A battery recycling method and system based on machine vision

Abstract

The present application provides a battery recycling method and system based on machine vision. By obtaining the sample appearance data of each sample storage battery, further determining the noise interference domain and damage distribution domain of the corresponding sample storage battery, and obtaining the confidence defect characteristics of each sample storage battery according to each noise interference domain and the corresponding damage distribution domain; collecting the data of the battery to be tested, and extracting the appearance characteristics of the target waste storage battery from the data of the battery to be tested; determining the collaborative similarity of the shell damage between the target waste storage battery and each sample storage battery through the appearance characteristics and the confidence defect characteristics of each sample storage battery; determining the appearance defect level value of the target waste storage battery according to all the collaborative similarities, and classifying and recycling the target waste storage battery through the appearance defect level value. By adopting the solution of the present application, the accuracy of classifying and recycling waste batteries such as waste new energy vehicle power batteries or lithium batteries can be enhanced.

Description

Technical Field

[0001] The present application relates to the technical field of battery recycling. More specifically, the present application relates to a battery recycling method and system based on machine vision. Background Art

[0002] Battery recycling refers to the process of collecting, processing, and reusing waste batteries to reduce environmental pollution and resource waste. With the wide application of batteries in various fields such as electronic devices and new energy vehicles, the number of waste batteries has increased sharply. In order to ensure the steady development of battery recycling work, it is necessary to classify and recycle waste batteries and ensure the safety of batteries in each recycling process.

[0003] The existing methods for classifying and recycling waste batteries mainly rely on manual judgment. However, there is a subjective awareness in manually identifying battery defects, and different people will make different judgments on the damage degree of waste batteries due to different work experiences, which is difficult to reach a unified standard and has low efficiency. Although the existing intelligent waste battery classification and recycling can automatically identify, quickly classify, and process waste batteries through a unified standard, it is difficult to identify the small and numerous defects (such as slight depressions and oxidation discoloration, etc.) on the outer shell of waste batteries, resulting in large errors in defect detection of waste batteries, and thus the accuracy of waste battery classification and recycling is not high. Therefore, how to enhance the recognition ability of the defects on the outer shell of waste batteries in the process of intelligent waste battery classification and recycling, so as to improve the accuracy of waste battery classification and recycling has become a difficult problem faced by the industry. Summary of the Invention

[0004] The present application provides a battery recycling method and system based on machine vision, which can enhance the recognition ability of the defects on the outer shell of waste batteries in the process of intelligent waste battery classification and recycling, and improve the accuracy of waste battery classification and recycling.

[0005] In a first aspect, the present application provides a battery recycling method based on machine vision, including:

[0006] Obtain the sample appearance data of each sample storage battery in the sample storage battery group;

[0007] Determine the noise interference domain of the corresponding sample storage battery through the noise characteristics in each sample appearance data, determine the damage distribution domain of the corresponding sample storage battery through the damage characteristics in each sample appearance data, and then perform binary coverage on the defect contour of each sample storage battery according to the noise interference domain and the corresponding damage distribution domain of each sample storage battery to obtain the confidence defect characteristics of the outer shell of each sample storage battery;

[0008] Collect the battery parameters of the target waste storage battery, and then obtain the test battery data, and extract the appearance characteristics of the outer shell of the target waste storage battery from the test battery data;

[0009] Determine the collaborative similarity of shell damage between the target waste battery and each sample battery based on the appearance features and the confidence defect features of each sample battery shell;

[0010] Determine the appearance defect level value of the target waste battery according to all the collaborative similarities, and then classify and recycle the target waste battery through the appearance defect level value.

[0011] In some embodiments, determining the noise interference domain of the corresponding sample battery through the noise features in each sample appearance data specifically includes:

[0012] Determine the noise binary image of the corresponding sample battery according to each sample appearance data;

[0013] Extract noise features from all the noise binary images to obtain the noise features of each sample battery;

[0014] Determine the noise area of each noise feature;

[0015] Determine the noise interference domain of the corresponding sample battery according to each noise area.

[0016] In some embodiments, determining the damage distribution domain of the corresponding sample battery through the damage features in each sample appearance data specifically includes:

[0017] Determine the damage binary image of the corresponding sample battery according to each sample appearance data;

[0018] Extract damage features from all the damage binary images to obtain the damage features of each sample battery;

[0019] Determine the damage area of each damage feature;

[0020] Determine the damage distribution domain of the corresponding sample battery according to each damage area.

[0021] In some embodiments, extracting the appearance features of the target waste battery shell from the to-be-tested battery data specifically includes:

[0022] Obtain the appearance display diagram of the target waste battery from the to-be-tested battery data;

[0023] Determine the appearance binary diagram of the target waste battery according to the appearance display diagram;

[0024] Extract features from the appearance binary diagram to obtain the appearance features of the target waste battery shell.

[0025] In some embodiments, binarizing and covering the defect profile of each sample battery according to the noise interference domain and the corresponding damage distribution domain of each sample battery to obtain the confidence defect features of the outer shell of each sample battery specifically includes:

[0026] For each sample battery, obtain the noise interference domain and the damage distribution domain of the sample battery;

[0027] Determine the defect profile of the sample battery according to the noise interference domain and the damage distribution domain;

[0028] Extract features from the area covered by the defect profile in the binary image of the sample battery to obtain the confidence defect features of the outer shell of the sample battery, and then determine the confidence defect features of the outer shell of each sample battery.

[0029] In some embodiments, determining the collaborative similarity of the outer shell damage between the target waste battery and each sample battery through the appearance features and the confidence defect features of the outer shell of each sample battery specifically includes:

[0030] Determine the feature similarity domain through the appearance features and the confidence defect features of the outer shell of each sample battery;

[0031] Based on the feature similarity domain, determine the collaborative similarity of the outer shell damage between the target waste battery and each sample battery.

[0032] In some embodiments, the target waste battery is a waste power battery for new energy vehicles or a waste lithium battery.

