have consistency.
  • the imaging consistency of the system by judging whether the first image information satisfies the first preset condition and whether the second image information satisfies the second preset condition, not only can the imaging consistency of the system be more comprehensively and effectively detected, but also the imaging consistency of the system can be detected based on different conditions.
  • Information that satisfies the first preset condition and the second preset condition determines the cause of inconsistent imaging of the detection system.
  • the second image information includes the brightness, clarity and similarity of the image
  • the second image information satisfying the second preset condition includes: the brightness of the image is within the third preset brightness range; the clarity of the image The degree is greater than or equal to the third preset definition; the similarity of the image is within the preset similarity range.
  • the imaging consistency of the system can be more comprehensively and effectively detected, but also the imaging consistency of the system can be detected based on the brightness, clarity and similarity of the image.
  • the degree of information determines the abnormality of the light source, light path adjustment equipment, image acquisition equipment and other components in the system.
  • a device for detecting the imaging consistency of a 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 above-mentioned first aspect or the first aspect.
  • a method for detecting imaging consistency of a system in any possible embodiment.
  • 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 detection system in the above-mentioned first aspect or any possible implementation of the first aspect. Methods for imaging consistency.
  • a fifth aspect provides a computer program product containing instructions, which when executed by a computer causes the computer to perform the components of the detection system in the above-mentioned first aspect or any possible implementation of the first aspect.
  • a computer program product containing instructions, which when executed by a computer causes the computer to perform the components of the detection system in the above-mentioned first aspect or any possible implementation of the first aspect.
  • Figure 1 is a schematic diagram of the system framework provided by the embodiment of the present application.
  • Figure 2 is a flow chart of a method for detecting imaging consistency of a system provided by an embodiment of the present application
  • Figure 3 is a flow chart of a method for detecting imaging consistency in a tab-based application scenario provided by an embodiment of the present application
  • Figure 4 is an original image of the pole provided by the embodiment of the present application.
  • Figure 5 is an interest area diagram of the original image of the pole provided by the embodiment of the present application.
  • Figure 6 is the line area in the area of interest diagram of the original image of the pole provided by the embodiment of the present application.
  • Figure 7 is a schematic structural block diagram of an imaging consistency device of a detection system provided according to an embodiment of the present application.
  • Figure 8 is a schematic diagram of the hardware structure of an imaging consistency device of a detection system according to an embodiment of the present application.
  • Embodiments of the present application may be applied to image processing systems, including but not limited to products based on infrared imaging.
  • the imaging consistency system of the detection system can be applied to various electronic devices with the imaging consistency device of the detection system.
  • the electronic devices can be personal computers, computer workstations, smartphones, tablets, smart cameras, media consumption devices, Wearable devices, set-top boxes, game consoles, augmented reality (AR) AR/virtual reality (VR) devices, vehicle-mounted terminals, etc.
  • AR augmented reality
  • VR virtual reality
  • the size of the sequence numbers of each process does not mean the order of execution.
  • the execution order of each process should be determined by its functions and internal logic, and should not be used in the embodiments of the present application.
  • the implementation process constitutes any limitation.
  • the multi-layer cross-section of the product is imaged in the system.
  • Multi-layer cross-sectional image due to the high reflectivity of the product, if the position of the light source or the position of the optical path adjustment device deviates, the product area (target area) in the multi-layer cross-sectional image will be partially overexposed, or the position will be offset. Shift (for example, degree of horizontal tilt) affects the imaging quality of the system, making the imaging of the system inconsistent, which has a great impact on the success and accuracy of the imaging consistency of the detection system.
  • Embodiments of the present application provide a method for detecting the imaging consistency of a system by acquiring first image information of a partial area (target area) including a target object (product to be detected) in an image, and detecting the system according to the first image information
  • the imaging consistency can avoid the problem of local overexposure near the target object that affects the detection results. It can effectively detect the imaging consistency of the system based on the information of the target object, improving the accuracy of product detection.
  • this embodiment of the present application provides a system architecture 100.
  • the light source 120 is used to provide an imaging light source.
  • the light path adjustment device 130 reflects the light beam emitted by the light source to the target object 160, the refracted light and scattered light of the target object 160 enter the image acquisition device 141 in the client device 140, and the image The acquisition device 141 acquires an image containing the target object 160 .
  • the execution device 110 may be a terminal, such as a computer, a mobile phone terminal, a tablet computer, a laptop, etc., or it may be a server or cloud.
  • the execution device 110 is configured with an input/output (I/O) interface 112 for data interaction with external devices.
  • the image acquisition device 141 can obtain the acquired data (including the image of the target object) transmitted to the execution device 110 through the I/O interface 112.
  • the client device 140 may be the same device as the above-mentioned execution device 110.
  • the client device 140 and the above-mentioned execution device 110 may both be terminal devices.
  • the client device 140 may be a different device from the above-mentioned execution device 110.
  • the client device 140 is a terminal device, and the execution device 110 is a cloud, server, or other device.
  • the client device 140 may use any communication mechanism/ The communication network of the communication standard interacts with the execution device 110.
  • the communication network may be a wide area network, a local area network, a point-to-point connection, or any combination thereof.
  • the computing module 111 of the execution device 110 is configured to perform the calculation according to the input data received by the I/O interface 112 (such as image containing the target object) for processing.
  • the execution device 110 can call the data, codes, etc. in the data storage system 150 for corresponding processing, or can also use the data, instructions, etc. obtained by the corresponding processing. stored in the data storage system 150.
  • the I/O interface 112 returns the processing results, such as the first image information and detection results obtained as described above, to the client device 140, thereby providing them to the user.
  • the user can manually enter the input data, and the manual input can be operated through the interface provided by the I/O interface 112 .
  • the client device 140 can automatically send input data to the I/O interface 112. If requiring the client device 140 to automatically send input data requires the user's authorization, the user can set corresponding permissions in the client device 140. The user can view the results output by the execution device 110 on the client device 140, and the specific presentation form may be display, sound, action, etc.
  • Figure 1 is only a schematic diagram of a system architecture provided by an embodiment of the present application.
  • the positional relationship between the devices, devices, modules, etc. shown in the figure does not constitute any limitation.
  • the data The storage system 150 is an external memory relative to the execution device 110. In other cases, the data storage system 150 can also be placed in the execution device 110.
  • the main process of the method for detecting the imaging consistency of the system according to the embodiment of the present application will be introduced below with reference to FIGS. 1 and 2 .
  • the method 200 for detecting imaging consistency of a system includes the following steps.
  • the target area is the partial area including the target object in the image collected by the system.
  • the system may be various systems for collecting images.
  • the image of the target object can be acquired through a charge coupled device (CCD) camera (such as the image acquisition device 141).
  • CCD charge coupled device
  • the target area in the image is considered, that is, the partial area in the image that includes the target object.
  • the target image can be determined in various possible ways. For example, the contour of the target object is extracted from the image, and the target area is determined based on the contour of the target object.
  • the first image information of the target area may be various image information of the target area.
  • the first image information can be determined based on the pixel value of the target area; the first image information can be determined based on the edge feature extraction map (grayscale image gradient) of the target image; the first image information can be determined based on the center coordinates of the target area, and based on the target
  • the angle of the straight line in the area determines the first image information.
  • the consistency of imaging of the system can be detected based on the relationship between the first image information and the first preset condition.
  • the imaging consistency of the system can be effectively detected based on the information of the target object. , improving the accuracy of product detection.
  • detecting the consistency of the system's imaging according to the first image information includes: if the first image information satisfies the first preset condition, determining that the system's imaging has consistency, or; if If the first image information does not meet the first preset condition, it is determined that the imaging of the system is not consistent.
  • the first image information may include multiple attributes, such as brightness of the target area, target area The clarity of the domain, the location of the target area, and the angle of the line in the target area. If the attributes in the first image information are all within the corresponding preset range, it is determined that the imaging of the system is consistent, or; if any attribute in the first image information is not within the corresponding preset range, it is determined that the system The imaging is inconsistent.
  • the first image information By determining whether the first image information satisfies the first preset condition, not only can it be determined whether the imaging of the system is consistent, but also when the imaging of the system is not consistent, it can also be analyzed which attribute in the first image information is not within the preset range. Within, the cause of the system's imaging inconsistencies can be determined.
  • the target area is an area of interest in the image
  • the first image information includes the brightness, clarity, and position of the target area
  • the first image information that satisfies the first preset condition includes: The brightness is within the first preset brightness range; the definition of the target area is greater than or equal to the first preset definition; and the position of the target area is within the preset position range.
  • the area of interest can be the area related to the target object obtained through various operators and functions in the image, or it can be outlined in the image collected by the system in the form of boxes, circles, ellipses, irregular polygons, etc. that need to be processed. Area.
  • the outline of the target object can be extracted from the image, a mask (Mask) area can be generated based on the outline of the detected product, binary connected component analysis and other processing methods, and the Region of Interest (ROI) can be determined based on the mask area.
  • a mask Mask
  • ROI Region of Interest
  • the brightness of the area of interest is the average pixel value of the area of interest (the sum of the pixel values of the area of interest is divided by the number of pixel values); the clarity of the area of interest is the grayscale image calculated based on the Laplacian operator
  • the variance of the gradient (the edge feature extraction map is obtained by convolving the Laplacian operator with the region of interest, and the variance of the pixel values of the edge feature extraction map is calculated); the position of the region of interest is the center coordinate value of the region of interest. Among them, the larger the average pixel value, the brighter the logo; the larger the variance, the higher the clarity.
  • the first preset brightness range can be determined in the following manner: counting the brightness of the area of interest of the standard image, and sorting from bright to dark according to the brightness of the area of interest of the standard image, and manually judging the acceptable
  • the range of brightness there is no overexposure of the area of interest, and there is no overdarkness of the area of interest
  • the brightness when the area of interest of the standard image is too dark in the lower order
  • the area of interest of the standard image is overexposed
  • the brightness at the time (in the first order) is used as the boundary of the first preset brightness range.
  • the first preset sharpness can be determined in the following way: counting the sharpness of the area of interest of the standard image, sorting from clear to blurry according to the sharpness of the area of interest of the standard image, and classifying the acceptable sharpness according to manual judgment.
  • the lower limit is used as the first default definition.
  • the preset position range can be determined in the following ways: counting the position of the standard image (the center coordinate value of the area of interest of the standard image), calculating the mean and variance of the position of the standard image (the mean value of the center coordinate value of the area of interest of the standard image) and variance), the mean value of the position of the standard image plus or minus three times the variance is used as the preset position range.
  • Preset definition whether the position of the area of interest is within the preset position range. If the brightness of the area of interest is within the first preset brightness range, the definition of the area of interest is greater than or equal to the first preset definition and the area of interest. If the position of the area is within the preset position range, it is determined that the first image information satisfies the first preset condition.
  • the brightness of the target area is not within the first preset brightness range, it can be determined that the light source 120 and/or the light path adjustment device 130 is abnormal; if the definition of the target area is less than the first preset definition , it can be determined that the light path adjustment device 130 and/or the image acquisition device 141 is abnormal; if the position of the target area is not within the preset position range, it can be determined that the light path adjustment device 130 and/or the image acquisition device 141 is abnormal. abnormal.
  • the imaging consistency of the system can be effectively detected, but also the imaging consistency of the system can be effectively detected based on the brightness, sharpness and position of the area of interest.
  • the information determines abnormalities in components such as light sources, light path adjustment equipment, and image acquisition equipment in the system.
  • determining the target area in the image collected by the system includes: processing the image based on a segmentation and positioning method to obtain the area of interest.
  • the region of interest can be obtained by first locating the target object in the image collected by the system and segmenting the target object.
  • the integral graph integrated graph algorithm
  • a small graph containing the target object is obtained, and then the small image containing the target object is obtained based on an efficient coarse segmentation algorithm (for example, a fully convolutional neural network (FCN)).
  • FCN fully convolutional neural network
  • the target object By processing the image through the segmentation and positioning method, the target object can be effectively identified and the area segmented according to the target object's information to obtain an accurate target area and make the target object in the target area account for a higher proportion of the image, thus making it more accurate to detect the consistency of the system.
  • the target area is a line area composed of lines of the target object in the area of interest of the image
  • the first image information includes the brightness, sharpness and line angle of the target area
  • the line angle is the target
  • the angle of the line of the object, the first image information satisfying the first preset condition includes: the brightness of the target area is within the second preset brightness range; the definition of the target area is greater than or equal to the second preset definition; the line angle of the target area within the preset angle range.
  • the lines of the target object in the area of interest of the image can be identified based on the straight line detection algorithm (for example, Hough lines), and the line area composed of the lines of the target object is used as the line area (target area).
  • the brightness and sharpness of the line area can be obtained in a manner similar to the brightness and sharpness of the area of interest, which will not be described again here.
  • the line angle of the line area can be determined in the following way: obtain the horizontal angle or vertical angle of each target object's line, determine the average rotation angle of the target object's line based on the horizontal angle or vertical angle of each target object's line, and The average rotation angle is used as the line angle of the line area.
  • the acquisition method of the second preset brightness range may be similar to the acquisition method of the first preset brightness range, and the acquisition method of the second preset definition may be similar to the acquisition method of the first preset definition, which will not be described again here.
  • the preset angle range can be determined by counting the line angles of the line areas of the standard image, and determining the preset angle range (for example, 5°-10°) based on manual judgment of the acceptable inclination of the target object.
  • the brightness of the target area is not within the second preset brightness range, it can be determined that the light source 120 and/or the light path adjustment device 130 is abnormal; if the definition of the target area is less than the second preset definition , then it can be determined that the light path adjustment device 130 and/or the image acquisition device 141 is abnormal; if the line angle of the target area is not within the preset angle range, it can be determined that the light path adjustment device 130 and/or the image acquisition device 141 Abnormal.
  • the imaging consistency of the system can be effectively detected, but also the imaging consistency of the system can be effectively detected based on the brightness, sharpness and position of the area of interest.
  • the information on the brightness, sharpness and line angle of the line area determines abnormalities in components such as the light source, light path adjustment equipment and image acquisition equipment in the system.
  • determining the target area in the image collected by the system includes: processing the image based on a segmentation and positioning method to obtain the area of interest; performing semantic segmentation on the area of interest to obtain the target area.
  • the integral graph (integral graph algorithm) is used to locate the target object, and a small graph containing the target object is obtained, and then based on an efficient coarse segmentation algorithm, such as a fully convolutional neural network (FCN), the small image containing the target object is obtained.
