CN115063414A - Method, device and equipment for detecting lithium battery pole piece gummed paper and storage medium - Google Patents

Method, device and equipment for detecting lithium battery pole piece gummed paper and storage medium Download PDF

Info

Publication number
CN115063414A
CN115063414A CN202210939668.7A CN202210939668A CN115063414A CN 115063414 A CN115063414 A CN 115063414A CN 202210939668 A CN202210939668 A CN 202210939668A CN 115063414 A CN115063414 A CN 115063414A
Authority
CN
China
Prior art keywords
image
pole piece
detection
target
channel
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.)
Granted
Application number
CN202210939668.7A
Other languages
Chinese (zh)
Other versions
CN115063414B (en
Inventor
罗育宏
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.)
Shenzhen Xinshizhi Technology Co ltd
Original Assignee
Shenzhen Xinshizhi 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 Shenzhen Xinshizhi Technology Co ltd filed Critical Shenzhen Xinshizhi Technology Co ltd
Priority to CN202210939668.7A priority Critical patent/CN115063414B/en
Publication of CN115063414A publication Critical patent/CN115063414A/en
Application granted granted Critical
Publication of CN115063414B publication Critical patent/CN115063414B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/0002Inspection of images, e.g. flaw detection
    • G06T7/0004Industrial image inspection
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00Image enhancement or restoration
    • G06T5/90Dynamic range modification of images or parts thereof
    • G06T5/94Dynamic range modification of images or parts thereof based on local image properties, e.g. for local contrast enhancement
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/90Determination of colour characteristics
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/20Special algorithmic details
    • G06T2207/20092Interactive image processing based on input by user
    • G06T2207/20104Interactive definition of region of interest [ROI]
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/20Special algorithmic details
    • G06T2207/20172Image enhancement details
    • G06T2207/20192Edge enhancement; Edge preservation
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02EREDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E60/00Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
    • Y02E60/10Energy storage using batteries

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Quality & Reliability (AREA)
  • Image Analysis (AREA)

Abstract

The embodiment of the invention discloses a method, a device, equipment and a storage medium for detecting lithium battery pole piece gummed paper, wherein the method comprises the following steps: acquiring a target image of a pole piece to be detected, wherein adhesive paper is arranged on the pole piece to be detected, and the target image is a color image; aiming at a plurality of color channels of a target image, calculating the gray scale statistical characteristics of the target image under each color channel respectively, and determining 2 target color channels based on the calculated gray scale statistical characteristics; performing preset image transformation on images corresponding to 2 target color channels in the target image to obtain a detection gray image; and performing linear detection based on the detection gray level image, and determining the gummed paper detection result of the pole piece to be detected according to the detected linear. By adopting the invention, the linear detection rate and the accuracy of linear detection can be improved, thereby improving the detection accuracy of the gummed paper.