[0033] In a second aspect, the present application provides a battery recycling system based on machine vision. The battery recycling system based on machine vision includes:

[0034] An acquisition module that acquires the sample appearance data of each sample battery in the sample battery group;

[0035] A processing module that determines the noise interference domain of the corresponding sample battery through the noise features in each sample appearance data, determines the damage distribution domain of the corresponding sample battery through the damage features in each sample appearance data, and then binarizes and covers the defect profile of each sample battery according to the noise interference domain and the corresponding damage distribution domain of each sample battery to obtain the confidence defect features of the outer shell of each sample battery;

[0036] The processing module is further configured to collect the battery parameters of the target waste battery, and then obtain the battery data to be measured, and extract the appearance features of the outer shell of the target waste battery from the battery data to be measured;

[0037] The processing module is further configured to determine the collaborative similarity of the shell damage between the target waste battery and each sample battery through the appearance features and the confidence defect features of each sample battery shell;

[0038] An execution module, configured to determine the appearance defect level value of the target waste battery according to all the collaborative similarities, and then classify and recycle the target waste battery through the appearance defect level value.

[0039] In a third aspect, the present application provides a computer device, which includes a memory and a processor. The memory stores code, and the processor is configured to obtain the code and execute the above-mentioned battery recycling method based on machine vision.

[0040] In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned battery recycling method based on machine vision.

[0041] The technical solutions provided by the disclosed embodiments of the present application have the following beneficial effects:

[0042] In the battery recycling method and system based on machine vision provided by the present application, first, the sample appearance data of each sample battery in the sample battery group is obtained; the noise interference domain of the corresponding sample battery is determined through the noise features in each sample appearance data, and the damage distribution domain of the corresponding sample battery is determined through the damage features in each sample appearance data. Then, according to the noise interference domain and the corresponding damage distribution domain of each sample battery, the defect contour of each sample battery is binary-covered to obtain the confidence defect features of each sample battery shell; the battery parameters of the target waste battery are collected, and then the data of the battery to be tested is obtained. The appearance features of the shell of the target waste battery are extracted from the data of the battery to be tested; the collaborative similarity of the shell damage between the target waste battery and each sample battery is determined through the appearance features and the confidence defect features of each sample battery shell; the appearance defect level value of the target waste battery is determined according to all the collaborative similarities, and then the target waste battery is classified and recycled through the appearance defect level value.

[0043] As can be seen, in this application, the target waste storage battery is classified and recycled through the appearance defect level value. First, the sample appearance data of each sample storage battery in the sample storage battery group is obtained. By using all the sample appearance data to determine the confidence defect features of each sample storage battery housing, a feature sequence used to describe the defects of the sample storage battery housing can be obtained. The feature sequence may include the contour perimeter, contour area, aspect ratio, convex hull area, and circularity of the defect. Furthermore, a detailed confidence defect feature database can be established, which helps to accurately identify the appearance defects of the target waste storage battery during detection, thereby improving the recognition accuracy. Second, the battery parameters of the target waste storage battery are collected to obtain the battery data to be measured, and the appearance features of the target waste storage battery housing are extracted from the battery data to be measured. Then, the collaborative similarity of the housing damage between the target waste storage battery and each sample storage battery is determined through the appearance features and the confidence defect features of each sample storage battery housing. A value describing the similarity between the target waste storage battery housing and the sample storage battery housing can be obtained. By comparing the similarity between the target waste storage battery housing and the sample storage battery housing, the damage degree between the two can be accurately matched, avoiding errors that may be caused by a single feature, thereby helping to identify the small and numerous defects (such as slight depressions and oxidation discoloration) on the waste battery housing. Finally, the appearance defect level value of the target waste storage battery is determined based on all the collaborative similarities, and then the target waste storage battery is classified and recycled through the appearance defect level value. In summary, this application can enhance the recognition ability of the defects of the waste battery housing during the intelligent waste battery classification and recycling process, thereby improving the accuracy of waste battery classification and recycling. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 is an exemplary flowchart of a battery recycling method based on machine vision according to some embodiments of the present application;

[0045] Figure 2 is an exemplary flowchart of determining a noise interference region according to some embodiments of the present application;

[0046] Figure 3 is an exemplary flowchart of determining an appearance defect level value according to some embodiments of the present application;

[0047] Figure 4 is a schematic diagram of exemplary hardware and / or software of a battery recycling system based on machine vision according to some embodiments of the present application;

[0048] Figure 5 is a schematic diagram of the structure of a computer device for implementing a battery recycling method based on machine vision according to some embodiments of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0049] The embodiment of the present application provides a battery recycling method and system based on machine vision, the core of which is to obtain sample appearance data of each sample battery in a sample battery group; then determine the noise interference domain and damage distribution domain of the corresponding sample battery, and obtain the confidence defect feature of each sample battery according to each noise interference domain and the corresponding damage distribution domain; collect test battery data, and extract the appearance features of the target waste battery from the test battery data; determine the collaborative similarity of shell damage between the target waste battery and each sample battery through the appearance features and the confidence defect features of each sample battery; determine the appearance defect grade value of the target waste battery according to all the collaborative similarities, and then classify and recycle the target waste battery according to the appearance defect grade value, which can enhance the recognition ability of waste battery shell defects in the intelligent waste battery classification and recycling process, thereby improving the accuracy of waste battery classification and recycling.

[0050] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. Figure 1 , which is an exemplary flow chart of a battery recycling method based on machine vision according to some embodiments of the present application. The battery recycling method 100 based on machine vision mainly includes the following steps:

[0051] In step 101, sample appearance data of each sample storage battery in a sample storage battery group is obtained.

[0052] It should be noted that the sample appearance data in the present application is an appearance display image of the sample battery. As a preferred embodiment, the sample appearance data of each sample battery in the sample battery group in the present application can be obtained in the following manner, namely: first use the robot's built-in camera to photograph the outer shell of each sample battery in the sample battery group, obtain the appearance display image of the outer shell of each sample battery, and then use each appearance display image as the sample appearance data of the corresponding sample battery, wherein the sample battery group is a collection of sample batteries with different types of damage to the outer shell, which may include sample batteries with deformed outer shells, sample batteries with damaged outer shells, sample batteries with corroded outer shells, sample batteries with traces of fire on the outer shells, and sample batteries with traces of water immersion on the outer shells. In addition, the robot used can be selected according to the specific situation. For example, the JAKAZu5 robot is used in this application, and the type of robot is not specifically limited here.

