WO2023019508A1 - Method for detecting glue application area, electronic device and computer-readable storage medium - Google Patents

Abstract

Embodiments of the present application provide a method for detecting a glue application area, an electronic device, and a computer-readable storage medium. The method for detecting the glue application area comprises: receiving an image of an region where a glue application operation is completed, the image being an image collected by a camera under a light source; acquiring a grayscale parameter value of the image; adjusting the brightness of the light source according to a deviation value between the grayscale parameter value and a preset reference value; receiving a target image of the region where the glue application operation is completed which is collected by the camera on the basis of the adjusted brightness of the light source; and according to the target image, detecting the glue application area of the region where the glue application operation is completed, wherein the target image is an image that meets a preset definition requirement. Data detection errors may be reduced.

Description

Glue-coated area detection method, electronic device, and computer-readable storage medium technical field

The present application relates to the technical field of detection, in particular to a method for detecting a glue-coated area, electronic equipment and a computer-readable storage medium.

Background technique

In the power battery system, the battery generates excess heat, which can be transferred through contact with the surface of the cooling plate, and finally taken away by the cooling fluid passing through the internal flow channel of the device. In order to make the cooling plate in close contact with the bottom plate of the equipment to be cooled: usually a layer of glue is applied on the cooling plate, and the glue-coated area is tested to ensure that the glue-coated area meets the preset requirements.

At present, the way to detect the glued area of the liquid cold plate is: scan the glued liquid cold plate with a line-scan camera to obtain a scanned image, and then directly detect the glued area based on the scanned image, which may easily lead to detection The data error is large.

Contents of the invention

In view of the above problems, the present application provides a method for detecting glued area, an electronic device and a computer-readable storage medium, which can reduce the error of detected data.

In a first aspect, the present application provides a method for detecting a gluing area, comprising: receiving an image of an area where the gluing operation is completed; wherein, the image is an image collected by a camera under a light source; brightness parameter value; adjust the brightness of the light source according to the deviation value between the gray parameter value and the preset reference value; receive the completed gluing collected by the camera based on the adjusted brightness of the light source A target image of the working area; according to the target image, detect the gluing area of the area where the gluing operation is completed; wherein, the target image is an image that meets a preset definition requirement.

In the technical solution of the embodiment of the present application, the image of the area where the gluing operation is completed is collected by the camera under a light source, and the brightness of the light source is adjusted according to the deviation between the grayscale parameter value of the image and the preset reference value. The adjustment is to adjust the current brightness of the light source in combination with the deviation value between the grayscale parameter value of the image collected under the current brightness and the preset reference value. The deviation value can reflect the clarity of the image captured by the camera at the current brightness. Combined with the deviation value, the brightness of the light source is adjusted, which is beneficial to enable the camera to capture the target image that meets the preset definition requirements based on the adjusted brightness of the light source. , the target image that meets the preset definition requirements can relatively clearly show the gluing area of the area where the gluing operation is completed. Therefore, detecting the gluing area of the area where the gluing operation is completed according to the target image can reduce the detection cost. data error.

In some embodiments, the grayscale parameter value is the grayscale mean value, and the preset reference value is the grayscale mean value reference value, or, the grayscale parameter value is the grayscale variance, and the preset reference value The value is the reference value of gray variance.

Both grayscale mean and grayscale variance are parameters that can accurately measure clarity. By setting the grayscale parameter value as grayscale mean or grayscale variance, the preset reference value is set as the grayscale mean reference value. Or the grayscale variance reference value, so that the deviation value between the grayscale parameter value and the preset reference value can accurately measure the deviation between the definition of the received image and the preset definition.

In some embodiments, the detecting the gluing area of the area where the gluing operation is completed according to the target image includes: affine transforming the preset area in the preset template image to the target image The position of the preset area in the preset template image on the target image is obtained, wherein the preset template image corresponds to the area where the gluing operation is completed and the preset template image is pre-set The position of the preset area is located; according to the position of the preset area in the preset template image on the target image, the size parameters of the area where the gluing operation is completed, and the preset adjacent presets The horizontal pitch and/or the vertical pitch between regions and the total number m of preset regions on the region where the gluing operation is completed are preset to obtain the positions of m preset regions on the target image; wherein, m is An integer greater than 1; according to the positions of the m preset areas on the target image, detect the gluing areas of the m preset areas on the area where the gluing operation is completed.

Since the position of the preset area in the preset template image on the target image, the size parameters of the area where the gluing operation is completed, the preset horizontal spacing and/or vertical spacing between adjacent preset areas and The total number m of the preset areas on the area where the pre-set gluing operation is completed can obtain the positions of the m preset areas on the target image, that is, it is not necessary to equalize the positions of the m preset areas when making the preset template image. Positioning on the preset template image, compared to obtaining the positions of the m preset regions on the target image, when making the preset template image, the positions of the m preset regions are all positioned on the preset template image, Embodiments of the present application help to reduce the complexity of making preset template images, and m is a preset number, so that the number of preset regions that need to be generated on the target image can be flexibly selected according to actual needs, which is conducive to satisfying practical applications different needs in.

In some embodiments, one preset area is pre-positioned on the preset template image.

That is to say, only one preset area needs to be set in the preset template image, which simplifies the design of the preset template image.

In some embodiments, the one preset area is located in the initial area of the preset template image, and the initial area corresponds to the area scanned by the camera in the area where the gluing operation is completed. The first glue detection sub-area.

Set one preset area in the preset template image as the starting area in the preset template image, which facilitates the subsequent combination of the size parameters of the area where the gluing operation is completed, and the relationship between the preset adjacent preset areas. The horizontal spacing and/or the vertical spacing and the total number m of the preset preset areas accurately and quickly generate the positions of the m preset areas on the target image.

In some embodiments, the affine transformation of the preset area in the preset template image to the target image to obtain the position of the preset area in the preset template image on the target image includes: : determine the relative displacement and relative angle between the preset template image and the target image; affine transform the preset region in the preset template image to the target according to the relative displacement and the relative angle On the image, the position of the preset area in the preset template image on the target image is obtained.