Description

Method, device and equipment for detecting lithium battery pole piece gummed paper and storage medium
Technical Field
The invention relates to the technical field of lithium batteries and the technical field of automatic visual detection of industrial machines, in particular to a method and a device for detecting lithium battery pole piece gummed paper, computer equipment and a computer readable storage medium.
Background
The battery is a type of battery using a nonaqueous electrolyte solution with lithium metal or a lithium alloy as a negative electrode material. Because the chemical characteristics of lithium metal are very active, the lithium battery has high requirements on the manufacturing process. Lithium batteries are broadly classified into two types: lithium metal batteries and lithium ion batteries. The lithium ion battery is used for the new energy automobile. With the strong promotion of new energy in China, the power battery industry becomes popular. At present, lithium ion batteries are widely applied to the fields of portable electronic products, electric vehicles, large power supplies, secondary charging, energy storage and the like, so that the quality problem of the lithium ion batteries is more and more important.
In the course of working of lithium cell, need go up and carry out the rubberizing on the pole piece and handle, wherein, the adhesive tape on the pole piece generally relies on rubberizing processing equipment direct once only to accomplish the rubberizing, and the production of rubberizing position and adhesive tape size are bad is inevitable, because constantly improve the requirement to security, quality uniformity, need measure the adhesive tape position and the adhesive tape size of semi-manufactured goods after the processing to confirm whether the pole piece after the rubberizing accords with the requirement of lithium cell production.
In the relevant technical scheme of the detection of the gummed paper of the lithium battery pole piece, the position and the size of the gummed paper can be measured in a manual measurement mode, but the manual measurement efficiency is low and the error is large. Or, the position and size of the gummed paper can be measured through a black-and-white image or a gray-scale image, but the black-and-white image is not good enough to represent the gummed paper, generally, the contrast is low, and the accuracy in measurement is low; the gray-scale image has low contrast and low accuracy in measurement.
Disclosure of Invention
In view of the above, it is necessary to provide a method and an apparatus for detecting a lithium battery pole piece adhesive tape, a computer device, and a computer readable storage medium.
In a first aspect of the present invention, a method for detecting a lithium battery electrode tab gummed paper is provided, the method comprising:
obtaining a target image of a pole piece to be detected, wherein adhesive paper is arranged on the pole piece to be detected, and the target image is a color image;
aiming at a plurality of color channels of the target image, calculating the gray scale statistical characteristics of the target image under each color channel respectively, and determining 2 target color channels based on the calculated gray scale statistical characteristics;
performing preset image transformation on images corresponding to the 2 target color channels in the target image to obtain a detection gray image;
and performing linear detection based on the detection gray level image, and determining the gummed paper detection result of the pole piece to be detected according to the detected linear.
Optionally, the step of obtaining the target image of the pole piece to be detected further includes: the method comprises the steps of collecting an image of a pole piece to be detected through a camera device, and determining one or more ROI (region of interest) areas in the collected image as a target image of the pole piece to be detected.
Optionally, the plurality of color channels include an R color channel, a G color channel, and a B color channel; the grayscale statistical feature includes the grayscale standard deviation; the step of calculating the grayscale statistical characteristics of the target image under each color channel respectively for the plurality of color channels of the target image, and determining 2 target color channels based on the calculated grayscale statistical characteristics further includes: calculating the gray standard deviation of the channel image of the target image under each color channel; determining a color channel corresponding to the maximum value of the gray standard deviation corresponding to each color channel as a first color channel, and determining a color channel corresponding to the minimum value of the gray standard deviation corresponding to each color channel as a second color channel; wherein the 2 target color channels include a first color channel and a second color channel.
Optionally, the step of performing preset image transformation on the image corresponding to the 2 target color channels in the target image to obtain a detection gray image further includes: calculating an average gray level image corresponding to the channel image under the first color channel and the channel image under the second color channel; calculating the absolute value of the difference between the channel image under the first color channel and the average gray scale image to be used as a first average difference image, and calculating the absolute value of the difference between the channel image under the second color channel and the average gray scale value to be used as a second average difference image; and summing the first average difference image and the second average difference image, and cutting a summation result to obtain a conversion image obtained by performing preset image conversion on the images corresponding to the 2 target color channels in the target image.
Optionally, the step of performing preset image transformation on the image corresponding to the 2 target color channels in the target image to obtain a detection gray image further includes: and amplifying the converted image, and determining the detection gray image based on the amplified converted image and the channel image under the first color channel.
Optionally, the step of performing amplification processing on the transformed image, and determining the detection gray image based on the amplified transformed image and the channel image in the first color channel further includes: according to the formula
Figure DEST_PATH_IMAGE001
Performing an enlargement process on the transformed image, wherein,
Figure 100002_DEST_PATH_IMAGE002
representing the transformed image after enlargement,
Figure DEST_PATH_IMAGE003
represents the maximum value of the gray-scale average of the channel images for a plurality of color channels,
Figure 100002_DEST_PATH_IMAGE004
represents the maximum value of the gray scale standard deviation of the channel images for a plurality of color channels,
Figure DEST_PATH_IMAGE005
representing a transformed image; according to the formula
Figure 100002_DEST_PATH_IMAGE006
Determining a detection gray scale image, wherein,
Figure DEST_PATH_IMAGE007
a gray-scale image is represented for detection,
Figure 100002_DEST_PATH_IMAGE008
representing a channel image corresponding to the first color channel.