[0053] In step 102, the noise interference domain of the corresponding sample battery is determined through the noise features in each sample appearance data, and the damage distribution domain of the corresponding sample battery is determined through the damage features in each sample appearance data. Then, based on the noise interference domain and the corresponding damage distribution domain of each sample battery, a coverage check is performed on the binary image of each sample battery to obtain the confidence defect features of the outer shell of each sample battery.

[0054] In some embodiments, referring to Figure 2 , this figure is an exemplary flowchart for determining the noise interference domain according to some embodiments of the present application. The determination of the noise interference domain of the corresponding sample battery through the noise features in each sample appearance data in the present application can be implemented by the following steps:

[0055] In step 1021, the noise binary image of the corresponding sample battery is determined according to each sample appearance data;

[0056] In step 1022, noise feature extraction is performed on all the noise binary images to obtain the noise features of each sample battery;

[0057] In step 1023, the noise area of each noise feature is determined;

[0058] In step 1024, the noise interference domain of the corresponding sample battery is determined according to each noise area.

[0059] It should be noted that in the present application, the noise interference domain is the noise area with noise in the binary image, and the noise in the binary image can be removed through this noise interference domain; the noise binary image refers to a grayscale image in which the value of each pixel has only two possibilities: black (pixel value is 0) or white (pixel value is 255) after processing the appearance display image of the sample battery; noise feature extraction is a means of extracting noise features in an image, and the noise feature is the set composed of all noise areas in the binary image; the noise area represents a parameter indicating the proportion of noise in the binary image. The larger the noise area, the more the proportion of noise in the corresponding binary image.

[0060] In specific implementation, the noise binary image of the corresponding sample battery can be determined according to the appearance data of each sample by the following method: First, select a sample battery, obtain the appearance data of the sample battery, and obtain the RGB values of all pixel points in the appearance display map corresponding to the appearance data. Subsequently, extract the components of the RGB value of each pixel point on the red, green, and blue channels, and add 0.299 times the component on the red channel, 0.587 times the component on the green channel, and 0.144 times the component on the blue channel. The obtained sum value is used as the gray value of the corresponding pixel point. Then, form an image with the gray values of all pixel points, and use this image as the gray image corresponding to the appearance data of the sample. Then, set the pixel points with pixel values greater than a preset fixed threshold (default is 128) in the gray image to white (pixel value is 255), and set the pixel points with pixel values less than the preset fixed threshold to black (pixel value is 0). Thus, a new image is obtained, and this new image is used as the noise binary image of the sample battery. Finally, continue to determine the noise binary images of the remaining sample batteries.

[0061] It should be noted that in this application, since the outer shell of the target waste battery is photographed indoors and the lighting conditions are stable and consistent, the fixed threshold can be directly set to the intermediate value 128 of the white pixel value (255) and the black pixel value (0). In other embodiments, for example, when the outer shell of the target waste battery is photographed outdoors and the lighting conditions change with the sunshine time, the histogram analysis method in the prior art can also be used to set the fixed threshold in real time.

[0062] In addition, in specific implementation, for all noise binary images, noise feature extraction is performed to obtain the noise features of each sample storage battery, which can be implemented in the following manner: Select a noise binary image of a sample storage battery. First, traverse each pixel point in this noise binary image from left to right and from top to bottom. If the pixel value of the pixel point is 255, then check the adjacent pixel points above and to the left of this pixel point. If the adjacent pixel point of this pixel point has been marked, then assign the same label as the adjacent pixel point to this pixel point. If the adjacent pixel point of this pixel point has not been marked, then assign a new label to this pixel point (for example, assign label 1 to this pixel point). Subsequently, traverse each pixel point in this noise binary image from left to right and from top to bottom again, connect the pixel points with the same label to obtain multiple connected regions, and count the total number of pixel points in each connected region. Take the total number of pixel points counted as the area of this connected region. Then, preset an area threshold, and use the set composed of all connected regions with an area smaller than this area threshold as the noise feature of this noise binary image. Finally, repeat the above steps to continue obtaining the noise features of the noise binary images of the remaining sample storage batteries, that is, realize noise feature extraction for all noise binary images; among them, the value of the area threshold can be preset according to specific situations. For example, in this application, considering that certain accuracy will be lost during the binarization process of the image, resulting in the enlargement of the area of the noise region in the image, the area threshold is preset to 5, and only the connected regions with an area smaller than 5 will be set as the noise regions. In other embodiments, the area threshold can also be preset to other values according to different image processing methods, which will not be specifically limited here; The noise area of each noise feature can be determined in the following manner: Use the set composed of the regional areas of all noise regions in each noise feature as the noise area of this noise feature; Determining the noise interference domain of the corresponding sample storage battery according to each noise area can be implemented in the following manner: First, calculate the average value of all regional areas (i.e., the area of the noise) in this noise area, and round down the obtained average value to get an integer A. Subsequently, construct a matrix of size, and the values of all elements in the matrix are 1. Finally, use the obtained matrix as the noise interference domain of this sample storage battery. Finally, repeat the above steps to obtain the noise interference domains of the remaining sample storage batteries.

[0063] In some embodiments, the damage distribution domain of the corresponding sample storage battery can be determined through the damage features in each sample appearance data, which can be implemented by the following steps:

[0064] Determine the damage binary image of the corresponding sample storage battery according to each sample appearance data;

[0065] Perform damage feature extraction on all damage binary images to obtain the damage features of each sample storage battery;

[0066] Determine the damaged area of each damaged feature;

[0067] Determine the damaged distribution domain of the corresponding sample battery according to each damaged area.

[0068] It should be noted that in this application, the damaged distribution domain is the damaged area covered by small defects in the binary image, and the small defects in the binary image can be repaired through this damaged distribution domain; the damaged binary image refers to a grayscale image in which each pixel value has only two possibilities, black (pixel value is 0) or white (pixel value is 255), after processing the appearance display image of the sample battery. Damaged feature extraction is a means of extracting damaged features in an image, and the damaged features are a set that includes all damaged areas in the binary image.

