Rigid contact network wear detection method, equipment and storage medium

Abstract

The present application belongs to the field of image processing technology, and specifically relates to a method, device, and storage medium for detecting wear of a rigid contact network, wherein the method comprises: obtaining a depth image to be detected; converting each row of depth image data into two-dimensional point cloud data; filtering the two-dimensional point cloud data to obtain contact line point cloud data and busbar groove point cloud data based on a preset threshold; obtaining the left and right endpoints of the contact line surface through a k-mean clustering algorithm based on the contact line point cloud data; matching the busbar groove point cloud data with the corresponding template point cloud data in the contact line and busbar template to determine a matching transformation relationship; obtaining contact line matching points that match the left and right endpoints of the contact line surface based on the matching transformation relationship; and obtaining the contact network wear detection result based on the contact line matching points and the intersection points between the contact line and the busbar in the contact line and busbar template. The present application method can accurately and comprehensively detect wear of the contact line.

Description

Technical Field

[0001] The present application belongs to the field of image processing technology, and specifically relates to a method for detecting wear of a rigid contact network. Background Art

[0002] As a crucial component of urban rail transit's traction power supply system, rigid overhead catenary systems are directly related to the safe and reliable operation of subways. Currently, severe wear and tear of the contact wires in certain sections of existing domestic lines (such as the acceleration section for electric passenger cars leaving stations, anchor joints, and segment insulators) increases the probability of accidents during operation. Therefore, it is necessary to monitor the wear and tear of the contact wires to ensure timely replacement.

[0003] When the contact wire is constantly worn by friction with the train pantograph, its surface will have a very smooth cross-section. Existing wear detection schemes for the contact network take advantage of the fact that the cross-section is more reflective to light than the rest of the curved portion of the contact wire and that the worn edge of the contact wire will produce a significant gradient change. A monocular camera is used to capture the contact network image from the bottom up. Based on image enhancement, image analysis, edge detection, and morphological processing methods, the contour information of the worn edge at the bottom of the contact wire is extracted to analyze the contact line wear. In addition to the common monocular camera scheme, some studies have adopted binocular vision schemes. Based on binocular ranging technology and triangulation imaging principles, the coordinate information of two points on the bottom edge is obtained to further analyze the bottom wear information.

[0004] However, existing monocular and binocular camera solutions only utilize information from the wear surface of the contact wire, assuming it is smooth, uniform, and nearly planar. This ignores the characteristic information in the central region of the wear surface. Furthermore, because conductive grease, carbon particles, and dust tend to adhere to the sides of the contact wire in real environments, this directly prevents imaging the intersection of the contact wire and the busbar, making it impossible to measure the wear allowance.

[0005] Therefore, how to accurately and comprehensively detect contact line wear has become an urgent problem to be solved. Summary of the Invention

[0006] (1) Technical issues to be resolved

[0007] In view of the above-mentioned shortcomings and deficiencies of the prior art, the present application provides a rigid contact network wear detection method, device and readable storage medium.

[0008] (2) Technical solution

[0009] To achieve the above objectives, this application adopts the following technical solutions:

[0010] In a first aspect, an embodiment of the present application provides a method for detecting wear of a rigid contact network, the method comprising:

[0011] S10, acquiring a depth image of the contact line and busbar to be detected, and using the acquired depth image as the depth image to be detected;

[0012] S20, converting each row of depth image data in the depth image to be detected into two-dimensional point cloud data; filtering the two-dimensional point cloud data based on a preset threshold to obtain contact line point cloud data and busbar groove point cloud data;

[0013] S30, obtaining the left and right endpoints of the contact line surface by using a k-mean clustering algorithm based on the contact line point cloud data;

[0014] S40, matching the busbar groove point cloud data with the corresponding template point cloud data in the pre-established contact line and busbar template to determine a matching transformation relationship;

[0015] S50, obtaining contact line matching points between the contact line and the left and right endpoints of the contact line surface in the busbar template based on the matching transformation relationship;

[0016] S60 , obtaining a detection result of contact network wear based on the contact line matching points and the intersection points of the contact line and the busbar in the contact line and busbar template.