Optionally, the step of performing linear detection based on the detection gray level image and determining the gummed paper detection result of the pole piece to be detected according to the detected linear image further includes: performing line detection on the detection gray level image based on a preset line detection algorithm, and determining one or more pieces of line information in the target image; and calculating distance information between straight lines according to the detected one or more pieces of straight line information, and determining a gummed paper detection result of the pole piece to be detected according to the calculated distance information, wherein the gummed paper detection result comprises position information and size information of the gummed paper on the pole piece to be detected.
In the second part of the invention, a detection device for lithium battery pole piece gummed paper is provided, which comprises:
the device comprises an image acquisition module, a detection module and a control module, wherein the image acquisition module is used for acquiring a target image of a pole piece to be detected, the pole piece to be detected is provided with adhesive paper, and the target image is a color image;
the characteristic statistical module is used for respectively calculating the gray scale statistical characteristics of the target image under each color channel aiming at a plurality of color channels of the target image, and determining 2 target color channels based on the calculated gray scale statistical characteristics;
the image transformation module is used for carrying out preset image transformation on the images corresponding to the 2 target color channels in the target image to obtain a detection gray image;
and the linear detection module is used for carrying out linear detection based on the detection gray level image and determining the gummed paper detection result of the pole piece to be detected according to the detected linear.
In a third aspect of the present invention, there is provided a computer device, where the computer device includes a memory and a processor, and the memory has an executable code, and when the executable code runs on the processor, the method for detecting the lithium battery pole piece gummed paper is implemented.
In a fourth aspect of the present invention, a computer-readable storage medium is provided, where the computer-readable storage medium is used to store a computer program, and the computer program is used to execute the foregoing method for detecting the lithium battery pole piece gummed paper.
By adopting the embodiment of the invention, the following beneficial effects are achieved:
after the detection method, the detection device, the computer equipment and the computer-readable storage medium of the lithium battery pole piece adhesive tape are adopted, a target image of a pole piece to be detected is obtained, wherein the adhesive tape is arranged on the pole piece to be detected, and the target image is a color image; aiming at a plurality of color channels of the target image, calculating the gray scale statistical characteristics of the target image under each color channel respectively, and determining 2 target color channels based on the calculated gray scale statistical characteristics; performing preset image transformation on images corresponding to the 2 target color channels in the target image to obtain a detection gray image; and performing linear detection based on the detection gray level image, and determining the gummed paper detection result of the pole piece to be detected according to the detected linear. That is to say, in the embodiment of the present invention, the images under each color channel are subjected to statistical analysis, and the images are subjected to processing such as conversion according to the analysis result, so that the contrast of the edges of the adhesive tape can be improved, and thus the linear detection rate and the accuracy of linear detection are improved, and the detection accuracy of the adhesive tape is improved; moreover, the image fusion with the maximum difference between the transformed image and the original image enables the detection method of the lithium battery pole piece adhesive tape to be applicable to more adhesive tape processes, and the compatibility and the application range of the detection method of the lithium battery pole piece adhesive tape are improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Wherein:
FIG. 1 is a schematic flow chart illustrating a method for detecting adhesive tape of a lithium battery electrode tab in one embodiment;
FIG. 2 is a schematic view of an image of a pole piece to be sensed in one embodiment;
FIG. 3 is a diagram of an image corresponding to an ROI area in an embodiment
FIG. 4 shows a first color channel in one embodiment
Figure DEST_PATH_IMAGE009
A gray scale schematic diagram corresponding to the lower channel image;
FIG. 5 shows a second color channel in one embodiment
Figure 100002_DEST_PATH_IMAGE010
A gray scale schematic diagram corresponding to the lower channel image;
FIG. 6 is an average gray scale map of an embodiment
Figure DEST_PATH_IMAGE011
A schematic diagram of (a);
FIG. 7 is a diagram of transforming an image in one embodiment
Figure 100002_DEST_PATH_IMAGE012
A schematic diagram of (a);
FIG. 8 is a diagram of a transformed image after magnification in one embodiment;
FIG. 9 is a diagram illustrating detection of a grayscale image according to one embodiment;
FIG. 10 is a diagram illustrating a target image corresponding to a ROI area in another embodiment;
FIG. 11 is a diagram illustrating detection of a gray scale image according to another embodiment;
FIG. 12 is a schematic structural diagram of a detection apparatus for a lithium battery electrode tab gummed paper in an embodiment;
fig. 13 is a schematic structural diagram of a computer device for operating the detection method for the gummed paper of the lithium battery pole piece in one embodiment.
Detailed Description
In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims of the present application and in the drawings described above, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In this embodiment, a method for detecting a lithium battery pole piece adhesive tape is provided, where the method may be performed in an industrial scene, for example, in a production line of a lithium battery pole piece or an adhesive tape product line of a lithium battery pole piece, a camera is arranged on the production line to acquire an image of the lithium battery pole piece on the production line, and then a position and a size of the adhesive tape on the corresponding lithium battery pole piece are detected based on image recognition to determine whether a semi-finished product of the pole piece adhesive tape in a lithium battery generation process has a problem, so as to distinguish a good product from an inferior product, thereby improving a yield of the pole piece entering a subsequent process of lithium battery production, and improving a yield of lithium battery generation.
In this embodiment, the detection method based on the lithium battery pole piece gummed paper may be implemented based on a computer device connected to a camera for collecting an image of the lithium battery pole piece to be detected, where the computer device may be a control device of a product line or a server connected to the product line, and is not limited in this embodiment.
The detection method of the lithium battery pole piece gummed paper can detect the gummed paper position and the gummed paper size of the lithium battery pole piece gummed paper so as to determine whether the position and the size of the gummed paper on the lithium battery pole piece are accurate or not, and therefore the possibility of poor gumming position and size of the gummed paper is reduced.
