A train brake shoe remaining thickness measurement method, system, storage medium and computer equipment

Abstract

The present invention discloses a method, system, storage medium and computer equipment for measuring the remaining thickness of train brake shoes. The specific technical scheme records the following contents: combining a 3D camera with an area array camera, wherein the 3D camera can obtain accurate depth information of the brake shoe, and the area array camera can provide clear high-resolution images of the brake shoe. Based on the brake shoe system calibration of the 3D camera and the area array camera, the alignment of the three-dimensional depth information and the two-dimensional image can be completed, that is, the depth information of the 3D camera and the high resolution of the area array camera are integrated, and at the same time, the brake shoe system calibration, brake shoe edge extraction, side plane fitting, side edge fitting and other algorithms are combined to achieve high-precision and high-stability brake shoe remaining thickness measurement.

Description

Technical Field

[0001] The invention relates to the field of measuring the remaining thickness of train brake shoes, and in particular to a method, a system, a storage medium and a computer device for measuring the remaining thickness of train brake shoes. Background Art

[0002] Brake shoes are one of the key components of the braking system of operating trains. At present, brake shoes have become a key component in the basic braking method of trains and are widely used in the field of railway transportation. When braking, they hold the wheel tread tightly and stop the wheel from rotating through friction. Usually, the main material of brake shoes is iron, which will wear during use, and wear will cause the braking force of the train to weaken, causing safety hazards to the train. Therefore, when the brake shoes are worn to a certain extent, the brake shoes of the train need to be replaced to ensure the safe operation of the train. When the remaining thickness of the brake shoe is less than 10mm, it must be replaced.

[0003] At present, the inspection of brake shoes is usually manual inspection and automatic inspection. Manual inspection is usually visual inspection, that is, a ruler is attached to the side of the brake shoe, and the remaining thickness of the brake shoe is judged by manual reading. This method requires manual observation and measurement of each brake shoe with the naked eye, which is labor-intensive and inefficient. Not only is the labor cost high, but the measurement time is long and the measurement accuracy is low, which can easily cause excessive or insufficient use of brake shoes, bring certain safety hazards or cause great waste. Automatic inspection is currently based on two-dimensional image recognition, which extracts the edge of the brake shoe, extracts the brake shoe contour, and matches it with the system calibration value to obtain the remaining thickness of the brake shoe. This method has poor accuracy and cannot provide stable measurement accuracy. Summary of the invention

[0004] In order to solve the problems existing in the above background technology, the present invention proposes a method for measuring the remaining thickness of a train brake shoe, the method comprising:

[0005] Perform system calibration on 3D camera and array camera to obtain coordinate transformation parameters;

[0006] Build an image positioning network to complete the brake shoe image positioning, perform edge detection on the brake shoe image to be tested in the positioning area, remove noise points, and obtain the left and right edges of the brake shoe image to be tested;

[0007] Obtaining a side plane of the brake shoe image to be measured according to the left and right edges of the brake shoe image to be measured, and then obtaining an equation of the side plane of the brake shoe image to be measured;

[0008] Acquire three-dimensional data of the left and right edges of the brake shoe image to be tested, filter and process the three-dimensional data of the left and right edges of the brake shoe image to be tested, and fit the three-dimensional data of the left and right edges of the brake shoe image to be tested after the filtering process to obtain left and right edge curves of the brake shoe image to be tested;

[0009] The left and right edge curves of the brake shoe image to be tested are circularly fitted to obtain a residual thickness curve of the brake shoe to be tested.

[0010] Furthermore, the 3D camera and the area array camera are calibrated to obtain the coordinate transformation parameters as follows:

[0011] L1: The 3D camera and the area array camera respectively acquire the same calibration plate image, where the calibration plate contains evenly distributed circles;

[0012] L2: Extract the center of each circle on the calibration plate as a feature point and calibrate using formula (1).