  • FCN fully convolutional neural network
  • FCN fully convolutional neural network
  • FCN fully convolutional neural network
  • functions in OpenCV can be called to identify lines of target objects in the area of interest of the image.
  • the first parameter mask (mask image);
  • the second parameter the distance accuracy of the line segment in pixels 1;
  • the third parameter the angle accuracy of the line segment in radians np.pi/180;
  • the fourth parameter the minimum length of the line segment in pixels is 2000. Line segments will be detected only if it exceeds 2000. The larger the value, basically means the longer the detected line segments and the fewer the number of detected line segments;
  • the fifth parameter minLineLength the minimum length of the line segment in pixels is 2000;
  • the sixth parameter maxLineGap the maximum allowable gap (break) between two line segments in the same direction is judged to be one line segment. If it exceeds the set value 800, the two line segments will be regarded as one line segment. The larger the value, the greater the break allowed on the line segment. The larger the value, the more likely it is to detect potential straight line segments.
  • edges are the lines of the target object, and the line area composed of the lines of the target object is the target area.
  • the image is processed by the segmentation and positioning method to obtain the area of interest, and by semantic segmentation of the interest, the target object can be identified more effectively and segmented more accurately based on the information of the target object, and the target area can be accurately determined, and the target area can be accurately determined.
  • the target area almost only includes the target object, so that the consistency of the system can be effectively detected.
  • the first image information includes the brightness, sharpness and position of the target area and the brightness, sharpness and line angle of the line area in the target area, the line area being the target object in the target area.
  • the line area composed of lines, the line angle is the angle of the line of the target object
  • the first image information satisfies the first preset condition including: the brightness of the target area is within the first preset brightness range; the clarity of the target area is greater than or equal to the first A preset clarity; the position of the target area is within the preset position range; the brightness of the line area in the target area is within the second preset brightness range; the clarity of the line area in the target area is greater than or equal to the second preset clarity degree; the line angle of the line area in the target area is within the preset angle range.
  • the brightness, clarity, and position of the target area can be obtained, and it can be determined whether the brightness, clarity, and position of the target area meet the first preset condition. If so, the brightness, clarity, and position of the line area in the target area can be obtained. degree and line angle, and then determine whether the brightness, sharpness and line angle of the line area in the target area meet the first preset condition. If so, it is determined that the first image information satisfies the first preset condition. You can also obtain the brightness, clarity, and position of the target area, as well as the brightness, clarity, and line angle of the line area in the target area, and then determine whether the above attributes all meet the first precondition, and if so, determine that the first image information satisfies The first preset condition.
  • the imaging consistency of the system By judging whether the brightness, sharpness and position of the area of interest and the brightness, sharpness and line angle of the line area meet the first preset condition, not only can the imaging consistency of the system be effectively detected, but also the imaging consistency of the system can be effectively detected based on the area of interest.
  • the brightness, sharpness and position of the line area as well as the brightness, sharpness and line angle information determine the abnormality of the light source, light path adjustment equipment, image acquisition equipment and other components in the system.
  • the method for detecting the consistency of the imaging of the system further includes: obtaining second image information of the image; detecting the consistency of the imaging of the system includes: detecting the system according to the second image information and the first image information. imaging consistency.
  • the second image information of the image collected by the system can be various image information of the image collected by the system.
  • the second image information can be obtained according to the pixel value of the image collected by the system; the edge feature extraction map (gray) of the image collected by the system can be obtained. degree image gradient) to obtain the second image information; obtain the first image information according to the histogram of the image collected by the system and the histogram of the standard image.
  • the consistency of imaging of the system can be detected based on the relationship between the second image information and the second preset condition and the relationship between the first image information and the first preset condition.
  • detecting the consistency of imaging of the system based on the second image information and the first image information includes: if the second image information satisfies the second preset condition and the first image information satisfies the first If the preset condition is met, it is determined that the imaging of the system is consistent, or if the second image information does not meet the second preset condition or the first image information does not meet the first preset condition, it is determined that the imaging of the system is not consistent.
  • the reason for the inconsistent imaging of the detection system can also be determined based on the information that does not satisfy the first preset condition and the second preset condition.
  • the second image information includes detecting the brightness, clarity and similarity of the image, and the second image information satisfying the second preset condition includes: the brightness of the image is within the third preset brightness range; The definition is greater than or equal to the third preset definition; the similarity of the image is within the preset similarity range.
  • the brightness of the image can be obtained in a manner similar to the acquisition method of determining the brightness of the area of interest (target area), and the sharpness can be obtained in a manner similar to the acquisition method of determining the sharpness of the area of interest, which will not be discussed here.
  • the similarity of the image can be determined in the following way: calculate the histogram of the image, and calculate the similarity between the histogram of the image and the histogram of the standard image (for example, correlation comparison, chi-square comparison, cross sex or Bartholin distance). Among them, the higher the similarity, the closer the image is to the standard image.
  • the third preset brightness range may be obtained in a manner similar to the first/second preset brightness range, and the third preset definition may be obtained in a manner similar to the first/second preset definition. , which will not be described in detail here.
  • the similarity of images can be determined in the following way: artificially setting the threshold according to the actual situation.
  • the brightness, clarity, and similarity of the image can be obtained, and it is judged whether the brightness, clarity, and similarity of the image meet the second preset condition. If so, the brightness, clarity, and position of the target area are obtained, and Determine whether the brightness, sharpness and position of the target area meet the first preset condition. If so, obtain the brightness, sharpness and line angle of the line area in the target area, and then determine the brightness, sharpness of the line area in the target area. Whether the sum line angle satisfies the first preset condition, if so, it is determined that the second image information satisfies the second preset condition and the first image information satisfies the first preset condition.
  • the brightness, sharpness and similarity of the image, the brightness, sharpness and position of the target area, and the brightness, sharpness and line angle of the line area in the target area and then judge the brightness, sharpness and line angle of the image. Whether the similarity meets the second preset condition, and whether the brightness, clarity, and position of the target area, and the brightness, clarity, and line angle of the line area in the target area meet the first precondition, and if so, determine the second image The information satisfies the second preset condition and the first image information satisfies the first preset condition.
  • the target object is a pole
  • the target area is a partial area in the image that includes the pole
  • the target area is a line area in the image composed of pole lines of the pole.
  • the line area composed of the tab lines of the tabs may be an area composed of lines in the multi-layer cross-sectional image of the tabs of the wound lithium battery.
  • the system can be effectively detected for the information of the tab or the information of the tab line
  • the imaging consistency improves the accuracy of product detection.
  • a method 300 for detecting the imaging consistency of a system includes the following steps.
  • the multiple irregular lines are the multi-layer tabs of the battery core to be detected, and the other parts are the background parts. It can be observed that the multi-layer tabs of the battery core to be detected occupy a relatively small proportion in the picture, and it is also That is to say, there are more background parts.
  • the region of interest is part of the multi-layer cross-sectional image and includes a large amount of multi-layer tab information.
  • the multi-layer tabs account for a high proportion of the image.
  • the area composed of light-colored irregular lines is the line area in the area of interest of the multi-layer cross-sectional image.
  • first image information and second image information of the multi-layer cross-sectional image acquired above will be visualized in the image.
  • the equipment in the system can also be adjusted so that the system is always in the best state without being interfered by other factors, further improving the accuracy of the detection. Accuracy.
  • the embodiment of the present application by obtaining the first image information and the second image information of the image, and based on whether the first image information satisfies the first preset condition and the second image information satisfies the second preset condition , not only can the imaging consistency of the system be more comprehensively and effectively detected, but also the light source, light path adjustment equipment, image acquisition equipment and other components in the system can be determined based on the information that does not meet the first preset condition and the second preset condition. abnormal situation.
  • Figure 7 shows a schematic block diagram of a device 700 for detecting imaging consistency of a system according to an embodiment of the present application.
  • the device 700 can execute the above method for detecting the imaging consistency of the system in the embodiment of the present application.
  • the device 700 can be the aforementioned execution device 110 .
  • the device 700 includes: a determination module 710 , an acquisition module 720 and a detection module 730 .
  • the determination module 710 is used to determine the target area in the image collected by the system, and the target area is the partial area in the image that includes the target object; the acquisition module 720 is used to obtain the first image information of the target area; the detection module 730 is used to The method is to detect the consistency of imaging of the system based on the first image information.
  • the detection module 730 is used to: if the first image information meets the first preset condition, determine that the imaging of the system is consistent, or; if the first image information does not meet the first preset condition, It is determined that the imaging of the system is inconsistent.
  • the target area is an area of interest in the image
  • the first image information includes the brightness, sharpness and position of the target area
  • the first image information satisfying the first preset condition includes: the brightness of the target area is at Within the first preset brightness range; the definition of the target area is greater than or equal to the first preset definition; and the position of the target area is within the preset position range.
  • the determination module 710 is configured to: process the image based on a segmentation and positioning method to obtain the region of interest.
  • the target area is a line area composed of lines of the target object in the area of interest of the image
  • the first image information includes the brightness, sharpness, and line angle of the target area
  • the line angle is the line angle of the target object.
  • the angle of the line, the first image information satisfying the first preset condition includes: the brightness of the target area is within the second preset brightness range; the definition of the target area is greater than or equal to the second preset definition; the line angle of the target area is within the preset within the set angle range.
  • the determination module 710 is used to: process the image based on the segmentation and positioning method to obtain the area of interest; perform semantic segmentation on the area of interest to obtain the target area.
  • the first image information includes the brightness, sharpness and position of the target area and the brightness, sharpness and line angle of the line area in the target area, and the line area is the line formed by the target object in the target area.
  • the line angle is the angle of the line of the target object.
  • the first image information satisfies the first preset condition including: the brightness of the target area is within the first preset brightness range; the clarity of the target area is greater than or equal to the first preset condition.
  • the position of the target area is within the preset position range; the brightness of the line area in the target area is within the second preset brightness range; the clarity of the line area in the target area is greater than or equal to the second preset definition;
  • the line angle of the line area in the target area is within the preset angle range.
  • the acquisition module 720 is also used to acquire the second image information of the image;
  • the detection module 730 is used to detect the consistency of imaging of the system based on the second image information and the first image information.
  • the detection module 730 is configured to: if the second image information satisfies the second preset condition and the first image information satisfies the first preset condition, determine that the imaging of the system is consistent, or; if the If the second image information does not meet the second preset condition or the first image information does not meet the first preset condition, it is determined that the imaging of the system is not consistent.
  • the second image information includes detecting the brightness, clarity and similarity of the image, and the second image information satisfying the second preset condition includes: the brightness of the image is within the third preset brightness range; The definition is greater than or equal to the third preset definition; the similarity of the image is within the preset similarity range.
  • FIG. 8 is a schematic diagram of the hardware structure of a device for detecting imaging consistency of a system according to an embodiment of the present application.
  • the device 800 for detecting the imaging consistency of the system shown in FIG. 8 includes a memory 801, a processor 802, a communication interface 803 and a bus 804.
  • the memory 801, the processor 802, and the communication interface 803 implement communication connections between each other through the bus 804.
  • the memory 801 may be a read-only memory (ROM), a static storage device, and a random access memory (RAM).
  • the memory 801 can store a program. When the program stored in the memory 801 is executed by the processor 802, the processor 802 and the communication interface 803 are used to perform various steps of the method for detecting the imaging consistency of the system according to the embodiment of the present application.
  • the processor 802 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 imaging consistency of the system according to the embodiment of the present application, or to execute the method for detecting the imaging consistency of the system according to the embodiment of the present application.
  • the processor 802 may also be an integrated circuit chip with signal processing capabilities. During the implementation process, each step of the method for detecting the imaging consistency of the 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 802 .
  • the above-mentioned processor 802 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, or 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 801.
  • the processor 802 reads the information in the memory 801, and combines its hardware to complete the functions required to be performed by the units included in the device for detecting the imaging consistency of the system in the embodiment of the present application, or to perform the implementation of the present application.
  • the communication interface 803 uses a transceiver device such as but not limited to a transceiver to implement communication between the device 800 and other devices or communication networks. For example, the traffic data of the unknown device can be obtained through the communication interface 803.
  • a transceiver device such as but not limited to a transceiver to implement communication between the device 800 and other devices or communication networks.
  • the traffic data of the unknown device can be obtained through the communication interface 803.
  • Bus 804 may include a path that carries information between various components of device 800 (eg, memory 801, processor 802, communication interface 803).
  • the device 800 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 800 may also include hardware devices that implement other additional functions. In addition, those skilled in the art should understand that the device 800 may only include components necessary to implement the embodiments of the present application, and does not necessarily include all components shown in FIG. 8 .
  • Embodiments of the present application also provide a computer-readable storage medium that stores program code for device execution, and the program code includes instructions for executing steps in the above method for detecting imaging consistency of a 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 above method for detecting imaging consistency of the 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 disclosed devices and methods can be implemented in other ways.
  • the device embodiments described above are only illustrative.
  • the division of the units is only a logical function division. In actual implementation, there may be other division methods.
  • multiple units or components may be combined or can be integrated into another system, or some features can be ignored, or not implemented.
  • the coupling or direct coupling or communication connection between each other shown or discussed may be through some interfaces, and the indirect coupling or communication connection of the devices or units may be in electrical, mechanical or other forms.
  • the described embodiments may be implemented by software, hardware, or a combination of software and hardware.
  • the described embodiments may also be embodied by computer-readable media having computer-readable code stored thereon, the computer-readable code including instructions executable by at least one computing device.
  • the computer-readable medium can be associated with any data storage device capable of storing data readable by a computer system. Examples of computer-readable media may include read-only memory, random access memory, compact disc read-only memory (Compact Disc Read-Only Memory, CD-ROM), hard disk drive (Hard Disk Drive, HDD), digital Video discs (Digital Video Disc, DVD), magnetic tapes, optical data storage devices, etc.
  • the computer readable medium also Can be distributed among computer systems connected through a network, so that computer-readable code can be stored and executed in a distributed manner.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Image Analysis (AREA)

