A pantograph carbon slide detection method and system based on three-dimensional reconstruction technology

Abstract

The application discloses a pantograph carbon slide plate detection method and system based on a three-dimensional reconstruction technology, and comprises the following steps: controlling four line laser ranging modules to collect data; processing each frame of imaging collected by the same line laser ranging module and splicing into a 1*W one-dimensional matrix; splicing adjacent H frame data to obtain an H*W depth matrix; performing threshold screening on data deepValue in a certain region of each depth matrix; dividing the data according to a set division rule to divide M groups of point cloud data, and giving an ID according to the order of appearance; performing point cloud splicing on the point cloud data of the same ID; performing posture adjustment on 3D point cloud of the pantograph carbon slide plate; calculating the Z-axis coordinate difference of the top and bottom point cloud of the same pantograph carbon slide plate within a certain range to obtain the overall residual thickness of the pantograph carbon slide plate. The application can clearly know the overall wear distribution, and has important significance.

Description

Technical Field

[0001] This invention relates to the field of pantograph detection technology, and in particular to a pantograph carbon strip detection method and system based on three-dimensional reconstruction technology. Background Technology

[0002] The overhead contact line is the main power supply device on electrified railways, supplying electrical energy to the train through sliding contact with the pantograph on the roof of the train. The carbon sliding plate is the current-collecting medium on the pantograph. Due to the relative movement between the pantograph and the contact line, the carbon sliding plate will inevitably wear down over time. Therefore, to ensure the normal operation of railway trains, checking the remaining thickness of the carbon sliding plate is an important part of railway train maintenance.

[0003] Currently, most methods in the industry use 2D cameras to detect the remaining thickness of carbon fiber sliding plates. This involves capturing images of the outer sides of the two carbon fiber sliding plates (facing the two ends of the vehicle) from a fixed position, calculating the pixel distance between the top and bottom edges of the carbon fiber sliding plates in the image, and then using calibration parameters to determine the relationship between the pixel distance and world coordinates to finally calculate the remaining usable thickness of the carbon fiber sliding plate. However, because this method only measures a single plane, it cannot determine the overall wear and tear of the carbon fiber sliding plate.

[0004] Therefore, improvements to existing technologies are necessary.

[0005] The above information is provided as background information only to aid in understanding this disclosure and does not constitute an assertion or admission that any of the above content can be used as prior art relative to this disclosure. Summary of the Invention

[0006] This invention provides a method and system for detecting pantograph carbon sliding plates based on three-dimensional reconstruction technology, in order to overcome the shortcomings of existing technologies.

[0007] To achieve the above objectives, the present invention provides the following technical solution:

[0008] In a first aspect, the present invention provides a method for detecting a pantograph carbon sliding plate based on three-dimensional reconstruction technology, the method comprising:

[0009] The system controls four line laser ranging modules to start and acquire data. Two of the line laser ranging modules are located at the top and bottom of the left side of the pantograph, respectively, and the other two line laser ranging modules are located at the top and bottom of the right side of the pantograph, respectively. Each line laser ranging module includes an area array camera and a line laser.

[0010] Each frame of image acquired by the same line laser ranging module is processed, and W depth data are obtained by combining the calibration parameters of the line laser ranging module, and then stitched into a 1*W one-dimensional matrix.

[0011] The adjacent H frames of data are stitched together to obtain an H*W depth matrix. There are a total of N frames of data, resulting in N / H H*W depth matrices.

[0012] Threshold filtering is applied to the data deepValue within a certain region of each depth matrix;

[0013] The data is divided according to the set division rules to divide it into M groups of point cloud data, and IDs are assigned according to the order of appearance, where M is the total number of pantograph carbon sliders;

[0014] Point cloud data with the same ID are stitched together using calibration parameters between modules;

[0015] Attitude adjustment of the 3D point cloud of the pantograph carbon skid plate;

[0016] The difference in Z-axis coordinates between the top and bottom point clouds of the same pantograph carbon slide plate within a certain range is calculated, and the resulting difference is the remaining thickness of the pantograph carbon slide plate as a whole.