In a specific embodiment, as shown in fig. 1, a schematic flow chart of the method for detecting the lithium battery pole piece gummed paper is given, where the method for detecting the lithium battery pole piece gummed paper includes steps S101 to S104 shown in fig. 1:
step S101: the method comprises the steps of obtaining a target image of a pole piece to be detected, wherein adhesive paper is arranged on the pole piece to be detected, and the target image is a color image.
In this embodiment, for a pole piece to be detected that needs to be subjected to adhesive tape detection, an image of the pole piece to be detected, that is, a target image in this embodiment, needs to be obtained through a camera device (for example, a CCD device) disposed above the pole piece to be detected. The target image is a color image and includes images of a plurality of color channels, that is, a channel image of each color channel. In a particular embodiment, the plurality of color channels includes an R color channel, a G color channel, and a B color channel; in other embodiments, the plurality of color channels may also include a Y color channel, a U color channel, and a V color channel, which are not limited herein.
After acquiring a target image of a pole piece to be detected, ROI (region of interest) identification needs to be further performed on the target image to determine one or more ROI regions in the target image, and then the following steps S101 to S104 are respectively performed with each ROI region as an image, that is, the ROI region extracted from the image corresponding to the pole piece to be detected is used as the target image of the pole piece to be detected, and then, the gummed paper detection results such as gummed paper position and gummed paper size are respectively acquired for the target image corresponding to each ROI region.
In a specific embodiment, as shown in fig. 2, a schematic diagram of an image of a pole piece to be detected is given (shown in the figure by a gray image, the image is a color image actually), wherein a black area corresponds to the pole piece to be detected, and a middle gray portion corresponds to an area where the gummed paper is located, as can be known from fig. 2, in the gray image, the gray contrast of the upper, lower, left and right edge positions of the area where the gummed paper is located is not high, and the accuracy of directly detecting the gummed paper position and the gummed paper size based on the gray image is not sufficient.
Further, the detection of the ROI area of the image of the pole piece to be detected may be based on a preset ROI area, and the translation following is performed by detecting the position of the pole piece to be detected and the position of the empty foil therein, so as to determine one or more ROI areas in the image of the pole piece to be detected, and determine a target image corresponding to the one or more ROI areas of the pole piece to be detected. Fig. 3 shows a schematic diagram of a map corresponding to a ROI region.
The analysis and processing of the target image in steps S102-S104 below is based on a single ROI region (or a single target image), and is set forth below directly as an example for the processing of the target image.
Step S102: and aiming at a plurality of color channels of the target image, calculating the gray scale statistical characteristics of the target image under each color channel respectively, and determining 2 target color channels based on the calculated gray scale statistical characteristics.
In this step, each target image needs to be processed separately, and the channel images under the multiple color channels of the target image need to be calculated separately for statistical analysis.
The color channels are illustrated here as comprising R, G, B3 color channels.
For the channel images corresponding to the target image under R, G, B3 color channels, the gray level mean value corresponding to each channel image needs to be calculated respectively
Figure DEST_PATH_IMAGE013
That is, the mean value of the gradations under the R color channel is calculated
Figure 100002_DEST_PATH_IMAGE014
Calculating the mean value of gray levels in G color channels
Figure DEST_PATH_IMAGE015
Calculating the mean value of gray levels in B color channel
Figure 100002_DEST_PATH_IMAGE016
Then, based on the calculated gray level mean value, the corresponding gray level standard deviation is further calculated
Figure DEST_PATH_IMAGE017
(ii) a I.e. calculating the standard deviation of the gray scale in the R color channel
Figure DEST_PATH_IMAGE018
Calculating the standard deviation of gray scale in G color channel
Figure DEST_PATH_IMAGE019
Calculating the standard deviation of gray scale in B color channel
Figure DEST_PATH_IMAGE020
The grayscale statistical characteristics of the channel image include one or more of corresponding grayscale mean and grayscale standard deviation.
Then, in the process of determining 2 target color channels based on the calculated gray scale statistical characteristics, the maximum value and the minimum value in the gray scale standard deviation are determined according to the size of the gray scale standard deviation of the channel image, and the maximum value is used for determining the maximum value
Figure DEST_PATH_IMAGE021
And minimum value
Figure DEST_PATH_IMAGE022
Corresponding colorThe color channels are respectively determined as first color channels
Figure DEST_PATH_IMAGE023
And a second color channel
Figure DEST_PATH_IMAGE024
That is, for a channel image of the target image under each color channel, calculating a gray standard deviation of the channel image; determining the maximum value of the corresponding gray standard deviation of each color channel
Figure DEST_PATH_IMAGE026
The corresponding color channel is used as the first color channel
Figure DEST_PATH_IMAGE027
Determining the minimum value of the corresponding gray standard deviation of each color channel
Figure DEST_PATH_IMAGE029
The corresponding color channel is used as the second color channel
Figure 420071DEST_PATH_IMAGE024
(ii) a Wherein the 2 target color channels include a first color channel
Figure 350593DEST_PATH_IMAGE027
And a second color channel
Figure DEST_PATH_IMAGE030
Referring specifically to fig. 4 and 5, fig. 4 and 5 show the first color channel, respectively
Figure DEST_PATH_IMAGE031
And a second color channel
Figure DEST_PATH_IMAGE032
The lower channel image corresponds to a gray scale diagram.
In this step, statistical analysis is performed on the channel images of the multiple color channels, and confirmation is performed based on the grayscale statistical characteristics, so as to determine 2 color channels corresponding to the maximum value and the minimum value of the grayscale standard deviation, and further perform further calculation in subsequent steps.
Step S103: and carrying out preset image transformation on the images corresponding to the 2 target color channels in the target image to obtain a detection gray image.
In this step, for the determined first color channel and second color channel, the original images (channel images of the target image in the first color channel and the second color channel) in the corresponding color channels need to be subjected to transformation calculation to obtain corresponding transformation images, and then processing is performed based on the transformation images to obtain grayscale images (detection grayscale images) finally used for line detection.