Abstract

本申请实施例公开了检测***的成像一致性的方法、装置和计算机存储介质，其中，方法包括：确定***采集的图像中的目标区域，目标区域为***采集的图像中包括目标对象的部分区域；获取目标区域的第一图像信息；根据第一图像信息，检测***的成像一致性。通过获取***采集的图像中的目标区域的第一图像信息，并根据第一图像信息确定***的成像的一致性，能够有效地检测***的成像一致性的情况，提高了产品检测的准确度。

Description

检测***的成像一致性的方法、装置和计算机存储介质
相关申请的交叉引用
本申请要求享有于2022年07月22日提交的名称为“检测***的成像一致性的方法、装置和计算机存储介质”的中国专利申请202210866453.7的优先权，该申请的全部内容通过引用并入本文中。
技术领域
本申请涉及图像处理领域，更为具体地，涉及一种检测***的成像一致性的方法、装置和计算机存储介质。
背景技术
随着图像处理技术的发展，越来越多的图像处理技术被应用到现代工业制造领域中，例如检测***的成像一致性领域。
为了能够准确地检测出产品缺陷，需要采集符合检测标准的检测图像。但是，由于工业生产环境复杂，可能影响***检测产品，例如，异物遮挡光源，光路调整设备移位等，从而导致***采集的待检测图像不符合检测标准，即检测***的成像不一致，影响了产品检测的准确性。
因此，如何有效地检测***的成像一致性的情况，是亟待解决的技术问题。
发明内容
本申请实施例提供了一种检测***的成像一致性的方法、装置和计算机存储介质，能够有效地检测***的成像一致性的情况，从而提高产品检测的准确度。
第一方面，提供了一种检测***的成像一致性的方法，包括：确定***采集的图像中的目标区域，目标区域为图像中包括目标对象的部分区域；获取目标区域的第一图像信息；根据第一图像信息，检测***的成像一致性。
在本申请实施例的技术方案中，通过获取图像中的目标区域的第一图像信息，并根据第一图像信息确定***的成像的一致性，能够针对目标对象的信息有效地检测***的成像一致性的情况，提高了产品检测的准确度。
在一些可能的实施方式中，根据第一图像信息，检测***的成像的一致性，包括：若第一图像信息满足第一预设条件，则确定***的成像具有一致性，或；若第 一图像信息不满足第一预设条件，则确定***的成像不具有一致性。
上述实施方式，通过判断第一图像信息是否满足第一预设条件，不仅可以确定***的成像是否具有一致性，还能确定不满足第一预设条件的信息，从而确定造成***的成像不一致的原因。
在一些可能的实施方式中，目标区域为图像中的感兴趣区域，第一图像信息包括目标区域的亮度、清晰度和位置，第一图像信息满足第一预设条件包括：目标区域的亮度处于第一预设亮度范围内；目标区域的清晰度大于等于第一预设清晰度；目标区域的位置处于预设位置范围内。
上述实施方式，通过判断感兴趣区域的亮度、清晰度和位置是否满足第一预设条件，不仅可以有效地检测***的成像一致性的情况，还可以根据感兴趣区域的亮度、清晰度和位置的信息确定***中的光源、光路调整设备和图像获取设备等部件的异常情况。
在一些可能的实施方式中，确定***采集的图像中的目标区域包括：基于分割定位方法对图像进行处理，获得感兴趣区域。
上述实施方式，通过分割定位方法对图像进行处理，可以有效地识别目标对象并根据目标对象的信息进行区域分割，能够准确地确定目标区域，并使得目标区域中目标对象在图像中的占比较高，从而可以更加有效地检测***的一致性的情况。
在一些可能的实施方式中，目标区域为图像的感兴趣区域中的由目标对象的线条组成的线条区域，第一图像信息包括目标区域的亮度、清晰度和线角度，线角度是目标对象的线条的角度，第一图像信息满足第一预设条件包括：目标区域的亮度处于第二预设亮度范围内；目标区域的清晰度大于等于第二预设清晰度；目标区域的线角度处于预设角度范围内。
上述实施方式，通过判断目标对象的线条组成的线条区域的亮度、清晰度和线角度是否满足第一预设条件，不仅可以更加有效地检测***的成像一致性的情况，还可以根据线条区域的亮度、清晰度和线角度的信息确定***中的光源、光路调整设备和图像获取设备等部件的异常情况。
在一些可能的实施方式中，确定***采集的图像中的目标区域包括：基于分割定位方法对图像进行处理，获得感兴趣区域；对感兴趣区域进行语义分割，获取目标区域。
上述实施方式，通过分割定位方法对图像进行处理，获得感兴趣区域，并通过对感兴趣区域进行语义分割，可以更加有效地识别目标对象并根据目标对象的信息进行更准确地分割，能够准确地确定目标区域，并使得目标区域几乎仅仅包括目标对象，从而可以更加有效地检测***的一致性的情况。
在一些可能的实施方式中，第一图像信息包括目标区域的亮度、清晰度和位置以及目标区域中的线条区域的亮度、清晰度和线角度，线条区域为目标区域中的由目标对象的线条组成的线条区域，线角度是目标对象的线条的角度，第一图像信息满足第一预设条件包括：目标区域的亮度处于第一预设亮度范围内；目标区域的清晰度大于等于第一预设清晰度；目标区域的位置处于预设位置范围内；目标区域中的线 条区域的亮度处于第二预设亮度范围内；目标区域中的线条区域的清晰度大于等于第二预设清晰度；目标区域中的线条区域的线角度处于预设角度范围内。
上述实施方式，通过判断感兴趣区域的亮度、清晰度和位置以及线条区域的亮度、清晰度和线角度是否满足第一预设条件不仅可以准确且快速地检测***的成像一致性的情况，还可以根据感兴趣区域的亮度、清晰度和位置以及线条区域的亮度、清晰度和线角度的信息确定***中的光源、光路调整设备和图像获取设备等部件的异常情况。
在一些可能的实施方式中，检测***的成像的一致性的方法还包括：获取***采集的图像的第二图像信息；检测***的成像的一致性包括：根据第二图像信息和第一图像信息，检测***的成像的一致性。
上述实施方式，通过根据第一图像信息和第二图像信息确定***的成像的一致性，可以针对***采集的图像信息和目标对象信息更加全面、有效地检测***的成像一致性的情况，提高了产品检测的准确度。
在一些可能的实施方式中，根据第二图像信息和第一图像信息，检测***的成像的一致性，包括：若第二图像信息满足第二预设条件且第一图像信息满足第一预设条件，则确定***的成像具有一致性，或；若第二图像信息不满足第二预设条件或第一图像信息不满足第一预设条件，则确定***的成像不具有一致性。
上述实施方式，通过判断第一图像信息是否满足第一预设条件和第二图像信息是否满足第二预设条件确定***的成像的一致性情况，不仅可以更加全面、有效地检测***的成像一致性的情况，还能根据不满足第一预设条件和第二预设条件的信息确定造成检测***的成像不一致的原因。
在一些可能的实施方式中，第二图像信息包括检测图像的亮度、清晰度和相似度，第二图像信息满足第二预设条件包括：图像的亮度处于第三预设亮度范围内；图像的清晰度大于等于第三预设清晰度；图像的相似度处于预设相似度范围内。
上述实施方式，通过判断图像的亮度、清晰度和相似度是否满足第二预设条件，不仅可以更加全面、有效地检测***的成像一致性的情况，还可以根据图像的亮度、清晰度和相似度的信息确定***中的光源、光路调整设备和图像获取设备等部件的异常情况。
在一些可能的实施方式中，目标对象为极耳，目标区域为图像中包括极耳的部分区域，或者，目标区域为图像中由极耳的极耳线组成的线条区域。
上述实施例中，通过将目标区域设置为图像中包括极耳的部分区域，或者，通过将目标区域设置为图像中由极耳的极耳线组成的线条区域，能够针对极耳的信息或者极耳线的信息有效地检测***的成像一致性的情况，提高了产品检测的准确度。
第二方面，提供了一种检测***的成像一致性的装置，包括确定模块、获取模块和检测模块，其中，确定模块，用于确定***采集的图像中的目标区域，目标区域为图像中包括目标对象的部分区域；获取模块，用于获取目标区域的第一图像信息；检测模块，用于根据第一图像信息，检测***的成像的一致性。
在本申请实施例的技术方案中，通过获取图像中的目标区域的第一图像信 息，并根据第一图像信息确定***的成像的一致性，能够针对目标对象的信息有效地检测***的成像一致性的情况，提高了产品检测的准确度。
在一些可能的实施方式中，检测模块用于：若第一图像信息满足第一预设条件，则确定***的成像具有一致性，或；若第一图像信息不满足第一预设条件，则确定***的成像不具有一致性。
上述实施方式，通过判断第一图像信息是否满足第一预设条件，不仅可以确定***的成像是否具有一致性，还能确定不满足第一预设条件的信息，从而确定造成***的成像不一致的原因。
在一些可能的实施方式中，目标区域为图像中的感兴趣区域，第一图像信息包括目标区域的亮度、清晰度和位置，第一图像信息满足第一预设条件包括：目标区域的亮度处于第一预设亮度范围内；目标区域的清晰度大于等于第一预设清晰度；目标区域的位置处于预设位置范围内。
上述实施方式，通过判断感兴趣区域的亮度、清晰度和位置是否满足第一预设条件，不仅可以有效地检测***的成像一致性的情况，还可以根据感兴趣区域的亮度、清晰度和位置的信息确定***中的光源、光路调整设备和图像获取设备等部件的异常情况。
在一些可能的实施方式中，确定模块用于：基于分割定位方法对图像进行处理，获得感兴趣区域。
上述实施方式，通过分割定位方法对图像进行处理，可以有效地识别目标对象并根据目标对象的信息进行区域分割，能够准确地确定目标区域，并使得目标区域中目标对象在图像中的占比较高，从而可以更加有效地检测***的一致性的情况。
在一些可能的实施方式中，目标区域为图像的感兴趣区域中的由目标对象的线条组成的线条区域，第一图像信息包括目标区域的亮度、清晰度和线角度，线角度是目标对象的线条的角度，第一图像信息满足第一预设条件包括：目标区域的亮度处于第二预设亮度范围内；目标区域的清晰度大于等于第二预设清晰度；目标区域的线角度处于预设角度范围内。
上述实施方式，通过判断目标对象的线条组成的线条区域的亮度、清晰度和线角度是否满足第一预设条件，不仅可以更加有效地检测***的成像一致性的情况，还可以根据线条区域的亮度、清晰度和线角度的信息确定***中的光源、光路调整设备和图像获取设备等部件的异常情况。
在一些可能的实施方式中，确定模块用于：基于分割定位方法对图像进行处理，获得感兴趣区域；对感兴趣区域进行语义分割，获取目标区域。
上述实施方式，通过分割定位方法对图像进行处理获得感兴趣区域，并通过对感兴趣区域进行语义分割，可以更加有效地识别目标对象并根据目标对象的信息进行更准确地分割，能够准确地确定目标区域，并使得目标区域几乎仅仅包括目标对象，从而可以更加有效地检测***的一致性的情况。
在一些可能的实施方式中，第一图像信息包括目标区域的亮度、清晰度和位置以及目标区域中的线条区域的亮度、清晰度和线角度，线条区域为目标区域中的 由目标对象的线条组成的线条区域，线角度是目标对象的线条的角度，第一图像信息满足第一预设条件包括：目标区域的亮度处于第一预设亮度范围内；目标区域的清晰度大于等于第一预设清晰度；目标区域的位置处于预设位置范围内；目标区域中的线条区域的亮度处于第二预设亮度范围内；目标区域中的线条区域的清晰度大于等于第二预设清晰度；目标区域中的线条区域的线角度处于预设角度范围内。
上述实施方式，通过判断感兴趣区域的亮度、清晰度和位置以及线条区域的亮度、清晰度和线角度是否满足第一预设条件，不仅可以有效地检测***的成像一致性的情况，还可以根据感兴趣区域的亮度、清晰度和位置以及线条区域的亮度、清晰度和线角度的信息确定***中的光源、光路调整设备和图像获取设备等部件的异常情况。
在一些可能的实施方式中，获取模块还用于获取***采集的图像的第二图像信息；检测模块用于根据第二图像信息和第一图像信息，检测***的成像的一致性。
上述实施方式，通过根据第一图像信息和第二图像信息确定***的成像的一致性，可以针对***采集的图像信息和目标对象信息更加全面、有效地检测***的成像一致性的情况，提高了产品检测的准确度。