[0017] Optionally, S10 includes:

[0018] S11, acquiring an initial depth image of the contact line and busbar captured by a line structured light camera;

[0019] S12. Perform median filtering on the initial depth image to obtain a depth image to be detected, wherein the median filtering method includes:

[0020] Set a window of size (2k+1)×1, and perform a sliding window operation with a step size of 1 along the X direction and Y direction of the initial depth image;

[0021] The median of the grayscale values of all pixels in the current window is used as the grayscale value of the center point of the current window.

[0022] Optionally, S20 further includes removing outliers in the two-dimensional point cloud data by statistical filtering, and the statistical filtering method includes:

[0023] Traverse all point cloud data and calculate the average distance between each point and its nearest neighboring points (n).

[0024] Calculate the mean and standard deviation of all average distances and set the distance threshold D max

[0025] D max =μ+α×δ;

[0026] Among them, μ is the mean of all average distances, δ is the standard deviation of all average distances, and α is the distance threshold parameter

[0027] Traverse all point clouds and remove points whose average distance to n neighboring points is greater than D max point.

[0028] Optionally, filtering the contact line point cloud data from the two-dimensional point cloud data based on a preset threshold value includes:

[0029] Determine the maximum value y in the Y direction of the two-dimensional point cloud data max ;

[0030] The contact line point cloud data of the contact line surface is filtered out based on the pre-set depth threshold T As shown in the formula:

[0031]

[0032] Among them, C is all two-dimensional point cloud data, p is a point in the point cloud data, p y The coordinate value of the point cloud data in the y direction.

[0033] Optionally, S30 includes:

[0034] S31, performing first-order difference and second-order difference operations on the contact line point cloud data along the X direction, and calculating the curvature of the contact line point cloud data in the X direction by the following formula:

[0035]

[0036] Among them, f x ' is the result of the first-order difference operation, f x ” is the result of second-order difference operation;

[0037] S32. Selecting a preset number of point cloud data with the largest curvature value, and applying a k-mean clustering algorithm to cluster them, and using the two obtained cluster centers as the left and right endpoints of the contact line surface.

[0038] Optionally, S40 includes:

[0039] S41, using the bus groove point cloud as the point cloud to be matched, calculating the nearest points of the contact line and each point in the bus template in the point cloud to be matched, and forming point pairs;

[0040] S42, calculating the rotation matrix and translation matrix;

[0041] S43, transforming the point cloud in the contact line and busbar template using a rotation matrix and a translation matrix to obtain a transformed template point cloud;

[0042] S44. Calculate the error function using the following formula:

[0043]

[0044] Among them, n is the number of nearest neighbor pairs, p i is the point to be matched in the i-th pair of nearest neighboring points, q i is the template point in the i-th pair of nearest neighbor points;

[0045] S45, repeat S42-S44 until the error function is less than the set error threshold or the set number of iterations is reached;

[0046] S46. Use the rotation matrix and translation matrix obtained from the last iteration as the matching matrix.

[0047] Optionally, S60 includes:

[0048] S61. Calculate the contact surface width, wear allowance, and eccentric wear angle based on the contact line matching point and the intersection point of the contact line and the busbar in the contact line and busbar template, respectively, wherein the contact surface width is equal to the Euclidean distance between the two points of the contact line matching point, the wear allowance is equal to the distance in the y direction from the intersection point of the contact line and the busbar to the farthest point of the contact line matching point, and the eccentric wear angle is equal to the angle between the line connecting the two points of the contact line matching point and the horizontal;

[0049] S62: Taking the contact surface width, the wear allowance, and the eccentric wear angle as the detection result of contact network wear.

[0050] In a second aspect, an embodiment of the present application provides an electronic device comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the computer program is executed by the processor, the steps of the rigid contact network wear detection method as described in any one of the first aspects above are implemented.

[0051] In a third aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the rigid contact network wear detection method as described in any one of the first aspects above are implemented.