[0069] When specifically implemented, determining the damaged binary image of the corresponding sample battery according to each sample appearance data can be achieved by the following method: First, select a sample appearance data, obtain the RGB values of all pixel points in the appearance display image corresponding to this sample appearance data, and then extract the components of the RGB value of each pixel point on the red, green, and blue channels, and add 0.299 times the component on the red channel, 0.587 times the component on the green channel, and 0.144 times the component on the blue channel. The obtained sum value is used as the grayscale value of the corresponding pixel point. Then, form an image with the grayscale values of all pixel points, and use this image as the grayscale image corresponding to this sample appearance data. Then, set the pixel points with pixel values greater than a preset fixed threshold (default is 128) in this grayscale image to white (pixel value is 255), and set the pixel points with pixel values less than the preset fixed threshold to black (pixel value is 0), thus obtaining a new image. Then, use this new image as the damaged binary image of the sample battery corresponding to this sample appearance data. Finally, continue to determine the damaged binary images of the sample batteries corresponding to the remaining sample appearance data.

[0070] It should be noted that in this application, since the outer shell of the target waste battery is photographed indoors and the lighting conditions are stable and consistent, the fixed threshold can be directly set to the intermediate value 128 of the white pixel value (255) and the black pixel value (0). In other embodiments, for example, when photographing the outer shell of the target waste battery outdoors and the lighting conditions vary with the sunshine time, the histogram analysis method in the prior art can also be used to set the fixed threshold in real time.

[0071] In addition, in specific implementation, for all damaged binary images, damaged feature extraction is performed to obtain the damaged features of each sample battery, which can be implemented in the following manner: select a damaged binary image of a sample battery, first traverse each pixel point in the damaged binary image from left to right and from top to bottom. If the pixel value of the pixel point is 255, then check the adjacent pixel points above and to the left of the pixel point. If the adjacent pixel points of the pixel point have been marked, then assign the same label to the pixel point as the adjacent pixel points. If the adjacent pixel points of the pixel point have not been marked, then assign a new label to the pixel point (for example, assign label 1 to the pixel point). Subsequently, traverse each pixel point in the damaged binary image from left to right and from top to bottom again, connect the pixel points with the same label to obtain multiple connected regions, and count the number of holes existing inside each connected region. Take the counted number of holes as the number of holes of the connected region. Then preset a hole threshold, regard the connected regions with the number of holes greater than the hole threshold as damaged regions and form a set, and then take this set as the damaged feature of the damaged binary image. Finally, repeat the above steps to continue obtaining the damaged features of the damaged binary images of the remaining sample batteries, that is, implement damaged feature extraction for all damaged binary images; among them, the value of the hole threshold can be preset according to specific circumstances. For example, in this application, considering that certain precision will be lost during the binarization process of the image, resulting in holes that may actually not exist in the image, the hole threshold is preset to 3, and only the regions with the number of holes greater than 3 will be marked as damaged regions. In other embodiments, the hole threshold can also be preset to other values according to different image processing methods, which is not specifically limited here.

[0072] It should be noted that in this application, the damaged area is the area of all damaged regions in the damaged feature, and the area of the damaged region can be the total value of the pixel points within the damaged region.

[0073] In specific implementation, the damaged distribution domain of the corresponding sample battery can be determined according to each damaged area in the following manner: first, calculate the average value of the areas of all regions in the damaged area, and round down the obtained average value to get an integer B. Subsequently, construct a matrix of size, and the values of all elements in the matrix are 1. Finally, take the obtained matrix as the damaged distribution domain of the sample battery, and finally continue to determine the damaged distribution domains of the remaining sample batteries.

[0074] In some embodiments, the confidence defect features of the outer shell of each sample battery can be obtained by performing binary coverage on the defect contour of each sample battery according to the noise interference domain and the corresponding damaged distribution domain of each sample battery, which can be implemented by the following steps:

[0075] For each sample battery, obtain the noise interference domain and the damage distribution domain of the sample battery;

[0076] Determine the defect contour of the sample battery according to the noise interference domain and the damage distribution domain;

[0077] Extract features from the area covered by the defect contour in the binary image of the sample battery to obtain the confidence defect features of the sample battery housing, and further determine the confidence defect features of each sample battery housing.

[0078] It should be noted that in this application, the confidence defect feature is a feature sequence used to describe the defects of the sample battery housing. The feature sequence may include the contour perimeter, contour area, aspect ratio, convex hull area, and circularity of the defect; the primary inspection image and the secondary inspection image are intermediate process images obtained when performing coverage inspection on the binary image of the sample battery and have no practical meaning; binary coverage is a means of extracting features from the area covered by the defect contour in the binary image of the sample battery, and the defect contour refers to the contour of all defect areas on the sample battery housing.

[0079] Specifically, in implementation, first, for each sample battery, obtain the noise interference domain and the damage distribution domain of the sample battery; second, determine the defect contour of the sample battery according to the noise interference domain and the damage distribution domain; finally, extract features from the area covered by the defect contour in the binary image of the sample battery, and then obtain the confidence defect features of each sample battery housing. The following method can be used to achieve this, that is: first select a sample battery, determine the defect contour of this sample battery, and then calculate the contour perimeter of this defect contour (that is, the sum of the distances between each pair of adjacent pixel points on this defect contour), the contour area (that is, the total number of pixel points inside and on the defect area corresponding to this defect contour), the aspect ratio (that is, the quotient obtained by dividing the width of the bounding box of this defect contour by the height of the bounding box, where the bounding box is a rectangle with the smallest area that completely encloses this defect contour, the width of the bounding box is the total number of pixel points between the right boundary and the left boundary of the bounding box, and the height of the bounding box is the total number of pixel points between the upper boundary and the lower boundary of the bounding box), the convex hull area (that is, the area of the smallest convex polygon that can completely enclose this defect contour), and the circularity (that is, the quotient obtained by multiplying the contour area of this defect contour by and then dividing by the square of the perimeter), and then use the obtained contour perimeter, contour area, aspect ratio, convex hull area, and circularity as the features of this defect contour respectively, form a sequence in the order of acquisition, and use this sequence as the confidence defect feature of this sample battery housing. Finally, continue to obtain the confidence defect features of the remaining sample battery housings; thus, binary coverage of the defect contour of each sample battery is achieved.