在一些可能的实施方式中，检测模块用于：若第二图像信息满足第二预设条件且第一图像信息满足第一预设条件，则确定***的成像具有一致性，或；若第二图像信息不满足第二预设条件或第一图像信息不满足第一预设条件，则确定***的成像不具有一致性。
上述实施方式，通过判断第一图像信息是否满足第一预设条件和第二图像信息是否满足第二预设条件，不仅可以更加全面、有效地检测***的成像一致性的情况，还能根据不满足第一预设条件和第二预设条件的信息确定造成检测***的成像不一致的原因。
在一些可能的实施方式中，第二图像信息包括图像的亮度、清晰度和相似度，第二图像信息满足第二预设条件包括：图像的亮度处于第三预设亮度范围内；图像的清晰度大于等于第三预设清晰度；图像的相似度处于预设相似度范围内。
上述实施方式，通过判断图像的亮度、清晰度和相似度是否满足第二预设条件，不仅可以更加全面、有效地检测***的成像一致性的情况，还可以根据图像的亮度、清晰度和相似度的信息确定***中的光源、光路调整设备和图像获取设备等部件的异常情况。
第三方面，提供了一种检测***的成像一致性的装置，包括处理器和存储器，存储器用于存储程序，处理器用于从存储器中调用并运行程序以执行上述第一方面或第一方面的任一可能的实施方式中的检测***的成像一致性的方法。
第四方面，提供了一种计算机可读存储介质，包括计算机程序，当计算机程序在计算机上运行时，使得计算机执行上述第一方面或第一方面的任一可能的实施方式中的检测***的成像一致性的方法。
第五方面，提供了一种含指令的计算机程序产品，该指令被计算机执行时使得该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检测***的成 像一致性的方法。
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是本申请实施例提供的***框架的示意图；
图2是本申请实施例提供的一种检测***的成像一致性的方法的流程图；
图3是本申请实施例提供的一种基于极耳的应用场景下的检测的成像一致性的方法的流程图；
图4是本申请实施例提供的极耳的原始图像；
图5是本申请实施例提供的极耳的原始图像的感兴趣区域图；
图6是本申请实施例提供的极耳的原始图像的感兴趣区域图中的线条区域；
图7是根据本申请实施例提供的一种检测***的成像一致性装置的示意性结构框图；
图8根据本申请实施例提供的一种检测***的成像一致性装置的硬件结构示意图。
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。
本申请实施例可适用于图像处理***，包括但不限于基于红外成像的产品。该检测***的成像一致性***可以应用于具有检测***的成像一致性装置的各种电子设备，该电子设备可以为个人计算机、计算机工作站、智能手机、平板电脑、智能摄像头、媒体消费设备、可穿戴设备、机顶盒、游戏机、增强现实(augmented reality，AR)AR/虚拟现实(virtual reality，VR)设备，车载终端等，本申请公开的实施例对此不做限定。
应理解，本文中的具体的例子只是为了帮助本领域技术人员更好地理解本申请实施例，而非限制本申请实施例的范围。
还应理解，在本申请的各种实施例中，各过程的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本申请实施例的实施过程构成任何限定。
还应理解，本说明书中描述的各种实施方式，既可以单独实施，也可以组合实施，本申请实施例对此并不限定。
除非另有说明，本申请实施例所使用的所有技术和科学术语与本申请的技术领域的技术人员通常理解的含义相同。本申请中所使用的术语只是为了描述具体的实施例的目的，不是旨在限制本申请的范围。本申请所使用的术语“和/或”包括一个或多个相关的所列项的任意的和所有的组合。
目前，随着工业技术和图像处理技术的发展，越来越多的工厂通过采集产品的图像信息，并根据图像信息检测产品的缺陷。虽然，通过图像处理技术检测缺陷能够加快检测速度，但是，由于工业生产环境复杂以及产品的特殊性，可能会影响***的成像质量(例如，图片过曝、图片不清晰以及产品在图像中不居中等问题)，使得***的成像不一致，从而影响产品检测的准确性。
因此，在检测***的成像一致性时，当产品具有高反光、多层且形态很薄的特性(例如，卷绕式锂电池的极耳)时，在***对该产品的多层截面进行成像(多层截面图像)时，由于产品的高反光性，若光源的位置或者光路调整设备的位置出现偏差，使得多层截面图像中的产品区域(目标区域)出现局部过曝，或者，位置偏移(例如，水平倾斜程度)等情况，影响了***的成像质量，使得***的成像不一致，从而对检测***的成像一致性的成功性和准确性产生了很大影响。
基于上述考虑，为了准确且快速地检测***的成像是否具有一致性，即准确且快速地检测***的成像质量是否均衡，且都符合检测标准。本申请实施例提供了一种检测***的成像一致性的方法，通过获取图像中包括目标对象(待检测产品)的部分区域(目标区域)的第一图像信息，并根据第一图像信息检测***的成像一致性，能够避免因目标对象附近局部过曝，影响检测结果的问题，可以针对目标对象的信息有效地检测***的成像一致性的情况，提高了产品检测的准确度。
为了更好地理解本申请实施例的方案，下面先结合图1对本申请实施例可能的应用场景进行简单的介绍。
如图1所示，本申请实施例提供了一种***架构100。在图1中，光源120用于提供成像光源，光路调整设备130将光源发出的光束反射至目标对象160后，目标对象160的折射光和散射光进入客户设备140中的图像获取设备141，图像获取设备141获取到包含目标对象160的图像。
执行设备110可以是终端，如计算机，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。在图1中，执行设备110配置输入/输出(input/output，I/O)接口112，用于与外部设备进行数据交互，图像获取设备141可以将获取到的数据(包含目标对象的图像)通过I/O接口112传输至执行设备110。
在一些实施方式中，该客户设备140可以与上述执行设备110为同一设备，例如，客户设备140可以与上述执行设备110均为终端设备。
在另一些实施方式中，该客户设备140可以与上述执行设备110为不同设备，例如，客户设备140为终端设备，而执行设备110为云端、服务器等设备，客户设备140可以通过任何通信机制/通信标准的通信网络与执行设备110进行交互，通信网络可以是广域网、局域网、点对点连接等方式，或它们的任意组合。
执行设备110的计算模块111用于根据I/O接口112接收到的输入数据(如 包含目标对象的图像)进行处理。在执行设备110的计算模块111执行计算等相关的处理过程中，执行设备110可以调用数据存储***150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***150中。
最后，I/O接口112将处理结果，如上述得到的第一图像信息和检测结果返回给客户设备140，从而提供给用户。
在图1中所示情况下，用户可以手动给定输入数据，该手动给定可以通过I/O接口112提供的界面进行操作。另一种情况下，客户设备140可以自动地向I/O接口112发送输入数据，如果要求客户设备140自动发送输入数据需要获得用户的授权，则用户可以在客户设备140中设置相应权限。用户可以在客户设备140查看执行设备110输出的结果，具体的呈现形式可以是显示、声音、动作等具体方式。
值得注意的是，图1仅是本申请实施例提供的一种***架构的示意图，图中所示设备、器件、模块等之间的位置关系不构成任何限制，例如，在图1中，数据存储***150相对执行设备110是外部存储器，在其它情况下，也可以将数据存储***150置于执行设备110中。
下面结合图1和图2对本申请实施例的检测***的成像一致性的方法的主要过程进行介绍。该检测***的成像一致性的方法200包括以下步骤。
210，确定***采集的图像中的目标区域，目标区域为***采集的图像中包括目标对象的部分区域。
具体地，***可以是各种采集图像的***。例如，可以通过电荷耦合元件(charge coupled device，CCD)相机(如图像获取设备141)获取目标对象的图像。
在本申请实施例中，为了检测***的成像一致性，考虑图像中的目标区域，即图像中包括目标对象的部分区域。可以通过各种可能的方式确定目标图像。例如，从图像中提取目标对象的轮廓，并根据目标对象的轮廓进行提取，确定目标区域。
220，获取目标区域的第一图像信息。
目标区域的第一图像信息可以是目标区域的各种图像信息。例如，可以根据目标区域的像素值确定第一图像信息；根据目标图像的边缘特征提取图(灰度图像梯度)确定第一图像信息；根据目标区域的中心坐标确定第一图像信息，以及根据目标区域中的直线的角度(水平角度、垂直角度)确定第一图像信息。
230，根据第一图像信息，检测***的成像的一致性。
具体地，可以根据第一图像信息与第一预设条件的关系，检测***的成像的一致性。
本申请的技术方案中，通过获取图像中的目标区域的第一图像信息，并根据第一图像信息确定***的成像的一致性，能够针对目标对象的信息有效地检测***的成像一致性的情况，提高了产品检测的准确度。
可选地，在一些实施例中，根据第一图像信息，检测***的成像的一致性，包括：若第一图像信息满足第一预设条件，则确定***的成像具有一致性，或；若第一图像信息不满足第一预设条件，则确定***的成像不具有一致性。
其中，第一图像信息可以包括多个属性，例如，目标区域的亮度、目标区 域的清晰度、目标区域的位置和目标区域中的直线的角度。若第一图像信息中的属性均处于相应的预设范围内，则确定***的成像具有一致性，或者；若第一图像信息中的任一属性不处于相应的预设范围内，则确定***的成像不具有一致性。
通过判断第一图像信息是否满足第一预设条件，不仅可以确定***的成像是否具有一致性，还能在***的成像不具有一致性时，分析第一图像信息中哪个属性不处于预设范围内，可以确定造成***的成像不一致的原因。
可选地，在一些实施例中，目标区域为图像中的感兴趣区域，第一图像信息包括目标区域的亮度、清晰度和位置，第一图像信息满足第一预设条件包括：目标区域的亮度处于第一预设亮度范围内；目标区域的清晰度大于等于第一预设清晰度；目标区域的位置处于预设位置范围内。
感兴趣区域可以是图像中通过各种算子和函数求得的与目标对象相关的区域，也可以是在***采集的图像中以方框、圆、椭圆、不规则多边形等方式勾勒出需要处理的区域。
例如，可以从图像中提取目标对象的轮廓，根据检测产品的轮廓、二值化联通组件分析等处理方法生成掩码(Mask)区域，根据掩码区域确定感兴趣区域(Region Of Interest，ROI)。感兴趣区域的亮度为感兴趣区域的平均像素值(感兴趣区域的像素值求和再除以像素值的个数)；感兴趣区域的清晰度为基于拉普拉斯算子计算灰度图像梯度的方差(拉普拉斯算子与感兴趣区域做卷积后得到边缘特征提取图，计算边缘特征提取图的像素值的方差)；感兴趣区域的位置为感兴趣区域的中心坐标值。其中，平均像素值越大，标识越亮；方差越大，清晰度越高。
可选地，第一预设亮度范围可以采用如下方式确定：统计标准图像的感兴趣区域的亮度，并根据标准图像的感兴趣区域的亮度进行从亮到暗的排序，根据人工判断可接受的亮度的范围(不存在感兴趣区域的过曝，且不存在感兴趣区域的过暗)，将标准图像的感兴趣区域过暗时的亮度(次序靠后)和标准图像的感兴趣区域过曝时的亮度(次序靠前)作为第一预设亮度范围的边界。第一预设清晰度可以采用如下方式确定：统计标准图像的感兴趣区域的清晰度，并根据标准图像的感兴趣区域的清晰度进行从清晰到模糊的排序，根据人工判断将可接受的清晰度下限作为第一预设清晰度。预设位置范围可以采用如下方式确定：统计标准图像的位置(标准图像的感兴趣区域的中心坐标值)，计算标准图像的位置的均值和方差(标准图像的感兴趣区域的中心坐标值的均值和方差)，将标准图像的位置的均值加减三倍的方差作为预设位置范围。
