Method and product for machine vision inspection of the shape and position of a filamentous brush array of a conductive slip ring

Abstract

An embodiment of the present invention provides a method and product for machine vision inspection of the shape and position of a filamentous brush array of a conductive slip ring, which relates to the technical field of machine vision inspection. The embodiment of the present invention can collect the images of the brushes to be inspected based on a single camera to realize the rapid inspection of the shape and position of the filamentous brush array of the conductive slip ring. In the embodiment of the present invention, based on the projection method to determine the range of the rectangular tolerance area of the brush wire top feature points corresponding to the feature dot matrix of the brush group, the position deviation value of the brush wire feature point coordinates can be accurately measured, which is beneficial to optimizing the conductive performance by combining the conductive parameter inspection, and further improving the conductive performance of the slip ring.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of machine vision inspection, and in particular to a method and product for machine vision inspection of the shape and position of a filamentary brush array of a conductive slip ring. Background Art

[0002] A conductive slip ring using filamentary brushes is an important component widely used in precision rotating devices such as pan-tilt heads, gyroscopes, and inertial platforms. This precision conductive slip ring realizes signal and current transmission between a fixed position and a continuously rotating mechanism through the sliding contact between a conductive ring and filamentary elastic brush filaments (hereinafter referred to as brush filaments). The contact state between the brush filaments and the ring track is an important factor affecting the conductive performance and service life of the slip ring. Because during the assembly of the slip ring, the welding of the brush filament leads, and the glue sealing process, it is easy to cause deformation or position deviation of the brush filaments. Therefore, on-line inspection of the shape and position of the brush filaments is an important link in the manufacturing process of the slip ring.

[0003] Since the brush filaments are soft, elastic, and arranged in a fine array, it is difficult to automatically detect their shape and position parameters by contact methods. At present, in the industry, the shape and position of the brush filaments are mainly detected manually using tools such as angle plates. The angle plate is printed with standard scale lines corresponding to the inclination angles of the brush filaments to be inspected. The operator manually compares the inclination angles of the brush filaments with the standard scale lines column by column to determine whether the shape and position of the brush filaments are qualified. This qualitative detection method cannot measure the actual position parameters of the brush filaments, and manual inspection is time-consuming and laborious and prone to introducing human errors.

[0004] Therefore, there is an urgent need for a new method for machine vision inspection of the shape and position of a filamentary brush array of a conductive slip ring to improve the efficiency and accuracy of machine vision inspection of the shape and position of a filamentary brush array of a conductive slip ring. Summary of the Invention

[0005] The embodiments of the present invention provide a method, device, electronic device, and storage medium for machine vision inspection of the shape and position of a filamentary brush array of a conductive slip ring to at least partially solve the problems existing in the related art.

[0006] In a first aspect of the embodiments of the present invention, a method for machine vision inspection of the shape and position of a filamentary brush array of a conductive slip ring is provided. The method includes:

[0007] Collect an image of the brush to be inspected;

[0008] Determine the pixel size range of the image of the brush to be inspected according to the structural size of the filamentary brush array of the brush to be inspected;

[0009] Perform binarization processing on the image of the brush to be inspected to obtain a binary image of the brush filaments;

[0010] Process the binary image of the brush filaments, extract the contour array of the image of the top region of each brush filament of the brush to be inspected, and determine the coordinates of the inner feature points of the vertex of each brush filament;

[0011] Determine whether the coordinates of the feature points are within the rectangular tolerance area of the top feature points of the brush filaments. The rectangular tolerance area of the top feature points of the brush filaments is determined according to the horizontal tolerance and vertical tolerance of the inner feature points at the top of the brush filaments;

[0012] When the coordinates of the feature points are within the rectangular tolerance area of the top feature points of the brush filaments, it is determined that the current brush to be detected is qualified in terms of shape and position.

[0013] Optionally, the rectangular tolerance area of the top feature points of the brush filaments is determined according to the following steps:

[0014] Collect the image of the standard brush;

[0015] Extract the left side line of the brush filament base in the standard brush image based on the Canny operator;

[0016] Calculate the angle a formed by the left side line and the longitudinal axis of the image. Through rotation correction, make the left side line parallel to the longitudinal axis of the image, and determine the midpoint coordinates O(X0, Y0) of the left side line of the base in the rotation-corrected image;

[0017] Take the horizontal line passing through point O as the X-axis center line of the standard brush image. A pair of brush filaments in the same column of the standard brush are symmetrically distributed on both sides of the X-axis center line, and the distance H from the inner center points of the two roots of the brush filaments to the X-axis center line b is equal;

[0018] Calculate the standard distance H from the center point P 11 of the top of the brush filament to the X-axis center line y : H y = H b -L×Sinθ, where L is the brush filament arm length of the standard brush, and θ is the angle between the brush arm and the brush filament fixed at the root of the base;

[0019] Determine the other top feature point P 11 symmetric to the center point P 21 of the top of the brush filament. The distance from this point to the X-axis center line is also Hy, and obtain the reference coordinates Q 11 、P 21 of the projection points of the center points P 11 (Xq 11 , Yq 11 )、Q 21 (Xq 21 , Yq 21 ) of the image plane XOY:

[0020] Xq 11 = X0-H0

[0021] Y 11 = Y0-H y

[0022] Xq 21 = X0-H0

[0023] Y 21 = Y0+H y

[0024] Where H0 is the Q in the image plane 11 Q 21 The distance from the intersection with the center line of the X axis to the origin O;

[0025] Determine the projection Q of the inner feature point of the brush top in row i and column j ij Coordinates (Xq ij ,Yq ij ):

[0026] Xq ij = X0+H0+(j-1)×H x

[0027] Y ij = Y0+C i ×H y

[0028] Among them, i=1, 2; j=1, 2, ..., n; when i=1, C i The value is -1, Yq ij Refers to the vertical coordinate of the brush feature point in the first row. When i=2, C i The value is 1, Yq ij Refers to the reference vertical coordinate of the brush feature point in the second row; Hx represents the distance between a pair of brushes in different columns;

[0029] According to the brush wire inclination and parallelism tolerance requirements, determine the characteristic point Q on the inner side of the brush wire top ij The horizontal tolerance is dx, and the vertical tolerance is dy; get the value with O as the origin and point Q as the ij The rectangular tolerance zone T of the brush wire shape and position detection is centered ij (XT ij ,YT ij , 2dx, 2dy), where (XT ij ,YT ij ) is the coordinate of the upper left corner of this rectangle, 2dx and 2dy are its width and height, then:

[0030] XT ij = Xq ij -dx

[0031] YT ij = Yq ij -dy.