[0017] Furthermore, in the pantograph carbon slider detection method based on three-dimensional reconstruction technology, before the step of controlling the four line laser ranging modules to start and acquire data, the method further includes:

[0018] Detect whether a trigger signal sent by the sensor has been received;

[0019] If so, then execute the steps described above to start the four line laser ranging modules and perform data acquisition;

[0020] If not, continue with the step of detecting whether a trigger signal sent by the sensor has been received.

[0021] Furthermore, in the pantograph carbon slider detection method based on 3D reconstruction technology, the step of threshold filtering of the data deepValue within a certain region of each depth matrix includes:

[0022] For each depth matrix, traverse the data deepValue within a certain region and record the row number hIndex of the data deepValue that meets the threshold range;

[0023] Clear the data in row hIndex that is outside the threshold range, deepVa lue.

[0024] Furthermore, in the pantograph carbon slider detection method based on 3D reconstruction technology, the step of dividing the data according to a set division rule to divide it into M groups of point cloud data, and assigning IDs according to their order of appearance, where M is the total number of pantograph carbon sliders, includes:

[0025] The number of rows hIndex is divided according to the rule that the number of rows hIndex of the same pantograph carbon slider is continuous, and the number of rows hIndex of different pantograph carbon sliders is non-continuous, so as to divide the point cloud data into M groups, where M is the total number of pantograph carbon sliders.

[0026] IDs are assigned based on the order in which they appear.

[0027] Furthermore, in the pantograph carbon sling detection method based on 3D reconstruction technology, the step of adjusting the attitude of the 3D point cloud of the pantograph carbon sling includes:

[0028] Obtain the coordinates of two points P11(X1,Y1,Z1) and P12(X2,Y2,Z2) on the top left edge of the same pantograph carbon slide, and the coordinates of two points P21(X3,Y3,Z3) and P22(X4,Y4,Z4) on the right edge of the same pantograph carbon slide.

[0029] Calculate the Euclidean distances D11, D12, D21, and D22 between P11 and P12, P21 and P22, P11 and P21, and P12 and P22, and set new points P11'(D11 / 2,D21 / 2,0), P12'(-D11 / 2,D21 / 2,0), P21'(D11 / 2,-D21 / 2,0), and P22'(-D11 / 2,-D21 / 2,0).

[0030] The point cloud rotation matrix can be obtained based on the four new points set, and the attitude of the 3D point cloud of the pantograph carbon skateboard can be adjusted.

[0031] Secondly, the present invention provides a pantograph carbon slider detection system based on three-dimensional reconstruction technology, the system comprising:

[0032] The acquisition and control module is used to control the start-up of four line laser ranging modules and to acquire data. Two of the line laser ranging modules are located at the top and bottom of the left side of the pantograph, respectively, and the other two line laser ranging modules are located at the top and bottom of the right side of the pantograph, respectively. Each line laser ranging module includes an area array camera and a line laser.

[0033] The imaging processing module is used to process each frame of image acquired by the same line laser ranging module, combine it with the calibration parameters of the line laser ranging module to obtain W depth data, and stitch them into a 1*W one-dimensional matrix.

[0034] The data stitching module is used to stitch adjacent H frames of data to obtain an H*W depth matrix. There are a total of N frames of data, resulting in N / H H*W depth matrices.

[0035] The threshold filtering module is used to perform threshold filtering on the data deepValue within a certain region of each depth matrix.

[0036] The data partitioning module is used to partition the data according to the set partitioning rules to divide it into M groups of point cloud data and assign IDs according to their order of appearance, where M is the total number of pantograph carbon sliders;

[0037] The point cloud stitching module is used to stitch point cloud data with the same ID together with the calibration parameters between modules.

[0038] The attitude adjustment module is used to adjust the attitude of the 3D point cloud of the pantograph carbon slider.

[0039] The thickness calculation module is used to calculate the Z-axis coordinate difference between the top and bottom point clouds of the same pantograph carbon slide plate within a certain range. The difference obtained is the remaining thickness of the pantograph carbon slide plate as a whole.