[0052] (3) Beneficial effects

[0053] The beneficial effects of the present application are as follows: the present application proposes a method, device, and readable storage medium for detecting wear of a rigid contact network, wherein the method comprises: obtaining a depth image to be detected; converting each row of depth image data into two-dimensional point cloud data; filtering contact line point cloud data and busbar groove point cloud data from the two-dimensional point cloud data based on a preset threshold; obtaining the left and right endpoints of the contact line surface through a k-mean clustering algorithm based on the contact line point cloud data; matching the busbar groove point cloud data with the corresponding template point cloud data in the contact line and busbar template to determine a matching transformation relationship; obtaining contact line matching points that match the left and right endpoints of the contact line surface based on the matching transformation relationship; and obtaining the contact network wear detection result based on the contact line matching points and the intersection points between the contact line and the busbar in the contact line and busbar template. The present method can accurately and comprehensively detect wear of the contact line, effectively adapt to real-world conditions, and improve measurement accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The present application is described with the aid of the following drawings:

[0055] Figure 1 This is a flow chart of a rigid contact network wear detection method in one embodiment of the present application;

[0056] Figure 2 This is a flow chart of a rigid contact network wear detection method in another embodiment of the present application;

[0057] Figure 3 This is a schematic diagram of a line structured light camera photographing the bottom of a busbar carrying contact wires in another embodiment of the present application;

[0058] Figure 4 This is an example diagram of a depth image in another embodiment of the present application;

[0059] Figure 5 This is an example diagram of the median filtering process in another embodiment of the present application;

[0060] Figure 6 This is an example diagram of feature point positions in another embodiment of the present application;

[0061] Figure 7 This is a schematic diagram of the structure of an electronic device in another embodiment of the present application.

[0062] Description of reference numerals:

[0063] 1-busbar, 2-contact line, 3-line structured light camera. DETAILED DESCRIPTION

[0064] To better explain the present invention and facilitate understanding, the present invention is described in detail below through specific embodiments in conjunction with the accompanying drawings. It should be understood that the specific embodiments described below are merely for explaining the relevant invention and are not intended to limit the invention. It should also be noted that the embodiments and features in the embodiments of this application can be combined with each other unless there is a conflict; for ease of description, only the parts relevant to the invention are shown in the accompanying drawings.

[0065] Example 1

[0066] Figure 1 This is a flow chart of a rigid contact network wear detection method in one embodiment of the present application, as shown in FIG. Figure 1 As shown, the rigid contact network wear detection method of this embodiment includes:

[0067] S10, acquiring a depth image of the contact line and busbar to be detected, and using the acquired depth image as the depth image to be detected;

[0068] S20, converting each row of depth image data in the depth image to be detected into two-dimensional point cloud data; filtering the two-dimensional point cloud data based on a preset threshold to obtain contact line point cloud data and busbar groove point cloud data;

[0069] S30, based on the contact line point cloud data, obtain the left and right endpoints of the contact line surface through the k-mean clustering algorithm;

[0070] S40, matching the bus groove point cloud data with the pre-established contact line and corresponding template point cloud data in the bus template to determine a matching transformation relationship;

[0071] S50, obtaining contact line matching points that match the left and right endpoints of the contact line surface in the contact line and the busbar template based on the matching transformation relationship;

[0072] S60 , obtaining a detection result of contact network wear based on the contact line matching points and the intersection points of the contact line and the busbar in the contact line and busbar template.

[0073] The rigid contact network wear detection method of this embodiment is adapted to the real field environment, can effectively cope with the complex scenes of the real rigid contact network, effectively solve the problems including oil stains, dust, etc. that easily affect the direct measurement of the camera, and accurately and comprehensively perform wear detection on the contact line, with higher measurement accuracy, faster speed, and better robustness.

[0074] In order to better understand the present invention, each step in this embodiment is described below.

[0075] In this embodiment, S10 may include:

[0076] S11. Acquire an initial depth image of the contact line and busbar captured by a line structured light camera.

[0077] The depth image can also be obtained by a binocular camera, etc., and the specific acquisition method is not specifically limited in the present invention.