[0032] Optionally, the method further includes:

[0033] Performing rotation correction on the brush image to be detected according to the included angle a;

[0034] Wherein, the brush to be detected and the standard brush adopt the same tooling and clamping method.

[0035] Optionally, performing binarization processing on the brush image to be detected to obtain a brush wire binary image, including:

[0036] Based on the OTSU automatic threshold image segmentation algorithm of the grayscale image, performing threshold segmentation and erosion and dilation operations on the brush image to be detected to obtain a brush wire binary image.

[0037] Optionally, processing the brush wire binary image, extracting the contour array of the image of the top region of each brush wire of the brush to be detected, and determining the coordinates of the inner feature points of the vertex of each brush wire, including:

[0038] By calling the contour extraction function FindContours of OpenCV, extracting the contour array of the image of the top region of each brush wire;

[0039] Respectively extracting the inner feature point S of each brush wire vertex from the contour array of the image of the top region of each brush wire ij (Xs ij , Ys ij ), where i is the number of brush wire rows and j is the number of brush wire columns.

[0040] Optionally, respectively extracting the inner feature point S of each brush wire vertex from the contour array of the image of the top region of each brush wire ij (Xs ij , Ys ij ), including:

[0041] For the brush wire in the first row, taking the point with the smallest Y coordinate in its contour array as the inner feature point of the brush wire vertex;

[0042] For the brush wire in the second row, taking the point with the largest Y coordinate in its contour array as the inner feature of the brush wire vertex.

[0043] Optionally, the method further includes:

[0044] Recording the deviation of the feature points corresponding to each brush wire with respect to the rectangular tolerance range of the top feature points of the brush wire;

[0045] Detecting the electrical conductivity parameters of each brush wire and the assembled finished product with the raceway, and performing statistical analysis in combination with the deviation corresponding to each brush wire to optimize the design parameters of the brush.

[0046] Optionally, the step of acquiring an image includes:

[0047] Adopt a low-angle illumination method on both sides, adjust the light source angle to highlight the contour features of the top area of the brush filaments in the brush image, and make other parts of the brush and the base area become the background of the acquired brush image.

[0048] The second aspect of the embodiment of the present invention provides a position and shape machine vision detection device for a conductive slip ring filamentary brush array, and the device includes:

[0049] An acquisition module for acquiring an image of a brush to be detected;

[0050] A pixel size range determination module for determining the pixel size range of the image of the brush to be detected according to the structure size of the brush filament array of the brush to be detected;

[0051] A first processing module for performing binarization processing on the image of the brush to be detected to obtain a binary image of the brush filaments;

[0052] A second processing module for processing the binary image of the brush filaments, extracting the contour array of the top area image of each brush filament of the brush to be detected, and determining the coordinates of the inner feature points of the vertex of each brush filament;

[0053] A judgment module for judging whether the coordinates of the feature points are within the rectangular tolerance area range of the top feature points of the brush filaments, and the rectangular tolerance area range of the top feature points of the brush filaments is determined according to the horizontal tolerance and vertical tolerance of the inner feature points at the top of the brush filaments;

[0054] A determination module for determining that the position and shape of the currently detected brush are qualified when the coordinates of the feature points are within the rectangular tolerance area range of the top feature points of the brush filaments.

[0055] Optionally, the rectangular tolerance area range of the top feature points of the brush filaments is determined according to the following steps:

[0056] Acquire a standard brush image;

[0057] Extract the left side line of the brush base in the standard brush image based on the Canny operator;

[0058] Calculate the included angle a formed by the left side line and the longitudinal axis of the image, and make the left side line parallel to the longitudinal axis of the image through rotation correction, and determine the midpoint coordinates O(X0, Y0) of the left side line of the base in the rotation-corrected image;

[0059] Take the horizontal line passing through point O as the X-axis center line of the standard brush image. A pair of brush filaments in the same column of the standard brush are symmetrically distributed on both sides of the X-axis center line, and the distance H from the inner center points of the two roots of the brush filaments to the X-axis center line bEqual;

[0060] Calculate the center point P of the top of the brush wire 11 The standard distance H to the X-axis center line y : H y = H b -L×Sinθ, where L is the brush wire arm length of the standard brush, and θ is the angle between the brush arm and the brush wire fixed at the root of the base;

[0061] Determine another brush wire top feature point P 11 Symmetric to the center point P of the top of the brush wire 21 The distance to the X-axis center line is also Hy, and obtain the projection point reference coordinates Q of the center point P of the top 11 、P 21 In the image plane XOY 11 (Xq 11 , Yq 11 )、Q 21 (Xq 21 , Yq 21 ):

[0062] Xq 11 = X0-H0

[0063] Yq 11 = Y0-H y

[0064] Xq 21 = X0-H0

[0065] Yq 21 = Y0+H y

[0066] Where H0 is the distance from the intersection of Q 11 Q 21 And the X-axis center line to the origin O;

[0067] Determine the projection Q of the inner feature point of the top of the brush wire in the i-th row and j-th column ij Coordinates (Xq ij ,Yq ij ):

[0068] Xq ij = X0+H0+(j-1)×H x

[0069] Yq ij = Y0+C i ×H y

[0070] Where i = 1, 2; j = 1, 2,..., n; when i = 1, C iThe value is -1, Yq ij Refers to the ordinate of the feature point of the brush filaments in the first row. When i = 2, C i The value is 1, Yq ij Refers to the reference ordinate of the feature point of the brush filaments in the second row; Hx represents the distance between a pair of brush filaments in different columns;

[0071] According to the requirements of the brush filament inclination and parallelism tolerances, determine the inner feature point Q at the top of the brush filaments ij The lateral tolerance is dx, and the longitudinal tolerance is dy; Obtain the brush filament form and position detection rectangular tolerance zone T with O as the origin and point Q ij as the center ij (XT ij , YT ij , 2dx, 2dy), where (XT ij , YT ij ) are the coordinates of the upper left corner of this rectangle, and 2dx, 2dy are its width and height. Then there are:

[0072] XT ij = Xq ij -dx

[0073] YT ij = Yq ij -dy.