在实际应用中，可以先获取感兴趣区域的亮度，并判断感兴趣区域的亮度是否处于第一预设亮度范围内；若是，获取感兴趣区域的清晰度，并判断感兴趣区域的清晰度是否大于等于第一预设清晰度，若感兴趣区域的清晰度大于等于第一预设清晰度，获取感兴趣区域的位置，并判断感兴趣区域的位置是否处于预设位置范围内，若是，则确定第一图像信息满足第一预设条件。
此外，也可以获取感兴趣区域的亮度、清晰度和位置后，再分别判断感兴趣区域的亮度是否处于第一预设亮度范围内，感兴趣区域的清晰度是否大于等于第一 预设清晰度，感兴趣区域的位置是否处于预设位置范围内，若感兴趣区域的亮度处于第一预设亮度范围内，感兴趣区域的清晰度大于等于第一预设清晰度以及感兴趣区域的位置处于预设位置范围内，则确定第一图像信息满足第一预设条件。
需要说明的是，若目标区域的亮度不处于第一预设亮度范围内，则可以确定光源120，和/或，光路调整设备130出现异常；若目标区域的清晰度小于第一预设清晰度，则可以确定光路调整设备130，和/或，图像获取设备141出现异常；若目标区域的位置不处于预设位置范围内，则可以确定光路调整设备130，和/或，图像获取设备141出现异常。
由此，通过判断感兴趣区域的亮度、清晰度和位置是否满足第一预设条件，不仅可以有效地检测***的成像一致性的情况，还可以根据感兴趣区域的亮度、清晰度和位置的信息确定***中的光源、光路调整设备和图像获取设备等部件的异常情况。
可选地，在一些实施例中，确定***采集的图像中的目标区域包括：基于分割定位方法对图像进行处理，获得感兴趣区域。
在本申请实施例中，可以通过先定位到***采集的图像中的目标对象，在目标对象部分进行分割，获得感兴趣区域。例如，采用积分图(积分图算法)对目标对象进行定位，得到包含目标对象的小图，再基于高效粗分割算法(例如，全卷积神经网络(Fully Convolutional Network，FCN))对包含目标对象的小图进行粗分割，获得感兴趣区域。
通过分割定位方法对图像进行处理，可以有效地识别目标对象并根据目标对象的信息进行区域分割，获得准确的目标区域，并使得目标区域中目标对象在图像中的占比较高，从而可以更加准确地检测***的一致性的情况。
可选地，在一些实施例中，目标区域为图像的感兴趣区域中的由目标对象的线条组成的线条区域，第一图像信息包括目标区域的亮度、清晰度和线角度，线角度是目标对象的线条的角度，第一图像信息满足第一预设条件包括：目标区域的亮度处于第二预设亮度范围内；目标区域的清晰度大于等于第二预设清晰度；目标区域的线角度处于预设角度范围内。
在实际应用中，可以基于直线检测算法(例如，霍夫线)识别图像的感兴趣区域中目标对象的线条(通常为多条)，并将目标对象的线条组成的线条区域作为线条区域(目标区域)。线条区域的亮度和清晰度的获取方式可以与感兴趣区域的亮度和清晰度的获取方式类似，在此不再赘述。线条区域的线角度可以采用如下方式确定：获取每条目标对象的线条的水平角度或者垂直角度，根据每条目标对象的线条的水平角度或垂直角度，确定目标对象线条的平均旋转角度，并将平均旋转角度作为线条区域的线角度。
第二预设亮度范围的获取方式可以与第一预设亮度范围的获取方式类似，以及第二预设清晰度的获取方式可以与第一预设清晰度的获取方式类似，在此不再赘述。预设角度范围可以采用如下方式确定：统计标准图像的线条区域的线角度，根据人工判断可接受的目标对象的倾斜程度确定预设角度范围(例如，5°-10°)。
在实际应用中，可以先获取线条区域的亮度，并判断线条区域的亮度是否 处于第二预设亮度范围内；若是，获取线条区域的清晰度，并判断线条区域的清晰度是否大于等于第二预设清晰度，若线条区域的清晰度大于等于第二预设清晰度，获取线条区域的线角度，并判断线条区域的线角度是否处于预设角度范围内，若是，则确定第一图像信息满足第一预设条件。
此外，也可以获取线条区域的亮度、清晰度和线角度后，再分别判断线条区域的亮度是否处于第二预设亮度范围内，线条区域的线角度是否大于等于第二预设清晰度，线条区域的线角度是否处于预设线角度范围内，若线条区域的亮度处于第二预设亮度范围内，线条区域的清晰度大于等于第二预设清晰度以及线条区域的线角度处于预设线角度范围内，则确定第一图像信息满足第一预设条件。
需要说明的是，若目标区域的亮度不处于第二预设亮度范围内，则可以确定光源120，和/或，光路调整设备130出现异常；若目标区域的清晰度小于第二预设清晰度，则可以确定光路调整设备130，和/或，图像获取设备141出现异常；若目标区域的线角度不处于预设角度范围内，则可以确定光路调整设备130，和/或，图像获取设备141出现异常。
由此，通过判断线条区域的亮度、清晰度和线角度是否满足第一预设条件，不仅可以有效地检测***的成像一致性的情况，还可以根据感兴趣区域的亮度、清晰度和位置以及线条区域的亮度、清晰度和线角度的信息确定***中的光源、光路调整设备和图像获取设备等部件的异常情况。
可选地，确定***采集的图像中的目标区域包括：基于分割定位方法对图像进行处理，获得感兴趣区域；对感兴趣区域进行语义分割，获取目标区域。
举例说明，采用积分图(积分图算法)对目标对象进行定位，得到包含目标对象的小图，再基于高效粗分割算法，例如，全卷积神经网络(Fully Convolutional Network，FCN)对包含目标对象的小图进行粗分割，获得感兴趣区域；对感兴趣区域进行语义分割，例如，基于物体区域表示网络(Object Region Representations Networks，OCRnet)，获取分割后的掩码图像，根据掩码图像得到目标区域。
在实际应用中，可以调用OpenCV中的函数识别图像的感兴趣区域中目标对象的线条。
edges＝cv2.HoughLinesP(mask，1，np.pi/180，2000，minLineLength＝2000，maxLineGap＝800)
第一个参数：mask(掩码图像)；
第二个参数：线段以像素为单位的距离精度1；
第三个参数：线段以弧度为单位的角度精度np.pi/180；
第四个参数：线段以像素为单位的最小长度2000，超过2000才被检测出线段，值越大，基本上意味着检出的线段越长，检出的线段个数越少；
第五个参数minLineLength：线段以像素为单位的最小长度2000；
第六个参数maxLineGap：同一方向上两条线段判定为一条线段的最大允许间隔(断裂)，超过了设定值800，则把两条线段当成一条线段，值越大，允许线段上的断裂越大，越有可能检出潜在的直线段。
也就是说，“edges”为目标对象的线条，目标对象的线条组成的线条区域即为目标区域。
通过分割定位方法对图像进行处理获得感兴趣区域，并通过对感兴趣进行语义分割，可以更加有效地识别目标对象并根据目标对象的信息进行更准确地分割，能够准确地确定目标区域，并使得目标区域几乎仅仅包括目标对象，从而可以有效地检测***的一致性的情况。
可选地，在一些实施例中，第一图像信息包括目标区域的亮度、清晰度和位置以及目标区域中的线条区域的亮度、清晰度和线角度，线条区域为目标区域中的由目标对象的线条组成的线条区域，线角度是目标对象的线条的角度，第一图像信息满足第一预设条件包括：目标区域的亮度处于第一预设亮度范围内；目标区域的清晰度大于等于第一预设清晰度；目标区域的位置处于预设位置范围内；目标区域中的线条区域的亮度处于第二预设亮度范围内；目标区域中的线条区域的清晰度大于等于第二预设清晰度；目标区域中的线条区域的线角度处于预设角度范围内。
在实际应用中，可以获取目标区域的亮度、清晰度和位置，并判断目标区域的亮度、清晰度和位置是否满足第一预设条件，若是，则获取目标区域中的线条区域的亮度、清晰度和线角度，再判断目标区域中的线条区域的亮度、清晰度和线角度是否满足第一预设条件，若是，则确定第一图像信息满足第一预设条件。也可以获取目标区域的亮度、清晰度和位置，以及目标区域中的线条区域的亮度、清晰度和线角度后，再判断上述属性是否均满足第一预条件，若是则确定第一图像信息满足第一预设条件。
通过判断感兴趣区域的亮度、清晰度和位置以及线条区域的亮度、清晰度和线角度是否满足第一预设条件，不仅可以有效地检测***的成像一致性的情况，还可以根据感兴趣区域的亮度、清晰度和位置以及线条区域的亮度、清晰度和线角度的信息确定***中的光源、光路调整设备和图像获取设备等部件的异常情况。
在一些可能的实施例中，检测***的成像的一致性的方法还包括：获取图像的第二图像信息；检测***的成像的一致性包括：根据第二图像信息和第一图像信息，检测***的成像的一致性。
***采集的图像的第二图像信息可以是***采集的图像的各种图像信息，例如，可以根据***采集的图像的像素值获取第二图像信息；根据***采集的图像的边缘特征提取图(灰度图像梯度)获取第二图像信息；根据***采集的图像的直方图以及标准图像的直方图获取第一图像信息。可以根据第二图像信息与第二预设条件的关系以及第一图像信息与第一预设条件的关系，检测***的成像的一致性。
可选地，在一些实施例中，根据第二图像信息和第一图像信息，检测***的成像的一致性，包括：若第二图像信息满足第二预设条件且第一图像信息满足第一预设条件，则确定***的成像具有一致性，或；若第二图像信息不满足第二预设条件或第一图像信息不满足第一预设条件，则确定***的成像不具有一致性。
通过判断第一图像信息是否满足第一预设条件和第二图像信息是否满足第二预设条件确定***的成像的一致性情况，不仅可以更加全面、有效地检测***的成 像一致性的情况，还能根据不满足第一预设条件和第二预设条件的信息确定造成检测***的成像不一致的原因。
在一些可能的实施例中，第二图像信息包括检测图像的亮度、清晰度和相似度，第二图像信息满足第二预设条件包括：图像的亮度处于第三预设亮度范围内；图像的清晰度大于等于第三预设清晰度；图像的相似度处于预设相似度范围内。
可选地，图像的亮度的获取方式可以与确定感兴趣区域(目标区域)的亮度的获取方式类似，清晰度的获取方式可以与确定感兴趣区域的清晰度的获取方式类似，在此不再赘述。图像的相似度(correlation)可以采用如下方式确定：计算图像的直方图，并计算图像的直方图和标准图像的直方图的之间的相似度(例如，相关性比较、卡方比较、十字交叉性或者巴氏距离)。其中，相似度越高，表示图像和标准图像越接近。
第三预设亮度范围的获取方式可以与第一/第二预设亮度范围的获取方式类似，以及第三预设清晰度的获取方式可以与第一/第二预设清晰度的获取方式类似，在此不再赘述。图像的相似度可以采用如下方式确定：根据实际情况进行人为设定阈值。
在实际应用中，可以获取图像的亮度、清晰度和相似度，判断的图像的亮度、清晰度和相似度是否满足第二预设条件，若是，获取目标区域的亮度、清晰度和位置，并判断目标区域的亮度、清晰度和位置是否满足第一预设条件，若是，则获取目标区域中的线条区域的亮度、清晰度和线角度，再判断目标区域中的线条区域的亮度、清晰度和线角度是否满足第一预设条件，若是，则确定第二图像信息满足第二预设条件且第一图像信息满足第一预设条件。
此外，也可以获取图像的亮度、清晰度和相似度，目标区域的亮度、清晰度和位置，以及目标区域中的线条区域的亮度、清晰度和线角度，再判断图像的亮度、清晰度和相似度是否满足第二预设条件，和目标区域的亮度、清晰度和位置，以及目标区域中的线条区域的亮度、清晰度和线角度是否满足第一预条件，若满足则确定第二图像信息满足第二预设条件且第一图像信息满足第一预设条件。
通过判断图像的亮度、清晰度和相似度是否满足第二预设条件，不仅可以更加全面、有效地检测***的成像一致性的情况，还可以根据图像的亮度、清晰度和相似度的信息更加准确地确定***中的光源、光路调整设备和图像获取设备等部件的异常情况。
可选地，在一些可能的实施例中，目标对象为极耳，目标区域为图像中包括极耳的部分区域，或者，目标区域为图像中由极耳的极耳线组成的线条区域。
其中，由极耳的极耳线组成的线条区域可以是卷绕式锂电池的极耳的多层截面图像中的线条组成的区域。
在实际应用中，由于极耳具有高反光且形态很薄的特性，可能在图像中出现局部过曝，使得***的成像不具有一致性，而在本实施例中通过将目标区域设置为图像中包括极耳的部分区域，或者，通过将目标区域设置为图像中包括极耳的部分区域中的由极耳线组成的线条区域，能够针对极耳的信息或者极耳线的信息有效地检测***的成像一致性的情况，提高了产品检测的准确度。