[0040] Furthermore, in the pantograph carbon slider detection system based on three-dimensional reconstruction technology, the system also includes a sensing trigger module for:

[0041] Before the step of controlling the four line laser ranging modules to start and acquire data, it is detected whether a trigger signal sent by the sensor is received;

[0042] If so, then execute the steps described above to start the four line laser ranging modules and perform data acquisition;

[0043] If not, continue with the step of detecting whether a trigger signal sent by the sensor has been received.

[0044] Furthermore, in the pantograph carbon slider detection system based on three-dimensional reconstruction technology, the threshold screening module is specifically used for:

[0045] For each depth matrix, traverse the data deepValue within a certain region and record the row number hIndex of the data deepValue that meets the threshold range;

[0046] Clear the data in row hIndex that is outside the threshold range, deepVa lue.

[0047] Furthermore, in the pantograph carbon slider detection system based on three-dimensional reconstruction technology, the data partitioning module is specifically used for:

[0048] The number of rows hIndex is divided according to the rule that the number of rows hIndex of the same pantograph carbon slider is continuous, and the number of rows hIndex of different pantograph carbon sliders is non-continuous, so as to divide the point cloud data into M groups, where M is the total number of pantograph carbon sliders.

[0049] IDs are assigned based on the order in which they appear.

[0050] Furthermore, in the pantograph carbon slider detection system based on three-dimensional reconstruction technology, the attitude adjustment module is specifically used for:

[0051] Obtain the coordinates of two points P11(X1,Y1,Z1) and P12(X2,Y2,Z2) on the top left edge of the same pantograph carbon slide, and the coordinates of two points P21(X3,Y3,Z3) and P22(X4,Y4,Z4) on the right edge of the same pantograph carbon slide.

[0052] Calculate the Euclidean distances D11, D12, D21, and D22 between P11 and P12, P21 and P22, P11 and P21, and P12 and P22, and set new points P11'(D11 / 2,D21 / 2,0), P12'(-D11 / 2,D21 / 2,0), P21'(D11 / 2,-D21 / 2,0), and P22'(-D11 / 2,-D21 / 2,0).

[0053] The point cloud rotation matrix can be obtained based on the four new points set, and the attitude of the 3D point cloud of the pantograph carbon skateboard can be adjusted.

[0054] Compared with the prior art, the present invention has the following beneficial effects:

[0055] This invention provides a method and system for detecting pantograph carbon sliding plates based on three-dimensional reconstruction technology. It utilizes four line laser ranging modules to construct depth information, obtaining point cloud data. By calibrating the modules, the world coordinates of the top and bottom point cloud data are unified, allowing the point cloud data to be stitched together to complete the three-dimensional reconstruction of the pantograph carbon sliding plate. Finally, by calculating the point cloud data, the remaining thickness of the pantograph carbon sliding plate can be determined, providing a relatively clear understanding of the overall wear distribution. This method is highly valuable and worthy of adoption and promotion. Attached Figure Description

[0056] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0057] Figure 1 This is a flowchart illustrating a pantograph carbon slider detection method based on three-dimensional reconstruction technology provided in Embodiment 1 of the present invention;

[0058] Figure 2 This is a schematic diagram of the functional modules of a pantograph carbon sliding plate detection system based on three-dimensional reconstruction technology provided in Embodiment 2 of the present invention. Detailed Implementation

[0059] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0060] In the description of this invention, it should be understood that when a component is considered to be "connected" to another component, it can be directly connected to the other component or there may be an intermediate component present simultaneously. When a component is considered to be "set" on another component, it can be directly set on the other component or there may be an intermediate component present simultaneously.

[0061] Furthermore, terms such as “long,” “short,” “inner,” and “outer” indicate orientation or positional relationships based on the orientation or positional relationships shown in the accompanying drawings. They are used only for the purpose of describing the present invention and are not intended to indicate or imply that the device or component referred to must have this specific orientation or operate in a specific orientational configuration. Therefore, they should not be construed as limitations of the present invention.

[0062] The technical solution of the present invention will be further described below with reference to the accompanying drawings and specific embodiments.