[0074] Optionally, the device further includes:

[0075] A correction module for rotating and correcting the image of the brush to be detected according to the included angle a;

[0076] Wherein, the brush to be detected and the standard brush adopt the same tooling and clamping methods.

[0077] Optionally, the first processing module is specifically configured to:

[0078] Based on the OTSU automatic threshold image segmentation algorithm of the grayscale image, perform threshold segmentation and erosion and dilation operations on the image of the brush to be detected to obtain a binary image of the brush filaments.

[0079] Optionally, the second processing module includes:

[0080] A first extraction sub-module for extracting the contour array of the image of the top region of each brush filament by calling the contour extraction function FindContours of OpenCV;

[0081] A second extraction sub-module for respectively extracting the inner feature point S of each brush filament vertex from the contour array of the image of the top region of each brush filament ij (Xs ij , Ys ij), where i is the number of rows of brush filaments and j is the number of columns of brush filaments.

[0082] Optionally, the second extraction sub-module is specifically configured to:

[0083] For the brush filaments in the first row, take the point with the minimum Y coordinate in its contour array as the inner feature point of the brush filament vertex;

[0084] For the brush filaments in the second row, take the point with the maximum Y coordinate in its contour array as the inner feature of the brush filament vertex.

[0085] Optionally, the device further includes:

[0086] A distance module, configured to record the deviation of the feature points corresponding to each brush filament with respect to the rectangular tolerance region range of the brush filament top feature point;

[0087] A statistics module, configured to detect the conductive performance parameters of each brush filament and the assembled finished product of the loop track, and perform statistical analysis in combination with the deviation corresponding to each brush filament to optimize the design parameters of the carbon brush.

[0088] Optionally, the step of collecting the image includes:

[0089] Adopt a low-angle illumination method on both sides, adjust the light source angle to highlight the contour features of the brush filament top area in the carbon brush image, and make other parts of the carbon brush and the base area become the background of the collected carbon brush image.

[0090] A third aspect of an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps in the method described in the first aspect of the present invention are implemented.

[0091] A fourth aspect of an embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes, the steps in the method described in the first aspect of the present invention are implemented.

[0092] In an embodiment of the present invention, the image of the carbon brush to be detected can be collected based on a single camera to realize the rapid detection of the shape and position of the filamentous carbon brush array of the conductive slip ring. In an embodiment of the present invention, based on the projection method to determine the rectangular tolerance region range of the brush filament top feature point corresponding to the feature dot matrix of the carbon brush group, the position deviation value of the brush filament feature point coordinates can be accurately measured, which is beneficial to optimizing the conductive performance in combination with the conductive parameter detection, and further improving the conductive performance of the slip ring. Description of the Drawings

[0093] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments of the present invention. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0094] Figure 1 is a flowchart of a method for machine vision inspection of the shape and position of a filamentous brush array of a conductive slip ring;

[0095] Figure 2 is a schematic diagram of the composition of a vision inspection system corresponding to the method for machine vision inspection of the shape and position of a filamentous brush array of a conductive slip ring according to an embodiment of the present invention;

[0096] Figure 3 is a flowchart of another method for machine vision inspection of the shape and position of a filamentous brush array of a conductive slip ring according to an embodiment of the present invention;

[0097] Figure 4 is a schematic diagram of a standard brush filament array with a base in the method for machine vision inspection of the shape and position of a filamentous brush array of a conductive slip ring according to an embodiment of the present invention;

[0098] Figure 5 is a schematic diagram of the projection points in the standard brush image plane XOY determined by the method for machine vision inspection of the shape and position of a filamentous brush array of a conductive slip ring according to an embodiment of the present invention;

[0099] Figure 6 is a schematic diagram of an example brush to be inspected image obtained by the method for machine vision inspection of the shape and position of a filamentous brush array of a conductive slip ring according to an embodiment of the present invention;

[0100] Figure 7 is a schematic diagram of an example binary image of brush filaments obtained by the method for machine vision inspection of the shape and position of a filamentous brush array of a conductive slip ring according to an embodiment of the present invention;

[0101] Figure 8 is a schematic diagram of an example inspection result effect obtained by the method for machine vision inspection of the shape and position of a filamentous brush array of a conductive slip ring according to an embodiment of the present invention;

[0102] Figure 9 is a structural block diagram of a device for machine vision inspection of the shape and position of a filamentous brush array of a conductive slip ring according to an embodiment of the present invention. Detailed implementation manners

[0103] To make the above objects, features, and advantages of the present invention more obvious and understandable, the present invention will be further described in detail below with reference to the drawings and specific implementation manners.

[0104] Refer to Figure 1, showing a flowchart of a method for machine vision inspection of the shape and position of a filament brush array of a conductive slip ring according to an embodiment of the present invention. The method for machine vision inspection of the shape and position of a filament brush array of a conductive slip ring provided by the embodiment of the present invention may include the following steps:

[0105] S101, collect an image of the brush to be inspected.

[0106] In the embodiment of the present invention, the brush to be inspected can be fixed, and a camera can be used to collect the brush to be inspected that meets the inspection requirements.

[0107] In the embodiment of the present invention, the image of the brush to be inspected can be an image corresponding to the standard brush image, so as to detect the image of the brush to be inspected based on the standard brush image.

[0108] S102, determine the pixel size range of the image of the brush to be inspected according to the structural size of the filament brush array of the brush to be inspected.

[0109] In the embodiment of the present invention, the pixel size range of the image of the brush to be inspected can be determined according to the structural size of the filament brush array of the brush to be inspected, and this range can be determined as the region of interest for subsequent feature point extraction.

[0110] S103, perform binarization processing on the image of the brush to be inspected to obtain a binary image of the filaments.

[0111] In the embodiment of the present invention, any mature technology in the field of image processing can be used to perform binarization processing on the image of the brush to be inspected to obtain a binary image of the filaments, so as to highlight the projection of the filaments in the image of the brush to be inspected.

[0112] S104, process the binary image of the filaments, extract the contour array of the image of the top region of each filament of the brush to be inspected, and determine the coordinates of the inner feature points of the vertex of each filament.

[0113] In the embodiment of the present invention, multiple pixel points included in the binary image can be searched to obtain the contour array of the image of the top region of each filament, and the coordinates of the inner feature points of the vertex of each filament can be determined therefrom.

[0114] S105, determine whether the coordinates of the feature points are within the rectangular tolerance region of the top feature points of the filaments. The rectangular tolerance region of the top feature points of the filaments is determined according to the horizontal tolerance and vertical tolerance of the inner feature points at the top of the filaments.

[0115] In the embodiment of the present invention, the standard position of each filament on the brush image can be determined based on the standard brush image, and the rectangular tolerance region of the top feature points corresponding to each filament can be determined based on the horizontal tolerance and vertical tolerance.

[0116] In the embodiments of the present invention, the rectangular tolerance region range of the feature points at the top of the brush filaments can also be statistically obtained based on the positions of the respective brush filaments corresponding to a large number of qualified electric brushes on the electric brush image.

[0117] S106. When the coordinates of the feature points are within the rectangular tolerance region range of the feature points at the top of the brush filaments, it is determined that the shape and position of the currently to-be-detected electric brush are qualified.

[0118] In the embodiments of the present invention, the shape and position of the filamentous electric brush array of the conductive slip ring can be rapidly detected based on the acquisition of the to-be-detected electric brush image by a single camera. In the embodiments of the present invention, based on determining the rectangular tolerance region range of the feature points at the top of the brush filaments corresponding to the feature dot matrix of the brush group by the projection method, the position deviation value of the coordinates of the feature points of the brush filaments can be accurately measured, which is beneficial to optimizing the conductive performance in combination with the conductive parameter detection, and further improving the conductive performance of the slip ring.

[0119] For the sake of easy understanding, taking a specific vision detection system as an example, the machine vision detection method for the shape and position of the filamentous electric brush array of the conductive slip ring provided by the embodiments of the present invention is explained. Refer to Figure 2 , which shows a schematic diagram of the composition of the vision detection system corresponding to the machine vision detection method for the shape and position of the filamentous electric brush array of the conductive slip ring according to an embodiment of the present invention. It includes: an industrial camera 1 for acquiring the brush filament image, an optical lens 2, a slip ring tooling 3 for installing the to-be-tested slip ring filamentous electric brush 4, two side light sources 6 and 8, a backlight source 7, a bottom plate 5 for fixing the slip ring tooling 3 and the light sources 6, 7, 8, and a computer processing system 9. The computer processing system 9 runs the machine vision detection software for the shape and position of the filamentous electric brush array of the conductive slip ring corresponding to the machine vision detection method provided by the embodiments of the present invention. The backlight source 6 is installed in the reserved space between the slip ring tooling 3 and the bottom plate 5 for illuminating when detecting the left reference line 7 where the slip ring filamentous electric brush 4 is limited by the slip ring tooling 3.

[0120] Among them, the camera 1 uses a 6-million-pixel, cache-equipped, gigabit Ethernet interface, 1 / 1.8-inch CMOS black-and-white digital industrial camera, and the maximum resolution is 3072x2048 pixels. The optical lens 2 uses an FA lens with a focal length of 12 mm, a standard C interface, and an adjustable working distance, and the field of view size is 70.8 mm x 47.2 mm. The two side light sources 6 and 8 both use 100 mm×20 mm LED white bar light sources with adjustable angles. The backlight source 7 uses a 60×20 mm white bar light source. The computer processing system 9 is a WIN 10 operating system, and the image processing algorithm programming environment is Microsoft Visual Studio 2017.

[0121] Refer to Figure 3, showing a flowchart of a method for machine vision inspection of the shape and position of a filamentous brush array of a conductive slip ring according to an embodiment of the present invention. The method for machine vision inspection of the shape and position of a filamentous brush array of a conductive slip ring provided by the embodiment of the present invention may include the following steps:

[0122] S301, determine the range of the rectangular tolerance area of the feature points at the top of the brush filaments.

[0123] In the embodiment of the present invention, by determining the range of the rectangular tolerance area of the feature points at the top of the brush filaments, a detection reference model corresponding to the standard brush can be established, so as to use this detection reference model to detect the brush to be detected. Specifically, the step S301 may include the following sub-steps:

[0124] S3011, collect an image of the standard brush.

[0125] In the embodiment of the present invention, a low-angle illumination method on both sides can be adopted, and the light source angle can be adjusted to highlight the contour features of the area at the top of the brush filaments in the standard brush image, so that other parts of the brush and the base area become the background of the collected standard brush image. In the embodiment of the present invention, backlight illumination is used when collecting the image of the left reference line area of the brush base to highlight the features of the brush base side line. A low-angle rectangular light or ring light illumination method is also adopted to highlight the contour features of the area at the top of the brush filaments.

[0126] In the embodiment of the present invention, the collected standard brush image is an image of the part where one end of the brush base is connected to the tooling reference plane.

[0127] Exemplarily, the filamentous brush array of the standard brush with a base is as Figure 4 shown, Figure 4 is a schematic diagram of the filamentous brush array of the standard brush with a base in the method for machine vision inspection of the shape and position of a filamentous brush array of a conductive slip ring according to the embodiment of the present invention. The left side of the slip ring base 42 is limited by the tooling reference plane. Take the midpoint O of its left side line 41 as the origin of the brush filament positioning. The imaging plane 43 is illuminated by light sources on both sides, so that the camera can completely collect the image of the top 44 of the brush filaments, and other positions become the dark field background of the image. Figure 4 The corresponding slip ring model of the measured brush filament shown in

[0128] S3012, extract the left side line of the brush base in the standard brush image based on the Canny operator.

[0129] S3013, calculate the angle a formed by the left side line and the longitudinal axis of the image, and make the left side line parallel to the longitudinal axis of the image through rotation correction, and determine the midpoint coordinates O (X0, Y0) of the left side line of the base in the rotation-corrected image.

[0130] In the embodiment of the present invention, by calculating the included angle α formed by the left line and the longitudinal axis of the image, and then performing rotational correction by the corresponding angle to make the left line of the base parallel to the longitudinal axis of the camera.

[0131] S3014. Take the horizontal line passing through point O as the X-axis center line of the standard brush image. A pair of brush filaments in the same column of the standard brush are symmetrically distributed on both sides of the X-axis center line, and the distance H from the inner center points of the two roots of the brush filaments to the X-axis center line b is equal.

[0132] S3015. Calculate the standard distance H from the center point P of the top of the brush filament 11 to the X-axis center line y : H y = H b - L×Sinθ, where L is the brush filament arm length of the standard brush, and θ is the included angle between the brush arm and the brush filament fixed at the root of the base.