需要说明的是，获取第二图像信息的各个属性和判断第二图像信息中的各个属性是否满足相应的预设范围的顺序，以及获取第一图像信息的各个属性和判断第一图像信息中的各个属性是否满足相应的预设范围的顺序，在此不做限定，可以根据实际需求进行确定。
为便于本领域技术人员理解，本申请提供一个具体应用场景的实施例。如图3、图4、图5和图6所示，一种检测***的成像一致性的方法300，包括以下步骤。
310，获取待检测电芯的多层极耳(目标对象)的多层截面图像(***采集的图像，如图4所示的图像)。
如图4所示，多条不规则的线条就是待检测电芯的多层极耳，其他部分为背景部分，可以考察到待检测电芯的多层极耳在图中的占比较小，也就是说背景部分较多。
320，获取多层截面图像的亮度、清晰度和相似度。
330，获取多层截面图像的感兴趣区域(如图5所示的区域)的亮度、清晰度和位置。
如图4和图5所示，感兴趣区域是多层截面图像的一部分，且包括了大量的多层极耳信息，通过感兴趣区域图，使得多层极耳在图像中占比较高。
340，获取多层截面图像的感兴趣区域中的多条极耳线组成的线条区域(如图6所示的区域)的亮度、清晰度和线角度。
如图6所示，浅色的不规则的线条组成的区域就是多层截面图像的感兴趣区域中的线条区域。
350，判断多层截面图像的信息是否满足预设条件。
判断多层截面图像的亮度是否处于第三预设亮度范围内；
判断多层截面图像的清晰度是否大于等于第三预设清晰度；
判断多层截面图像的相似度是否处于预设相似度范围内；
判断多层截面图像的感兴趣区域的亮度是否处于第一预设亮度范围内；
判断多层截面图像的感兴趣区域的清晰度是否大于等于第一预设清晰度；
判断多层截面图像的感兴趣区域的位置是否处于预设位置范围内；
判断多层截面图像的感兴趣区域中的线条区域的亮度是否处于第二预设亮度范围内；
判断多层截面图像的感兴趣区域中的线条区域的清晰度是否大于等于第二预设清晰度；
判断多层截面图像的感兴趣区域中的线条区域的线角度是否处于预设线角度范围内。
360，若是，则确定***的成像具有一致性；否则，确定***的成像不具有一致性。
需要说明的是，上述获取的多层截面图像的相关的图像信息(第一图像信息和第二图像信息)将可视化于图像中。并且，根据检测结果，还可以调整***中的设备，使得***的状态一直处于最佳状态，不受其他因素的干扰，进一步提高检测的 准确度。
综上所述，在本申请实施例中，通过获取图像的第一图像信息和第二图像信息，并根据第一图像信息是否满足第一预设条件以及第二图像信息满足第二预设条件，不仅可以更加全面、有效地检测***的成像一致性的情况，还可以根据不满足第一预设条件和第二预设条件的信息确定***中的光源、光路调整设备和图像获取设备等部件的异常情况。
图7示出了本申请一个实施例的检测***的成像一致性的装置700的示意性框图。该装置700可以执行上述本申请实施例的检测***的成像一致性的方法，例如，该装置700可以为前述执行设备110。
如图7所示，该装置700包括：确定模块710、获取模块720和检测模块730。
其中，确定模块710，用于确定***采集的图像中的目标区域，目标区域为图像中包括目标对象的部分区域；获取模块720，用于获取目标区域的第一图像信息；检测模块730，用于根据第一图像信息，检测***的成像的一致性。
在一些可能的实施例中，检测模块730用于：若第一图像信息满足第一预设条件，则确定***的成像具有一致性，或；若第一图像信息不满足第一预设条件，则确定***的成像不具有一致性。
在一些可能的实施例中，目标区域为图像中的感兴趣区域，第一图像信息包括目标区域的亮度、清晰度和位置，第一图像信息满足第一预设条件包括：目标区域的亮度处于第一预设亮度范围内；目标区域的清晰度大于等于第一预设清晰度；目标区域的位置处于预设位置范围内。
在一些可能的实施例中，确定模块710用于：基于分割定位方法对图像进行处理，获得感兴趣区域。
在一些可能的实施例中，目标区域为图像的感兴趣区域中的由目标对象的线条组成的线条区域，第一图像信息包括目标区域的亮度、清晰度和线角度，线角度是目标对象的线条的角度，第一图像信息满足第一预设条件包括：目标区域的亮度处于第二预设亮度范围内；目标区域的清晰度大于等于第二预设清晰度；目标区域的线角度处于预设角度范围内。
在一些可能的实施例中，确定模块710用于：基于分割定位方法对图像进行处理，获得感兴趣区域；对感兴趣区域进行语义分割，获取目标区域。
在一些可能的实施例中，第一图像信息包括目标区域的亮度、清晰度和位置以及目标区域中的线条区域的亮度、清晰度和线角度，线条区域为目标区域中的由目标对象的线条组成的线条区域，线角度是目标对象的线条的角度，第一图像信息满足第一预设条件包括：目标区域的亮度处于第一预设亮度范围内；目标区域的清晰度大于等于第一预设清晰度；目标区域的位置处于预设位置范围内；目标区域中的线条区域的亮度处于第二预设亮度范围内；目标区域中的线条区域的清晰度大于等于第二预设清晰度；目标区域中的线条区域的线角度处于预设角度范围内。
在一些可能的实施例中，获取模块720还用于获取图像的第二图像信息；检 测模块730用于根据第二图像信息和第一图像信息，检测***的成像的一致性。
在一些可能的实施例中，检测模块730用于：若第二图像信息满足第二预设条件且第一图像信息满足第一预设条件，则确定***的成像具有一致性，或；若第二图像信息不满足第二预设条件或第一图像信息不满足第一预设条件，则确定***的成像不具有一致性。
在一些可能的实施例中，第二图像信息包括检测图像的亮度、清晰度和相似度，第二图像信息满足第二预设条件包括：图像的亮度处于第三预设亮度范围内；图像的清晰度大于等于第三预设清晰度；图像的相似度处于预设相似度范围内。
图8是本申请实施例的检测***的成像一致性的装置的硬件结构示意图。图8所示的检测***的成像一致性的装置800包括存储器801、处理器802、通信接口803以及总线804。其中，存储器801、处理器802、通信接口803通过总线804实现彼此之间的通信连接。
存储器801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801可以存储程序，当存储器801中存储的程序被处理器802执行时，处理器802和通信接口803用于执行本申请实施例的检测***的成像一致性的方法的各个步骤。
处理器802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***的成像一致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检测***的成像一致性的方法。
处理器802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，本申请实施例的检测***的成像一致性的方法的各个步骤可以通过处理器802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802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801，处理器802读取存储器801中的信息，结合其硬件完成本申请实施例的检测***的成像一致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检测***的成像一致性的方法。
通信接口803使用例如但不限于收发器一类的收发装置，来实现装置800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803获取未知设备的流量数据。
总线804可包括在装置800各个部件(例如，存储器801、处理器802、通信接口803)之间传送信息的通路。
应注意，尽管上述装置800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800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800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800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8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检测***的成像一致性的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检测***的成像一致性的方法。
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、计算机可读存储介质和计算机程序产品的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个***，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
本申请中使用的用词仅用于描述实施例并且不用于限制权利要求。如在实施例以及权利要求的描述中使用的，除非上下文清楚地表明，否则单数形式的“一个”和“所述”旨在同样包括复数形式。类似地，如在本申请中所使用的术语“和/或”是指包含一个或一个以上相关联的列出的任何以及所有可能的组合。另外，当用于本申请中时，术语“包括”指陈述的特征、整体、步骤、操作、元素，和/或组件的存在，但不排除一个或一个以上其它特征、整体、步骤、操作、元素、组件和/或这些的分组的存在或添加。
所描述的实施例中的各方面、实施方式、实现或特征能够单独使用或以任意组合的方式使用。所描述的实施例中的各方面可由软件、硬件或软硬件的结合实现。所描述的实施例也可以由存储有计算机可读代码的计算机可读介质体现，该计算机可读代码包括可由至少一个计算装置执行的指令。所述计算机可读介质可与任何能够存储数据的数据存储装置相关联，该数据可由计算机***读取。用于举例的计算机可读介质可以包括只读存储器、随机存取存储器、紧凑型光盘只读储存器(Compact Disc Read-Only Memory，CD-ROM)、硬盘驱动器(Hard Disk Drive，HDD)、数字视频光盘(Digital Video Disc，DVD)、磁带以及光数据存储装置等。所述计算机可读介质还 可以分布于通过网络联接的计算机***中，这样计算机可读代码就可以分布式存储并执行。
上述技术描述可参照附图，这些附图形成了本申请的一部分，并且通过描述在附图中示出了依照所描述的实施例的实施方式。虽然这些实施例描述的足够详细以使本领域技术人员能够实现这些实施例，但这些实施例是非限制性的；这样就可以使用其它的实施例，并且在不脱离所描述的实施例的范围的情况下还可以做出变化。比如，流程图中所描述的操作顺序是非限制性的，因此在流程图中阐释并且根据流程图描述的两个或两个以上操作的顺序可以根据若干实施例进行改变。作为另一个例子，在若干实施例中，在流程图中阐释并且根据流程图描述的一个或一个以上操作是可选的，或是可删除的。另外，某些步骤或功能可以添加到所公开的实施例中，或两个以上的步骤顺序被置换。所有这些变化被认为包含在所公开的实施例以及权利要求中。
另外，上述技术描述中使用术语以提供所描述的实施例的透彻理解。然而，并不需要过于详细的细节以实现所描述的实施例。因此，实施例的上述描述是为了阐释和描述而呈现的。上述描述中所呈现的实施例以及根据这些实施例所公开的例子是单独提供的，以添加上下文并有助于理解所描述的实施例。上述说明书不用于做到无遗漏或将所描述的实施例限制到本申请的精确形式。根据上述教导，若干修改、选择适用以及变化是可行的。在某些情况下，没有详细描述为人所熟知的处理步骤以避免不必要地影响所描述的实施例。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 (14)