[0063] Example 1

[0064] In view of the shortcomings of existing pantograph carbon strip wear detection technologies, the applicant, based on years of practical experience and professional knowledge in the design and manufacture of such products, and in conjunction with theoretical application, has actively researched and innovated to create a technology that can overcome the shortcomings of existing technologies, making pantograph carbon strip wear detection technology more practical. After continuous research, design, and repeated prototype production and improvements, this invention, which has proven to be of practical value, has finally been created.

[0065] Please refer to Figure 1This is a flowchart illustrating a pantograph carbon strip detection method based on three-dimensional reconstruction technology, provided in Embodiment 1 of the present invention. This method is applicable to scenarios requiring the detection of the overall remaining thickness of the pantograph carbon strip. The method is executed by a pantograph carbon strip detection system based on three-dimensional reconstruction technology, which can be implemented in software and / or hardware. The method specifically includes the following steps:

[0066] S101. Control the four line laser ranging modules to start and collect data. Two of the line laser ranging modules are located at the top and bottom of the left side of the pantograph, respectively, and the other two line laser ranging modules are located at the top and bottom of the right side of the pantograph, respectively. Each line laser ranging module includes an area array camera and a line laser.

[0067] It should be noted that this embodiment uses four line laser ranging modules to construct depth information for the pantograph carbon slider in order to obtain point cloud data.

[0068] In this embodiment, prior to step S101, the method may further include the following steps:

[0069] Detect whether a trigger signal sent by the sensor has been received;

[0070] If so, then execute the steps described above to start the four line laser ranging modules and perform data acquisition;

[0071] If not, continue with the step of detecting whether a trigger signal sent by the sensor has been received.

[0072] It should be noted that once the pantograph of the subway train triggers the sensor, the host computer will receive the trigger signal from the sensor, and then the host computer will start the four line laser ranging modules to collect data.

[0073] S102. Process each frame of image acquired by the same line laser ranging module, combine it with the calibration parameters of the line laser ranging module to obtain W depth data, and stitch them into a 1*W one-dimensional matrix.

[0074] It should be noted that the calibration parameters of the line laser ranging module are pre-saved parameters used to determine the relative relationship between the acquired data and the module. Since these aspects are already widely implemented in existing technologies and are not the focus of this design, they will not be elaborated upon here.

[0075] S103. Consolidate adjacent H-frame data to obtain an H*W depth matrix. There are a total of N frames of data, resulting in N / H H*W depth matrices.

[0076] S104. Perform threshold filtering on the data deepValue within a certain region of each depth matrix.

[0077] In this embodiment, step S104 can be further refined into the following steps:

[0078] Traverse the data deepValue within a certain area of each depth matrix (deepValue(0 < a < w < b < W, 0 < h < H)), and record the row number hIndex where the data deepValue within the threshold range is located;

[0079] Clear the data deepValue outside the threshold range in the row number hIndex.

[0080] It should be noted that this step aims to screen out the data that does not belong to the pantograph carbon slide, leaving effective depth data to reduce interference and save computing power.

[0081] S105. Divide the data according to the set division rule to divide into M groups of point cloud data, and assign an ID according to the order of appearance, where M is the total number of pantograph carbon slides.

[0082] In this embodiment, step S105 can be further refined into the following steps:

[0083] Divide the row number hIndex according to the division rule that the row numbers hIndex of the same pantograph carbon slide are continuous and the row numbers hIndex of different pantograph carbon slides are discontinuous, so as to divide into M groups of point cloud data, where M is the total number of pantograph carbon slides;

[0084] Assign an ID according to the order of appearance.

[0085] It should be noted that this step aims to divide the data of different pantograph carbon slides.

[0086] S106. Perform point cloud stitching on the point cloud data with the same ID in combination with the calibration parameters between modules.

[0087] It should be noted that the calibration parameters between modules are parameters pre-saved for determining the relative relationship between modules. Since these contents have been implemented in the prior art and are not the focus of the design of this solution, no in-depth elaboration will be made here.

[0088] S107. Adjust the pose of the 3D point cloud of the pantograph carbon slide.