[0133] S3016. Determine that the distance from another brush filament top feature point P 11 symmetrical to the center point P of the top of the brush filament to the X-axis center line is also Hy, and obtain the reference coordinates Q 21 of the projection points of the top center points P 11 , P 21 in the image plane XOY 11 (Xq 11 , Yq 11 ): 21 (Xq 21 , Yq 21 ):

[0134] Xq 11 = X0 - H0

[0135] Yq 11 = Y0 - H y

[0136] Xq 21 = X0 - H0

[0137] Yq 21 = Y0 + H y

[0138] Among them, H0 is the distance from the intersection point of Q 11 Q 21 and the X-axis center line in the image plane to the origin O.

[0139] In the embodiments of the present invention, the essence of the qualified wire shape of the brush is to ensure the effective contact between the brush wire and the conductive ring. The actual contact point P0 is at the tangent point between the conductive ring and the inner side of the brush wire. The projection of P0 is restricted by the structure and cannot be detected through the projection image. The inner end point P at the top of the brush wire and the actual contact point P0 are in the same reference direction. If there is a deviation in the inclination angle of the P0 point, it will be proportionally reflected on the projection point Q of the P point.

[0140] Specifically, as Figure 5 shown, Figure 5 is a schematic diagram of the projection points in the standard brush image plane XOY determined in the embodiments of the present invention. In the figure, Q 11 , Q 21 schematically represent the projection points corresponding to a pair of brush wires in the same column of the standard brush.

[0141] S3017, determine the projection Q ij coordinates (Xq ij , Yq ij ) of the inner feature point at the top of the i-th row and j-th column brush wire:

[0142] Xq ij = X0 + H0 + (j - 1) × H x

[0143] Yq ij = Y0 + C i ×H y

[0144] Among them, i = 1, 2; j = 1, 2,..., n; when i = 1, C i takes the value of -1, and Yq ij refers to the ordinate of the feature point of the first row brush wire. When i = 2, C i takes the value of 1, and Yq ij refers to the reference ordinate of the feature point of the second row brush wire; Hx represents the distance between a pair of brush wires in different columns.

[0145] In the embodiments of the present invention, Q ij is the projection of the inner feature point at the top of the brush wire. Subsequently, when applied, the inner end point at the top of the brush wire is also taken as the feature point.

[0146] S3018, according to the brush wire inclination and parallelism tolerance requirements, determine that the lateral tolerance of the inner feature point Q ij at the top of the brush wire is dx, and the longitudinal tolerance is dy; obtain the brush wire shape and position detection rectangular tolerance zone T ij with O as the origin and the point Q ij as the center (XT ij , YT ij , 2dx, 2dy), where (XT ij , YT ij)(For the coordinates of the upper left corner of this rectangle, where 2dx and 2dy are its width and height, there are:

[0147] XT ij = Xq ij -dx

[0148] YT ij = Yq ij -dy.

[0149] In the embodiment of the present invention, the left line is extracted from the standard brush image; the offset angle of the slip ring brush base tooling is calculated according to the slope of the left line; image correction is performed through rotation transformation, and the plane formed by the left line and the X-axis center line passing through the midpoint of the left line in the corrected image is taken as the base reference plane; then, according to the brush size and its positional relationship with the base fixation, the standard position coordinates and the rectangular tolerance zone of the brush wire array feature points in the base reference plane are calculated to form a detection reference model.

[0150] S302. Adopt a low-angle illumination method on both sides, and adjust the light source angle to highlight the contour features of the brush wire top area in the standard brush image, so that other parts of the brush and the base area become the background of the collected brush image to be detected.

[0151] In the embodiment of the present invention, in specific applications, the method for collecting the brush image to be detected is the same as the method for collecting the standard brush image described above.

[0152] Exemplarily, as Figure 6 shown, Figure 6 is a schematic diagram of an exemplary brush image to be detected obtained by the method for detecting the shape and position of the conductive slip ring filamentous brush array in the embodiment of the present invention.

[0153] S303. Rotate and correct the brush image to be detected according to the included angle a.

[0154] Among them, the brush to be detected and the standard brush adopt the same tooling and clamping method.

[0155] In the embodiment of the present invention, because the brush to be detected and the standard brush adopt the same tooling and clamping method, when performing image rotation correction on the image to be detected, the rotation offset angle а inherent in the tooling determined during the process of directly establishing the detection reference model can be used to improve the detection efficiency.

[0156] S304. Determine the pixel size range of the brush image to be detected according to the structural dimensions of the brush wire array of the brush to be detected.

[0157] In the embodiment of the present invention, the pixel size range of the brush image to be detected can be determined according to the structural dimensions of the brush wire array of the brush to be detected, and this range is determined as the region of interest for subsequent feature point extraction.

[0158] Specifically, in the embodiments of the present invention, the pixel size range of the brush image to be detected can be determined as rectangle T according to the structure size of the brush wire array. ss (XT ss , YT ss , Hsx, Hsy), (XT ss , YT ss ) is the upper left corner of the rectangular area, Hsx is the width of the rectangle, and Hsy is the height of the rectangle. Then:

[0159] XT ss < XT 11

[0160] YT ss < YT 11

[0161] Hsx > XT nn - XT 11 + 2dx

[0162] Hsy > 2H1 + 2dy.

[0163] Among them, (XT 11 , YT 11 ) is the upper left corner coordinate of the rectangular tolerance of the brush wire in the first row and the first column.

[0164] S305, based on the OTSU automatic threshold image segmentation algorithm of the grayscale image, perform threshold segmentation and erosion dilation operations on the brush image to be detected to obtain a binary image of the brush wire.

[0165] Exemplarily, as Figure 7 shown, Figure 7 is a schematic diagram of an exemplary binary image of the brush wire obtained by the method for detecting the shape and position of the filamentous brush array of the conductive slip ring according to the embodiments of the present invention.

[0166] S306, by calling the contour extraction function FindContours of OpenCV, extract the contour array of each brush wire top area image.

[0167] S307, respectively extract the inner feature points S of each brush wire vertex from the contour array of each brush wire top area image ij (Xs ij , Ys ij ), where i is the row number of the brush wire and j is the column number of the brush wire.

[0168] In the embodiments of the present invention, a dedicated inner point search program of the brush wire can be applied to extract the inner end points of each brush wire.