  1. 一种检测***的成像一致性的方法，其特征在于，所述方法包括：
    确定***采集的图像中的目标区域，所述目标区域为所述图像中包括目标对象的部分区域；
    获取所述目标区域的第一图像信息；
    根据所述第一图像信息，检测所述***的成像一致性。
  2. 根据权利要求1所述的方法，其特征在于，所述根据所述第一图像信息，检测所述***的成像一致性，包括：
    若所述第一图像信息满足第一预设条件，则确定所述***的成像具有一致性，或；
    若所述第一图像信息不满足第一预设条件，则确定所述***的成像不具有一致性。
  3. 根据权利要求2所述的方法，其特征在于，所述目标区域为所述图像中的感兴趣区域，所述第一图像信息包括所述目标区域的亮度、清晰度和位置，所述第一图像信息满足所述第一预设条件包括：
    所述目标区域的亮度处于第一预设亮度范围内；
    所述目标区域的清晰度大于等于第一预设清晰度；
    所述目标区域的位置处于预设位置范围内。
  4. 根据权利要求3所述的方法，其特征在于，所述确定***采集的图像中的目标区域包括：
    基于分割定位方法对所述图像进行处理，获得所述感兴趣区域。
  5. 根据权利要求2所述的方法，其特征在于，所述目标区域为所述图像的感兴趣区域中的由所述目标对象的线条组成的线条区域，所述第一图像信息包括所述目标区域的亮度、清晰度和线角度，所述线角度是所述目标对象的线条的角度，所述第一图像信息满足所述第一预设条件包括：
    所述目标区域的亮度处于第二预设亮度范围内；
    所述目标区域的清晰度大于等于第二预设清晰度；
    所述目标区域的线角度处于预设角度范围内。
  6. 根据权利要求5所述的方法，其特征在于，所述确定***采集的图像中的目标区域包括：
    基于分割定位方法对所述图像进行处理，获得所述感兴趣区域；
    对所述感兴趣区域进行语义分割，获取所述目标区域。
  7. 根据权利要求2所述的方法，其特征在于，所述第一图像信息包括所述目标区域的亮度、清晰度和位置以及所述目标区域中的线条区域的亮度、清晰度和线角度，所述线条区域为所述目标区域中的由所述目标对象的线条组成的线条区域，所述线角度是所述目标对象的线条的角度，所述第一图像信息满足所述第一预设条件包括：
    所述目标区域的亮度处于第一预设亮度范围内；
    所述目标区域的清晰度大于等于第一预设清晰度；
    所述目标区域的位置处于预设位置范围内；
    所述目标区域中的线条区域的亮度处于第二预设亮度范围内；
    所述目标区域中的线条区域的清晰度大于等于第二预设清晰度；
    所述目标区域中的线条区域的线角度处于预设角度范围内。
  8. 根据权利要求1至7中任一项所述的方法，其特征在于，所述方法还包括：
    获取所述图像的第二图像信息；
    所述检测所述***的成像一致性包括：
    根据所述第二图像信息和所述第一图像信息，检测所述***的成像一致性。
  9. 根据权利要求8所述的方法，其特征在于，所述根据所述第二图像信息和所述第一图像信息，检测所述***的成像一致性，包括：
    若所述第二图像信息满足第二预设条件且所述第一图像信息满足第一预设条件，则确定所述***的成像具有一致性，或；
    若所述第二图像信息不满足第二预设条件或所述第一图像信息不满足第一预设条件，则确定所述***的成像不具有一致性。
  10. 根据权利要求9所述的方法，其特征在于，所述第二图像信息包括所述图像的亮度、清晰度和相似度，所述第二图像信息满足所述第二预设条件包括：
    所述图像的亮度处于第三预设亮度范围内；
    所述图像的清晰度大于等于第三预设清晰度；
    所述图像的相似度处于预设相似度范围内。
  11. 根据权利要求1-10中任一项所述的方法，其特征在于，所述目标对象为极耳，所述目标区域为所述图像中包括所述极耳的部分区域，或者，所述目标区域为所述图像中由所述极耳的极耳线组成的线条区域。
  12. 一种检测***的成像一致性的装置，其特征在于，包括：
    确定模块，用于确定***采集的图像中的目标区域，所述目标区域为所述图像中包括目标对象的部分区域；
    获取模块，用于获取所述目标区域的第一图像信息；
    检测模块，用于根据所述第一图像信息，检测所述***的成像一致性。
  13. 一种检测***的成像一致性的装置，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11中任一项所述的检测***的成像一致性的方法。
  14. 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11中任一项所述的检测***的成像一致性的方法。
PCT/CN2023/084549 2022-07-22 2023-03-29 检测***的成像一致性的方法、装置和计算机存储介质 WO2024016715A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP23733191.3A EP4332889A1 (en) 2022-07-22 2023-03-29 Method and apparatus for testing imaging consistency of system, and computer storage medium
US18/474,262 US20240029240A1 (en) 2022-07-22 2023-09-26 Method and device for detecting imaging consistency of system, and computer storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210866453.7 2022-07-22
CN202210866453.7A CN115829911A (zh) 2022-07-22 2022-07-22 检测***的成像一致性的方法、装置和计算机存储介质