Considering that there may be an offset between the preset template image and the target image in the specific detection process, according to the relative displacement and relative angle between the preset template image and the target image, the preset area in the preset template image is affine transformed On the target image, it is possible to avoid the impact of the offset between the preset template image and the target image on the detection data during the detection process, which is beneficial to improve the accuracy of the detection data.

In some embodiments, after detecting the gluing areas of the m preset areas on the area where the gluing operation is completed according to the positions of the m preset areas on the target image, it further includes: Compare the gluing areas of the m preset areas with the preset reference areas respectively, and determine whether the gluing areas of the m preset areas meet the preset gluing requirements; according to the m preset Whether the gluing area of the area satisfies the preset gluing requirements, and determine the detection result of the gluing area of the area where the gluing operation is completed.

Integrating whether the gluing area of each preset area in the m preset areas meets the preset gluing requirements, the detection result of the gluing area of the area where the gluing operation is completed can be more accurately and comprehensively determined, that is, for gluing The detection result of the glued area of the region is more accurate and comprehensive.

In a second aspect, the present application provides an electronic device, including: at least one processor; and a memory connected in communication with the at least one processor; wherein, the memory stores information that can be executed by the at least one processor. Instructions, the instructions are executed by the at least one processor, so that the at least one processor can execute the above-mentioned glue-coated area detection method.

In a third aspect, the present application provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the above-mentioned glue-coated area detection method is realized.

The above description is only an overview of the technical solution of the present application. In order to better understand the technical means of the present application, it can be implemented according to the contents of the description, and in order to make the above and other purposes, features and advantages of the present application more obvious and understandable , the following specifically cites the specific implementation manner of the present application.

Description of drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the accompanying drawings that need to be used in the embodiments of the present application. Obviously, the accompanying drawings described below are only some embodiments of the present application. Those of ordinary skill in the art can also obtain other drawings based on the accompanying drawings on the premise of not paying creative efforts.

Fig. 1 is a schematic diagram of a detection scene disclosed in an embodiment of the present application;

Fig. 2 is a schematic flow chart of a detection method of a glue-coated area disclosed in an embodiment of the present application;

FIG. 3 is a schematic flowchart of the implementation process of step 205 disclosed in an embodiment of the present application;

Fig. 4 is a schematic diagram of the positions of m preset regions on the target image disclosed by an embodiment of the present application;

Fig. 5 is a schematic diagram of a preset template image disclosed in an embodiment of the present application;

Fig. 6 is a schematic flow chart of another detection method for glue area disclosed in an embodiment of the present application;

FIG. 7 is a schematic flowchart of the preprocessing process mentioned in step 612 disclosed in an embodiment of the present application;

FIG. 8 is a schematic flowchart of the process of adjusting the brightness of the light source mentioned in step 620 disclosed in an embodiment of the present application;

Fig. 9 is a schematic structural diagram of an electronic device disclosed in an embodiment of the present application;

In the drawings, the drawings are not drawn to actual scale;

Explanation of symbols: lift module 101 , traverse module 102 , camera 103 , light source 104 , detection platform 105 , cooling plate 106 , T-shaped connecting rod 107 , first motor 108 , second motor 109 .

Detailed ways

The implementation manner of the present application will be further described in detail below with reference to the drawings and embodiments. The detailed description and drawings of the following embodiments are used to illustrate the principles of the application, but not to limit the scope of the application, that is, the application is not limited to the described embodiments.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field of the application; the terms used herein are only for the purpose of describing specific embodiments, and are not intended to To limit this application; the terms "comprising" and "having" and any variations thereof in the specification and claims of this application and the description of the above drawings are intended to cover a non-exclusive inclusion.

In the description of this application, it should be noted that, unless otherwise specified, the meaning of "plurality" is more than two; the terms "upper", "lower", "left", "right", "inner", " The orientation or positional relationship indicated by "outside", etc. are only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a reference to this application. Application Restrictions. In addition, the terms "first", "second", "third", etc. are used for descriptive purposes only and should not be construed as indicating or implying relative importance. "Vertical" is not strictly vertical, but within the allowable range of error. "Parallel" is not strictly parallel, but within the allowable range of error.

The orientation words appearing in the following description are the directions shown in the figure, and do not limit the specific structure of the application. In the description of this application, it should also be noted that, unless otherwise clearly specified and limited, the terms "installation", "connection", and "connection" should be interpreted in a broad sense, for example, it can be a fixed connection or a flexible connection. Disassembled connection, or integral connection; it can be directly connected or indirectly connected through an intermediary. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific situations.

Reference herein to an "embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The occurrences of this phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is understood explicitly and implicitly by those skilled in the art that the embodiments described herein can be combined with other embodiments.

In the description of the embodiment of the present application, the term "and/or" is only a kind of association relationship describing associated objects, which means that there may be three kinds of relationships, such as A and/or B, which may mean: A exists alone, and A exists at the same time and B, there are three cases of B alone. In addition, the character "/" in this article generally indicates that the contextual objects are an "or" relationship.

At present, judging from the development of the market situation, the application of power batteries is becoming more and more extensive. Power batteries are not only used in energy storage power systems such as hydraulic, thermal, wind and solar power plants, but also widely used in electric vehicles such as electric bicycles, electric motorcycles, electric vehicles, as well as military equipment and aerospace and other fields . With the continuous expansion of power battery application fields, its market demand is also constantly expanding.

The inventor noticed that in the power battery system, the battery generates excess heat, which can be transferred through contact with the surface of the cooling plate, and finally taken away by the cooling liquid passing through the internal flow channel of the device. The cooling system takes advantage of the large heat transfer coefficient of the coolant flow, and relies on the coolant flow to transfer heat. It is one of the effective heat dissipation methods at present, and can dissipate hundreds of watts to thousands of watts of heat. The cooling plate is directly in contact with the bottom plate of the cooled equipment by placing the coolant pipeline, which can reduce the number of heat exchange interfaces between the cooled equipment and the coolant, thereby maintaining the lowest thermal resistance and improving performance. In order to achieve better heat dissipation performance, in addition to the heat dissipation performance of the cooling plate itself, it is also required that the cooling plate is in close contact with the bottom plate of the cooled equipment during the assembly process and has a sufficient contact area. In order to realize the close contact between the cooling plate and the bottom plate of the cooled equipment, the following method is usually adopted: apply a layer of glue on the cooling plate, and detect the glue-coated area of the cooling plate to ensure that the glue-coated area meets the preset requirements, so that The liquid cold plate can be in close contact with the cooled equipment.

In order to realize the close contact between the cooling plate and the bottom plate of the equipment to be cooled, the inventors found that the glued cooling plate can be scanned by a 4K line scan camera to obtain a scanned image, and then the glued area can be detected directly based on the scanned image. However, such detection may easily lead to large errors in the detected data. For example, if the scanned image itself is not clear enough, the detection of the glued area based on the insufficiently clear image will easily lead to inaccurate detection data and large errors.

Based on the above considerations, in order to solve the problem of inaccurate and large errors in the detection data of the glued area, the inventor has designed a detection method for the glued area after in-depth research. The image of the area where the gluing operation is completed is collected, and the brightness of the light source is adjusted according to the deviation between the gray parameter value of the image and the preset reference value, that is, combined with the image collected by the camera at the current brightness of the light source The deviation value between the grayscale parameter value and the preset reference value is used to adaptively adjust the current brightness of the light source. The deviation value can reflect the clarity of the image captured by the camera at the current brightness. Combined with the deviation value, the brightness of the light source is adjusted, which is beneficial to enable the camera to capture the target image that meets the preset definition requirements based on the adjusted brightness of the light source. , the target image that meets the preset definition requirements can relatively clearly show the gluing area of the area where the gluing operation is completed. Therefore, detecting the gluing area of the area where the gluing operation is completed according to the target image can reduce the detection cost. data error.

The detection method of the gluing area disclosed in the embodiment of the present application is applied to electronic equipment, and the electronic equipment can be an industrial computer equipped with a charge coupled device (charge coupled device, referred to as: CCD) software system, and can also be other devices capable of executing the application. The equipment of the detection method of glue-coated area in the embodiment.

In some embodiments, the schematic diagram of the detection scene can refer to FIG. Motor 108, second motor 109. The camera 103 and the light source 104 may be respectively arranged on the transverse connecting rod and the longitudinal connecting rod of the T-shaped connecting rod 107 . The camera 103 is parallel to the horizontal plane and perpendicular to the transverse connecting rod of the T-shaped connecting rod 107 . The upper surface area of the cooling plate 106 can be understood as an area where the gluing operation is completed. In a specific implementation, the cooling plate 106 can be a water-cooled plate. The lifting module 101 can move up and down driven by the first motor 108 to change the distance between the camera 103 and the detection platform 105 to adjust the focal length of the camera. The traverse module 102 can move left and right under the drive of the second motor 109 to change the lateral position of the camera. During the movement of the traverse module 102 , the camera 103 can scan the cooling plate 106 to obtain an image of the cooling plate 106 . That is to say, the camera 103 scans the cooling plate 106 coated with glue below in real time as the traverse module 102 moves (adjustable at 5-40 m/min). Cooling plate image. The 10 black squares on the cooling plate 106 can be understood as glued areas.

In some embodiments, the camera 103 may be a line scan camera, such as an 8K line scan camera, and the light source 104 may be a line light source. The cooling plate 106 after gluing is placed on the detection platform 105. The line-scanning camera and the line light source move left and right along with the traverse module 102 to take a line-scan photo of the cooling plate 106. The moving distance of the traverse module 102 can be determined according to The length configuration of the cooling plate 106 achieves the effect of full-frame and full-frame-rate imaging, and realizes the global detection of the cooling plate 106 .

In some embodiments, the size of the cooling plate 106 is: 500*1100mm, the detection accuracy of the camera 103 is: 0.065mm, the distance from the camera 103 to the cooling plate 106 is: 680±40mm, and the distance from the light source 104 to the cooling plate 106 is : 80±30mm, the installation angle of the light source 104 is: 65°±20°, and the horizontal distance between the light source 104 and the camera 103 is: 20±5mm. The focal length of the camera 103 can be adjusted by the lifting module 101 . The vertical detection range of the camera 103 is within 530 mm, and the horizontal detection range can be set by setting the moving distance of the lateral movement module 102 .

According to some embodiments of the present application, the schematic flow chart of the detection method of glue coating area can refer to Fig. 2, comprises:

Step 201: Receive an image of the area where the gluing operation is completed; wherein, the image is an image collected by a camera under a light source;

Step 202: Obtain the grayscale parameter value of the image;

Step 203: Adjust the brightness of the light source according to the deviation between the gray scale parameter value and the preset reference value;

Step 204: Receive the target image of the area where the gluing operation is completed collected by the camera based on the adjusted brightness of the light source; wherein, the target image is an image that meets the preset definition requirement;

Step 205: According to the target image, detect the gluing area of the area where the gluing operation is completed.

In step 201, the area where the gluing operation is completed can be understood as the area after gluing, for example, after gluing the upper surface of the cooling plate, the upper surface of the cooling plate is the area where the gluing operation is completed; wherein, the cooling plate Can be a water-cooled plate. With reference to Fig. 1, the camera 103 can collect the image of the cooling plate 106 that has completed the gluing operation under the light source 104, as the image of the area where the gluing operation has been completed, and then the camera 103 can send the image of the area where the gluing operation has been completed to the electronic device , so that the electronic device can receive an image of the area where the gluing job is done.

In step 202, the electronic device may acquire a grayscale parameter value of the received image; wherein, the grayscale parameter value may be a parameter related to image grayscale, and the grayscale parameter value may be used to measure the clarity of the image.

In step 203, a preset reference value may be set according to actual needs, and the preset reference value may be a grayscale parameter value of a clear image acquired in advance. For example, the preset reference value is a grayscale parameter value of a pre-acquired reference image that satisfies the preset reference condition. Optionally, the pre-acquired reference image that satisfies the preset reference condition may be: the image with the highest resolution among the batch images collected by the pre-acquired camera. The deviation value between the grayscale parameter value and the preset reference value can measure the difference in clarity between the received image and the reference image. The larger the absolute value of the deviation value, it means that the definition of the received image is worse than that of the reference image, and the smaller the absolute value of the deviation value, it means that the definition of the received image is better than that of the reference image.

Wherein, the electronic device can determine the adjustment amount of the brightness of the light source according to the deviation value, and send the determined adjustment amount to the controller of the light source, and the controller of the light source adjusts the brightness of the light source according to the received adjustment amount of the light source. The greater the absolute value of the deviation value, the greater the determined adjustment amount. When the deviation value is positive, the brightness of the light source will be lowered according to the determined adjustment amount; when the deviation value is negative, the brightness of the light source will be increased according to the determined adjustment amount. .

In one example, the deviation value includes a positive deviation value and a negative deviation value. When the grayscale parameter value is greater than a preset reference value, the deviation value is a positive deviation value; when the grayscale parameter value is smaller than a preset reference value, the deviation value is Negative bias value. The implementation of step 203 may include: reducing the brightness of the light source when the positive deviation value is greater than the first preset threshold; increasing the brightness of the light source when the negative deviation value is smaller than the second preset threshold. Decreasing the brightness of the light source, including: determining the decrement of the brightness according to the deviation represented by the positive deviation value; reducing the brightness of the light source according to the decrement of the brightness; increasing the brightness of the light source, including: according to the deviation represented by the negative deviation value Determine the incremental amount of brightness; according to the incremental amount of brightness, increase the brightness of the light source. Wherein, the first preset threshold and the second preset threshold may respectively represent the maximum value of the allowed positive deviation value and the minimum value of the negative deviation value, and the specific size of the first preset threshold value and the second preset threshold value may be determined according to actual needs It is set, which is not specifically limited in this embodiment.

Wherein, the decrement can be, for example, 1/5 of the deviation represented by the positive deviation value, and the increment can be 1/5 of the deviation represented by the negative deviation value. However, in this embodiment, only 1/5 is taken as an example. It is not limited to this in specific implementation.

In step 204: the electronic device may receive the target image of the area where the gluing operation is completed and collected by the camera based on the adjusted brightness of the light source; wherein, the target image is an image that meets a preset definition requirement. The preset resolution requirement can be set according to actual needs, and the preset resolution requirement is used to measure whether the received image can be regarded as a clear image. For example, the preset definition requirement may include: the deviation value between the grayscale parameter value of the image and the preset reference value is within the preset tolerance range, and the lower limit value of the preset tolerance range may be the above-mentioned first Two preset thresholds, the upper limit of the preset tolerance range may be the above-mentioned first preset threshold.

In a specific implementation, the electronic device can perform definition detection on each received image to determine whether the image meets the preset definition requirements, and if the image does not meet the preset definition requirements, adjust the brightness of the light source and continue The image of the area where the gluing operation is completed is collected by the camera based on the adjusted brightness of the light source, and the adjustment of the brightness of the light source is stopped until a target image that meets the preset definition requirements is received.

In step 205, the electronic device may detect the gluing area of the area where the gluing operation is completed according to the target image. Since the target image meets the preset definition requirements, the target image can clearly reflect the gluing area of the area where the gluing operation is completed, so that the gluing area of the area where the gluing operation is completed in the target image can be accurately detected size.

In this embodiment, the current brightness of the light source is adjusted in combination with the deviation value between the gray scale parameter value of the image captured by the camera under the current brightness of the light source and a preset reference value. The deviation value can reflect the clarity of the image captured by the camera at the current brightness. Combined with the deviation value, the brightness of the light source is adjusted, which is beneficial to enable the camera to capture the target image that meets the preset definition requirements based on the adjusted brightness of the light source. , the target image that meets the preset definition requirements can relatively clearly show the gluing area of the area where the gluing operation is completed. Therefore, detecting the gluing area of the area where the gluing operation is completed according to the target image can reduce the detection cost. data error.

According to some embodiments of the present application, optionally, the grayscale parameter value in step 202 may be a grayscale mean value, and the corresponding preset reference value mentioned in step 203 is a grayscale mean value reference value.

According to some embodiments of the present application, optionally, the grayscale parameter value in step 202 may be a grayscale variance, and the corresponding preset reference value mentioned in step 203 is a grayscale variance reference value.

The mean value of the gray level is: the average value of the gray level of each pixel in the image, reflecting the average level of the gray level of the image. The preset gray-scale average reference value may be: a gray-scale average value of a reference image that satisfies a preset reference condition and is obtained in advance. Optionally, the pre-acquired reference image that satisfies the preset reference condition may be: the image with the highest resolution among the batch images collected by the pre-acquired camera.

The grayscale variance is: the average of the square value of the difference between the grayscale of each pixel in the image and the grayscale mean of the image, which characterizes the average degree of grayscale change in the image. The greater the average degree of grayscale change, the more image clear. The gray variance reflects the size of the high frequency part of the image. Generally speaking, the clearer the image, the more high-frequency components in the image. The preset grayscale variance reference value may be: the grayscale variance of a reference image that satisfies a preset reference condition and is obtained in advance. Optionally, the pre-acquired reference image that satisfies the preset reference condition may be: the image with the highest resolution among the batch images collected by the pre-acquired camera.

Among them, the method of determining the reference image that satisfies the preset reference conditions can be as follows: collecting batch images, training the batch images, establishing a grayscale histogram model, and finding the clearest one of the batch images according to the grayscale histogram model as Reference image. For example, the grayscale mean and grayscale variance of each image in a batch of images can be calculated, and a grayscale histogram model can be established according to the grayscale mean and grayscale variance of each image. The grayscale histogram model can display the sharpness results, such as , the image corresponding to the peak in the grayscale histogram model is taken as the clearest image in the batch of images.

Both grayscale mean and grayscale variance are parameters that can accurately measure clarity. By setting the grayscale parameter value as grayscale mean or grayscale variance, the preset reference value is set as the grayscale mean reference value. Or the grayscale variance reference value, so that the deviation value between the grayscale parameter value and the preset reference value can accurately measure the deviation between the definition of the received image and the preset definition.

According to some embodiments of the present application, optionally, the implementation process of step 205 may refer to FIG. 3 , including;

Step 301: Affine transform the preset area in the preset template image to the target image to obtain the position of the preset area in the preset template image on the target image.

Step 302: According to the position of the preset area in the preset template image on the target image, the size parameters of the area where the gluing operation is completed, the preset horizontal spacing and/or vertical spacing between adjacent preset areas, and the preset The total number m of preset areas on the area where the gluing operation is completed is set to obtain the positions of m preset areas on the target image;

Step 303: According to the positions of the m preset areas on the target image, detect the gluing areas of the m preset areas on the area where the gluing operation is completed.

In step 301, the preset template image corresponds to the area where the gluing operation is completed, and the position of the preset area is pre-positioned on the preset template image. The preset template image can be understood as the template image designed by those skilled in the art in advance for the area where the gluing operation is completed. The position of the preset area is pre-positioned on the template image. The region of interest (referred to as: ROI) on the region where the gluing operation is completed can also be understood as: detecting sub-regions.

In an example, the area where the gluing operation is completed is the upper surface area of the water-cooled plate, and the preset template image may be a template image corresponding to the model of the water-cooled plate, that is, a template image designed for the model of the water-cooled plate. Different types of water cooling plates can correspond to different preset template images, and different types of water cooling plates can be understood as water cooling plates with different size parameters.

Affine transformation, also known as affine mapping, means that in geometry, a vector space is transformed into another vector space by performing a linear transformation followed by a translation. Correspondingly, the affine transformation in this embodiment can be understood as: the preset region in the preset template image undergoes a linear change followed by a translation to transform it into the target image. For example, if the number of preset regions in the preset template image is 1, affine transformation of 1 preset region in the preset template image to the target image is obtained to obtain 1 preset region in the preset template image The location of the region on the target image. If the number of preset regions in the preset template image is 2, then affine transform the 2 preset regions in the preset template image to the target image to obtain the 2 preset regions in the preset template image in location on the target image.

In step 302, m is an integer greater than 1. For a schematic diagram of the positions of m preset areas on the target image, reference may be made to FIG. 4 . One small square represents a preset area, and it can be seen that m=8. The size parameters of the area where the gluing operation is completed can be pre-stored in the electronic device, or can be input by the operator during inspection. The size of the area where the gluing operation is completed can be, for example, the length and width of the water-cooled plate.

Referring to FIG. 5 , the horizontal spacing between preset adjacent preset areas is a, and the vertical spacing is b. m can be set according to actual needs, for example, if it is expected to detect the gluing area of 6 preset areas in the area where the gluing operation is completed, then m can be set to 6, and if it is expected to detect 8 in the area where the gluing operation is completed If the gluing area of a preset area can be set, m can be set to 8.

In one example, if the number of preset areas in the preset template image is 1, the electronic device can determine the area where the gluing operation is completed according to the position of 1 preset area in the preset template image on the target image The size parameter, the preset horizontal spacing and vertical spacing between adjacent preset areas, and the preset total number m of preset areas on the area where the gluing operation is completed, obtain the positions of m preset areas on the target image . It can be understood that the position of one preset area on the target image is obtained through affine transformation, and the positions of m-1 preset areas are obtained through the position of one preset area on the target image, and the gluing is completed The size parameters of the working area, the preset horizontal spacing and vertical spacing between adjacent preset areas are automatically generated.

In an example, if the number of preset regions in the preset template image is 2, and the two preset regions are horizontally adjacent, the electronic device can recognize the difference between the two preset regions in the preset template image. Horizontal spacing, and according to the position of the two preset areas in the preset template image on the target image, the size parameters of the area where the gluing operation is completed, the vertical spacing between the preset adjacent preset areas, and the identified The horizontal spacing and the total number m of preset areas on the preset area where the gluing operation is completed, obtain the positions of m preset areas on the target image.

In one example, if the number of preset areas in the preset template image is 2, and the two preset areas are vertically adjacent, the electronic device can identify the distance between the two preset areas in the preset template image. Vertical spacing, and according to the position of the two preset areas in the preset template image on the target image, the size parameters of the area where the gluing operation is completed, the preset horizontal spacing between adjacent preset areas, and the identified The vertical spacing and the total number m of preset areas on the preset area where the gluing operation is completed obtain the positions of m preset areas on the target image.

In step 303, the electronic device can identify the glued areas in the m preset areas on the target image, determine the size of the glued areas in each preset area, and determine the size of the glued areas in each preset area according to the glued area in each preset area The size of the area determines the glued area in each preset area. For example, when the gluing area is a rectangle, the size of the gluing area can be length and width, then the gluing area in the m preset areas can be calculated according to the length and width of the gluing area in the m preset areas.

In some embodiments, the electronic device may perform BLOB analysis on m preset regions on the target image to obtain glued areas of the m preset regions. In machine vision, BLOB refers to a connected area composed of similar colors, textures and other features in the image. BLOB analysis is to perform geometric analysis on the connected area to obtain some important geometric features, such as the area of the area, the coordinates of the center point, the coordinates of the centroid, and the smallest circumscribed rectangle. In this embodiment, considering that the glued areas in the preset areas are usually areas with similar colors, textures, etc., the connected areas in each preset area can be used as the glued areas in each preset area . The electronic device can determine a connected area composed of similar colors, textures and other features in each preset area. For example, the glued area in each preset area can be marked according to the connectivity of the glued area, and each Connected areas in the preset area, and then perform geometric feature analysis on the connected areas in each preset area to obtain the area of the connected area in each preset area, and calculate the connected area in each preset area area as the glued area for each preset area. Through BLOB analysis, the glued area of each preset area can be obtained conveniently and accurately.

Since the position of the preset area in the preset template image on the target image, the size parameters of the area where the gluing operation is completed, the preset horizontal spacing and/or vertical spacing between adjacent preset areas and The total number m of the preset areas on the area where the pre-set gluing operation is completed can obtain the positions of the m preset areas on the target image, that is, it is not necessary to equalize the positions of the m preset areas when making the preset template image. Positioning on the preset template image, compared to obtaining the positions of the m preset regions on the target image, when making the preset template image, the positions of the m preset regions are all positioned on the preset template image, Embodiments of the present application help to reduce the complexity of making preset template images, and m is a preset number, so that the number of preset regions that need to be generated on the target image can be flexibly selected according to actual needs, which is conducive to satisfying practical applications The different needs in the system are more adaptable to different needs.

According to some embodiments of the present application, optionally, a position of a preset area is pre-positioned on the preset template image.

That is to say, only one preset region needs to be preset on the preset template image, or in other words, only one ROI needs to be preset on the preset template image.

Only one preset region needs to be set in the preset template image, and there is no need to set m preset region locations on the preset template image according to actual detection requirements, which simplifies the design of the preset template image.

According to some embodiments of the present application, optionally, the one preset area is located in the initial area of the preset template image, and the initial area corresponds to the first gluing area scanned by the camera in the area where the gluing operation is completed. Glue detects subregions.

Wherein, the schematic diagram of the preset template image can refer to FIG. 5 . In FIG. 5 , one preset area is located at the upper left position of the preset template image, and the upper left position can be understood as the starting area in the preset template image. The camera is a line-scan camera, that is, the starting area corresponds to the first gluing detection sub-area scanned by the line-scan camera in the area where the gluing operation is completed. In this embodiment, when one preset area is located in the initial area of the preset template image, when one preset area in the preset template image is affine transformed to the target image, the obtained target image One preset area is the first gluing detection sub-area scanned by the line scan camera in the area where the gluing operation is completed.

The number of preset areas on the preset template image is 1, and it is located in the initial area of the preset template image, which facilitates the subsequent combination of the size parameters of the area where the gluing operation is completed and the preset adjacent preset areas. The horizontal spacing and/or vertical spacing between them and the total number of preset preset areas m, accurately and quickly generate the positions of m preset areas on the target image.

According to some embodiments of the present application, optionally, the preset region in the preset template image is affine transformed onto the target image to obtain the position of the preset region in the preset template image on the target image, including : Determine the relative displacement and relative angle between the preset template image and the target image; according to the relative displacement and relative angle, affine transform the preset area in the preset template image to the target image to obtain the The position of the preset area on the target image.

In the actual detection process, there are angle and displacement deviations between the target image and the preset template image. The preset area, that is, the ROI is set in the preset template image. Therefore, in order to make the ROI in the target image obtained after affine transformation change with the change of angle and displacement, the preset template image and the target image can be determined The relative displacement and relative angle between, and then according to the relative displacement and relative angle, the preset area in the preset template image is affine transformed to the target image, and the preset area in the preset template image on the target image is obtained. Location. In a specific implementation, the matching relationship between the preset template image and the target image can be established according to the determined relative displacement and relative angle, and the preset area in the preset template image is affine transformed to the target image according to the matching relationship , to obtain the position of the preset area in the preset template image on the target image, so that the preset area in the preset template image can be accurately shifted to the corresponding area in the target image after affine transformation.

Wherein, the angle and displacement deviation between the target image and the preset template image may be the angle deviation and position deviation caused when the area where the gluing operation is completed is placed on the detection platform. For example, the area where the gluing operation is completed is the upper surface area of the water-cooled plate. When the water-cooled plate is placed on the detection platform, angular offset and position offset are allowed.

Considering that there may be an offset between the preset template image and the target image in the specific detection process, according to the relative displacement and relative angle between the preset template image and the target image, the preset area in the preset template image is affine transformed On the target image, it is possible to avoid the impact of the offset between the preset template image and the target image on the detection data during the detection process, which is beneficial to improve the accuracy of the detection data.

According to some embodiments of the present application, optionally, after detecting the gluing areas of the m preset areas on the area where the gluing operation is completed according to the positions of the m preset areas on the target image, the method further includes: Compare the gluing areas of the m preset areas with the preset reference areas to determine whether the gluing areas of the m preset areas meet the preset gluing requirements; according to whether the gluing areas of the m preset areas Meet the preset gluing requirements, and determine the detection results of the gluing area in the area where the gluing operation is completed.

Wherein, the preset reference area can be understood as the standard value of the glue application area, and the specific size is set according to actual needs. The preset gluing requirement can also be set according to actual needs, for example, it can be set as: the gluing area is greater than 80% of the reference area. That is to say, if the glued area of one preset area is greater than 80% of the reference area, it can be determined that the glued area of this preset area meets the preset glued requirements. According to the above method, it can be sequentially determined whether the gluing areas of the m preset regions meet the preset gluing requirements.

The detection result of the glued area of the area where the glued operation is completed may include: passing the detection and failing the detection. Wherein, the detection result may be determined according to the number of preset areas meeting the preset glue application requirements among the m preset areas. For example, if the number of preset areas that meet the preset gluing requirements in the m preset areas is greater than or equal to the preset number threshold, it can be determined that the detection result is passed; if the m preset areas meet the preset If the number of preset regions required for glue coating is less than the preset number threshold, it can be determined that the detection result is a failure of the detection. The preset quantity threshold can be set according to actual needs. For example, it can be set to m, that is, only when the gluing areas of m preset areas meet the preset gluing requirements, the detection result will be determined as a pass. However, in a specific implementation, the preset number threshold may also be set to a number smaller than m, which is not specifically limited in this embodiment.

Integrating whether the gluing area of each preset area in the m preset areas meets the preset gluing requirements, the detection result of the gluing area of the area where the gluing operation is completed can be more accurately and comprehensively determined, that is, for gluing The detection result of the glued area of the region is more accurate and comprehensive.

According to some embodiments of the present application, in combination with the schematic diagram of the detection scene in FIG. 1 , the schematic flow chart of the detection method of the glue-coated area can refer to FIG. 6 , including:

Step 600: Place the water-cooled plate that has completed the gluing operation on the detection platform;

Step 601: Trigger a start command through an external button;

Step 602: After receiving the start command, the traverse module drives the camera and light source to move to the left, and transmits the moving speed and moving distance to the camera in the form of pulses;

Step 603: The traverse module moves to the target distance according to the size parameters of the water-cooled plate; wherein, the target distance can be the length of the water-cooled plate;

Step 604: the programmable controller (Programmable Logic Controller, referred to as: PLC) transmits the start command to the CCD software system;

Step 605: Turn on the line light source; for example, the CCD software system sends a command to turn on the light source to the light source controller to provide brightness support for camera scanning;

Step 606: The CCD software system starts scanning synchronously, and the camera starts scanning the water cooling plate;

Step 607: After the traversing module moves to the target distance, send the signal of completion of the movement to the CCD software system;

Step 608: After the CCD software system receives the signal that the movement is completed, it controls the camera to stop scanning and controls the light source to turn off;

Step 609: the camera transmits the scanned image to the CCD software system;

Step 610: The traverse module moves to the right and returns to the initial position; wherein, after the traverse module returns to the initial position, it waits for the next start command;

Step 611: judging whether the image is the target image; wherein, the CCD software system can perform sharpness detection on the image, thereby judging whether the image is the target image, and the target image is an image that meets the preset sharpness requirements; if yes, then execute step 612 , otherwise execute step 620;

Step 612: Image preprocessing; wherein, image preprocessing refers to preprocessing the target image to obtain a preprocessed image;

Step 613: Affine transformation; wherein, affine transformation can be understood as: according to the relative displacement and relative angle between the preset template image and the target image, affine transformation of one ROI in the preset template image to the preprocessed On the image, get the position of a ROI in the preset template image on the preprocessed image;

Step 614: Generate the positions of m ROIs; wherein, generating the positions of m ROIs can be understood as: according to the position of one ROI in the preset template image on the preprocessed image, and related configuration parameters, the preprocessed The positions of the m ROIs on the final image; wherein, the relevant configuration parameters include: the size parameters of the water-cooled plate, the preset horizontal and vertical spacing between adjacent ROIs, and the preset total number m of ROIs on the water-cooled plate ;

Step 615: Detect the glued areas of m ROIs; for example, BLOB measurement can be performed on m ROIs to obtain the glued areas of m ROIs on the water cooling plate;

Step 616: Comparing and calculating the gluing area of m ROIs with the reference area; wherein, ROIs whose gluing area is greater than or equal to 80% of the reference area meet the preset gluing requirements;

Step 617: Get the test result; for example, determine the test result of the glue-coated area of the water-cooled plate according to whether the glue-coated areas of the m ROIs meet the preset glue-coating requirements;

Step 618: Upload the test results to the PLC and the host computer; wherein, after the CCD software system uploads the test results to the PLC and the host computer, it can be considered that a measurement cycle is completed;

Step 619: The upper computer uploads the test results and the model of the water-cooled plate to the manufacturing execution system (manufacturing execution system, MES for short); after uploading to the MES, the water-cooled plate can be removed from the testing platform to complete the glue coating of the water-cooled plate Area detection;

Step 620: Adjust the brightness of the light source until the target image scanned by the camera and meeting the preset definition requirement is received. Enter step 612 after step 620 is executed.

In some embodiments, the preprocessing process mentioned in step 612 can refer to FIG. 7 , including:

Step 701: smoothing and denoising the target image; for example, median filtering can be used to eliminate isolated noise and noise;

Step 702: perform morphological transformation on the target image, and remove edge burrs and small noise points; wherein, morphological transformation can use operations such as erosion, expansion, and opening and closing;

Step 703: Enhance the contrast of the target image; for example, enhance the edges and details of the target image to make the light and dark changes more obvious;

Step 704: Perform a sharpening operation on the edge of the target image; for example, the sharpening operation can be realized by using an impact filter operator;

Step 705: Perform threshold segmentation on the target image to extract darker regions;

Step 706: Perform connected domain segmentation on the target image to separate out unconnected regions;

Step 707: Perform area selection on the target image to select the feature area of interest.

In some embodiments, the process of adjusting the brightness of the light source mentioned in step 620 can refer to FIG. 8 , including:

Step 801: Input a preset light source intensity to the light source controller to control the light source to emit light with the preset light source intensity;

Step 802: Receive the image of the water-cooled plate that has completed the gluing operation collected by the camera;

Step 803: Calculate the grayscale parameter value of the image, and calculate the deviation value between the grayscale parameter value and the preset reference value;

Step 804: Determine whether the deviation value is within the preset tolerance range; if yes, execute step 805, otherwise execute step 806;

Step 805: the adjustment is completed, and the light source controller runs at the current brightness;

Step 806: Determine whether the deviation value is greater than the upper limit of the preset tolerance range; if yes, execute step 807, otherwise execute step 808;

Step 807: sending out an adjustment control signal for lowering the brightness until receiving the target image captured by the camera and meeting the preset definition requirements;

Step 808: Determine whether the deviation value is less than the lower limit of the preset tolerance range; if yes, execute step 809, otherwise execute step 805;

Step 809: sending an adjustment control signal for increasing the brightness until the target image captured by the camera meeting the preset definition requirement is received.

In some embodiments, the implementation process of step 807 may be: sending an adjustment control signal to lower the brightness, and the decrement amount of each adjustment is 1/5 of the deviation represented by the deviation value. Then continue to receive the image collected by the camera based on the adjusted brightness of the light source, and calculate the deviation value between the gray parameter value of the image and the preset reference value, until the calculated deviation value is within the preset tolerance range, stop Adjust the brightness of the light source.

In some embodiments, the implementation process of step 809 may be: sending an adjustment control signal to increase the brightness, and the incremental amount of each adjustment is 1/5 of the deviation represented by the deviation value. Then continue to receive the image collected by the camera based on the adjusted brightness of the light source, and calculate the deviation value between the gray parameter value of the image and the preset reference value, until the calculated deviation value is within the preset tolerance range, stop Adjust the brightness of the light source.

In some embodiments, considering that due to the uncertainty of ambient light, the quality of the image captured by the camera has a large deviation before and after, and at the same time, with the prolongation of the use time, the brightness of the light source will also attenuate, which will affect the quality of the captured image. Quality, and image clarity is an important index to measure image quality, which will affect the error of the detection result of the glued area. Therefore, in some embodiments of the present application, the sharpness detection of the image captured by the camera and the adaptive adjustment of the brightness of the light source are added, so as to facilitate the collection of images that meet the preset sharpness requirements, based on meeting the preset sharpness It is helpful to improve the accuracy of the detection results by detecting the glue-coated area on the image with the required precision.

According to some embodiments of the present application, please refer to FIG. 9 , the electronic device includes: at least one processor 901; and a memory 902 communicated with the at least one processor 901; An instruction executed by a processor 901, the instruction is executed by the at least one processor 901, so that the at least one processor 901 can execute the glue-applied area detection method in the above method embodiment.

Wherein, the memory 902 and the processor 901 are connected by a bus, and the bus may include any number of interconnected buses and bridges, and the bus connects one or more processors 901 and various circuits of the memory 902 together. The bus may also connect together various other circuits such as peripherals, voltage regulators, and power management circuits, all of which are well known in the art and therefore will not be further described herein. The bus interface provides an interface between the bus and the transceivers. A transceiver may be a single element or multiple elements, such as multiple receivers and transmitters, providing means for communicating with various other devices over a transmission medium. The data processed by the processor 901 is transmitted on the wireless medium through the antenna, and further, the antenna also receives the data and transmits the data to the processor 901 .

Processor 901 is responsible for managing the bus and general processing, and may also provide various functions, including timing, peripheral interface, voltage regulation, power management, and other control functions. And the memory 902 may be used to store data used by the processor 901 when performing operations.

Some embodiments of the present application relate to a computer-readable storage medium storing a computer program. The above method embodiments are implemented when the computer program is executed by the processor.

That is, those skilled in the art can understand that all or part of the steps in the method of the above-mentioned embodiments can be completed by instructing related hardware through a program, the program is stored in a storage medium, and includes several instructions to make a device ( It may be a single-chip microcomputer, a chip, etc.) or a processor (processor) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disc, etc., which can store program codes. .

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit it; although the application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: It is still possible to modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the technical solutions of the various embodiments of the present application. All of them should be covered by the scope of the claims and description of the present application. In particular, as long as there is no structural conflict, the technical features mentioned in the various embodiments can be combined in any manner. The present application is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims (9)

1. A method for detecting a glued area, comprising:

   Receive the image of the region where the gluing operation is completed; wherein, the image is an image collected by a camera under a light source;

   Acquiring the grayscale parameter value of the image;

   adjusting the brightness of the light source according to the deviation between the grayscale parameter value and a preset reference value;

   receiving the target image of the area where the gluing operation is completed and collected by the camera based on the adjusted brightness of the light source;

   Detecting the gluing area of the region where the gluing operation has been completed according to the target image;

   Wherein, the target image is an image meeting a preset definition requirement.
2. The detection method of the gluing area according to claim 1, wherein the grayscale parameter value is a grayscale mean value, and the preset reference value is a grayscale mean value reference value, or, the grayscale parameter value is Grayscale variance, the preset reference value is a grayscale variance reference value.
3. The detection method of the gluing area according to claim 1 or 2, wherein, according to the target image, detecting the gluing area of the area where the gluing operation is completed comprises:

   Affine transforming the preset area in the preset template image onto the target image to obtain the position of the preset area in the preset template image on the target image,

   Wherein, the preset template image corresponds to the area where the gluing operation is completed and the position of the preset area is pre-positioned on the preset template image;

   According to the position of the preset area in the preset template image on the target image, the size parameter of the area where the gluing operation is completed, the preset horizontal distance and/or vertical distance between adjacent preset areas The spacing and the preset total number m of preset areas on the area where the gluing operation is completed, obtain the positions of m preset areas on the target image; wherein, m is an integer greater than 1;

   According to the positions of the m preset areas on the target image, the gluing areas of the m preset areas on the area where the gluing operation is completed are detected.
4. The method for detecting glue-coated areas according to claim 3, wherein one position of the preset area is pre-positioned on the preset template image.
5. The detection method of the gluing area according to claim 4, wherein said one preset area is located in the starting area in the preset template image, and the starting area corresponds to the completed gluing The first gluing detection sub-area scanned by the camera in the working area.
6. The detection method of the glue-coated area according to any one of claims 3 to 5, wherein the affine transformation of the preset area in the preset template image to the target image obtains the preset template image The position of the preset area in the target image includes:

   determining a relative displacement and a relative angle between the preset template image and the target image;

   According to the relative displacement and the relative angle, the preset area in the preset template image is affine transformed onto the target image to obtain the preset area in the preset template image on the target image. Location.
7. According to the detection method of the gluing area described in any one of claims 3 to 6, wherein, in the position according to the m preset areas on the target image, m on the area where the gluing operation is completed After testing the glued area of a preset area, it also includes:

   Comparing the gluing areas of the m preset areas with the preset reference areas respectively, and determining whether the gluing areas of the m preset areas meet the preset gluing requirements;

   According to whether the gluing areas of the m preset areas meet the preset gluing requirements, the detection result of the gluing area of the area where the gluing operation is completed is determined.
8. An electronic device comprising:

   at least one processor; and,

   a memory communicatively coupled to the at least one processor; wherein,

   The memory is stored with instructions executable by the at least one processor, the instructions are executed by the at least one processor, so that the at least one processor can perform any one of claims 1 to 7 The detection method of the gluing area.
9. A computer-readable storage medium, storing a computer program, which implements the glue-applied area detection method according to any one of claims 1 to 7 when the computer program is executed by a processor.

Images