[0169] Specifically, the step S307 includes:

[0170] For the brush filaments in the first row, take the point with the minimum Y coordinate in its contour array as the inner feature point of the brush filament vertex.

[0171] For the brush filaments in the second row, take the point with the maximum Y coordinate in its contour array as the inner feature of the brush filament vertex.

[0172] S308, determine whether the coordinates of the feature point are within the rectangular tolerance area of the brush filament top feature point, and the rectangular tolerance area of the brush filament top feature point is determined according to the horizontal tolerance and vertical tolerance of the inner feature point at the top of the brush filament.

[0173] S309, when the coordinates of the feature point are within the rectangular tolerance area of the brush filament top feature point, determine that the current brush to be detected has qualified form and position.

[0174] In the embodiment of the present invention, when the coordinates of the feature point are not within the rectangular tolerance area of the brush filament top feature point, determine that the current brush to be detected has unqualified form and position.

[0175] Specifically, Figure 8 is the effect diagram of the example detection result obtained by using the method for machine vision detection of the form and position of the filamentous brush array of the conductive slip ring in the embodiment of the present invention, as Figure 8 shown, each white point is the projection of the brush filament on the base, and the small rectangular box is the rectangular tolerance area of the top feature point corresponding to each brush filament.

[0176] S310, record the deviation of the feature point corresponding to each brush filament relative to the rectangular tolerance area of the brush filament top feature point.

[0177] S311, detect the conductive performance parameters of the assembled finished product of each brush filament and the raceway, and conduct statistical analysis in combination with the deviation corresponding to each brush filament to optimize the design parameters of the brush.

[0178] Specifically, in the embodiment of the present invention, the deviation of the feature point corresponding to each brush filament relative to the reference position (the rectangular tolerance area of the brush filament top feature point) can be recorded, the conductive performance parameters of the assembled finished product of the corresponding brush filament and the raceway are detected, such as the change in dynamic resistance, and statistical analysis is conducted in combination with the position deviation of the brush, so as to optimize the design parameters of the brush, such as the tilt angle θ of the brush arm.

[0179] In the embodiment of the present invention, after determining the detection reference model, the brush position and shape detection can be carried out. First, according to the relative position relationship between the base reference plane and the brush array, the pixel size range of the projected image of the brush group is determined, the independent connected regions within the pixel size range are searched, and the actual coordinates of the characteristic points at the top of the brush to be measured are found from the obtained contour array; whether the brush position and shape are qualified is determined according to whether the coordinates of the characteristic points are within the rectangular tolerance region of the characteristic points at the top of the brush filaments. By using the method for machine vision detection of the position and shape of the filamentous brush array of the conductive slip ring provided by the embodiment of the present invention, the position and shape detection of the key characteristic points of the brush array of the conductive slip ring can be realized based on a single camera, so as to batch judge the assembly quality of the filamentous brush arms, and improve the detection efficiency and detection accuracy of the conductive slip ring.

[0180] In the embodiment of the present invention, for the same series of slip rings with the same outer diameter, the specifications of the tooling fixtures used are the same. After determining the detection reference model corresponding to the position and shape detection of the brush filament array, batch detection can be carried out based on this detection reference model.

[0181] The method for machine vision detection of the position and shape of the filamentous brush array of the conductive slip ring provided by the embodiment of the present invention is used to conduct position and shape deviation inspection on the brush filament images of 11 specifications of slip rings in series such as SRC012, SRC015, and SRC022 to be measured. The qualified brush filaments screened are assembled and tested, and the qualification rate of the conductive performance reaches 100%. The average inspection rate is 0.782 s / image, which can efficiently and accurately realize the detection of the position and shape deviation of the precision conductive slip ring brush filaments.

[0182] Based on the same inventive concept, the embodiment of the present invention provides a machine vision detection device for the position and shape of the filamentous brush array of the conductive slip ring, referring to Figure 9 , Figure 9 is a schematic diagram of the machine vision detection device for the position and shape of the filamentous brush array of the conductive slip ring provided by the embodiment of the present invention. In the embodiment of the present invention, the machine vision detection device for the position and shape of the filamentous brush array of the conductive slip ring is a virtual device, including a plurality of functional modules for implementing the above-mentioned method for machine vision detection of the position and shape of the filamentous brush array of the conductive slip ring. As Figure 9 shown, the device includes:

[0183] An acquisition module 901 for acquiring the image of the brush to be detected;

[0184] A pixel size range determination module 902 for determining the pixel size range of the image of the brush to be detected according to the structural dimensions of the brush filament array of the brush to be detected;

[0185] A first processing module 903 for performing binarization processing on the image of the brush to be detected to obtain a binary image of the brush filaments;

[0186] The second processing module 904 is configured to process the binary image of the brush filaments, extract the contour array of the image of the top region of each brush filament of the brush to be detected, and determine the coordinates of the inner feature points of the vertex of each brush filament;

[0187] The judgment module 905 is configured to judge whether the coordinates of the feature points are within the rectangular tolerance region of the top feature points of the brush filaments, and the rectangular tolerance region of the top feature points of the brush filaments is determined according to the horizontal tolerance and the vertical tolerance of the inner feature points at the top of the brush filaments;

[0188] The determination module 906 is configured to determine that the shape and position of the currently detected brush are qualified when the coordinates of the feature points are within the rectangular tolerance region of the top feature points of the brush filaments.

[0189] Optionally, the rectangular tolerance region of the top feature points of the brush filaments is determined according to the following steps:

[0190] Collect the standard brush image;

[0191] Extract the left line of the brush filament base in the standard brush image based on the Canny operator;

[0192] Calculate the angle α formed by the left line and the longitudinal axis of the image, and make the left line parallel to the longitudinal axis of the image through rotation correction, and determine the midpoint coordinates O(X0, Y0) of the left line of the base in the rotation-corrected image;

[0193] Take the horizontal line passing through point O as the X-axis center line of the standard brush image. A pair of brush filaments in the same column of the standard brush are symmetrically distributed on both sides of the X-axis center line, and the distance H from the inner center points of the two roots of the brush filaments to the X-axis center line b is equal;

[0194] Calculate the standard distance Hy from the center point P of the top of the brush filament 11 to the X-axis center line y : Hy y = H b -L×Sinθ, where L is the brush filament arm length of the standard brush, and θ is the angle between the brush arm and the brush filament fixed at the root of the base;

[0195] Determine another top feature point P of the brush filament 11 symmetric to the center point P of the top of the brush filament 21 The distance to the X-axis center line is also Hy, and the reference coordinates Q of the projection points of the top center points P 11 , P 21 in the image plane XOY are obtained 11 (Xq 11 , Yq 11 ), Q 21 (Xq 21 ​​​​​​​​​, Yq 21 ):

[0196] Xq 11 = X0 - H0

[0197] Yq 11 = Y0 - H y

[0198] Xq 21 = X0 - H0

[0199] Yq 21 = Y0 + H y

[0200] Among them, H0 is the distance from the intersection point of Q 11 Q 21 in the image plane and the center line of the X-axis to the origin O;

[0201] Determine the projection Q of the inner feature point at the top of the wire brush in the i-th row and j-th column ij coordinates (Xq ij , Yq ij ):

[0202] Xq ij = X0 + H0 + (j - 1) × H x

[0203] Yq ij = Y0 + C i × H y

[0204] Among them, i = 1, 2; j = 1, 2,..., n; when i = 1, C i takes the value of -1, and Yq ij refers to the ordinate of the feature point of the wire brush in the first row. When i = 2, C i takes the value of 1, and Yq ij refers to the reference ordinate of the feature point of the wire brush in the second row; Hx represents the distance between a pair of wire brushes in different columns;

[0205] According to the requirements of the wire brush inclination and parallelism tolerances, determine that the lateral tolerance of the inner feature point Q ij at the top of the wire brush is dx, and the longitudinal tolerance is dy; obtain the wire brush form and position detection rectangular tolerance zone T ij with O as the origin and point Q ij as the center (XT ij , YT ij , 2dx, 2dy), where (XT ij , YT ij ) are the coordinates of the upper left corner of this rectangle, and 2dx and 2dy are its width and height, then there are:

[0206] XTij = Xq ij -dx

[0207] YT ij = Yq ij -dy。

[0208] Optionally, the device further includes:

[0209] A correction module for rotationally correcting the to-be-detected brush image according to the included angle a;

[0210] wherein the to-be-detected brush and the standard brush adopt the same tooling and clamping method.

[0211] Optionally, the first processing module is specifically configured to:

[0212] Based on the OTSU automatic threshold image segmentation algorithm of the grayscale image, perform threshold segmentation and erosion and dilation operations on the to-be-detected brush image to obtain a binary image of the brush filaments.

[0213] Optionally, the second processing module includes:

[0214] A first extraction sub-module for extracting a contour array of the top region image of each brush filament by calling the contour extraction function FindContours of OpenCV;

[0215] A second extraction sub-module for respectively extracting the inner feature point S of each brush filament vertex from the contour array of the top region image of each brush filament ij (Xs ij , Ys ij ), where i is the number of rows of brush filaments and j is the number of columns of brush filaments.

[0216] Optionally, the second extraction sub-module is specifically configured to:

[0217] For the brush filaments in the first row, take the point with the smallest Y coordinate in its contour array as the inner feature point of the brush filament vertex;

[0218] For the brush filaments in the second row, take the point with the largest Y coordinate in its contour array as the inner feature of the brush filament vertex.

[0219] Optionally, the device further includes:

[0220] A distance module for recording the deviation of the feature points corresponding to each brush filament with respect to the rectangular tolerance range of the top feature points of the brush filaments;

[0221] A statistics module for detecting the conductive performance parameters of each brush filament and the assembled finished product of the loop track, and performing statistical analysis in combination with the deviations corresponding to each brush filament to optimize the design parameters of the brush.

[0222] Optionally, the step of acquiring an image includes:

[0223] Adopt a low-angle illumination method on both sides, adjust the light source angle to highlight the contour features of the top area of the brush filaments in the brush image, and make other parts of the brush and the base area become the background of the acquired brush image.

[0224] For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple. For related parts, refer to the partial description of the method embodiment.

[0225] Based on the same inventive concept, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps in the method for machine vision detection of the shape and position of the filamentous brush array of a conductive slip ring described in any of the above embodiments are implemented.

[0226] Based on the same inventive concept, an embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes, the steps in the method for machine vision detection of the shape and position of the filamentous brush array of a conductive slip ring described in any of the above embodiments are implemented.

[0227] Each embodiment in this specification is described in a progressive manner. The key point of each embodiment is to illustrate the differences from other embodiments. For the same and similar parts among the embodiments, reference can be made to each other.

[0228] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a device, or a computer program product. Therefore, the embodiments of the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0229] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the processes and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal devices generate for implementing in the process Figure 1 each process or multiple processes and / or blocks Figure 1means for the functions specified in one or more boxes.

[0230] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including an instruction means that implements the functions specified in one Figure 1 one or more processes and / or boxes Figure 1 means for the functions specified in one or more boxes.

[0231] These computer program instructions may also be loaded onto a computer or other programmable data processing terminal device, such that a series of operation steps are performed on the computer or other programmable terminal device to produce a computer-implemented process, and thus the instructions executed on the computer or other programmable terminal device provide steps for implementing the functions specified in one Figure 1 one or more processes and / or boxes Figure 1 means for the functions specified in one or more boxes.

[0232] Although the preferred embodiments of the embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present invention.

[0233] Finally, it should also be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article or terminal device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or terminal device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or terminal device comprising the element.