[0078] S12. Perform median filtering on the initial depth image to obtain a depth image to be detected, wherein the median filtering method includes:

[0079] Set a window of size (2k+1)×1, and perform a sliding window operation with a step size of 1 along the X direction and Y direction of the initial depth image;

[0080] The median of all pixel grayscale values in the current window is used as the grayscale value of the center point of the current window, that is,

[0081] v(x,y)=mid{u(x,yk),u(x,y-k+1),u(x,y-k+2),...,u(x,y+k)},u(x,y)∈I

[0082] Where I is the initial depth image and u is any point on image I.

[0083] It should be noted that, in this embodiment, the axial direction of the contact line is taken as the Y direction, and the radial direction of the contact line parallel to the horizontal plane is taken as the X direction.

[0084] In this embodiment, S20 may further include removing outliers in the two-dimensional point cloud data by statistical filtering. The statistical filtering method includes:

[0085] Traverse all point cloud data and calculate the average distance between each point and its nearest neighboring points (n).

[0086] Calculate the mean and standard deviation of all average distances and set the distance threshold D max

[0087] D max =μ+α×δ;

[0088] Among them, μ is the mean of all average distances, δ is the standard deviation of all average distances, and α is the distance threshold parameter;

[0089] Traverse all point clouds and remove points whose average distance to n neighboring points is greater than D max point.

[0090] In this embodiment, contact line point cloud data is obtained by screening from two-dimensional point cloud data based on a preset threshold, including:

[0091] Determine the maximum value y in the Y direction of the two-dimensional point cloud data max ;

[0092] The contact line point cloud data of the contact line surface is filtered out based on the pre-set depth threshold T As shown in the formula:

[0093]

[0094] Among them, C is all two-dimensional point cloud data, p is a point in the point cloud data, p y The coordinate value of the point cloud data in the y direction.

[0095] In this embodiment, S30 includes:

[0096] S31. Perform first-order difference and second-order difference operations on the contact line point cloud data along the X direction, and calculate the curvature of the contact line point cloud data in the X direction using the following formula:

[0097]

[0098] Among them, f x ' is the result of the first-order difference operation, f x ” is the result of second-order difference operation;

[0099] S32. Selecting a preset number of point cloud data with the largest curvature value, and applying a k-mean clustering algorithm to cluster them, and using the two obtained cluster centers as the left and right endpoints of the contact line surface.

[0100] Specifically, the steps of the k-mean clustering algorithm are:

[0101] A1. Select the initial k points as the initial cluster center a i ,i∈[1,k];

[0102] A2. For each point, calculate its distance to the k cluster centers and assign it to the cluster center with the smallest distance. i ,i∈[1,k];

[0103] A3. Recalculate the cluster center of each class:

[0104]

[0105] Among them, a i is the cluster center of the i-th class, c i are all points belonging to the i-th class.

[0106] A4. Repeat steps A2 and A3 above until the error value calculated according to the following error function is less than the set error threshold, or the set number of iterations is reached.

[0107]

[0108] Where N represents c i The number of points in the class.

[0109] In this embodiment, in S40, the 2D point cloud template matching uses the Iterative ClosetPoint algorithm. Its basic principle is to find the nearest neighbor of each point in the template point cloud in the point cloud data to be matched, and calculate the optimal matching parameters R and t to minimize the error function. The specific process includes:

[0110] S41, using the bus groove point cloud as the point cloud to be matched, calculating the nearest neighboring points of the contact line and each point in the bus template in the point cloud to be matched, and forming point pairs;

[0111] S42, calculating the rotation matrix and translation matrix;

[0112] S43, transforming the point cloud in the contact line and busbar templates by using a rotation matrix and a translation matrix to obtain a transformed template point cloud;

[0113] S44. Calculate the error function using the following formula:

[0114]

[0115] Among them, n is the number of nearest neighbor pairs, p i is the point to be matched in the i-th pair of nearest neighboring points, q i is the template point in the i-th pair of nearest neighbor points;

[0116] S45, repeat S42-S44 until the error function is less than the set error threshold or the set number of iterations is reached;

[0117] S46. Use the rotation matrix and translation matrix obtained from the last iteration as the matching matrix.