Specifically, an average gray level image corresponding to a channel image under a first color channel and a channel image under a second color channel is calculated; calculating the absolute value of the difference between the channel image under the first color channel and the average gray level image to be used as a first average difference image, and calculating the absolute value of the difference between the channel image under the second color channel and the average gray level value to be used as a second average difference image; and summing the first average difference image and the second average difference image, and cutting off a summation result to obtain a conversion image obtained by performing preset image conversion on the images corresponding to the 2 target color channels in the target image.
That is, for the first color channel
Figure DEST_PATH_IMAGE033
And a second color channel
Figure DEST_PATH_IMAGE034
By the formula
Figure DEST_PATH_IMAGE035
Calculating the average gray level image corresponding to the channel images under the two color channels
Figure DEST_PATH_IMAGE036
That is, the average gray scale map corresponds to the gray scale map corresponding to the average gray scale value of the channel image in the 2 color channels. See in particular the schematic diagram given in fig. 6.
Then, the first color channels are calculated respectively
Figure DEST_PATH_IMAGE037
And a second color channel
Figure DEST_PATH_IMAGE038
Obtaining the absolute value of the difference between the lower channel image and the average gray level image to obtain a first average difference image
Figure DEST_PATH_IMAGE039
And a second average difference image
Figure DEST_PATH_IMAGE040
Namely:
Figure DEST_PATH_IMAGE041
Figure DEST_PATH_IMAGE042
for the first average difference image
Figure DEST_PATH_IMAGE043
And a second average difference image
Figure DEST_PATH_IMAGE044
Performing summation to obtain
Figure DEST_PATH_IMAGE045
Figure DEST_PATH_IMAGE046
Then, the result of the summation is further processed for cutting (also as a cut-off)Physical) to reduce the effects of noise, namely:
Figure DEST_PATH_IMAGE047
wherein,
Figure DEST_PATH_IMAGE048
the result after the cutting process is the converted image obtained by performing the preset image conversion on the image corresponding to the 2 target color channels in the target image in the step
Figure DEST_PATH_IMAGE049
. See in particular the schematic illustration of fig. 7.
In obtaining a transformed image
Figure 170476DEST_PATH_IMAGE049
After that, further processing is required.
Specifically, the converted image is amplified, and the detection grayscale image is determined based on the amplified converted image and the channel image in the first color channel. Wherein according to the formula
Figure DEST_PATH_IMAGE050
Performing an enlargement process on the transformed image, wherein,
Figure DEST_PATH_IMAGE051
showing the transformed image after enlargement (see in particular the schematic diagram of figure 8),
Figure DEST_PATH_IMAGE052
represents the maximum value of the gray-scale average of the channel images for a plurality of color channels,
Figure DEST_PATH_IMAGE053
represents the maximum value of the gray scale standard deviation of the channel images in a plurality of color channels,
Figure DEST_PATH_IMAGE054
representing a transformed image; according to the formula
Figure DEST_PATH_IMAGE055
Determining a detection gray scale image, wherein,
Figure DEST_PATH_IMAGE056
representing a detected gray scale image (see in particular the schematic diagram of fig. 9).
Figure DEST_PATH_IMAGE057
The expressed detection gray level image can be directly used for linear detection, so that the linear position between the gummed paper and the pole piece in the target image of the pole piece to be detected is determined.
Step S104: and performing linear detection based on the detection gray level image, and determining the gummed paper detection result of the pole piece to be detected according to the detected linear.
Performing line detection on the detection gray level image based on a preset line detection algorithm, and determining one or more pieces of line information in the target image; and calculating distance information between straight lines according to the detected one or more pieces of straight line information, and determining a gummed paper detection result of the pole piece to be detected according to the calculated distance information, wherein the gummed paper detection result comprises position information and size information of the gummed paper on the pole piece to be detected.
That is to say, in this embodiment, the processing and the line detection in the above steps are respectively performed on the target image corresponding to each ROI region, so that the line position in each ROI region can be determined, where the line position is a line corresponding to the edge position between the gummed adhesive tape and the pole piece, and the position information and the size information of the adhesive tape can be determined according to the detected line position, so as to determine the adhesive tape detection result.
Fig. 10-11 show another embodiment, in the case of the target image corresponding to the ROI shown in fig. 10, which corresponds to the obtained detection gray image, wherein the edge between the adhesive tape and the pole piece is clearer than the edge in fig. 10, and the accuracy of detecting the position information and the size information of the adhesive tape is improved.
In this embodiment, in the above steps S101 to S104, the statistical analysis of the gray scale features is performed on the image of the pasted pole piece to be detected in each color channel to determine the color channel used in the image transformation later, and then the contrast of the edge of the gummed paper is maximized by the average gray scale image calculation, the difference calculation, the absolute value calculation, and the summation calculation in the image transformation, and the offset cutting is performed on the gray scale image after the summation, so that the influence of noise is reduced, and the accuracy of the edge detection of the gummed paper is improved. And the converted image is summed with the channel image under the original color channel by the method, and the maximum difference value in the original image and the converted image is fused, so that the compatibility of the adhesive tape detection scheme to various processes can be improved, and the application range of the adhesive tape detection method is widened.
After the detection method of the lithium battery pole piece gummed paper is adopted, the images under each color channel are subjected to statistical analysis, the images are subjected to conversion and other processing according to the analysis result, the contrast of the gummed paper edge can be improved, the linear detection rate and the accuracy of linear detection are improved, and the detection accuracy of the gummed paper is improved; moreover, the image fusion with the maximum difference between the transformed image and the original image enables the detection method of the lithium battery pole piece adhesive tape to be applicable to more adhesive tape processes, and the compatibility and the application range of the detection method of the lithium battery pole piece adhesive tape are improved.
In another embodiment, a device for detecting the gummed paper of the lithium battery pole piece is provided, as shown in fig. 12,