[0089] In this embodiment, step S107 can be further refined into the following steps:

[0090] Obtain the coordinates of two points P11(X1,Y1,Z1) and P12(X2,Y2,Z2) on the top left edge of the same pantograph carbon slide, and the coordinates of two points P21(X3,Y3,Z3) and P22(X4,Y4,Z4) on the right edge of the same pantograph carbon slide.

[0091] Calculate the Euclidean distances D11, D12, D21, and D22 between P11 and P12, P21 and P22, P11 and P21, and P12 and P22, and set new points P11'(D11 / 2,D21 / 2,0), P12'(-D11 / 2,D21 / 2,0), P21'(D11 / 2,-D21 / 2,0), and P22'(-D11 / 2,-D21 / 2,0).

[0092] The point cloud rotation matrix can be obtained based on the four new points set, and the attitude of the 3D point cloud of the pantograph carbon skateboard can be adjusted.

[0093] It should be noted that P11(X1,Y1,Z1) and P12(X2,Y2,Z2) are the top left and bottom left points of the top view of the carbon skateboard, respectively, while P21(X3,Y3,Z3) and P22(X4,Y4,Z4) are the top right and bottom right points of the top view of the carbon skateboard, respectively.

[0094] Furthermore, the method of obtaining the point cloud rotation matrix based on four points has been implemented in many existing technologies and is not the focus of this design, so it will not be elaborated on here.

[0095] S108. Calculate the Z-axis coordinate difference between the top and bottom point clouds of the same pantograph carbon slide plate within a certain range. The difference obtained is the remaining thickness of the pantograph carbon slide plate as a whole.

[0096] Although this paper frequently uses terms such as line laser ranging module, pantograph, calibration parameters, and depth matrix, the possibility of using other terms is not excluded. These terms are used merely for the convenience of describing and explaining the essence of this invention; interpreting them as any additional limitation would contradict the spirit of this invention.

[0097] This invention provides a method for detecting pantograph carbon skid plates based on 3D reconstruction technology. It utilizes four line laser ranging modules to construct depth information, obtaining point cloud data. By calibrating the modules, the world coordinates of the top and bottom point cloud data are unified, allowing the point cloud data to be stitched together. This completes the 3D reconstruction of the pantograph carbon skid plate. Finally, by calculating the point cloud data, the remaining thickness of the pantograph carbon skid plate can be determined, providing a clear understanding of the overall wear distribution. This method is highly valuable and worthy of adoption and promotion.

[0098] Example 2

[0099] Please refer to Figure 2 , Figure 2 This is a functional module diagram of a pantograph carbon strip detection system based on three-dimensional reconstruction technology provided in Embodiment 2 of the present invention. This system is applicable to executing the pantograph carbon strip detection method based on three-dimensional reconstruction technology provided in this embodiment of the invention. The system specifically includes the following modules:

[0100] The acquisition control module 201 is used to control the four line laser ranging modules to start and acquire data. Two of the line laser ranging modules are located at the top and bottom of the left side of the pantograph, respectively, and the other two line laser ranging modules are located at the top and bottom of the right side of the pantograph, respectively. Each line laser ranging module includes an area array camera and a line laser.

[0101] The imaging processing module 202 is used to process each frame of image acquired by the same line laser ranging module, combine it with the calibration parameters of the line laser ranging module to obtain W depth data, and stitch them into a 1*W one-dimensional matrix.

[0102] The data stitching module 203 is used to stitch adjacent H frame data to obtain an H*W depth matrix. There are a total of N frames of data, resulting in N / H H*W depth matrices.

[0103] The threshold filtering module 204 is used to perform threshold filtering on the data deepValue within a certain region of each depth matrix.

[0104] The data partitioning module 205 is used to partition the data according to the set partitioning rules to divide it into M groups of point cloud data and assign IDs according to their order of appearance, where M is the total number of pantograph carbon sliders.

[0105] Point cloud stitching module 206 is used to stitch point cloud data with the same ID together with the calibration parameters between modules;

[0106] The attitude adjustment module 207 is used to adjust the attitude of the 3D point cloud of the pantograph carbon slider;

[0107] The thickness calculation module 208 is used to calculate the Z-axis coordinate difference between the top and bottom point clouds of the same pantograph carbon slide plate within a certain range. The difference obtained is the remaining thickness of the pantograph carbon slide plate as a whole.