[0118] In this embodiment, S60 includes:

[0119] S61. Calculate the contact surface width, wear allowance, and eccentric wear angle based on the contact line matching points and the intersection points of the contact line and the busbar in the contact line and busbar template, respectively. The contact surface width is equal to the Euclidean distance between the two points of the contact line matching points, the wear allowance is equal to the distance in the y direction from the intersection point of the contact line and the busbar to the farthest point of the contact line matching points, and the eccentric wear angle is equal to the angle between the line connecting the two points of the contact line matching points and the horizontal.

[0120] S62. Use the contact surface width, wear allowance and eccentric wear angle as the detection results of contact network wear.

[0121] Example 2

[0122] Figure 2 This is a flow chart of a rigid contact network wear detection method in another embodiment of the present application. Based on the first embodiment, this embodiment describes the specific implementation process of this embodiment in detail. Figure 2 As shown, the method may include:

[0123] S1. Photograph the contact line and busbar to obtain a depth image.

[0124] S2, performing Y-median filtering on the acquired image along the vertical direction;

[0125] S3, select a row of image data and convert it into two-dimensional point cloud data, and then perform two statistical filtering to obtain C;

[0126] S4. Filter out the point cloud data of the contact line surface And get the left and right endpoints P of the contact line surface A 、P B ;

[0127] S5. Filter the point cloud data C of the bus groove of the real data and the template data respectively according to the distance from the center of the contact line. G 、C G T ;

[0128] S6. Point cloud data C of bus groove based on real data and template data G 、C G T , perform two-dimensional point cloud template matching to obtain the transformation matrix R and t;

[0129] S7. Calculate the two endpoints P of the contact line surface based on the transformation matrix R and t A 、P B The transformed point P A '、P B ';

[0130] S8, point P after the contact line surface transformation in the real data A '、P B ', and the intersection point Q of the contact line and busbar in the template data T As characteristic points, the contact surface width, wear allowance and eccentric wear angle are calculated respectively.

[0131] The following describes each step in detail.

[0132] Figure 3 This is a schematic diagram of a line structured light camera photographing the bottom of a busbar carrying contact wires in another embodiment of the present application, as shown in FIG. Figure 3As shown in step S1, the initial depth image is obtained by setting a hanging rail mobile device on the bus, which can move along the bus. The 3D line structured light camera 3 on the device is used to capture the bottom of the bus 1 carrying the contact wire 2. The corresponding depth image I is obtained as shown in the attached figure. Figure 4 As shown, Figure 4 This is an example diagram of a depth image in another embodiment of the present application.

[0133] In S2, when performing median filtering, k is set to 1, and the sliding window size is 3×1. Figure 5 This is an example diagram of the median filtering process in another embodiment of the present application, such as Figure 5 As shown in the figure, the median filtering result of 31, 22, and 7 is 22. Moving the window downward, the filtering results of 22, 22, and 29 are obtained in sequence.

[0134] In S3, during the two statistical filtering operations, the number of nearest neighbor points n is set to 20 and 10 respectively, and the value of α is set to α=2 and α=1 respectively.

[0135] In S4, based on the first-order difference and second-order difference along the X direction, calculate Curvature in the X direction; select N (=20) points with the largest curvature value and apply k-mean clustering (class=2) to finally obtain two class centers, namely the left and right endpoints P of the contact line surface A 、P B , Figure 6 This is an example diagram of the locations of feature points in another embodiment of the present application, such as Figure 6 As shown, the dots are the left and right endpoints.

[0136] In S5, the point cloud data C of the bus groove of the real data and the template data are respectively screened according to the distance interval Γ from the bus groove to the center of the contact line. G 、C G T ,like Figure 6 As shown in the figure, the circled area is the point cloud data of the bus groove.

[0137] In S6, the template matching method uses the iterative closest point algorithm.

[0138] In S8, the point P after the contact line surface transformation in the real data is A '、P B ', and the intersection point Q of the contact line and busbar in the template data T (As attached Figure 6 The contact surface width, wear allowance and eccentric wear angle are calculated respectively. The contact surface width is equal to point P. A '、P B 'Euclidean distance, wear allowance equal to point QT To point P A '、P B 'The farthest y-direction distance, the eccentric wear angle is equal to point P A '、P B 'The angle between the line and the horizontal.