the image acquisition module 101 is configured to acquire a target image of a pole piece to be detected, wherein the pole piece to be detected is provided with adhesive paper, and the target image is a color image;
a feature statistics module 102, configured to calculate, for multiple color channels of the target image, a grayscale statistics feature of the target image under each color channel, and determine 2 target color channels based on the calculated grayscale statistics feature;
the image transformation module 103 is configured to perform preset image transformation on images corresponding to the 2 target color channels in the target image to obtain a detection gray image;
and the linear detection module 104 is used for performing linear detection based on the detection gray level image and determining a gummed paper detection result of the pole piece to be detected according to the detected linear.
In an optional embodiment, the image acquisition module 101 is further configured to acquire an image of the pole piece to be detected by using a camera, and determine one or more ROI regions in the acquired image as a target image of the pole piece to be detected.
In an alternative embodiment, the plurality of color channels includes an R color channel, a G color channel, and a B color channel; the grayscale statistical feature includes the grayscale standard deviation; the feature statistics module 102 is further configured to calculate, for a channel image of the target image under each color channel, a gray standard deviation of the channel image; determining a color channel corresponding to the maximum value of the gray standard deviation corresponding to each color channel as a first color channel, and determining a color channel corresponding to the minimum value of the gray standard deviation corresponding to each color channel as a second color channel; wherein the 2 target color channels include a first color channel and a second color channel.
In an optional embodiment, the image transformation module 103 is further configured to calculate an average grayscale map corresponding to the channel image in the first color channel and the channel image in the second color channel; calculating the absolute value of the difference between the channel image under the first color channel and the average gray level image to be used as a first average difference image, and calculating the absolute value of the difference between the channel image under the second color channel and the average gray level value to be used as a second average difference image; and summing the first average difference image and the second average difference image, and cutting off a summation result to obtain a conversion image obtained by performing preset image conversion on the images corresponding to the 2 target color channels in the target image.
In an optional embodiment, the image transformation module 103 is further configured to perform an amplification process on the transformed image, and determine the detection grayscale image based on the amplified transformed image and the channel image in the first color channel.
In an alternative embodiment, the image transformation module 103 is further configured to generate the image according to a formula
Figure DEST_PATH_IMAGE058
Performing an enlargement process on the transformed image, wherein,
Figure DEST_PATH_IMAGE059
representing the transformed image after enlargement,
Figure DEST_PATH_IMAGE060
represents the maximum value of the gray-scale average of the channel images for a plurality of color channels,
Figure DEST_PATH_IMAGE061
represents the maximum value of the gray scale standard deviation of the channel images for a plurality of color channels,
Figure 985592DEST_PATH_IMAGE054
representing a transformed image; according to the formula
Figure DEST_PATH_IMAGE062
Determining a detection gray scale image, wherein,
Figure DEST_PATH_IMAGE063
a gray-scale image is represented for detection,
Figure DEST_PATH_IMAGE064
representing a channel image corresponding to the first color channel.
In an optional embodiment, the line detection module 104 is further configured to perform line detection on the detected grayscale image based on a preset line detection algorithm, and determine one or more pieces of line information in the target image; and calculating distance information between straight lines according to the detected one or more pieces of straight line information, and determining a gummed paper detection result of the pole piece to be detected according to the calculated distance information, wherein the gummed paper detection result comprises position information and size information of the gummed paper on the pole piece to be detected.
Fig. 13 shows an internal structure diagram of a computer device for implementing the detection method of the lithium battery pole piece gummed paper in one embodiment. The computer device may specifically be a terminal, and may also be a server. As shown in fig. 13, the computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program which, when executed by the processor, causes the processor to carry out the above-mentioned method. The internal memory may also have stored therein a computer program which, when executed by the processor, causes the processor to perform the method described above. Those skilled in the art will appreciate that the architecture shown in fig. 13 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
After the detection method, the detection device, the computer equipment and the computer-readable storage medium of the lithium battery pole piece adhesive tape are adopted, a target image of a pole piece to be detected is obtained, wherein the adhesive tape is arranged on the pole piece to be detected, and the target image is a color image; aiming at a plurality of color channels of the target image, calculating the gray scale statistical characteristics of the target image under each color channel respectively, and determining 2 target color channels based on the calculated gray scale statistical characteristics; performing preset image transformation on images corresponding to the 2 target color channels in the target image to obtain a detection gray image; and performing linear detection based on the detection gray level image, and determining the gummed paper detection result of the pole piece to be detected according to the detected linear. That is to say, in the embodiment of the present invention, the images under each color channel are subjected to statistical analysis, and the images are subjected to processing such as conversion according to the analysis result, so that the contrast of the edges of the adhesive tape can be improved, and thus the linear detection rate and the accuracy of linear detection are improved, and the detection accuracy of the adhesive tape is improved; moreover, the image fusion with the maximum difference between the transformed image and the original image enables the detection method of the lithium battery pole piece adhesive tape to be applicable to more adhesive tape processes, and the compatibility and the application range of the detection method of the lithium battery pole piece adhesive tape are improved.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a non-volatile computer-readable storage medium, and can include the processes of the embodiments of the methods described above when the program is executed. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims (10)