[0108] Preferably, the system further includes a sensing trigger module, used for:

[0109] Before the step of controlling the four line laser ranging modules to start and acquire data, it is detected whether a trigger signal sent by the sensor is received;

[0110] If so, then execute the steps described above to start the four line laser ranging modules and perform data acquisition;

[0111] If not, continue with the step of detecting whether a trigger signal sent by the sensor has been received.

[0112] Preferably, the threshold filtering module is specifically used for:

[0113] For each depth matrix, traverse the data deepValue within a certain region and record the row number hIndex of the data deepValue that meets the threshold range;

[0114] Clear the data in row hIndex that is outside the threshold range, deepVa lue.

[0115] Preferably, the data partitioning module is specifically used for:

[0116] The number of rows hIndex is divided according to the rule that the number of rows hIndex of the same pantograph carbon slider is continuous, and the number of rows hIndex of different pantograph carbon sliders is non-continuous, so as to divide the point cloud data into M groups, where M is the total number of pantograph carbon sliders.

[0117] IDs are assigned based on the order in which they appear.

[0118] Preferably, the attitude adjustment module is specifically used for:

[0119] Obtain the coordinates of two points P11(X1,Y1,Z1) and P12(X2,Y2,Z2) on the top left edge of the same pantograph carbon slide, and the coordinates of two points P21(X3,Y3,Z3) and P22(X4,Y4,Z4) on the right edge of the same pantograph carbon slide.

[0120] Calculate the Euclidean distances D11, D12, D21, and D22 between P11 and P12, P21 and P22, P11 and P21, and P12 and P22, and set new points P11'(D11 / 2,D21 / 2,0), P12'(-D11 / 2,D21 / 2,0), P21'(D11 / 2,-D21 / 2,0), and P22'(-D11 / 2,-D21 / 2,0).

[0121] The point cloud rotation matrix can be obtained based on the four new points set, and the attitude of the 3D point cloud of the pantograph carbon skateboard can be adjusted.

[0122] This invention provides a pantograph carbon skid plate detection system based on 3D reconstruction technology. It utilizes four line laser ranging modules to construct depth information, obtaining point cloud data. By calibrating the modules, the world coordinates of the top and bottom point cloud data are unified, allowing the point cloud data to be stitched together to complete the 3D reconstruction of the pantograph carbon skid plate. Finally, by calculating the point cloud data, the remaining thickness of the pantograph carbon skid plate can be determined, providing a clear understanding of the overall wear distribution. This system is highly valuable and worthy of adoption and promotion.

[0123] The above system can execute the methods provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the methods.

[0124] In summary, after reading this detailed disclosure, those skilled in the art will understand that the foregoing detailed disclosure is presented by way of example only and is not restrictive. Although not explicitly stated herein, those skilled in the art will understand that this application is intended to encompass various reasonable changes, improvements, and modifications to the embodiments. These changes, improvements, and modifications are intended to be made by this application and are within the spirit and scope of the exemplary embodiments of this application.

[0125] Furthermore, certain terms used in this application have been used to describe embodiments of this application. For example, "an embodiment," "an embodiment," and / or "some embodiments" mean that a particular feature, structure, or characteristic described in connection with that embodiment may be included in at least one embodiment of this application. Therefore, it is to be emphasized and understood that two or more references to "an embodiment" or "an embodiment" or "an alternative embodiment" in various parts of this specification do not necessarily refer to the same embodiment. Moreover, specific features, structures, or characteristics may be appropriately combined in one or more embodiments of this application.

[0126] It should be understood that in the foregoing description of the embodiments of this application, various features are combined in a single embodiment, drawing, or description for the purpose of simplifying the understanding of a feature. However, this does not mean that the combination of these features is necessary, and those skilled in the art may extract some features as separate embodiments when reading this application. That is, the embodiments in this application can also be understood as an integration of multiple sub-embodiments. It is also valid when the content of each sub-embodiment contains fewer than all the features of a single foregoing disclosed embodiment.