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/474,262 Continuation US20240029240A1 (en) 2022-07-22 2023-09-26 Method and device for detecting imaging consistency of system, and computer storage medium

Publications (1)

Publication Number Publication Date
WO2024016715A1 true WO2024016715A1 (zh) 2024-01-25

Family

ID=85522877

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/084549 WO2024016715A1 (zh) 2022-07-22 2023-03-29 检测***的成像一致性的方法、装置和计算机存储介质

Country Status (2)

Country Link
CN (1) CN115829911A (zh)
WO (1) WO2024016715A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115829911A (zh) * 2022-07-22 2023-03-21 宁德时代新能源科技股份有限公司 检测***的成像一致性的方法、装置和计算机存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112329575A (zh) * 2020-10-27 2021-02-05 苏州中科先进技术研究院有限公司 一种基于图像质量评价的鼻纹检测方法及装置
CN113642434A (zh) * 2021-07-30 2021-11-12 江苏范特科技有限公司 人脸图像序列中的人脸择优方法、设备
CN114332030A (zh) * 2021-12-30 2022-04-12 华中科技大学 一种阀体焊缝x光图像去噪方法、***及装置
CN114983338A (zh) * 2021-03-02 2022-09-02 华为技术有限公司 一种皮肤检测方法和电子设备
CN115829911A (zh) * 2022-07-22 2023-03-21 宁德时代新能源科技股份有限公司 检测***的成像一致性的方法、装置和计算机存储介质

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108053438B (zh) * 2017-11-30 2020-03-06 Oppo广东移动通信有限公司 景深获取方法、装置及设备
CN112597785A (zh) * 2020-06-24 2021-04-02 陕西利丰恒信生物科技发展有限公司 一种目标对象图像采集的引导方法及***
CN112616028A (zh) * 2020-12-15 2021-04-06 深兰人工智能(深圳)有限公司 车载相机参数调整方法、装置、电子设备及存储介质
CN112633200A (zh) * 2020-12-29 2021-04-09 平安普惠企业管理有限公司 基于人工智能的人脸图像比对方法、装置、设备及介质
CN114648749A (zh) * 2022-03-31 2022-06-21 上海商汤临港智能科技有限公司 一种生理状态检测方法、装置、电子设备及存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112329575A (zh) * 2020-10-27 2021-02-05 苏州中科先进技术研究院有限公司 一种基于图像质量评价的鼻纹检测方法及装置
CN114983338A (zh) * 2021-03-02 2022-09-02 华为技术有限公司 一种皮肤检测方法和电子设备
CN113642434A (zh) * 2021-07-30 2021-11-12 江苏范特科技有限公司 人脸图像序列中的人脸择优方法、设备
CN114332030A (zh) * 2021-12-30 2022-04-12 华中科技大学 一种阀体焊缝x光图像去噪方法、***及装置
CN115829911A (zh) * 2022-07-22 2023-03-21 宁德时代新能源科技股份有限公司 检测***的成像一致性的方法、装置和计算机存储介质

Also Published As

Publication number Publication date
CN115829911A (zh) 2023-03-21

Similar Documents

Publication Publication Date Title
US9740967B2 (en) Method and apparatus of determining air quality
CN110544258B (zh) 图像分割的方法、装置、电子设备和存储介质
US10373380B2 (en) 3-dimensional scene analysis for augmented reality operations
CN111340752A (zh) 屏幕的检测方法、装置、电子设备及计算机可读存储介质
CN112669344B (zh) 一种运动物体的定位方法、装置、电子设备及存储介质
WO2019134504A1 (zh) 图像背景虚化方法、装置、存储介质及电子设备
RU2607774C2 (ru) Способ управления в системе захвата изображения, устройство управления и машиночитаемый носитель данных
CN111325717B (zh) 手机缺陷位置识别方法及设备
WO2024016715A1 (zh) 检测***的成像一致性的方法、装置和计算机存储介质
WO2021013049A1 (zh) 前景图像获取方法、前景图像获取装置和电子设备
CN116503414B (zh) 屏幕缺陷检测方法、装置、计算机设备和存储介质
CN112995535A (zh) 用于处理视频的方法、装置、设备以及存储介质
CN115471476A (zh) 一种部件缺陷检测方法、装置、设备及介质
CN116559177A (zh) 一种缺陷检测方法、装置、设备以及存储介质
CN111898610A (zh) 卡片缺角检测方法、装置、计算机设备及存储介质
CN113781511B (zh) 传送带边缘磨损检测方法、装置、计算机设备及存储介质
CN114359161A (zh) 一种缺陷检测方法、装置、设备和存储介质
WO2024016686A1 (zh) 角点检测的方法和装置
CN110689556A (zh) 跟踪方法、装置及智能设备
JP2019067377A (ja) 画像処理装置及び方法及び監視システム
WO2022142172A1 (zh) 一种检测近场物体的方法、装置、介质和电子设备
CN116993654A (zh) 摄像头模组缺陷检测方法、装置、设备、存储介质及产品
EP4332889A1 (en) Method and apparatus for testing imaging consistency of system, and computer storage medium
US11205064B1 (en) Measuring quality of depth images in real time
CN110782439B (zh) 一种辅助检测图像标注质量的方法及装置

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 2023733191

Country of ref document: EP

Effective date: 20230808