[0139] The method provided by the present invention is based on collecting depth images with a 3D structured light camera, using Y-median filtering and statistical filtering to denoise the bus and contact line data, combining the contact line surface curvature and K-means clustering to extract the contact line feature endpoints, and measuring the contact line wear parameters including contact surface width, wear allowance and eccentric wear angle through template matching, so as to solve the problem that existing contact line wear detection methods cannot adapt to real field environments and have low measurement accuracy.

[0140] Example 3

[0141] In the second aspect of the present application, an electronic device is provided through Example 3, comprising: a memory, a processor, and a computer program stored in the memory and runnable on the processor. When the computer program is executed by the processor, the steps of the rigid contact network wear detection method as described in any one of the above embodiments are implemented.

[0142] Figure 7 This is a schematic diagram of the structure of an electronic device in another embodiment of the present application.

[0143] Figure 7 The electronic device shown may include: at least one processor 101, at least one memory 102, at least one network interface 104 and other user interfaces 103. The various components in the electronic device are coupled together via a bus system 105. It is understood that the bus system 105 is used to achieve connection and communication between these components. In addition to including a data bus, the bus system 105 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, the bus system 105 is not described in detail. Figure 7 Various buses are labeled as bus system 105 .

[0144] The user interface 103 may include a display, a keyboard, or a pointing device (eg, a mouse, a trackball, or a touchpad).

[0145] It is understood that the memory 102 in this embodiment can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus RAM (DRRAM). The memory 102 described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0146] In some embodiments, the memory 102 stores the following elements, executable units, or data structures, or a subset thereof, or an extended set thereof: an operating system 1021 and application programs 1022 .

[0147] The operating system 1021 includes various system programs, such as a framework layer, a core library layer, and a driver layer, for implementing various basic services and handling hardware-based tasks. Application programs 1022 include various application programs for implementing various application services. Programs implementing the methods of the embodiments of the present invention may be included in application programs 1022.

[0148] In an embodiment of the present invention, the processor 101 calls a program or instruction stored in the memory 102, specifically, a program or instruction stored in the application 1022, and the processor 101 is used to execute the method steps provided in the first aspect.

[0149] The methods disclosed in the above embodiments of the present invention can be applied to or implemented by processor 101. Processor 101 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be performed by hardware integrated logic circuits in processor 101 or by software instructions. Processor 101 may be a general-purpose processor, a digital signal processor, an application-specific integrated circuit, an off-the-shelf programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component. The methods, steps, and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in conjunction with the embodiments of the present invention can be directly implemented and executed by a hardware decoding processor or by a combination of hardware and software units in the decoding processor. The software units can be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. This storage medium is located in memory 102. Processor 101 reads information from memory 102 and, in conjunction with its hardware, completes the steps of the above method.

[0150] In addition, in combination with the rigid contact network wear detection method in the above embodiment, an embodiment of the present invention can provide a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, any one of the rigid contact network wear detection methods in the above method embodiments is implemented.

[0151] It should be noted that in the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claim. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The present invention can be implemented by means of hardware comprising several distinct components and by means of a suitably programmed computer. The use of the words first, second, third, etc. is merely for convenience and does not imply any order. These words should be understood as part of the component name.

[0152] In addition, it should be noted that, in the description of this specification, the description of the terms "one embodiment", "some embodiments", "embodiment", "example", "specific example" or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0153] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments after learning the basic creative concept. Therefore, the claims should be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0154] Obviously, those skilled in the art may make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if such modifications and variations fall within the scope of the claims and their equivalents, the present invention shall also include such modifications and variations.