1. A detection method for lithium battery pole piece gummed paper is characterized by comprising the following steps:
obtaining a target image of a pole piece to be detected, wherein adhesive paper is arranged on the pole piece to be detected, and the target image is a color image;
aiming at a plurality of color channels of the target image, calculating the gray scale statistical characteristics of the target image under each color channel respectively, and determining 2 target color channels based on the calculated gray scale statistical characteristics;
performing preset image transformation on images corresponding to the 2 target color channels in the target image to obtain a detection gray image;
and performing linear detection based on the detection gray level image, and determining the gummed paper detection result of the pole piece to be detected according to the detected linear.
2. The method for detecting the gummed paper of the lithium battery pole piece according to claim 1, wherein the step of obtaining the target image of the pole piece to be detected further comprises the following steps:
the method comprises the steps of collecting an image of a pole piece to be detected through a camera device, and determining one or more ROI (region of interest) areas in the collected image to serve as target images of the pole piece to be detected.
3. The method for detecting the gummed paper of the lithium battery pole piece according to claim 1, wherein the plurality of color channels comprise an R color channel, a G color channel and a B color channel;
the grayscale statistical feature includes the grayscale standard deviation;
the step of calculating the grayscale statistical characteristics of the target image under each color channel respectively for the plurality of color channels of the target image, and determining 2 target color channels based on the calculated grayscale statistical characteristics further includes:
calculating the gray standard deviation of the channel image of the target image under each color channel; determining a color channel corresponding to the maximum value of the gray standard deviation corresponding to each color channel as a first color channel, and determining a color channel corresponding to the minimum value of the gray standard deviation corresponding to each color channel as a second color channel;
wherein the 2 target color channels include a first color channel and a second color channel.
4. The method for detecting the gummed paper of the lithium battery pole piece according to claim 3, wherein the step of performing preset image transformation on the images corresponding to the 2 target color channels in the target image to obtain a detection gray image further comprises:
calculating an average gray level image corresponding to the channel image under the first color channel and the channel image under the second color channel;
calculating the absolute value of the difference between the channel image under the first color channel and the average gray level image to be used as a first average difference image, and calculating the absolute value of the difference between the channel image under the second color channel and the average gray level value to be used as a second average difference image;
and summing the first average difference image and the second average difference image, and cutting a summation result to obtain a conversion image obtained by performing preset image conversion on the images corresponding to the 2 target color channels in the target image.
5. The method for detecting the gummed paper of the lithium battery pole piece according to claim 4, wherein the step of performing preset image transformation on the images corresponding to the 2 target color channels in the target image to obtain a detection gray image further comprises:
and amplifying the converted image, and determining the detection gray image based on the amplified converted image and the channel image under the first color channel.
6. The method for detecting the gummed paper of the lithium battery pole piece as claimed in claim 5, wherein the step of amplifying the converted image and determining the detection gray image based on the amplified converted image and the channel image under the first color channel further comprises:
according to the formula
Figure DEST_PATH_IMAGE002
Performing an enlargement process on the transformed image, wherein,
Figure DEST_PATH_IMAGE004
representing the transformed image after enlargement,
Figure DEST_PATH_IMAGE006
represents the maximum value of the grayscale averages of the channel images in a plurality of color channels,
Figure DEST_PATH_IMAGE008
represents the maximum value of the gray scale standard deviation of the channel images for a plurality of color channels,
Figure DEST_PATH_IMAGE010
representing a transformed image;
according to the formula
Figure DEST_PATH_IMAGE012
Determining a detection gray scale image, wherein,
Figure DEST_PATH_IMAGE014
a gray-scale image is represented for detection,
Figure DEST_PATH_IMAGE016
representing a channel image corresponding to the first color channel.
7. The method for detecting the gummed paper of the lithium battery pole piece according to claim 1, wherein the step of performing the line detection based on the detection gray image and determining the gummed paper detection result of the pole piece to be detected according to the detected line further comprises the following steps:
performing line detection on the detection gray level image based on a preset line detection algorithm, and determining one or more pieces of line information in the target image;
and calculating distance information between straight lines according to the detected one or more pieces of straight line information, and determining a gummed paper detection result of the pole piece to be detected according to the calculated distance information, wherein the gummed paper detection result comprises position information and size information of the gummed paper on the pole piece to be detected.
8. The utility model provides a detection apparatus for lithium-ion battery pole piece adhesive tape which characterized in that, the device includes:
the device comprises an image acquisition module, a detection module and a control module, wherein the image acquisition module is used for acquiring a target image of a pole piece to be detected, the pole piece to be detected is provided with adhesive paper, and the target image is a color image;
the characteristic statistical module is used for respectively calculating the gray scale statistical characteristics of the target image under each color channel aiming at a plurality of color channels of the target image, and determining 2 target color channels based on the calculated gray scale statistical characteristics;
the image transformation module is used for carrying out preset image transformation on the images corresponding to the 2 target color channels in the target image to obtain a detection gray image;
and the linear detection module is used for carrying out linear detection based on the detection gray level image and determining the gummed paper detection result of the pole piece to be detected according to the detected linear.
9. A computer device, characterized in that the computer device comprises a memory and a processor, the memory has an executable code, and when the executable code runs on the processor, the method for detecting the lithium battery pole piece gummed paper is realized according to any one of claims 1 to 7.
10. A computer-readable storage medium for storing a computer program for executing the method for detecting the lithium battery pole piece adhesive tape according to any one of claims 1 to 7.
CN202210939668.7A 2022-08-05 2022-08-05 Method, device and equipment for detecting lithium battery pole piece gummed paper and storage medium Active CN115063414B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210939668.7A CN115063414B (en) 2022-08-05 2022-08-05 Method, device and equipment for detecting lithium battery pole piece gummed paper and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210939668.7A CN115063414B (en) 2022-08-05 2022-08-05 Method, device and equipment for detecting lithium battery pole piece gummed paper and storage medium