[0013]

[0014] Among them, Xw, Yw, Zw represent the three-dimensional coordinates of each corner point on the calibration plate, u, v represent the pixel coordinates of each corner point on the calibration plate in the 3D camera image coordinate system, R represents the rotation amount from the 3D camera image coordinate system to the physical coordinate system of the calibration plate, and T represents the translation amount from the 3D camera image coordinate system to the calibration plate coordinate system.

[0015] L3: Similarly, based on formula (1), calculate the rotation R from the 2D area array camera image coordinate system to the physical coordinate system of the calibration plate, and the translation T from the 2D area array camera image coordinate system to the calibration plate coordinate system.

[0016] L4: Convert the 3D image pixel coordinates to the checkerboard coordinates of the calibration plate coordinate system through step L2, and then convert the checkerboard coordinates to the two-dimensional array image coordinates through step L3 to obtain the pixel coordinates on the two-dimensional array image corresponding to the 3D image pixel coordinates.

[0017] Furthermore, the image positioning network is constructed to complete the brake shoe image positioning, edge detection is performed on the brake shoe image to be tested in the positioning area, and noise points are removed to obtain the left and right edges of the brake shoe image to be tested as follows:

[0018] Build an image positioning network, input the annotated standard brake shoe images as samples into the training set, and complete the brake shoe image positioning through training;

[0019] The brake shoe image positioning area is expanded, edge detection is performed on the brake shoe image to be tested in the brake shoe image positioning area, and noise points are eliminated to obtain the left and right edges of the brake shoe image to be tested.

[0020] Furthermore, the step of removing noise points is specifically as follows:

[0021] P1: Get the edge points of the brake shoe image to be tested;

[0022] P2: loop processing each edge point of the brake shoe image to be tested, calculate the difference in the grayscale values ​​of the pixels in the left and right neighborhoods of each edge point within the 5×5 area of ​​the edge point, when the grayscale value of the left neighborhood minus the grayscale value of the right neighborhood < 0, the edge point is the left edge point; when the grayscale value of the left neighborhood minus the grayscale value of the right neighborhood > 0, the edge point is the right edge point;

[0023] P3: Perform segmented straight line fitting on the left edge point and the right edge point according to the upper, middle and lower parts, and remove the noise points in each segment that deviate far from the fitting straight line.

[0024] Furthermore, the side plane of the brake shoe image to be tested is obtained according to the left and right edges of the brake shoe image to be tested, and then the equation for obtaining the side plane of the brake shoe image to be tested is specifically:

[0025] Obtaining a side plane of the brake shoe image to be tested according to the left and right edges of the brake shoe image to be tested, wherein the area between the left and right edges of the brake shoe image to be tested is the side plane of the brake shoe image to be tested;

[0026] Obtaining three-dimensional data of the side plane of the brake shoe image to be tested according to the coordinate conversion parameters;

[0027] Plane fitting is performed on the three-dimensional data of the side plane of the brake shoe image to be measured to obtain the equation of the side plane of the brake shoe image to be measured.

[0028] Further, the three-dimensional data of the left and right edges of the brake shoe image to be tested are obtained, the three-dimensional data of the left and right edges of the brake shoe image to be tested are screened, and the three-dimensional data of the left and right edges of the brake shoe image to be tested after the screening are fitted to obtain the left and right edge curves of the brake shoe image to be tested:

[0029] Based on the coordinate conversion parameters, three-dimensional data of the left and right edges of the brake shoe image to be measured are obtained according to the left and right edges of the brake shoe image to be measured;

[0030] Substituting the three-dimensional data of the left and right edges of the brake shoe image to be tested into the equation of the side plane of the brake shoe image to be tested, eliminating the three-dimensional data not on the side plane of the brake shoe image to be tested, and obtaining the corrected three-dimensional data of the left and right edges of the brake shoe to be tested;

[0031] The corrected three-dimensional data of the left and right edges of the brake shoe to be tested are subjected to cubic B-spline fitting to obtain the left and right edge curves of the brake shoe to be tested image.