[0234] The above has introduced in detail a method and product for machine vision inspection of the shape and position of a filament brush array of a conductive slip ring provided by the present invention. Specific examples are used in this article to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A method for machine vision inspection of the position and shape of a filamentous brush array of a conductive slip ring, characterized in that, The method includes: Collecting the image of the brush to be detected; Determining the pixel size range of the image of the brush to be detected according to the structural size of the wire array of the brush to be detected; Performing binarization processing on the image of the brush to be detected to obtain a binary image of the wires; Processing the binary image of the wires, extracting the contour array of the image of the top area of each wire of the brush to be detected, and determining the coordinates of the inner feature points of the vertex of each wire; Judging whether the coordinates of the feature points are within the rectangular tolerance area of the top feature points of the wires, and the rectangular tolerance area of the top feature points of the wires is determined according to the horizontal tolerance and vertical tolerance of the inner feature points at the top of the wires; When the coordinates of the feature points are within the rectangular tolerance area of the top feature points of the wires, determining that the shape and position of the current brush to be detected are qualified; The rectangular tolerance area of the top feature points of the wires is determined according to the following steps: Collecting the image of the standard brush; Extracting the left side line of the wire base in the image of the standard brush based on the Canny operator; Calculating the included angle a formed by the left side line and the longitudinal axis of the image, and making the left side line parallel to the longitudinal axis of the image through rotation correction, and determining the midpoint coordinates O(X0, Y0) of the left side line of the base in the rotation-corrected image; Take the horizontal line passing through point O as the X-axis center line of the standard brush image. A pair of brush filaments in the same column of the standard brush are symmetrically distributed on both sides of the X-axis center line, and the distance H from the inner center points of the two roots of the brush filaments to the X-axis center line b is equal; Calculate the center point P at the top of the brush filaments 11 The standard distance H from the center line of the X-axis y : H y = H b - L×Sinθ, where L is the brush filament arm length of the standard brush, and θ is the angle between the brush arm and the brush filaments fixed at the root of the base; Determine the other bristle top feature point P 11 symmetric to the center point P of the bristle top 21 The distance to the X-axis center line is also Hy, obtaining the center point P of the top 11 、P 21 The reference coordinates Q of the projection points of P 11 (Xq 11 , Yq 11 )、Q 21 (Xq 21 ,Yq 21 ): Xq 11 = X0-H0 Yq 11 = Y0-H y Xq 21 = X0-H0 Yq 21 = Y0+H y ; where H0 is the distance from the intersection point of Q in the image plane and the X-axis center line to the origin O; 11 Q 21 and the X-axis center line to the origin O; Determine the projection Q of the inner feature point at the top of the brush filaments in the i-th row and j-th column ij Coordinates (Xq ij , Yq ij ): Xq ij = X0 + H0 + (j - 1) × H x Yq ij = Y0 + C i ×H y ; where i = 1, 2; j = 1, 2, …, n; when i = 1, C i takes the value of -1, and Yq ij refers to the ordinate of the wire-brushing feature point in the first row. When i = 2, C i takes the value of 1, and Yq ij refers to the reference ordinate of the wire-brushing feature point in the second row; Hx represents the distance between a pair of wire-brushes in different columns; Determine the characteristic point Q on the inner side of the top of the brush filaments according to the tolerance requirements of the inclination and parallelism of the brush filaments ij has a lateral tolerance of dx and a longitudinal tolerance of dy; obtain the brush filament form and position detection rectangular tolerance zone T ij centered at point Q with O as the origin ij (XT ij , YT ij , 2dx, 2dy), where (XT ij , YT ij ) are the coordinates of the upper left corner of this rectangle, and 2dx and 2dy are its width and height, then there is: XT ij = Xq ij -dx YT ij = Yq ij -dy.

2. The method for machine vision inspection of the geometric position of the filamentous brush array of the conductive slip ring according to claim 1, wherein The method further includes: Performing rotation correction on the image of the brush to be detected according to the included angle a; Wherein, the brush to be detected and the standard brush adopt the same tooling and clamping method.

3. The method for geometric vision inspection of the filamentous brush array of the conductive slip ring according to claim 1, wherein Performing binarization processing on the image of the brush to be detected to obtain a binary image of the wires, including: Based on the OTSU automatic threshold image segmentation algorithm of the grayscale image, performing threshold segmentation and erosion and dilation operations on the image of the brush to be detected to obtain a binary image of the wires.

4. The method for machine vision inspection of the geometric position of the filamentary brush array of the conductive slip ring according to claim 1, wherein, Processing the binary image of the wires, extracting the contour array of the image of the top area of each wire of the brush to be detected, and determining the coordinates of the inner feature points of the vertex of each wire, including: Calling the contour extraction function FindContours of OpenCV to extract the contour array of the image of the top area of each wire; Extract each inner feature point S of the brush filament vertex from the contour array of the top region image of each brush filament ij (Xs ij , Ys ij ), where i is the number of brush filament rows and j is the number of brush filament columns.

5. The method for geometric vision inspection of the filamentous brush array of the conductive slip ring according to claim 4, characterized in that, Extract the inner feature points S of each bristle vertex from the contour arrays of the top region images of each bristle respectively ij (Xs ij , Ys ij ), including: For the wires in the first row, taking the point with the smallest Y coordinate in its contour array as the inner feature point of the wire vertex; For the wires in the second row, taking the point with the largest Y coordinate in its contour array as the inner feature of the wire vertex.

6. The method for machine vision inspection of the shape and position of the filamentary brush array of the conductive slip ring according to claim 1, characterized in that The method further includes: Recording the deviation of the feature points corresponding to each wire with respect to the rectangular tolerance area of the top feature points of the wires; Detecting the electrical conductivity parameters of each wire and the assembled finished product with the raceway, and performing statistical analysis in combination with the deviation corresponding to each wire to optimize the design parameters of the brush.

7. The method for geometric vision inspection of the filamentous brush array of the conductive slip ring according to claim 1, wherein, The steps of collecting the image include: Adopting a low-angle illumination method on both sides, adjusting the light source angle to highlight the contour features of the top area of the wires in the brush image, so that other parts of the brush and the base area become the background of the collected brush image.

8. A machine vision detection device for the shape and position of a filament brush array of a conductive slip ring, characterized in that, The device is used to implement the method for machine vision detection of the shape and position of the filament brush array of the conductive slip ring according to any one of claims 1 to 7, and the device includes: An acquisition module for collecting the image of the brush to be detected; A pixel size range determination module for determining the pixel size range of the image of the brush to be detected according to the structural size of the wire array of the brush to be detected; The first processing module is used to perform binarization processing on the to-be-detected brush image to obtain a brush wire binary image; The second processing module is used to process the brush wire binary image, extract the contour array of the image of the top region of each brush wire of the to-be-detected brush, and determine the coordinates of the inner feature points of the vertex of each brush wire; The judgment module is used to judge whether the coordinates of the feature points are within the rectangular tolerance region of the top feature points of the brush wire, and the rectangular tolerance region of the top feature points of the brush wire is determined according to the horizontal tolerance and the vertical tolerance of the inner feature points at the top of the brush wire; The determination module is used to determine that the current to-be-detected brush is qualified in terms of its shape and position when the coordinates of the feature points are within the rectangular tolerance region of the top feature points of the brush wire.

9. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the method for machine vision detection of the shape and position of the filamentous brush array of the conductive slip ring according to any one of claims 1-7.

Images