Claims

1. A method for detecting wear of a rigid contact network, characterized in that: The method includes: S10, acquiring a depth image of the contact line and busbar to be detected, and using the acquired depth image as the depth image to be detected; The S10 includes: S11, acquiring an initial depth image of the contact line and busbar captured by a line structured light camera; S12, performing median filtering on the initial depth image to obtain a depth image to be detected; S20, converting each row of depth image data in the depth image to be detected into two-dimensional point cloud data; filtering the two-dimensional point cloud data to obtain contact line point cloud data and busbar groove point cloud data based on a preset threshold; The S20 includes: Eliminate outliers in the two-dimensional point cloud data by statistical filtering; S30, obtaining the left and right endpoints of the contact line surface by using a k-mean clustering algorithm based on the contact line point cloud data; S40, matching the busbar groove point cloud data with the corresponding template point cloud data in the pre-established contact line and busbar template to determine a matching transformation relationship; S50, obtaining contact line matching points between the contact line and the left and right endpoints of the contact line surface in the busbar template based on the matching transformation relationship; S60, obtaining a detection result of contact network wear based on the contact line matching point and the intersection point between the contact line and the busbar in the contact line and busbar template; S60 includes: S61. Calculate the contact surface width, wear allowance, and eccentric wear angle based on the contact line matching point and the intersection point of the contact line and the busbar in the contact line and busbar template, respectively, wherein the contact surface width is equal to the Euclidean distance between the two points of the contact line matching point, the wear allowance is equal to the distance in the y direction from the intersection point of the contact line and the busbar to the farthest point of the contact line matching point, and the eccentric wear angle is equal to the angle between the line connecting the two points of the contact line matching point and the horizontal; S62: Taking the contact surface width, the wear allowance, and the eccentric wear angle as the detection result of contact network wear.

2. The rigid contact network wear detection method according to claim 1, characterized in that: Median filtering methods include: Set a window of size (2k+1)×1, and perform a sliding window operation with a step size of 1 along the X direction and Y direction of the initial depth image; The median of the grayscale values of all pixels in the current window is used as the grayscale value of the center point of the current window.

3. The rigid contact network wear detection method according to claim 1, characterized in that: Statistical filtering methods include: Traverse all point cloud data and calculate the average distance between each point and its nearest neighboring points (n). Calculate the mean and standard deviation of all average distances and set the distance threshold D max D max =μ+α×δ; Among them, μ is the mean of all average distances, δ is the standard deviation of all average distances, and α is the distance threshold parameter; Traverse all point clouds and remove points whose average distance to n neighboring points is greater than D max point.

4. The rigid contact network wear detection method according to claim 1, characterized in that: Screening the two-dimensional point cloud data based on a preset threshold to obtain contact line point cloud data includes: Determine the maximum value y in the Y direction of the two-dimensional point cloud data max ; The contact line point cloud data C of the contact line surface is screened based on the pre-set depth threshold T S , as shown in the formula: Among them, C is all two-dimensional point cloud data, p is a point in the point cloud data, P y The coordinate value of the point cloud data in the y direction.

5. The rigid contact network wear detection method according to claim 1, characterized in that: The S30 includes: S31, performing first-order difference and second-order difference operations on the contact line point cloud data along the X direction, and calculating the curvature of the contact line point cloud data in the X direction by the following formula: Among them, J x is the result of the first-order difference operation, f x ″ is the result of second-order difference operation; S32. Selecting a preset number of point cloud data with the largest curvature value, and applying a k-mean clustering algorithm to cluster them, and using the two obtained cluster centers as the left and right endpoints of the contact line surface.

6. The rigid contact network wear detection method according to claim 1, characterized in that: The S40 includes: S41, using the bus groove point cloud as the point cloud to be matched, calculating the nearest points of the contact line and each point in the bus template in the point cloud to be matched, and forming point pairs; S42, calculating the rotation matrix and translation matrix; S43, transforming the point cloud in the contact line and busbar template using a rotation matrix and a translation matrix to obtain a transformed template point cloud; S44. Calculate the error function using the following formula: Among them, n is the number of nearest neighbor pairs, p i is the point to be matched in the i-th pair of nearest neighboring points, q i is the template point in the i-th pair of nearest neighbor points; S45, repeat S42-S44 until the error function is less than the set error threshold or the set number of iterations is reached; S46. Use the rotation matrix and translation matrix obtained from the last iteration as the matching matrix.

7. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the rigid contact network wear detection method as described in any one of claims 1 to 6.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the rigid contact network wear detection method as described in any one of claims 1 to 6 are implemented.

Images