[0127] Each patent, patent application, publication of the patent application, and other materials such as articles, books, specifications, publications, documents, articles, etc., cited herein may be incorporated by reference. The entire contents used for all purposes, except for any history of prosecution documents associated with it, that may be inconsistent with or conflict with this document, or that may have a limiting effect on the widest extent of the claims, are now or hereafter associated with this document. For example, in the event of any inconsistency or conflict between the description, definition, and / or use of terms associated with any of the included materials and the terms, description, definition, and / or used in connection with this document, the terms used herein shall prevail.

[0128] Finally, it should be understood that the embodiments disclosed herein are illustrative of the principles of the embodiments of this application. Other modified embodiments are also within the scope of this application. Therefore, the embodiments disclosed herein are merely examples and not limitations. Those skilled in the art can adopt alternative configurations to implement the applications in this application based on the embodiments in this application. Therefore, the embodiments of this application are not limited to the embodiments precisely described in the application.

Claims

1. A method for detecting pantograph carbon sliding plates based on three-dimensional reconstruction technology, characterized in that, The method includes: The system controls four line laser ranging modules to start and acquire data. Two of the line laser ranging modules are located at the top and bottom of the left side of the pantograph, respectively, and the other two line laser ranging modules are located at the top and bottom of the right side of the pantograph, respectively. Each line laser ranging module includes an area array camera and a line laser. Each frame of image acquired by the same line laser ranging module is processed, and W depth data are obtained by combining the calibration parameters of the line laser ranging module, and then stitched into a 1*W one-dimensional matrix. The adjacent H frames of data are stitched together to obtain an H*W depth matrix. There are a total of N frames of data, resulting in N / H H*W depth matrices. Threshold filtering is applied to the deepValue data within a certain region of each depth matrix; The data is divided according to the set division rules to divide it into M groups of point cloud data, and IDs are assigned according to the order of appearance, where M is the total number of pantograph carbon sliders; Point cloud data with the same ID are stitched together using calibration parameters between modules; Attitude adjustment of the 3D point cloud of the pantograph carbon skid plate; The difference in Z-axis coordinates between the top and bottom point clouds of the same pantograph carbon slide plate within a certain range is calculated, and the resulting difference is the remaining thickness of the pantograph carbon slide plate as a whole.

2. The pantograph carbon slider detection method based on three-dimensional reconstruction technology according to claim 1, characterized in that, Before the step of controlling the four line laser ranging modules to start and acquire data, the method further includes: Detect whether a trigger signal sent by the sensor has been received; If so, then execute the steps described above to start the four line laser ranging modules and perform data acquisition; If not, continue with the step of detecting whether a trigger signal sent by the sensor has been received.

3. The pantograph carbon slider detection method based on three-dimensional reconstruction technology according to claim 1, characterized in that, The step of threshold filtering the data depthValue within a certain region of each depth matrix includes: For each depth matrix, iterate through the data deepValue within a certain region and record the row number hIndex of the data deepValue that meets the threshold range; Clear the data deepValue in the row hIndex that is outside the threshold range.

4. The pantograph carbon slider detection method based on three-dimensional reconstruction technology according to claim 3, characterized in that, The steps of dividing the data according to the set division rules to divide it into M groups of point cloud data, and assigning IDs according to their order of appearance, where M is the total number of pantograph carbon skateboards, include: The hIndex of the row number is divided according to the rule that the row number hIndex of the same pantograph carbon slider is continuous and the row number hIndex of different pantograph carbon sliders is non-continuous, so as to divide the point cloud data into M groups, where M is the total number of pantograph carbon sliders. IDs are assigned based on the order in which they appear.

5. The pantograph carbon slider detection method based on three-dimensional reconstruction technology according to claim 1, characterized in that, The steps for adjusting the attitude of the 3D point cloud of the pantograph carbon skateboard include: Obtain the coordinates of two points P11(X1,Y1,Z1) and P12(X2,Y2,Z2) on the top left edge of the same pantograph carbon slide, and the coordinates of two points P21(X3,Y3,Z3) and P22(X4,Y4,Z4) on the right edge of the same pantograph carbon slide. Calculate the Euclidean distances D11, D12, D21, and D22 between P11 and P12, P21 and P22, P11 and P21, and P12 and P22, and set new points P11'(D11 / 2,D21 / 2,0), P12'(-D11 / 2,D21 / 2,0), P21'(D11 / 2,-D21 / 2,0), and P22'(-D11 / 2,-D21 / 2,0). The point cloud rotation matrix can be obtained based on the four new points set, and the attitude of the 3D point cloud of the pantograph carbon skateboard can be adjusted.