[0032] Furthermore, the left and right edge curves of the brake shoe image to be tested are circularly fitted to obtain the remaining thickness curve of the brake shoe to be tested, which is specifically:

[0033] The left and right edge curves of the brake shoe image to be tested are circularly fitted to obtain a circular equation of the left edge of the brake shoe; each point on the left edge of the brake shoe is traversed as a test point, the intersection of the radius of the test point and the right edge curve is recorded as a reference point, the distance between the test point and the reference point is calculated, and the residual thickness curve of the brake shoe to be tested is obtained.

[0034] A train brake shoe remaining thickness measurement system, the system comprising:

[0035] System calibration module: used to calibrate the 3D camera and array camera to obtain coordinate conversion parameters;

[0036] Brake shoe edge extraction module: used to build an image positioning network, complete brake shoe image positioning, perform edge detection on the brake shoe image to be tested in the positioning area, remove noise points, and obtain the left and right edges of the brake shoe image to be tested;

[0037] Brake shoe side plane extraction module: used for obtaining the side plane of the brake shoe image to be tested according to the left and right edges of the brake shoe image to be tested, and then obtaining the equation of the side plane of the brake shoe image to be tested;

[0038] Brake shoe side edge curve extraction module: used for obtaining the three-dimensional data of the left and right edges of the brake shoe image to be tested, screening the three-dimensional data of the left and right edges of the brake shoe image to be tested, fitting the three-dimensional data of the left and right edges of the brake shoe image to be tested after the screening, and obtaining the left and right edge curves of the brake shoe image to be tested;

[0039] Brake shoe remaining thickness calculation module: used for performing circular fitting on the left and right edge curves of the brake shoe image to be measured to obtain the brake shoe remaining thickness curve to be measured.

[0040] A storage medium having a computer program stored thereon, characterized in that when the program is executed by a processor, any of the methods described above is implemented.

[0041] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the above-mentioned methods when executing the program.

[0042] Beneficial effect: The present invention provides a method for measuring the remaining thickness of train brake shoes. The present invention combines a 3D camera with an area array camera, wherein the 3D camera can obtain accurate depth information of the brake shoes, and the area array camera can provide clear high-resolution images of the brake shoes. Based on the brake shoe system calibration of the 3D camera and the area array camera, the three-dimensional depth information and the two-dimensional image can be aligned, that is, the depth information of the 3D camera and the high resolution of the area array camera are integrated, and at the same time, the brake shoe system calibration, brake shoe edge extraction, side plane fitting, side edge fitting and other algorithms are combined to achieve high-precision and high-stability brake shoe remaining thickness measurement. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 A schematic flow chart of a method for measuring the remaining thickness of a train brake shoe according to an embodiment of the present invention;

[0044] Figure 2 The pictures are acquired by the 3D camera and the area array camera in the embodiments of the present invention;

[0045] Figure 3 This is an image of a brake shoe taken by an area array camera according to an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0047] The present application provides a method for measuring the remaining thickness of a train brake shoe, wherein the computer device includes a processor, a memory, a network interface and a database connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data of the classification method. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for calculating the wear of a pantograph slide is implemented.

[0048] The embodiments of the present application provide a method, system, computer device and storage medium for measuring the remaining thickness of a train brake shoe, aiming to solve the problem that the calibration surface in the prior art cannot be completely identical to the brake shoe imaging surface, and that the two-dimensional image is taken by an area array camera, and there is a deviation between the imaging depth at the exposure time and the vehicle information depth, resulting in large measurement errors.

[0049] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems will be described in detail below through embodiments and in combination with the accompanying drawings. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. It should be noted that a method for measuring the remaining thickness of a train brake shoe provided in an embodiment of the present application, wherein its executor can also be a classification device, wherein the device can be implemented as part or all of the classification method by software, hardware, or a combination of software and hardware.

[0050] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments.