Publications (2)

Publication Number Publication Date
CN115063414A true CN115063414A (en) 2022-09-16
CN115063414B CN115063414B (en) 2022-12-20

Family

ID=83208517

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210939668.7A Active CN115063414B (en) 2022-08-05 2022-08-05 Method, device and equipment for detecting lithium battery pole piece gummed paper and storage medium

Country Status (1)

Country Link
CN (1) CN115063414B (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120236133A1 (en) * 2011-03-18 2012-09-20 Andrew Charles Gallagher Producing enhanced images from anaglyph images
CN110100251A (en) * 2016-12-30 2019-08-06 华为技术有限公司 For handling the equipment, method and graphic user interface of document
CN111696072A (en) * 2020-04-23 2020-09-22 西安电子科技大学 Color image line detection method, color image line detection device, electronic device, and storage medium
CN112417993A (en) * 2020-11-02 2021-02-26 湖北亿咖通科技有限公司 Parking space line detection method for parking area and computer equipment
CN113538430A (en) * 2021-09-16 2021-10-22 深圳新视智科技术有限公司 Pole piece defect detection method, device, equipment and medium based on difference
CN114308709A (en) * 2021-12-28 2022-04-12 傲普(上海)新能源有限公司 Battery cell pole piece lamination alignment detection method

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120236133A1 (en) * 2011-03-18 2012-09-20 Andrew Charles Gallagher Producing enhanced images from anaglyph images
CN110100251A (en) * 2016-12-30 2019-08-06 华为技术有限公司 For handling the equipment, method and graphic user interface of document
CN111696072A (en) * 2020-04-23 2020-09-22 西安电子科技大学 Color image line detection method, color image line detection device, electronic device, and storage medium
CN112417993A (en) * 2020-11-02 2021-02-26 湖北亿咖通科技有限公司 Parking space line detection method for parking area and computer equipment
CN113538430A (en) * 2021-09-16 2021-10-22 深圳新视智科技术有限公司 Pole piece defect detection method, device, equipment and medium based on difference
CN114308709A (en) * 2021-12-28 2022-04-12 傲普(上海)新能源有限公司 Battery cell pole piece lamination alignment detection method

Also Published As

Publication number Publication date
CN115063414B (en) 2022-12-20

Similar Documents

Publication Publication Date Title
CN114764804B (en) Lithium battery pole piece defect detection method, device, equipment and storage medium
CN113538430B (en) Pole piece defect detection method, device, equipment and medium based on difference
Schnell et al. Data mining in lithium-ion battery cell production
US10663524B2 (en) Battery state estimating apparatus
CN114723942B (en) Method, device and equipment for detecting size of lithium battery pole piece and storage medium
JP5354480B2 (en) Fuel cell evaluation system
US11442113B2 (en) On-line estimation method of battery state of health in wide temperature range based on “standardized temperature”
CN105093114B (en) The combined estimation method and system of a kind of battery line modeling and state-of-charge
CN112883531B (en) Lithium ion battery data processing method, computer device and storage medium
KR101366585B1 (en) Electrode evaluation apparatus and electrode evaluation method
CN117280513A (en) Method and device for detecting defects of battery pole piece insulating coating and computer equipment
US20240243367A1 (en) Electrode position tracking system
CN115063414B (en) Method, device and equipment for detecting lithium battery pole piece gummed paper and storage medium
CN116543056A (en) Linear camera calibration and calibration method, device and storage medium
CN115600728A (en) Annual carbon emission estimation method and device for power battery
CN117173100B (en) Polymer lithium ion battery production control system and method thereof
CN116739997A (en) X-ray imaging-based online imaging analysis method for lithium battery
CN114859250B (en) Method and device for determining state of charge information of battery and electronic equipment
US20210123977A1 (en) Analyzing Electrical Impedance Measurements of an Electromechanical Battery
CN116680506B (en) Self-adaptive interval optimization incremental capacity curve number point statistical method and device
CN116359741B (en) Lithium battery safety detection method, device, computer equipment and storage medium
CN116298977B (en) Method and system for testing cycle performance of lithium battery
CN118604645A (en) Method for improving consistency and accuracy of capacity
US20240062336A1 (en) Correction method and apparatus for depth image, and method for welding inspection of shell assembly of battery
CN117907837A (en) Battery SOC and SOE joint estimation method based on Kalman filtering

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant