System and method for detecting inclination of workpiece loading plate of coating machine and coating equipment

Abstract

The invention discloses an inclination detection system and method for a workpiece loading plate of a coating machine and coating equipment, and the system comprises a sampling area obtaining module which is used for building at least one sampling area in the surrounding area of the workpiece loading plate; the image acquisition module is used for acquiring first image data of the sampling area; the image processing module is used for carrying out binarization processing on the first image data and obtaining the number of pixel points in the sampling area; and the inclination analysis module is used for acquiring a preset pixel point threshold value, comparing the number of the pixel points with the preset pixel point threshold value, and determining an inclination detection result of the workpiece loading plate according to a comparison result. According to the invention, inclination detection is carried out on the workpiece loading plate of the coating machine through pixel point extraction, the inclination detection algorithm is simple, and the detection efficiency and accuracy are effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of coating machine detection technology, and in particular to a coating machine workpiece loading plate tilt detection system, method and coating equipment. Background Art

[0002] A vacuum coating machine is a device that performs coating under a high vacuum degree. When performing optical coating, the substrate to be coated is placed on a workpiece loading plate, which then transports the substrate into the vacuum chamber. After the workpiece loading plate is placed, the coating is performed.

[0003] Before the workpiece loading plate enters the vacuum chamber, it is necessary to detect the inclination of the workpiece loading plate. In the prior art, a slot is usually set on the trolley for mounting the workpiece loading plate, and the inclination of the workpiece loading plate inside the chamber is manually detected through the observation window next to the coating machine. The disadvantage of positioning by the slot is that the errors caused by repeated wear and human factors are not obvious, and the manual inspection results are limited by the level of the inspectors, which is prone to misjudgment and has low inspection efficiency. Summary of the invention

[0004] The present invention provides a coating machine workpiece loading plate tilt detection system, method and coating equipment to solve the problems of large error and low detection efficiency in existing tilt detection methods and improve the tilt detection efficiency.

[0005] According to one aspect of the present invention, a system for detecting the tilt of a workpiece loading plate of a coating machine is provided, wherein the coating machine comprises a vacuum chamber, a viewing window and a workpiece loading plate, and the tilt detection system comprises: a sampling area acquisition module, for establishing at least one sampling area in the surrounding area of ​​the workpiece loading plate; an image acquisition module, for acquiring first image data of the sampling area; an image processing module, for binarizing the first image data and acquiring the number of pixels in the sampling area; and a tilt analysis module, for acquiring a preset pixel threshold, comparing the number of pixels with the preset pixel threshold, and determining a tilt detection result of the workpiece loading plate according to the comparison result.

[0006] Optionally, the coating machine workpiece loading plate tilt detection system also includes: a reference object module; the reference object module is arranged in the vacuum chamber; the sampling area acquisition module is configured to: obtain edge feature parameters of the reference object module, and establish the at least one sampling area according to the edge feature parameters.

[0007] Optionally, the reference object module is arranged in the image acquisition area of ​​the image acquisition module; the image acquisition module is further configured to: acquire the second image data of the reference object module; the image processing module is further configured to: at least perform edge extraction and straight line fitting on the second image data; the sampling area acquisition module is configured to: determine the edge feature parameters according to the edge straight line fitting result of the reference object module.

[0008] Optionally, the edge feature parameters include at least an edge line inclination angle and endpoint coordinates; and the sampling area is a rectangular area established based on the edge line inclination angle and the endpoint coordinates.

[0009] Optionally, the image acquisition module includes: a camera and a light source, the camera and the light source are fixedly mounted on the outside of the window; the imaging area of ​​the camera covers the entire area of ​​the sampling area and at least a portion of the workpiece loading plate; the effective illumination area of ​​the light source covers the entire area of ​​the sampling area and at least a portion of the workpiece loading plate.

[0010] Optionally, the at least one sampling area includes a first sampling area and a second sampling area located on both sides of the same workpiece loading plate; wherein, the first sampling area has a first edge line on the side facing the workpiece loading plate, and the second sampling area has a second edge line on the side facing the workpiece loading plate, the first edge line and the second edge line are established based on a reference boundary line of the workpiece loading plate at an ideal position, and the interval distance between the first edge line and the reference boundary line is less than a preset unit pixel size, and the interval distance between the second edge line and the reference boundary line is less than a preset unit pixel size; the tilt analysis module is configured to: determine the preset pixel threshold according to the area size of the sampling area.

[0011] Optionally, the at least one sampling area includes a third sampling area, and when the workpiece loading plate is located at an ideal position, the projection of the third sampling area on the workpiece loading plate all falls into the workpiece loading plate; the third sampling area has a first size along the width direction of the workpiece loading plate, and the workpiece loading plate has a second size along the width direction of the workpiece loading plate, and the first size is equal to or approximately equal to the second size; the tilt analysis module is configured to: determine the preset pixel point threshold according to the area size of the sampling area.

[0012] Optionally, the coating machine workpiece loading plate tilt detection system also includes: a warning module and / or a cleaning module; the warning module is used to issue corresponding warning information according to the tilt detection result of the workpiece loading plate; the cleaning module is used to perform cleaning operations on the coating machine workpiece loading plate tilt detection system.

[0013] According to another aspect of the present invention, a method for detecting the inclination of a workpiece loading plate of a coating machine is provided, the coating machine comprising a vacuum chamber, a viewing window and a workpiece loading plate, and the method is performed using the above-mentioned system for detecting the inclination of the workpiece loading plate of the coating machine, the method comprising: establishing at least one sampling area in the surrounding area of ​​the workpiece loading plate; acquiring first image data of the sampling area; binarizing the first image data and acquiring the number of pixels in the sampling area; acquiring a preset pixel threshold, comparing the number of pixels with the preset pixel threshold, and determining a result of detecting the inclination of the workpiece loading plate based on the comparison result.

[0014] According to another aspect of the present invention, a coating device is provided, comprising: the above-mentioned coating machine workpiece loading plate tilt detection system.

[0015] The technical solution of the embodiment of the present invention is to set up a sampling area acquisition module, an image acquisition module, an image processing module and a tilt analysis module. At least one sampling area is established in the surrounding area of ​​the workpiece loading plate through the sampling area acquisition module, and the first image data of the sampling area is acquired through the image acquisition module. The image processing module performs binarization processing on the first image data and acquires the number of pixels in the sampling area; the tilt analysis module compares the number of pixels with a preset pixel threshold, and determines whether the workpiece loading plate is tilted according to the comparison result, thereby solving the problem of large error and low efficiency of the existing tilt detection method. The tilt of the workpiece loading plate of the coating machine is detected by pixel extraction. The tilt detection algorithm is simple and has strong real-time performance, which effectively improves the detection efficiency and accuracy.

[0016] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 A schematic structural diagram of a coating machine provided by an embodiment of the present invention;

[0019] Figure 2 A schematic structural diagram of a coating machine workpiece loading plate tilt detection system provided by the first embodiment of the present invention;

[0020] Figure 3 A schematic diagram of the layout position of a sampling area provided in the first embodiment of the present invention;

[0021] Figure 4 A schematic diagram of another sampling area layout position provided for the first embodiment of the present invention;

[0022] Figure 5 A schematic structural diagram of a coating machine workpiece loading plate tilt detection system according to an alternative embodiment of the present invention;

[0023] Figure 6 A schematic structural diagram of a coating machine workpiece loading plate tilt detection system provided by a second embodiment of the present invention;

[0024] Figure 7 A schematic structural diagram of a coating machine workpiece loading plate tilt detection system provided by a third embodiment of the present invention;

[0025] Figure 8 A flow chart of a method for detecting the tilt of a workpiece loading plate of a coating machine provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] Figure 1 A schematic structural diagram of a coating machine provided by an embodiment of the present invention; Figure 2This is a schematic structural diagram of a system for detecting the tilt of a workpiece loading plate of a coating machine provided in the first embodiment of the present invention. This embodiment is applicable to application scenarios where the tilt of a workpiece loading plate in a coating machine is detected based on image recognition technology.

[0029] like Figure 1 As shown, the coating machine includes a vacuum chamber 01, a viewing window 02 and a workpiece loading plate 03. The workpiece loading plate 03 can be fixed on a transport trolley. During the film forming operation, the workpiece loading plate 03 is transported to the vacuum chamber 01 by the transport trolley. The viewing window 02 is set on any side wall of the vacuum chamber 01, and the viewing window 02 is provided with a viewing mirror, so that the operator can observe the situation inside the vacuum chamber 01 through the viewing window 02; or, use a camera to shoot the situation inside the vacuum chamber 01 through the viewing window 02.

[0030] like Figure 2 As shown, the tilt detection system includes: a sampling area acquisition module 100, an image acquisition module 200, an image processing module 300 and a tilt analysis module 400.

[0031] The sampling area acquisition module 100 is used to establish at least one sampling area in the surrounding area of ​​the workpiece loading plate 03. The area where the workpiece loading plate 03 is located is a highlight area, and the sampling area can be preferably a rectangular area. The rectangular area can be established based on the boundary line of the workpiece loading plate 03 in the ideal position (i.e., the non-tilted position). If the workpiece loading plate 03 is defined to be in the ideal position (i.e., the non-tilted position), the workpiece loading plate 03 has two reference boundary lines in the image shooting plane. When establishing the sampling area, it can be set that at least one side of the rectangular area is basically coincident with one of the two reference boundary lines. Typically, the establishment of the sampling area can adopt any of the following technical solutions: two sampling areas are established on both sides of the same workpiece loading plate 03, and the edge lines of the two sampling areas facing the side of the workpiece loading plate 03 coincide with the two reference boundary lines of the workpiece loading plate 03 in the ideal position (i.e., the non-tilted position); or, a sampling area is established in the overlapping area of ​​the workpiece loading plate, and the two edge lines of the sampling area coincide with the two reference boundary lines of the workpiece loading plate 03 in the ideal position (i.e., the non-tilted position) so as to identify the area position based on the number of pixels in the sampling area. Preferably, the area of ​​the sampling region may be equal to an integer multiple of the unit pixel value.

[0032] The image acquisition module 200 is arranged outside the window 02. The image sampling range of the image acquisition module 200 completely covers the sampling area and is used to obtain the first image data of the sampling area. In an embodiment of the present invention, the image acquisition module 200 can set the image data acquisition cycle and the single acquisition duration according to the moving speed of the transport vehicle.

[0033] The image processing module 300 is used to perform a binarization process on the first image data and obtain the number of pixels in the sampling area. In an embodiment of the present invention, the image of the sampling area can be binarized, and the sub-pixel level edge detection can be performed on the binarized image, the edges whose lengths do not meet the requirements are removed, and the image is denoised by mean filtering. For example, if the binarization interval range is defined as: the pixel value is greater than or equal to 220, and the pixel value is less than or equal to 250, then after the binarization process, the pixel values ​​of the pixels within the range of [220, 255] are set to 255, and the pixel values ​​of the pixels outside the range of [220, 255] are set to 0. The number of pixels represents the number of pixels whose pixel values ​​are equal to 255 or whose pixel values ​​are equal to 0.

[0034] The tilt analysis module 400 is used to obtain a preset pixel threshold, compare the number of pixels with the preset pixel threshold, and determine the tilt detection result of the workpiece loading plate according to the comparison result. In this embodiment, the tilt analysis module 400 is configured to: determine the preset pixel threshold according to the area size of the sampling area.

[0035] In some embodiments, the image processing module 300 and the tilt analysis module 400 may be integrated into the same programmable logic controller (PLC).

[0036] For example, if the area size of the defined sampling region is equal to 50,000 unit pixel sizes, the preset pixel threshold may be set to 500.

[0037] Take the case where two sampling areas are established on both sides of the same workpiece loading plate 03, and the number of pixels is the number of pixels with a pixel value equal to 255; the image acquisition module 200 collects the first image data intercepted by the two sampling areas on the original image in real time; the image processing module 300 performs binarization processing on the first image data, and counts the number of pixels with a pixel value equal to 255 in the two sampling areas. If the number of pixels in the two sampling areas is less than or equal to the preset pixel threshold (for example, 500), it is determined that the workpiece loading plate 03 is not tilted; if the number of pixels in any one of the sampling areas is greater than the preset pixel threshold (for example, 500), it is determined that the workpiece loading plate is tilted.

[0038] Taking the example of establishing a sampling area in the area where the workpiece loading plate is located, and the number of pixels is the number of pixels with a pixel value equal to 0, the two edge lines of the sampling area coincide with the two reference boundaries of the workpiece loading plate 03 in the ideal position (i.e., the non-tilted position), and the image acquisition module 200 collects the first image data in the sampling area in real time; the image processing module 300 performs binarization processing on the first image data and counts the number of pixels with a pixel value equal to 0. If the number of pixels is less than or equal to a preset pixel threshold (e.g., 500), it is determined that the workpiece loading plate is not tilted; if the number of pixels is greater than the preset pixel threshold (e.g., 500), it is determined that the workpiece loading plate is tilted.

[0039] Therefore, the technical solution of the present invention performs tilt detection on the workpiece loading plate of the coating machine through pixel point extraction, which solves the problems of large errors and low efficiency of the existing tilt detection method. The tilt detection algorithm is simple and has strong real-time performance, which effectively improves the detection efficiency and accuracy.

[0040] Figure 3 A schematic diagram of the layout position of a sampling area provided in the first embodiment of the present invention. This embodiment is applicable to an application scenario in which tilt detection is performed based on two sampling areas.

[0041] like Figure 3 As shown, two sampling areas are established on both sides of the same workpiece loading plate 03, such as the first sampling area A1 and the second sampling area A2. The sampling area is located between any two adjacent workpiece loading plates 03. The first sampling area A1 has a first edge line on the side facing the workpiece loading plate 03, and the second sampling area A2 has a second edge line on the side facing the workpiece loading plate 03. The first edge line and the second edge line are established based on the reference boundary line of the workpiece loading plate 03 at an ideal position (i.e., a non-tilted position), and the spacing distance between the first edge line and the reference boundary line of the workpiece loading plate at the ideal position is less than a preset unit pixel size (e.g., a 50 unit pixel size), and the spacing distance between the second edge line and the reference boundary line of the workpiece loading plate at the ideal position is less than a preset unit pixel size (e.g., a 50 unit pixel size). When the workpiece loading plate 03 is at an ideal position (i.e., a non-tilted position), the sampling area does not overlap with the workpiece loading plate 03 at all.

[0042] Combination Figure 3As shown, the image capture plane of the image acquisition module 200 is defined as S, a virtual coordinate system is established at the upper left corner of the image capture plane S, and the first side of the image capture plane S is defined as the positive direction of the Y axis downward, and the second side of the image capture plane S perpendicular to the first side is defined as the positive direction of the X axis to the right. The first sampling area A1 is located on the left side of the workpiece loading plate 03, and the second sampling area A2 is located on the right side of the workpiece loading plate 03. The left side of the workpiece loading plate 03 has a first reference boundary line, and the right side of the workpiece loading plate 03 has a second reference boundary line. When establishing the first sampling area A1, the first reference boundary line of the workpiece loading plate 03 can be used as a rectangular side to establish the first sampling area A1, so that the first edge line on the right side of the first sampling area A1 is approximately coincident with the first reference boundary line of the workpiece loading plate 03; when establishing the second sampling area A2, the second reference boundary line of the workpiece loading plate 03 can be used as a rectangular side to establish the second sampling area A2, so that the second edge line on the left side of the second sampling area A2 is approximately coincident with the second reference boundary line of the workpiece loading plate 03. The area sizes of the first sampling area A1 and the second sampling area A2 are configured according to actual needs and are not limited thereto.

[0043] During the tilt detection process, the length dimension of the first sampling area A1 is defined as 150 unit pixel dimensions, and the width dimension is defined as 70 unit pixel dimensions. The image intercepted by the first sampling area A1 on the original image is binarized, and the interval range is defined as [220, 255], that is, the pixel values ​​of the pixels in the range of [220, 255] are all set to 255, and the pixel values ​​of the pixels outside the range of [220, 255] are all set to 0. Then, the number of pixels with a pixel value of 255 in the image intercepted by the first sampling area A1 is counted. If the number of pixels with a pixel value of 255 in the first sampling area A1 is greater than a preset pixel threshold (for example, 500), it is determined that the workpiece loading plate is tilted.

[0044] The principle of tilt detection based on the number of pixels in the second sampling area A2 is the same as that of the first sampling area A1 and will not be described in detail.

[0045] It can be understood that only when the number of pixels with a pixel value of 255 in the images captured by the first sampling area A1 and the second sampling area A2 is less than the preset pixel threshold, it can be determined that the workpiece loading plate is not tilted.

[0046] Figure 4 This is a schematic diagram of another sampling area layout position provided in the first embodiment of the present invention. This embodiment is suitable for application scenarios in which tilt detection is performed based on one sampling area.

[0047] Combination Figure 4As shown, a sampling area, namely the third sampling area A3, is established in the overlapping area of ​​the workpiece loading plate. When the workpiece loading plate 03 is located in an ideal position (ie, not tilted), the projection of the third sampling area A3 on the workpiece loading plate 03 falls entirely into the workpiece loading plate 03.

[0048] Combination Figure 4 As shown, the image capture plane of the image acquisition module 200 is defined as S, a virtual coordinate system is established at the upper left corner of the image capture plane S, and the first side of the image capture plane S is defined as the positive direction of the Y axis downward, and the second side of the image capture plane S that is perpendicular to the first side is defined as the positive direction of the X axis to the right. The third sampling area A2 has a first size along the width direction of the workpiece loading plate 03 (i.e., the X axis direction), and the workpiece loading plate 03 has a second size along the width direction of the workpiece loading plate (i.e., the X axis direction), and the first size is equal to or approximately equal to the second size.

[0049] During the tilt detection process, the length dimension of the third sampling area A3 is defined as 150 unit pixel dimensions, and the width dimension is defined as 70 unit pixel dimensions. The image intercepted by the third sampling area A3 on the original image is binarized, and the interval range is defined as [220, 255], that is, the pixel values ​​of the pixel points within the range of [220, 255] are all set to 255, and the pixel values ​​of the pixel points outside the range of [220, 255] are all set to 0. Then, the number of pixels with a pixel value of 0 in the image intercepted by the third sampling area A3 is counted. If the number of pixels is greater than a preset pixel threshold (for example, 500), it is determined that the workpiece loading plate is tilted.

[0050] In some other embodiments, the length dimension of the third sampling area A3 may also be set to 250 unit pixel dimensions, and the width dimension may be set to 200 unit pixel dimensions.

[0051] It should be noted that after the length and width of the sampling area are adjusted, the value of the preset pixel threshold can be adjusted accordingly. For example, the larger the area of ​​the sampling area, the larger the value of the preset pixel threshold. The specific vertex coordinates, length and width dimensions and preset pixel threshold of the sampling area can be configured according to the actual needs of the detection site, and there is no restriction on this.

[0052] Figure 5 A schematic diagram of a coating machine workpiece loading plate tilt detection system according to an alternative embodiment of the present invention is provided. Figure 2 On the basis of the illustrated embodiment, a specific implementation of an image acquisition module is exemplarily shown.

[0053] like Figure 5As shown, the image acquisition module 200 includes: a camera 201 and a light source 202, which are fixedly mounted on the outside of the window 02; the imaging area of ​​the camera 201 covers the entire area of ​​the sampling area and at least a portion of the workpiece loading plate; the effective illumination area of ​​the light source covers the entire area of ​​the sampling area and at least a portion of the workpiece loading plate, and the light source is used to enhance the light and dark contrast between the workpiece loading plate and the surrounding area.

[0054] In the embodiment of the present invention, the image data acquired by the camera 201 may be a black and white picture, and the light and dark contrast effect is enhanced by binarizing the image.

[0055] In one embodiment, the camera 201 may be an area array camera.

[0056] Specifically, for stationary detection or slow detection, an area array camera is usually preferred to make the captured image more intuitive and facilitate the extraction of two-dimensional image information. The resolution of the camera 201 can be set to 3840×2748. For example, the lens model selected is AZURE-0414M5M, with a resolution of 150lp / mm, a focal length of 4mm, and a back focus of 10.33mm.

[0057] Exemplarily, the camera 201 may be a Daheng image camera with a corresponding lens. The camera 201 has a synchronous acquisition function.

[0058] In one embodiment, the light source 202 may be a ring light source. The ring light source 202, the camera 201, and the lens matched with the camera 201 are all installed outside the endoscope on the side of the vacuum chamber 01, forming the image acquisition module 200 of the detection system. By setting the ring light source and the area array camera, the quality of the sampled image data is enhanced, and image recognition and tilt detection effects are provided.

[0059] Figure 6 The schematic structural diagram of a coating machine workpiece loading plate tilt detection system provided in the second embodiment of the present invention adds a specific implementation method of setting a sampling area based on a reference object on the basis of the first embodiment.

[0060] like Figure 6 As shown, the coating machine workpiece loading plate tilt detection system further includes: a reference module 500; the reference module 500 is arranged in the vacuum chamber 01. A first plane is arranged in the vacuum chamber 01.

[0061] In some embodiments, the projection of the reference module 500 on the first plane is located between the projections of any two adjacent workpiece loading plates 03 on the first plane, and the reference module 500 and the workpiece loading plates 03 have a fixed angle.

[0062] In some other embodiments, the projection of the reference module 500 on the first plane is located on the same side (eg, the left side) of the projections of all the workpiece loading plates 03 on the first plane.

[0063] like Figure 6 As shown, the reference object module 500 can be a cubic module or a rectangular module, and a rectangular reflective material is provided on the side of the reference object module 500 facing the viewing window 02; the rectangular reflective material is used to enhance the light-dark contrast between the reference object and the surrounding area. In the embodiment of the present invention, the reflective material can be the same material as the workpiece loading plate 03. Under the illumination of the annular light source 202, the rectangular reflective material is in a high-brightness state to enhance the light-dark contrast between the reference object module 500 and the surrounding area, which is beneficial to enhance the image edge extraction effect.

[0064] like Figure 6 As shown, the reference module 500 can be installed in the middle position of the two workpiece loading plates 03 that are placed correctly, and the reference module 500 is set in the image acquisition area of ​​the image acquisition module 200, so that the image acquisition module 200 can simultaneously acquire image data for the workpiece loading plates 03 and the reference module 500.

[0065] The sampling region acquisition module 100 is configured to: acquire edge feature parameters of the reference object module 500, and establish at least one sampling region according to the edge feature parameters.

[0066] Specifically, the sub-pixel edge extraction is performed on the binarized image through the relevant operator, and the edges whose length does not meet the requirements are eliminated. The edge information is fitted with a straight line, and the first end point on the straight line is used as the starting point and the distance of a fixed pixel value is extended to the left or right perpendicular to the straight line to determine the upper left corner end point of the sampling area for the specific area around the workpiece loading plate 03, and the length and width of the sampling area are set to intercept the image of the workpiece loading plate 03.

[0067] In this embodiment, the image acquisition module 200 is also configured to: obtain the second image data of the reference object module 500; the image processing module 300 is also configured to: at least perform edge extraction and straight line fitting on the second image data; the sampling area acquisition module 100 is configured to: determine the edge feature parameters based on the edge straight line fitting results of the reference object module.

[0068] In one embodiment, the image processing module 300 is further configured to: perform data processing on the edge information of the reference object module based on a preset length threshold, and perform straight line fitting on the edge information after data processing based on a preset weighted least squares method to establish the edge line of the reference object module corresponding to the feature area.

[0069] Specifically, the preset length threshold is the minimum edge line length required for straight line fitting. If the edge line length obtained by sub-pixel edge extraction is less than the preset length threshold, the edge data is deleted to eliminate the influence of outliers. In the straight line fitting algorithm, based on the principle of emphasizing near and ignoring far, the sum of squared deviations is weighted, and the sub-pixel edge data retained by the reference object module 500 is respectively fitted with a straight line in combination with the weighted least squares method to obtain the edge line. By setting a preset length threshold to remove outliers, performing straight line fitting on the data after the outliers are removed, and combining the weighted least squares method, the accuracy of straight line fitting can be improved, which is conducive to improving the accuracy of tilt detection results and improving the tilt detection effect.

[0070] Optionally, the edge feature parameters include at least an edge line inclination angle and endpoint coordinates; and the sampling area is a rectangular area established based on the edge line inclination angle and endpoint coordinates.

[0071] Specifically, the endpoint coordinates can be transformed based on the edge line inclination angle, and then, combined with the length and width dimensions of the sampling area, a rectangular figure in the tilted coordinate system is established so that the rectangular figure is relatively parallel to the tilted reference module 500.

[0072] For example, in conjunction with reference Figure 6 As shown, the image capture plane of the image acquisition module 200 is defined as S, and at least part of the area of ​​the reference module 500 falls within the image capture plane S. The image data of the area of ​​the reference module 500 that falls within the image capture plane S is the second image data, and the second image data is denoised by mean filtering, and the denoised second image data is binarized. For example, the interval range is set to [220, 255], that is, the pixel values ​​of the pixels in the range of [220, 255] are all set to 255, and the pixel values ​​of the pixels outside the range of [220, 255] are all set to 0. The edge is extracted by the Canny operator, and the first hysteresis threshold of the operator is 50, and the second hysteresis threshold is 100. The effect of the edge extracted straight line is displayed by Hough line detection.

[0073] A virtual coordinate system is established based on the image shooting plane S. For example, a virtual coordinate system is established at the upper left corner of the image shooting plane S. The first side of the image shooting plane S is defined as the positive direction of the Y axis, and the second side of the image shooting plane S perpendicular to the first side is defined as the positive direction of the X axis. All edge points extracted by the Canny operator are fitted with a straight line to obtain an edge fitting line L, and the coordinates of the two endpoints of the edge fitting line L are extracted to obtain the inclination angle of the edge fitting line L, and the angle is converted into radians. If the inclination angle of the reference object module 500 is defined as Angle, the inclination angle Angle can be equal to the angle between the edge fitting line L and the Y axis, plus 90°. After conversion from radians, the inclination angle can be expressed as (Angle*π) / 180.

[0074] Combination Figure 6 As shown, two sampling areas are established on both sides of the same workpiece loading plate 03 ( Figure 6 Only the sampling area A) located on the left side of the workpiece loading plate 03 is shown as an example. In the process of establishing the sampling area, the upper end point D0 of the fitting line L is taken as the foot of the perpendicular, and the preset extension distance is extended in the direction perpendicular to the fitting line L and toward the workpiece loading plate 03, which is the radius R. The coordinates of the upper left corner vertex of the sampling area A are calculated by the following formula: X1=X0+R*Cos[(Angle*π) / 180]; Y1=Y0+R*Sin[(Angle*π) / 180]. Among them, X1, Y1 are the calculated coordinates of the upper left corner vertex, X0, YO are the coordinates of the upper end point D0 of the fitting line L, R is the radius, and Angle is the inclination angle. Combined with Figure 6 As shown, after obtaining the coordinates of the upper left corner vertex, the edge line on the left side of the sampling area A is determined by combining the length dimension of the sampling area and the tilt angle of the reference module 500, and then the edge line on the right side of the sampling area A is determined by combining the width dimension of the sampling area and the tilt angle of the reference module 500, so that the edge line on the right side of the sampling area A approximately coincides with the reference boundary line on the left side of the workpiece loading plate 03. During the tilt detection process, the image in the sampling area A is binarized, and the number of pixels with a pixel value of 255 in the sampling area is counted. Based on the number of pixels, the above technical solution is used to determine whether the workpiece loading plate 03 is tilted. The specific analysis process refers to the above embodiment and will not be repeated here. By constructing the sampling area with a reference object, the influence of a slight tilt of the camera on the detection result can be avoided, thereby improving the accuracy of image recognition and tilt detection.

[0075] Figure 7 A schematic structural diagram of a coating machine workpiece loading plate tilt detection system provided in the third embodiment of the present invention adds additional functions such as warning and / or cleaning on the basis of the first embodiment.

[0076] like Figure 7As shown, the coating machine workpiece loading plate tilt detection system also includes: a warning module 600 and / or a cleaning module 700; the warning module 600 is used to issue corresponding warning information according to the tilt detection result of the workpiece loading plate; the cleaning module 700 is used to perform cleaning operations on the coating machine workpiece loading plate tilt detection system.

[0077] In one embodiment, the warning module 600 includes but is not limited to: any one or a combination of multiple items of a display screen, an audible and visual alarm, or an intelligent terminal device.

[0078] In one embodiment, the cleaning module 700 can be used to clean the reference object module 500 and the image acquisition module 200. By cleaning the reference object and the camera lens, the identifiability of the reference object is improved, the image quality is improved, and the tilt detection effect is improved.

[0079] In an embodiment of the present invention, after cleaning the hardware module, before the workpiece loading plate 03 enters the vacuum chamber 01, the initial angle of the reference module 500 can be obtained first; after the workpiece loading plate 03 enters the vacuum chamber 01, a sampling area is constructed around the workpiece loading plate 03 through a reference object, and the number of pixels in the sampling area is obtained through image recognition technology, and whether the workpiece loading plate is tilted is determined based on the number of pixels. The sampling area is constructed based on the reference object, and the number of pixels in the sampling area is less affected by the change of the camera position, and the system has strong adaptability, which improves the convenience and efficiency of system maintenance while ensuring the detection results.

[0080] In one embodiment, the image processing module 300 is configured to: filter the image data based on a preset filtering algorithm to obtain a filtered image; adjust the contrast of the filtered image based on a preset image enhancement algorithm to obtain a contrast enhanced image; and capture the feature area of ​​the contrast enhanced image based on preset coordinates, and perform sub-pixel extraction of edge information of the feature area based on a preset edge algorithm.

[0081] In an embodiment of the present invention, the preset filtering algorithm includes but is not limited to: mean filtering algorithm and bilateral filtering algorithm. Bilateral filtering traverses the entire image based on the set window size, compares all pixel values ​​in the window with the center point pixel, obtains the size of the spatial domain kernel and the image pixel domain kernel, and multiplies the two as the eigenvalue of the point; adds the product of the eigenvalue of each point and the pixel value of the point, divides it by the sum of all eigenvalues, and the result is the pixel value of the center point.

[0082] Exemplarily, the calculation formula of mean filtering can be expressed as the following formula 1:

[0083]

[0084] Among them, f(x,y) represents the pixel mean in the filter window to be calculated, g(x,y) represents the input pixel value, and γ is used to represent the filter window size. If γ is defined as 1, the filter window size is 3×3.

[0085] The bilateral filtering algorithm uses a two-dimensional Gaussian function to generate a spatial domain template and a one-dimensional Gaussian function to generate a range template. Based on this, its calculation formula is divided into two parts, namely the spatial domain kernel (also known as the spatial coefficient) and the range kernel (also known as the range coefficient).

[0086] Exemplarily, the calculation formula of the spatial domain kernel is shown in Formula 2:

[0087]

[0088] Among them, (i, j) represents the coordinates of other coefficients of the template window, (k, l) is the coordinates of the center point of the template window, σ d is the standard deviation of the Gaussian function, and the weight ω d Represents the spatial domain kernel.

[0089] The calculation formula of the range kernel is shown in Formula 3:

[0090]

[0091] Among them, f(i,j) represents the pixel value of the image at the coordinate (i,j), f(k,l) represents the pixel value at the center point (k,l), ω r Represents the range kernel.

[0092] Multiply the above two templates to get the template weight of bilateral filtering, as shown in Formula 4:

[0093]

[0094] Therefore, the calculation formula for bilateral filtering is as follows:

[0095]

[0096] Among them, g(i,j) represents the pixel mean in the filter window to be determined; f(k,l) represents the pixel value at the center point (k,l).

[0097] In an embodiment of the present invention, the preset image enhancement algorithm may be an Emphasize image enhancement algorithm. Under the illumination of a light source, the sampling area has obvious reflections, and the grayscale value of the edge information of the image captured by the camera changes significantly. Based on the Emphasize image enhancement algorithm, a linear grayscale transformation is performed on the image edges and corners to make the bright positions in the image brighter and the dark positions darker, thereby enhancing the local contrast without affecting the overall contrast and making the edges look clearer.

[0098] For example, the calculation formula of the preset image enhancement algorithm can be expressed as the following formula 6:

[0099] res:=round((orig-mean)*Factor)+orig (Formula 6)

[0100] Among them, the new pixel value res is equal to the pixel value of the original image at that point minus the average pixel value of the pixel values ​​of all points within the kernel size range, and this result is approximately rounded, the result can be positive or negative, and then this value is added to the original pixel value of this point to obtain the final result to replace the original pixel value of this point.

[0101] In the embodiment of the present invention, the Canny edge detection operator may be used to perform sub-pixel extraction of edge information.

[0102] Based on the same inventive concept, an embodiment of the present invention provides a method for detecting the inclination of a workpiece loading plate of a coating machine. The coating machine includes a vacuum chamber, a window and a workpiece loading plate, and is executed using a coating machine workpiece loading plate inclination detection system provided by any of the above embodiments.

[0103] Figure 8 A flow chart of a method for detecting the tilt of a workpiece loading plate of a coating machine provided in an embodiment of the present invention.

[0104] like Figure 8 As shown, the coating machine workpiece loading plate tilt detection method includes the following steps:

[0105] S1: Establish at least one sampling area in the surrounding area of ​​the workpiece loading plate.

[0106] S2: Acquire first image data of the sampling area.

[0107] S3: Binarize the first image data and obtain the number of pixels in the sampling area.

[0108] S4: Obtain a preset pixel threshold, compare the number of pixels with the preset pixel threshold, and determine the tilt detection result of the workpiece loading plate according to the comparison result.

[0109] In some embodiments, at least one sampling area includes a first sampling area and a second sampling area located on both sides of the same workpiece loading plate; wherein the first sampling area has a first edge line on the side facing the workpiece loading plate, and the second sampling area has a second edge line on the side facing the workpiece loading plate, and the first edge line and the second edge line are established based on the reference boundary line of the workpiece loading plate at an ideal position, and the spacing distance between the first edge line and the reference boundary line is less than a preset unit pixel size, and the spacing distance between the second edge line and the reference boundary line is less than a preset unit pixel size. The coating machine workpiece loading plate tilt detection method also includes determining a preset pixel threshold according to the area size of the sampling area.

[0110] In some other embodiments, at least one sampling area includes a third sampling area, and when the workpiece loading plate is located at an ideal position, the projection of the third sampling area on the workpiece loading plate falls entirely into the workpiece loading plate; the third sampling area has a first size along the width direction of the workpiece loading plate, and the workpiece loading plate has a second size along the width direction of the workpiece loading plate, and the first size is equal to or approximately equal to the second size; the coating machine workpiece loading plate tilt detection method further includes determining a preset pixel point threshold value according to the area size of the sampling area. Determine the preset pixel point threshold value according to the area size of the sampling area.

[0111] In one embodiment, the coating machine workpiece loading plate tilt detection method further includes: configuring a reference object module in the vacuum chamber, acquiring edge feature parameters of the reference object module, and establishing at least one sampling area according to the edge feature parameters.

[0112] In one embodiment, the reference object module is arranged in the image acquisition area of ​​the image acquisition module; the coating machine workpiece loading plate tilt detection method also includes: acquiring second image data of the reference object module; performing edge extraction and straight line fitting on the second image data; and determining edge feature parameters according to the edge straight line fitting result of the reference object module.

[0113] In one embodiment, the edge feature parameters include at least an edge line inclination angle and endpoint coordinates; and the sampling area is a rectangular area established based on the edge line inclination angle and endpoint coordinates.

[0114] In one embodiment, the coating machine workpiece loading plate tilt detection method further includes: using a light source to irradiate the sampling area and the workpiece loading plate, and the effective irradiation area of ​​the light source covers the entire area of ​​the sampling area and at least a portion of the area of ​​the workpiece loading plate.

[0115] In one embodiment, the light source is a ring-shaped light source.

[0116] In one embodiment, the sampling area is located between any two adjacent workpiece loading plates, or the projection of the sampling area on the workpiece loading plate is completely located on the side of the workpiece loading plate facing the image acquisition module; wherein the area of ​​the sampling area is equal to an integer multiple of a unit pixel; the coating machine workpiece loading plate tilt detection method also includes: determining a preset pixel threshold according to the area size of the sampling area.

[0117] In one embodiment, the workpiece loading plate tilt detection method further includes: cleaning the reference module and the image acquisition module; after the cleaning is completed, recording and storing the initial angle of the reference module.

[0118] Based on any of the above embodiments, an embodiment of the present invention further provides a coating device, including: the coating machine workpiece loading plate tilt detection system provided by any of the above embodiments, having the corresponding functional modules and beneficial effects of the coating machine workpiece loading plate tilt detection system.

[0119] In this embodiment, the coating equipment can issue an alarm message to the coating operator based on the tilt detection result of the workpiece loading plate given by the workpiece loading plate tilt detection system of the coating machine, or output the corresponding workpiece loading plate adjustment strategy so that the coating operator can correct the tilt defect in time.

[0120] The coating equipment of the embodiment of the present invention is provided with a sampling area acquisition module, an image acquisition module, an image processing module and a tilt analysis module. At least one sampling area is established in the surrounding area of ​​the workpiece loading plate through the sampling area acquisition module, the first image data of the sampling area is acquired through the image acquisition module, the image processing module performs binarization processing on the first image data, and acquires the number of pixels in the sampling area; the tilt analysis module compares the number of pixels with a preset pixel threshold, and determines whether the workpiece loading plate is tilted according to the comparison result, thereby solving the problem of large error and low efficiency of the existing tilt detection method. The tilt of the workpiece loading plate of the coating machine is detected through pixel extraction. The tilt detection algorithm is simple, which effectively improves the detection efficiency and accuracy, avoids the tilt of the workpiece loading plate in the coating machine affecting the coating, and is beneficial to improving the efficiency of the coating operation.

[0121] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0122] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A coating machine workpiece loading plate tilt detection system, the coating machine comprising a vacuum chamber, a viewing window and a workpiece loading plate, characterized in that: The tilt detection system comprises: A sampling area acquisition module, used to establish at least one sampling area in the surrounding area of ​​the workpiece loading plate; An image acquisition module, used for acquiring first image data of the sampling area; An image processing module, used for performing binarization processing on the first image data and obtaining the number of pixels in the sampling area; The tilt analysis module is used to obtain a preset pixel threshold, compare the number of pixels with the preset pixel threshold, and determine the tilt detection result of the workpiece loading plate according to the comparison result.

2. The coating machine workpiece loading plate tilt detection system according to claim 1, characterized in that: Also includes: Reference module; The reference object module is disposed in the vacuum chamber; The sampling region acquisition module is configured to: acquire edge feature parameters of the reference object module, and establish the at least one sampling region according to the edge feature parameters.

3. The coating machine workpiece loading plate tilt detection system according to claim 2, characterized in that: The reference object module is arranged in the image acquisition area of ​​the image acquisition module; The image acquisition module is further configured to: acquire second image data of the reference object module; The image processing module is further configured to: at least perform edge extraction and straight line fitting on the second image data; The sampling area acquisition module is configured to determine the edge feature parameter according to the edge straight line fitting result of the reference object module.

4. The coating machine workpiece loading plate tilt detection system according to claim 3, characterized in that: The edge feature parameters include at least the edge line inclination angle and the endpoint coordinates; The sampling area is a rectangular area established based on the edge line inclination angle and the endpoint coordinates.

5. The coating machine workpiece loading plate tilt detection system according to claim 1, characterized in that: The image acquisition module includes: a camera and a light source, wherein the camera and the light source are fixedly mounted outside the window; The imaging area of ​​the camera covers the entire area of ​​the sampling area and at least a portion of the area of ​​the workpiece loading plate; The effective irradiation area of ​​the light source covers the entire area of ​​the sampling area and at least a part of the area of ​​the workpiece loading plate.

6. The coating machine workpiece loading plate tilt detection system according to any one of claims 1 to 5, characterized in that: The at least one sampling area includes a first sampling area and a second sampling area located on both sides of the same workpiece loading plate; Wherein, the first sampling area has a first edge line on one side facing the workpiece loading plate, and the second sampling area has a second edge line on one side facing the workpiece loading plate, the first edge line and the second edge line are established based on a reference boundary line of the workpiece loading plate at an ideal position, and the interval between the first edge line and the reference boundary line is less than a preset unit pixel size, and the interval between the second edge line and the reference boundary line is less than a preset unit pixel size; The tilt analysis module is configured to determine the preset pixel threshold according to the area size of the sampling region.

7. The coating machine workpiece loading plate tilt detection system according to any one of claims 1 to 5, characterized in that: The at least one sampling area includes a third sampling area, and when the workpiece loading plate is located at an ideal position, the projection of the third sampling area on the workpiece loading plate all falls into the workpiece loading plate; The third sampling area has a first size along the width direction of the workpiece loading plate, the workpiece loading plate has a second size along the width direction of the workpiece loading plate, and the first size is equal to or approximately equal to the second size; The tilt analysis module is configured to determine the preset pixel threshold according to the area size of the sampling region.

8. The coating machine workpiece loading plate tilt detection system according to any one of claims 1 to 5, characterized in that: Also includes: Warning module and / or cleaning module; The warning module is used to issue corresponding warning information according to the tilt detection result of the workpiece loading plate; The cleaning module is used to perform a cleaning operation on the coating machine workpiece loading plate tilt detection system.

9. A method for detecting the tilt of a workpiece loading plate of a coating machine, wherein the coating machine comprises a vacuum chamber, a viewing window and a workpiece loading plate, wherein: The method is performed by using the coating machine workpiece loading plate tilt detection system according to any one of claims 1 to 8, and comprises: establishing at least one sampling area in the surrounding area of ​​the workpiece loading plate; Acquire first image data of the sampling area; Binarizing the first image data and obtaining the number of pixels in the sampling area; A preset pixel point threshold is obtained, the number of pixels is compared with the preset pixel point threshold, and a tilt detection result of the workpiece loading plate is determined according to the comparison result.

10. A coating device, characterized in that: include: A coating machine workpiece loading plate tilt detection system as described in any one of claims 1 to 8.

Images