[0051] In one embodiment, Figure 1 As shown, a method for measuring the remaining thickness of a train brake shoe comprises:

[0052] S1: perform system calibration on the 3D camera and the array camera to obtain coordinate transformation parameters;

[0053] S2: Build an image positioning network to complete the brake shoe image positioning, perform edge detection on the brake shoe image to be tested in the positioning area, remove noise points, and obtain the left and right edges of the brake shoe image to be tested;

[0054] S3: obtaining a side plane of the brake shoe image to be tested according to the left and right edges of the brake shoe image to be tested, and then obtaining an equation of the side plane of the brake shoe image to be tested;

[0055] S4: acquiring three-dimensional data of the left and right edges of the brake shoe image to be tested, screening the three-dimensional data of the left and right edges of the brake shoe image to be tested, and fitting the three-dimensional data of the left and right edges of the brake shoe image to be tested after the screening process to obtain left and right edge curves of the brake shoe image to be tested;

[0056] S5: performing circular fitting on the left and right edge curves of the brake shoe image to be measured to obtain a residual thickness curve of the brake shoe to be measured.

[0057] In S1, the relative positions of the 3D camera and the area array camera are fixed according to actual needs, a calibration plate is placed within the measurement range, and the same calibration plate is photographed by the 3D camera and the area array camera respectively. The pictures obtained by the 3D camera and the area array camera are shown in the attached figure. Figure 2 As shown, the left picture is a picture taken by a 3D camera, and the right picture is a picture taken by an array camera. The calibration plate posture is changed to take random pictures, and multiple postures are covered as much as possible, such as straight shot, left oblique shot, right oblique shot, upper oblique shot, and lower oblique shot. At the same time, each picture contains a complete chessboard. Shoot at least 20 groups to obtain a series of calibration plate images taken by a 3D camera and an array camera. The center of each circle on the calibration plate is extracted as a feature point, and the calibration is performed using formula (1) to complete the calibration of the rotation and translation from the 3D camera coordinate system to the calibration plate.

[0058] L1: The 3D camera and the area array camera respectively acquire the same calibration plate image, where the calibration plate contains evenly distributed circles;

[0059] L2: Extract the center of each circle on the calibration plate as a feature point and calibrate using formula (1).

[0060]

[0061] Among them, Xw, Yw, Zw represent the three-dimensional coordinates of each corner point on the calibration plate, u, v represent the pixel coordinates of each corner point on the calibration plate in the 3D camera image coordinate system, R represents the rotation amount from the 3D camera image coordinate system to the physical coordinate system of the calibration plate, and T represents the translation amount from the 3D camera image coordinate system to the calibration plate coordinate system.

[0062] L3: Similarly, the calibration of the rotation and translation from the area array camera coordinate system to the calibration plate can be completed. Since the calibration plate is photographed by the 3D camera and the area array camera in each posture, the above formula can be used to complete the calibration of the rotation and translation from the 3D camera coordinate system to the area array camera coordinate system. That is, based on formula (1), the rotation R from the 2D area array camera image coordinate system to the physical coordinate system of the calibration plate and the translation T from the 2D area array camera image coordinate system to the calibration plate coordinate system can be obtained.

[0063] L4: Convert the 3D image pixel coordinates to the checkerboard coordinates of the calibration plate coordinate system through step L2, and then convert the checkerboard coordinates to the two-dimensional array image coordinates through step L3 to obtain the pixel coordinates on the two-dimensional array image corresponding to the 3D image pixel coordinates.

[0064] In addition, since the area array camera takes a separate image of the calibration plate, the coordinates of the circular center of the area array camera are extracted as feature points to complete the intrinsic calibration of the area array camera.

[0065] In S2, the brake shoe image captured by the area array camera is as follows: Figure 3 As shown, an image positioning network is built, and the annotated brake shoe images are input as samples into the training set. When the training samples reach a certain number, which is at least 1000, deep learning is introduced. Through training, the brake shoe positioning can be completed, the brake shoe positioning area is expanded, and the edge detection is performed on the brake shoe image to be tested in the positioning area, and the noise points are removed to obtain the left and right edges of the brake shoe image to be tested.

[0066] The edge detection adopts the canny edge detection algorithm.

[0067] The noise removal is as follows: Since the light source is on the side surface of the brake shoe, all side surfaces are brighter, and the image outside the brake shoe edge is darker, so the algorithm uses the left edge (dark on the left and bright on the right) and the right edge (bright on the left and dark on the right) to once again screen the edge points extracted by the canny edge detection algorithm. The specific steps are as follows:

[0068] P1: Get the edge points of the brake shoe image to be tested;

[0069] P2: Loop through each point and calculate the difference in the grayscale values ​​of the pixels in the left and right neighborhoods of each point within a 5×5 area. When the grayscale value of the left neighborhood minus the grayscale value of the right neighborhood is less than 0, the point is a left edge point; when the grayscale value of the left neighborhood minus the grayscale value of the right neighborhood is greater than 0, the point is a right edge point.

[0070] P3: Perform segmented straight line fitting on the left and right edge points from top to bottom, and remove the noise points that deviate far from the fitting straight line in each segment.

[0071] In S3, a side plane of the brake shoe image to be tested is obtained according to the left and right edges of the brake shoe image to be tested, wherein the area between the left and right edges of the brake shoe image to be tested is the side plane of the brake shoe image to be tested;

[0072] That is, the side plane area of ​​the brake shoe image to be tested is found in the area array camera image, and the conversion parameters obtained by calibration calculation (conversion from area array camera to 3D camera, that is, selecting a point in the image taken by the area array camera, the position of the point in the image taken by the 3D camera can be obtained) are used to map the side plane area of ​​the brake shoe image to be tested in the area array camera image to the 3D camera image, so that the three-dimensional data of the side plane of the brake shoe image to be tested can be extracted from the 3D image. Combined with the system calibration result, the depth value of the side plane of the brake shoe image to be tested in the area array camera image can be obtained, and then combined with the internal parameters of the area array camera, the three-dimensional data of the side plane of the brake shoe image to be tested in the area array camera coordinate system can be obtained. The RANSAC algorithm (random sampling consensus algorithm) is used to perform plane fitting on the three-dimensional data of the side plane, and the equation of the side plane of the brake shoe image to be tested can be obtained.

[0073] In S4, the left and right edges of the brake shoe image to be tested are used, based on the conversion parameters obtained by calibration calculation (conversion from area array camera to 3D camera, that is, by selecting a point in the image taken by the area array camera, the position of the point in the image taken by the 3D camera can be obtained), and the left and right edge pixels of the brake shoe image to be tested in the area array camera image are mapped to the 3D camera image, so that the three-dimensional data of the left and right edges of the brake shoe image to be tested can be extracted from the 3D image.

[0074] The three-dimensional data of the left and right edges of the brake shoe image to be tested are respectively brought into the equation of the side plane of the brake shoe image to be tested, and the three-dimensional data not on the side plane of the brake shoe image to be tested are eliminated to obtain the corrected three-dimensional data of the left and right edges of the brake shoe to be tested; the three-dimensional data of the left and right edges of the brake shoe to be tested are subjected to cubic B-spline fitting to obtain the complete upper and lower edge curves of the brake shoe image to be tested.

[0075] In S5, circular fitting is performed on the left and right edge curves of the brake shoe image to be tested to obtain a circular equation of the left edge of the brake shoe; each point on the left edge of the brake shoe is traversed as a test point, and the intersection of the radius of the test point and the right edge curve is recorded as a reference point. The distance between the test point and the reference point is calculated, and a series of thickness values ​​can be obtained by cyclically calculating the distance between each test point on the left edge and the corresponding reference point on the right edge, and the residual thickness curve of the brake shoe to be tested is obtained according to the thickness values.

[0076] In one embodiment, a train brake shoe remaining thickness measurement system is provided, the system comprising:

[0077] System calibration module: used to calibrate the 3D camera and array camera to obtain coordinate conversion parameters;

[0078] Brake shoe edge extraction module: used to build an image positioning network, complete brake shoe image positioning, perform edge detection on the brake shoe image to be tested in the positioning area, remove noise points, and obtain the left and right edges of the brake shoe image to be tested;

[0079] Brake shoe side plane extraction module: used for obtaining the side plane of the brake shoe image to be tested according to the left and right edges of the brake shoe image to be tested, and then obtaining the equation of the side plane of the brake shoe image to be tested;

[0080] Brake shoe side edge curve extraction module: used for obtaining the three-dimensional data of the left and right edges of the brake shoe image to be tested, screening the three-dimensional data of the left and right edges of the brake shoe image to be tested, fitting the three-dimensional data of the left and right edges of the brake shoe image to be tested after the screening, and obtaining the left and right edge curves of the brake shoe image to be tested;

[0081] Brake shoe remaining thickness calculation module: used for performing circular fitting on the left and right edge curves of the brake shoe image to be measured to obtain the brake shoe remaining thickness curve to be measured.

[0082] The above embodiment provides a train brake shoe remaining thickness measurement system, the implementation principle and technical effect of which are similar to those of the above method embodiment, and will not be repeated here.

[0083] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0084] Perform system calibration on 3D camera and array camera to obtain coordinate transformation parameters;

[0085] Build an image positioning network to complete the brake shoe image positioning, perform edge detection on the brake shoe image to be tested in the positioning area, remove noise points, and obtain the left and right edges of the brake shoe image to be tested;

[0086] Obtaining a side plane of the brake shoe image to be measured according to the left and right edges of the brake shoe image to be measured, and then obtaining an equation of the side plane of the brake shoe image to be measured;

[0087] Acquire three-dimensional data of the left and right edges of the brake shoe image to be tested, filter and process the three-dimensional data of the left and right edges of the brake shoe image to be tested, and fit the three-dimensional data of the left and right edges of the brake shoe image to be tested after the filtering process to obtain left and right edge curves of the brake shoe image to be tested;

[0088] The left and right edge curves of the brake shoe image to be tested are circularly fitted to obtain a residual thickness curve of the brake shoe to be tested.

[0089] The above embodiment provides a computer device, whose implementation principle and technical effect are similar to those of the above method embodiment, and will not be repeated here.

[0090] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: system calibration of a 3D camera and an area array camera is performed to obtain coordinate conversion parameters;

[0091] Build an image positioning network to complete the brake shoe image positioning, perform edge detection on the brake shoe image to be tested in the positioning area, remove noise points, and obtain the left and right edges of the brake shoe image to be tested;

[0092] Obtaining a side plane of the brake shoe image to be measured according to the left and right edges of the brake shoe image to be measured, and then obtaining an equation of the side plane of the brake shoe image to be measured;

[0093] Acquire three-dimensional data of the left and right edges of the brake shoe image to be tested, filter and process the three-dimensional data of the left and right edges of the brake shoe image to be tested, and fit the three-dimensional data of the left and right edges of the brake shoe image to be tested after the filtering process to obtain left and right edge curves of the brake shoe image to be tested;

[0094] The left and right edge curves of the brake shoe image to be tested are circularly fitted to obtain a residual thickness curve of the brake shoe to be tested.

[0095] The above embodiment provides a computer-readable storage medium, whose implementation principle and technical effect are similar to those of the above method embodiment, and will not be repeated here.