6. A pantograph carbon slider detection system based on three-dimensional reconstruction technology, characterized in that, The system includes: The acquisition and control module is used to control the start-up of four line laser ranging modules and to acquire data. Two of the line laser ranging modules are located at the top and bottom of the left side of the pantograph, respectively, and the other two line laser ranging modules are located at the top and bottom of the right side of the pantograph, respectively. Each line laser ranging module includes an area array camera and a line laser. The imaging processing module is used to process each frame of image acquired by the same line laser ranging module, combine it with the calibration parameters of the line laser ranging module to obtain W depth data, and stitch them into a 1*W one-dimensional matrix. The data stitching module is used to stitch adjacent H frames of data to obtain an H*W depth matrix. There are a total of N frames of data, resulting in N / H H*W depth matrices. The threshold filtering module is used to perform threshold filtering on the deepValue data within a certain region of each depth matrix. The data partitioning module is used to partition the data according to the set partitioning rules to divide it into M groups of point cloud data and assign IDs according to their order of appearance, where M is the total number of pantograph carbon sliders; The point cloud stitching module is used to stitch point cloud data with the same ID together with the calibration parameters between modules. The attitude adjustment module is used to adjust the attitude of the 3D point cloud of the pantograph carbon slider. The thickness calculation module is used to calculate the Z-axis coordinate difference between the top and bottom point clouds of the same pantograph carbon slide plate within a certain range. The difference obtained is the remaining thickness of the pantograph carbon slide plate as a whole.

7. The pantograph carbon slider detection system based on three-dimensional reconstruction technology according to claim 6, characterized in that, The system also includes a sensing trigger module for: Before the step of controlling the four line laser ranging modules to start and acquire data, it is detected whether a trigger signal sent by the sensor is received; If so, then execute the steps described above to start the four line laser ranging modules and perform data acquisition; If not, continue with the step of detecting whether a trigger signal sent by the sensor has been received.

8. The pantograph carbon slider detection system based on three-dimensional reconstruction technology according to claim 6, characterized in that, The threshold filtering module is specifically used for: For each depth matrix, iterate through the data deepValue within a certain region and record the row number hIndex of the data deepValue that meets the threshold range; Clear the data deepValue in the row hIndex that is outside the threshold range.

9. The pantograph carbon slider detection system based on three-dimensional reconstruction technology according to claim 8, characterized in that, The data partitioning module is specifically used for: The hIndex of the row number is divided according to the rule that the row number hIndex of the same pantograph carbon slider is continuous and the row number hIndex of different pantograph carbon sliders is non-continuous, so as to divide the point cloud data into M groups, where M is the total number of pantograph carbon sliders. IDs are assigned based on the order in which they appear.

10. The pantograph carbon slider detection system based on three-dimensional reconstruction technology according to claim 6, characterized in that, The attitude adjustment module is specifically used for: Obtain the coordinates of two points P11(X1,Y1,Z1) and P12(X2,Y2,Z2) on the top left edge of the same pantograph carbon slide, and the coordinates of two points P21(X3,Y3,Z3) and P22(X4,Y4,Z4) on the right edge of the same pantograph carbon slide. Calculate the Euclidean distances D11, D12, D21, and D22 between P11 and P12, P21 and P22, P11 and P21, and P12 and P22, and set new points P11'(D11 / 2,D21 / 2,0), P12'(-D11 / 2,D21 / 2,0), P21'(D11 / 2,-D21 / 2,0), and P22'(-D11 / 2,-D21 / 2,0). The point cloud rotation matrix can be obtained based on the four new points set, and the attitude of the 3D point cloud of the pantograph carbon skateboard can be adjusted.

Images