[0080] In the above embodiments, the defect profile of the sample storage battery can be determined according to the noise interference domain and the damage distribution domain by the following steps:

[0081] Check each pixel point in the binary image of the sample storage battery according to the noise interference domain of the sample storage battery, and transform the gray value of the corresponding pixel point according to the check result, so as to obtain a primary inspection image of the sample storage battery;

[0082] Check each pixel point in the primary inspection image according to the damage distribution domain of the sample storage battery, and transform the gray value of the corresponding pixel point according to the check result, so as to obtain a secondary inspection image of the sample storage battery;

[0083] Determine the defect profile of the sample storage battery according to the secondary inspection image.

[0084] Specifically, when implementing, checking each pixel point in the binary image of the sample storage battery according to the noise interference domain of the sample storage battery, and transforming the gray value of the corresponding pixel point according to the check result, so as to obtain a primary inspection image of the sample storage battery, can be implemented in the following way, that is: first determine the noise interference domain and the binary image of this sample storage battery, then align the center of the noise interference domain with each pixel point in this binary image. If all the pixel points covered by this noise interference domain are white, then this pixel point remains white. If there is a black pixel point among all the pixel points covered by this noise interference domain, then this pixel point is changed to black to obtain a new image. Finally, this new image is used as the primary inspection image of this sample storage battery; checking each pixel point in the primary inspection image according to the damage distribution domain of the sample storage battery, and transforming the gray value of the corresponding pixel point according to the check result, so as to obtain a secondary inspection image of the sample storage battery, can be implemented in the following way, that is: first determine the damage distribution domain and the binary image of this sample storage battery, then align the center of the damage distribution domain with each pixel point in this binary image. If all the pixel points covered by this damage distribution domain are white, then this pixel point remains white. If there is a black pixel point among all the pixel points covered by this damage distribution domain, then this pixel point is changed to black to obtain a new image. Finally, this new image is used as the primary inspection image of this sample storage battery.

[0085] In addition, specifically, when implementing, determining the defect profile of the sample storage battery according to the secondary inspection image can be implemented in the following way, that is: first traverse all the pixel points in this secondary inspection image from top to bottom and from left to right, determine the connected regions in this secondary inspection image, and use these connected regions as the defect regions of the shell of this sample storage battery. Then, use the contour formed by the outermost pixel points of this defect region as the defect profile of this sample storage battery.

[0086] In step 103, battery parameters of the target used waste battery are collected, and then the battery data to be measured is obtained. Appearance features of the shell of the target used waste battery are extracted from the battery data to be measured.

[0087] It should be noted that in this application, the target used waste battery can be a used power battery of a new energy vehicle, a used lithium battery, etc., and no specific limitation is made here. The battery parameters can include the insulation resistance value, temperature value, cell voltage value, cell current value, and appearance display diagram of the battery. In other embodiments, the battery parameters can also include other battery parameters related to the aging condition of the target used waste battery, and no limitation is made here. Specifically, existing tools (such as an insulation tester and a JAKAZu5 robot) can be used to detect all battery parameters of the target used waste battery, and the set of all battery parameters is used as the battery data to be measured.

[0088] In some embodiments, the extraction of the appearance features of the shell of the target used waste battery from the battery data to be measured can be implemented by the following steps:

[0089] Obtain the appearance display diagram of the target used waste battery from the battery data to be measured;

[0090] Determine the appearance binary diagram of the target used waste battery according to the appearance display diagram;

[0091] Extract features from the appearance binary diagram to obtain the appearance features of the shell of the target used waste battery.

[0092] It should be noted that in this application, the appearance features are characteristic quantities used to describe the defects of the shell of the target used waste battery; the appearance binary diagram is a grayscale image used to describe the appearance color distribution in the target used waste battery.

[0093] Specifically, the determination of the appearance binary diagram of the target used waste battery according to the appearance display diagram can be implemented in the following manner, that is: obtain the RGB values of all pixel points in the appearance display diagram, then extract the components of the RGB value of each pixel point on the three channels of red, green, and blue, and add 0.299 times the component on the red channel, 0.587 times the component on the green channel, and 0.144 times the component on the blue channel. The obtained sum value is used as the grayscale value of the corresponding pixel point. Then, the grayscale values of all pixel points are combined into an image, and this image is used as the grayscale image of the appearance display diagram. Then, set the pixel points with pixel values greater than a preset fixed threshold in the grayscale image to white (pixel value 255), and set the pixel points with pixel values less than the preset fixed threshold to black (pixel value 0). Thus, a new image is obtained, and this new image is used as the appearance binary diagram of the target used waste battery.

[0094] It should be noted that in this application, since the outer shell of the target used waste battery is photographed indoors and the lighting conditions are stable and consistent, the fixed threshold can be directly set to the intermediate value 128 between the white pixel value (255) and the black pixel value (0). In other embodiments, for example, when the outer shell of the target used waste battery is photographed outdoors and the lighting conditions vary with the sunshine time, the histogram analysis method in the prior art can also be used to set the fixed threshold in real time.

[0095] In addition, in specific implementation, the feature extraction of the appearance binary image to obtain the appearance features of the outer shell of the target used waste battery can be realized in the following way: First, traverse each pixel point in the appearance binary image from left to right and from top to bottom. If the pixel value of the pixel point is 255, check the adjacent pixel points above and to the left of this pixel point. If the adjacent pixel points of this pixel point have been marked, assign the same label as the adjacent pixel points to this pixel point. If the adjacent pixel points of this pixel point have not been marked, assign a new label to this pixel point (for example, assign label 1 to this pixel point). Subsequently, traverse each pixel point in the appearance binary image from left to right and from top to bottom again, connect the pixel points with the same label to obtain multiple connected regions, and regard the obtained multiple connected regions as the defect regions of the outer shell of the target used waste battery respectively. Then, calculate the contour perimeter (that is, the sum of the distances between each pair of adjacent pixel points on the contour), the contour area (that is, the total number of pixel points inside and on the contour of this defect region), the aspect ratio (that is, the quotient obtained by dividing the width of the bounding box of this contour by the height of the bounding box, where the bounding box is a rectangle with the smallest area that completely encloses this contour, the width of the bounding box is the total number of pixel points between the right boundary and the left boundary of the bounding box, and the height of the bounding box is the total number of pixel points between the upper boundary and the lower boundary of the bounding box), the convex hull area (that is, the area of the smallest convex polygon that can completely enclose this contour), and the circularity (that is, the quotient obtained by multiplying the contour area of this contour by 4π and then dividing by the square of the perimeter) of the contour surrounded by the outermost pixel points of each defect region. Subsequently, form a sequence of the contour perimeter, contour area, aspect ratio, convex hull area, and circularity of each contour in the order of acquisition, and regard the obtained sequence as the features of each defect region. Finally, sort all the features in ascending order according to the contour area to obtain a feature sequence, and regard this feature sequence as the appearance features of the outer shell of the target used waste battery.

[0096] In step 104, the collaborative similarity of the shell damage between the target used waste battery and each sample battery is determined through the appearance features and the confidence defect features of each sample battery shell.

[0097] In some embodiments, the co - similarity of the shell damage between the target waste battery and each sample battery can be determined by the appearance features and the confidence defect features of each sample battery shell through the following steps:

[0098] Determine the feature similarity domain through the appearance features and the confidence defect features of each sample battery shell;

[0099] Based on the feature similarity domain, determine the co - similarity of the shell damage between the target waste battery and each sample battery.

[0100] It should be noted that in this application, the co - similarity is a value describing the similarity degree of shell damage between the target waste battery shell and the shell of this sample battery. The larger the co - similarity, the more similar the shell damage degree of the target waste battery shell and the shell of this sample battery; the feature similarity domain is a matrix representing the similarity between the appearance features of the battery data to be measured and the confidence defect features of the sample battery shell.

[0101] Specifically, when implementing, determining the feature similarity domain through the appearance features and the confidence defect features of each sample battery shell can be achieved in the following way: first, sort the confidence defect features of each sample battery shell in ascending order according to the contour area, then calculate the similarity between the features of each defect area in the appearance features and the confidence defect features of each sample battery shell, and fill all the obtained similarities into a matrix to obtain a similarity matrix. The element in the i - th row and j - th column of this similarity matrix represents the similarity between the features of the i - th defect area in the appearance features and the confidence defect features of the j - th sample battery shell, and use this similarity matrix as the feature similarity domain. Among them, calculating the similarity between the features of each defect area in the appearance features and the confidence defect features of each sample battery shell can be achieved by calculating the dot product between the two features; determining the co - similarity of the shell damage between the target waste battery and each sample battery based on the feature similarity domain can be achieved in the following way: first, select a sample battery, find the similarity between the confidence defect features of the shell of this sample battery and the features of all defect areas in the appearance features of the target waste battery in this feature similarity domain, then calculate the average value of all the similarities, and use the obtained average value as the co - similarity of the shell damage between the target waste battery and this sample battery. Finally, continue to determine the co - similarity of the shell damage between the target waste battery and the remaining sample batteries.

[0102] In step 105, determine the appearance defect grade value of the target waste battery according to all the co - similarities, and then classify and recycle the target waste battery through the appearance defect grade value.

[0103] In some embodiments, refer to Figure 3 , which is an exemplary flowchart for determining the label hierarchy path according to some embodiments of the present application. The steps for determining the appearance defect level value of the target used battery according to all collaborative similarity degrees in the present application can be implemented as follows:

[0104] In step 1051, determine the confidence cost of each sample battery in the sample battery group through all collaborative similarity degrees;

[0105] In step 1052, determine the appearance defect level value of the target used battery according to all the confidence costs.

[0106] It should be noted that in the present application, the appearance defect level value is a parameter describing the damage degree of the shell of the target used battery. The larger the appearance defect level value, the more serious the damage degree of the shell of the target used battery; the confidence cost is a probability value describing whether there is a defect in the shell of the target used battery that is the same as the shell of this sample battery. The larger the confidence cost, the greater the probability that there is a defect in the shell of the target used battery that is the same as the shell of this sample battery.

[0107] Specifically, when implemented, determining the confidence cost of each sample battery in the sample battery group through all collaborative similarity degrees can be achieved in the following manner, that is: take the sum of the powers of the natural constants of all collaborative similarity degrees as the similarity sum. Subsequently, select a sample battery in the sample battery group, determine the collaborative similarity corresponding to this sample battery, and take this collaborative similarity as the power of the natural constant. The obtained value is divided by the value of the similarity sum to obtain a quotient, and then take the obtained quotient as the confidence cost of this sample battery. Finally, continue to determine the confidence costs of the remaining sample batteries in the sample battery group; determining the appearance defect level value of the target used battery according to all the confidence costs can be achieved in the following manner, that is: first preset a confidence threshold. Subsequently, select the confidence costs with values greater than this confidence threshold among all the confidence costs, and determine the total number of the selected confidence costs. Finally, take this total number as the appearance defect level value of the appearance damage of the target used battery. Among them, the value of the confidence threshold can be preset according to the actual situation. For example, in the present application, since the confidence cost is a probability value with a value range between 0 and 1, the larger the confidence cost, the greater the probability that there is a defect in the shell of the target used battery that is the same as the shell of the sample battery. At the same time, considering the area of the shell of the target used battery and the complexity of the existing defects, the confidence threshold can be preset to 0.7. In other embodiments, the confidence threshold can also be preset to other values between 0 and 1. For example, when the area of the used battery is small and the complexity of the existing defects is not high, the value of the confidence threshold can also be preset to 0.9. There is no specific limitation here.

[0108] In some embodiments, the classified recycling of the target waste storage battery according to the appearance defect level value can be achieved by the following steps:

[0109] Determine the cell defect amount of the internal cell of the target waste storage battery based on the cell parameter data in the battery data to be measured;

[0110] Determine the battery recycling grade of the target waste storage battery according to the cell defect amount and the appearance defect level value;

[0111] Classify and recycle the target waste storage battery according to the battery recycling grade.

[0112] It should be noted that in this application, the battery recycling grade is the recycling state of the target waste storage battery obtained after determining the safety state of the target waste storage battery according to the appearance and battery working conditions of the target waste storage battery. During battery recycling, the operation requirements of the target waste storage batteries belonging to different battery recycling grades need to be treated differently in terms of packaging, transportation, warehousing, etc. to ensure the safety of the recycling link; the cell defect amount is a parameter describing the damage degree of the internal cell of the target waste storage battery. The larger the cell defect amount, the more serious the damage degree of the internal cell of the target waste storage battery; the cell parameter data refers to the specific values of the key parameters that can affect the performance of the internal cell of the target waste storage battery. In some preferred embodiments, the cell parameter data can be the insulation resistance, temperature, cell voltage, and cell current of the battery. In other embodiments, the cell parameter data can also be other key parameters in the storage battery that can affect the performance of the internal cell of the target waste storage battery, which is not limited here.

[0113] Preferably, in some embodiments, determining the cell defect amount of the internal cell of the target waste storage battery based on the cell parameter data in the battery data to be measured can be achieved by the following steps:

[0114] Determine the deviation degree of each key parameter in the internal cell of the target waste storage battery according to the cell parameter data;

[0115] Determine the cell defect amount of the internal cell of the target waste storage battery through all the deviation degrees.

[0116] It should be noted that in this application, the deviation degree is a parameter used to measure the difference degree between the internal cell of the target waste storage battery and the internal cell of the normal target waste storage battery. The larger the deviation degree, the greater the difference in the numerical value of this key parameter between the target waste storage battery and the normal waste storage battery, and the higher the defect grade of the target waste storage battery.

[0117] In specific implementation, to determine the deviation degree of each key parameter in the cells of the target waste battery according to the cell parameter data, the following method can be adopted, that is: First, select a key parameter in the cells of the target waste battery. The standard value of the same type of battery as the target waste battery in this key parameter can be queried in the user manual of the target waste battery. Then, obtain the parameter value corresponding to this key parameter from the cell parameter data, and take the difference between this parameter value and the standard value as the deviation degree of this key parameter. If the standard value of this key parameter is an interval, take the difference between this parameter value and the upper bound of the corresponding interval of the standard value as the deviation degree of this key parameter. Repeat the above steps to continue obtaining the deviation degrees of the remaining key parameters in the cell parameter data; To determine the cell defect amount of the cells in the target waste battery through all the deviation degrees, the following method can be adopted, that is: The average value of all the deviation degrees can be used as the cell defect amount of the cells in the target waste battery; To determine the cell defect amount of the cells in the target waste battery through all the deviation degrees, the following method can be adopted, that is: Calculate the average value of all the deviation degrees, and take this average value as the cell defect amount of the cells in the target waste battery.

[0118] In specific implementation, to determine the battery recycling grade of the target waste battery according to the cell defect amount and the appearance defect grade value, the following method can be adopted, that is: If both the cell defect amount and the appearance defect grade value of the target waste battery are zero, set the battery recycling grade of the target waste battery to grade A. If the cell defect amount of the target waste battery is zero while the appearance defect grade value is not zero, set the battery recycling grade of the target waste battery to grade B. If both the cell defect amount and the appearance defect grade value of the target waste battery are not zero, set the battery recycling grade of the target waste battery to grade C; To classify and recycle the target waste battery according to the battery recycling grade, the following method can be adopted, that is: Use a robot to package the target waste battery according to the battery recycling grade of the target waste battery, and put the target waste battery into a transport vehicle corresponding to the battery recycling grade, waiting for transportation and subsequent processing. Among them, the requirements for packaging and transportation of waste target waste batteries with different battery recycling grades are different. For example, grade A waste batteries should use anti-static and moisture-proof packaging materials to avoid short circuits and overheating, and avoid extrusion and vibration during transportation. Grade B waste batteries should be packaged in leak-proof and anti-corrosive containers to avoid electrolyte leakage, and prevent the battery from tipping and breaking during transportation to avoid electrolyte leakage. Each grade C waste battery should be individually packaged in a plastic bag or plastic film and placed in a leak-proof plastic box or metal box for separate storage, and also prevent the battery from tipping and breaking during transportation to avoid electrolyte leakage. In addition, the robot can be selected according to specific circumstances. For example, the JAKAZu5 robot is used in this application.

[0119] In addition, on the other hand of the present application, in some embodiments, the present application provides a battery recycling system based on machine vision. Refer to Figure 4 , which is a schematic diagram of exemplary hardware and / or software of the battery recycling system based on machine vision shown in some embodiments of the present application. The battery recycling system 400 based on machine vision includes: a collection module 401, a processing module 402, and an execution module 403, which are described as follows:

[0120] The collection module 401. In the present application, the collection module 401 is mainly used to obtain the sample appearance data of each sample storage battery in the sample storage battery group;

[0121] The processing module 402. In the present application, the processing module 402 is mainly used to determine the noise interference domain of the corresponding sample storage battery through the noise characteristics in each sample appearance data, determine the damage distribution domain of the corresponding sample storage battery through the damage characteristics in each sample appearance data, and then perform binary coverage on the defect contour of each sample storage battery according to the noise interference domain and the corresponding damage distribution domain of each sample storage battery to obtain the confidence defect characteristics of the outer shell of each sample storage battery;

[0122] It should be noted that the processing module 402 in the present application is also used to collect the battery parameters of the target waste storage battery, and then obtain the battery data to be measured, and extract the appearance characteristics of the outer shell of the target waste storage battery from the battery data to be measured;

[0123] In addition, it should be noted that the processing module 402 in the present application is also used to determine the collaborative similarity of the outer shell damage between the target waste storage battery and each sample storage battery through the appearance characteristics and the confidence defect characteristics of the outer shell of each sample storage battery;

[0124] The execution module 403. In the present application, the execution module 403 is mainly used to determine the appearance defect grade value of the target waste storage battery according to all the collaborative similarities, and then classify and recycle the target waste storage battery through the appearance defect grade value.

[0125] In addition, the present application also provides a computer device, which includes a memory and a processor. The memory stores code, and the processor is configured to obtain the code and execute the above-mentioned battery recycling method based on machine vision.

[0126] In some embodiments, refer to Figure 5 , which is a schematic structural diagram of a computer device for implementing the battery recycling method based on machine vision shown in some embodiments of the present application. The battery recycling method based on machine vision in the above embodiments can be passed through Figure 5It is implemented by the computer device shown. The computer device 500 includes at least one processor 501, a communication bus 502, a memory 503, and at least one communication interface 504.

[0127] The processor 501 can be a general - purpose central processing unit (CPU) or an application - specific integrated circuit (ASIC).

[0128] The communication bus 502 can be used to transfer information between the above - mentioned components.

[0129] The memory 503 can be a read - only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read - only memory (EEPROM), a compact disc read - only memory (CD ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital versatile discs, Blu - ray discs, etc.), magnetic disks or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to this. The memory 503 can exist independently and be connected to the processor 501 through the communication bus 502. The memory 503 can also be integrated with the processor 501.

[0130] Among them, the memory 503 is used to store the program code for executing the solution of this application and is controlled by the processor 501 for execution. The processor 501 is used to execute the program code stored in the memory 503. The program code can include one or more software modules. The battery recycling method based on machine vision in the above - mentioned embodiments can be implemented by one or more software modules in the program code in the processor 501 and the memory 503.

[0131] The communication interface 504, using any device such as a transceiver, is used to communicate with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0132] In a specific implementation, as an embodiment, the computer device may include multiple processors, and each of these processors may be a single-core (single CPU) processor or a multi-core (multi CPU) processor. The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions).

[0133] The above-mentioned computer device may be a general-purpose computer device or a special-purpose computer device. In a specific implementation, the computer device may be a desktop computer, a laptop computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. The embodiments of the present application do not limit the type of the computer device.

[0134] In addition, the present application also provides a computer-readable storage medium, and the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned battery recycling method based on machine vision is implemented.

[0135] Although the preferred embodiments of the present application have been described, those skilled in the art can make additional changes and modifications to these embodiments once they learn the basic creative concept. Therefore, the appended claims are intended to be construed as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0136] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application also intends to include these changes and modifications.

Claims

1. A battery recycling method based on machine vision, characterized in that: The steps include: Acquire sample appearance data of each sample battery in the sample battery group; The noise interference domain of the corresponding sample battery is determined by the noise characteristics in the appearance data of each sample, and the damage distribution domain of the corresponding sample battery is determined by the damage characteristics in the appearance data of each sample, and then the defect contour of each sample battery is binarized and covered according to the noise interference domain and the corresponding damage distribution domain of each sample battery to obtain the confidence defect feature of the shell of each sample battery; Collecting battery parameters of the target used battery to obtain test battery data, and extracting appearance features of the target used battery shell from the test battery data; Determine the collaborative similarity of shell damage between the target waste battery and each sample battery through the appearance features and the confidence defect features of each sample battery shell; Determine the appearance defect grade value of the target waste battery according to all the collaborative similarities, and then classify and recycle the target waste battery according to the appearance defect grade value; The collaborative similarity is a value describing the similarity of the shell damage between the target waste battery shell and the sample battery shell. The collaborative similarity of the shell damage between the target waste battery shell and each sample battery shell is determined by the appearance feature and the confidence defect feature of each sample battery shell, and specifically includes: Determine a feature similarity domain through the appearance features and the confidence defect features of each sample battery casing; The collaborative similarity of shell damage between the target used battery and each sample battery is determined based on the feature similarity domain.

2. The method according to claim 1, characterized in that The noise interference domain of the corresponding sample battery is determined by the noise characteristics in each sample appearance data, specifically including: Determine a noisy binary image of a corresponding sample battery according to each sample appearance data; Perform noise feature extraction on all noise binary images to obtain the noise feature of each sample battery; Determine the noise area of ​​each noise feature; The noise interference domain of the corresponding sample battery is determined according to each noise area.

3. The method according to claim 1, characterized in that The damage distribution domain of the corresponding sample battery is determined by the damage characteristics in the appearance data of each sample, specifically including: Determine a damaged binary image of a corresponding sample battery according to each sample appearance data; Extract damage features from all damaged binary images to obtain damage features of each sample battery; Determine the damaged area for each damage feature; The damage distribution domain of the corresponding sample battery is determined according to each damage area.

4. The method according to claim 1, characterized in that The defect profile of each sample battery is binarized and covered according to the noise interference domain and the corresponding damage distribution domain of each sample battery, and the confidence defect features of each sample battery shell are obtained, which specifically include: For each sample battery, obtain the noise interference domain and damage distribution domain of the sample battery; Determine a defect profile of a sample battery according to the noise interference domain and the damage distribution domain; Feature extraction is performed on the area covered by the defect contour in the binary image of the sample battery to obtain the confident defect feature of the sample battery shell, and then the confident defect feature of each sample battery shell is determined.

5. The method according to claim 1, characterized in that The appearance features of the target waste battery shell extracted from the battery data to be tested specifically include: Obtaining an appearance display image of a target used storage battery from the battery data to be tested; Determine the appearance binary image of the target waste battery according to the appearance display image; Feature extraction is performed on the appearance binary image to obtain appearance features of the target waste battery shell.

6. The method according to claim 1, characterized in that The target waste batteries are waste new energy vehicle power batteries or waste lithium batteries.

7. A battery recycling system based on machine vision, which uses the method according to any one of claims 1 to 6 to recycle batteries, characterized in that: The system includes: A collection module, for acquiring sample appearance data of each sample battery in the sample battery group; The processing module determines the noise interference domain of the corresponding sample battery through the noise characteristics in the appearance data of each sample, determines the damage distribution domain of the corresponding sample battery through the damage characteristics in the appearance data of each sample, and then performs binary coverage on the defect contour of each sample battery according to the noise interference domain and the corresponding damage distribution domain of each sample battery to obtain the confidence defect characteristics of the shell of each sample battery; The processing module is also used to collect battery parameters of the target waste battery, thereby obtaining the battery data to be tested, and extracting the appearance features of the shell of the target waste battery from the battery data to be tested; The processing module is also used to determine the collaborative similarity of shell damage between the target waste battery and each sample battery through the appearance feature and the confidence defect feature of each sample battery shell; The execution module is used to determine the appearance defect grade value of the target waste battery according to all the collaborative similarities, and then classify and recycle the target waste battery according to the appearance defect grade value.

8. A computer device, characterized in that: The computer device includes a memory and a processor, wherein the memory stores codes, and the processor is configured to obtain the codes and execute the battery recycling method based on machine vision according to any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the battery recycling method based on machine vision as described in any one of claims 1 to 6 is implemented.

Images