[0096] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0097] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0098] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for measuring the remaining thickness of a train brake shoe, characterized in that: The method comprises: Perform system calibration on 3D camera and array camera to obtain coordinate transformation parameters; Build an image positioning network to complete the brake shoe image positioning, perform edge detection on the brake shoe image to be tested in the positioning area, remove noise points, and obtain the left and right edges of the brake shoe image to be tested; Obtaining a side plane of the brake shoe image to be measured according to the left and right edges of the brake shoe image to be measured, and then obtaining an equation of the side plane of the brake shoe image to be measured; Acquire three-dimensional data of the left and right edges of the brake shoe image to be tested, filter and process the three-dimensional data of the left and right edges of the brake shoe image to be tested, and fit the three-dimensional data of the left and right edges of the brake shoe image to be tested after the filtering process to obtain left and right edge curves of the brake shoe image to be tested; Performing circular fitting on the left and right edge curves of the brake shoe image to be tested to obtain a residual thickness curve of the brake shoe to be tested; The side plane of the brake shoe image to be tested is obtained according to the left and right edges of the brake shoe image to be tested, and then the equation for the side plane of the brake shoe image to be tested is obtained as follows: Obtaining a side plane of the brake shoe image to be tested according to the left and right edges of the brake shoe image to be tested, wherein the area between the left and right edges of the brake shoe image to be tested is the side plane of the brake shoe image to be tested; Obtaining three-dimensional data of the side plane of the brake shoe image to be tested according to the coordinate conversion parameters; Performing plane fitting on the three-dimensional data of the side plane of the brake shoe image to be tested to obtain an equation of the side plane of the brake shoe image to be tested; The three-dimensional data of the left and right edges of the brake shoe image to be tested are obtained, the three-dimensional data of the left and right edges of the brake shoe image to be tested are screened, and the three-dimensional data of the left and right edges of the brake shoe image to be tested after the screening are fitted to obtain the left and right edge curves of the brake shoe image to be tested: Based on the coordinate conversion parameters, three-dimensional data of the left and right edges of the brake shoe image to be measured are obtained according to the left and right edges of the brake shoe image to be measured; Substituting the three-dimensional data of the left and right edges of the brake shoe image to be tested into the equation of the side plane of the brake shoe image to be tested, eliminating the three-dimensional data not on the side plane of the brake shoe image to be tested, and obtaining the corrected three-dimensional data of the left and right edges of the brake shoe to be tested; The corrected three-dimensional data of the left and right edges of the brake shoe to be tested are subjected to cubic B-spline fitting to obtain the left and right edge curves of the brake shoe to be tested image.

2. A train brake shoe remaining thickness measurement method according to claim 1, characterized in that: The coordinate transformation parameters obtained by calibrating the 3D camera and the area array camera are as follows: L1: The 3D camera and the area array camera respectively acquire the same calibration plate image, where the calibration plate contains evenly distributed circles; L2: Extract the center of each circle on the calibration plate as a feature point and calibrate using formula (1). （1） Among them, Xw, Yw, Zw represent the three-dimensional coordinates of each corner point on the calibration plate, u, v, represent the pixel coordinates of each corner point on the calibration plate in the 3D camera image coordinate system, R is the rotation amount from the 3D camera image coordinate system to the physical coordinate system of the calibration plate, and T represents the translation amount from the 3D camera image coordinate system to the calibration plate coordinate system; L3: Similarly, based on formula (1), calculate the rotation R from the 2D area array camera image coordinate system to the physical coordinate system of the calibration plate, and the translation T from the 2D area array camera image coordinate system to the calibration plate coordinate system; L4: Convert the 3D image pixel coordinates to the checkerboard coordinates of the calibration plate coordinate system through step L2, and then convert the checkerboard coordinates to the two-dimensional array image coordinates through step L3 to obtain the pixel coordinates on the two-dimensional array image corresponding to the 3D image pixel coordinates.

3. A train brake shoe remaining thickness measurement method according to claim 1, characterized in that: The image positioning network is constructed to complete the brake shoe image positioning, and edge detection is performed on the brake shoe image to be tested in the positioning area, and noise points are removed to obtain the left and right edges of the brake shoe image to be tested: Build an image positioning network, input the annotated standard brake shoe image as a sample into the training set, and complete the brake shoe image positioning through training; The brake shoe image positioning area is expanded, edge detection is performed on the brake shoe image to be tested in the brake shoe image positioning area, and noise points are eliminated to obtain the left and right edges of the brake shoe image to be tested.

4. A train brake shoe remaining thickness measurement method according to claim 3, characterized in that: The steps of removing noise points are specifically as follows: P1: Get the edge points of the brake shoe image to be tested; P2: loop processing each edge point of the brake shoe image to be tested, calculate the difference in the grayscale values ​​of the pixels in the left and right neighborhoods of each edge point within the 5×5 area of ​​the edge point, when the grayscale value of the left neighborhood minus the grayscale value of the right neighborhood < 0, the edge point is the left edge point; when the grayscale value of the left neighborhood minus the grayscale value of the right neighborhood > 0, the edge point is the right edge point; P3: Perform segmented straight line fitting on the left edge point and the right edge point according to the upper, middle and lower parts, and remove the noise points in each segment that deviate far from the fitting straight line.

5. The method for measuring the remaining thickness of a train brake shoe according to claim 1, characterized in that: The circular fitting of the left and right edge curves of the brake shoe image to be tested is performed to obtain the residual thickness curve of the brake shoe to be tested: Performing circular fitting on the left and right edge curves of the brake shoe image to be tested to obtain a circular equation of the upper left edge of the brake shoe; Traverse each point on the left edge of the brake shoe as a test point, record the intersection of the radius of the test point and the right edge curve as a reference point, calculate the distance between the test point and the reference point, and obtain the remaining thickness curve of the brake shoe to be tested.

6. A train brake shoe remaining thickness measurement system, characterized in that: The system comprises: System calibration module: used to calibrate the 3D camera and array camera to obtain coordinate conversion parameters; Brake shoe edge extraction module: used to build an image positioning network, complete brake shoe image positioning, perform edge detection on the brake shoe image to be tested in the positioning area, remove noise points, and obtain the left and right edges of the brake shoe image to be tested; Brake shoe side plane extraction module: used to obtain the side plane of the brake shoe image to be tested according to the left and right edges of the brake shoe image to be tested, and then obtain the equation of the side plane of the brake shoe image to be tested; specifically: obtain the side plane of the brake shoe image to be tested according to the left and right edges of the brake shoe image to be tested, wherein the area between the left and right edges of the brake shoe image to be tested is the side plane of the brake shoe image to be tested; Obtaining three-dimensional data of the side plane of the brake shoe image to be tested according to the coordinate conversion parameters; Performing plane fitting on the three-dimensional data of the side plane of the brake shoe image to be tested to obtain an equation of the side plane of the brake shoe image to be tested; Brake shoe side edge curve extraction module: used to obtain the three-dimensional data of the left and right edges of the brake shoe image to be tested, filter and process the three-dimensional data of the left and right edges of the brake shoe image to be tested, and fit the three-dimensional data of the left and right edges of the brake shoe image to be tested after the filtering process to obtain the left and right edge curves of the brake shoe image to be tested; specifically: based on the coordinate conversion parameters, the three-dimensional data of the left and right edges of the brake shoe image to be tested are obtained according to the left and right edges of the brake shoe image to be tested; Substituting the three-dimensional data of the left and right edges of the brake shoe image to be tested into the equation of the side plane of the brake shoe image to be tested, eliminating the three-dimensional data not on the side plane of the brake shoe image to be tested, and obtaining the corrected three-dimensional data of the left and right edges of the brake shoe to be tested; Performing cubic B-spline fitting on the corrected three-dimensional data of the left and right edges of the brake shoe to be tested to obtain left and right edge curves of the brake shoe to be tested image; Brake shoe remaining thickness calculation module: used for performing circular fitting on the left and right edge curves of the brake shoe image to be measured to obtain the brake shoe remaining thickness curve to be measured.

7. A storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 5 is implemented.

Images