Method, system and device for measuring geometric parameters of overhead line system lead and medium

Abstract

The invention provides a method, a device, equipment and a medium for measuring geometric parameters of an overhead line system conductor, and particularly relates to the technical field of overhead line system measurement, and the method comprises the steps: obtaining an overhead line system image, extracting the conductor based on image recognition and a preset geometric constraint condition, and obtaining first position information of the conductor under a camera coordinate system; obtaining a nearest point from the lead to the center point of the camera baseline, and obtaining a rotation angle according to a vector from the original point of the camera coordinate system to the nearest point; converting the first position information based on a rotation angle to obtain second position information; acquiring a roll angle of the vehicle body, and converting the second position information based on the roll angle to obtain third position information; and conducting wire geometric parameters are calculated based on the third position information. According to the method, the wire is identified according to the prior geometric constraint condition, and vertical angle correction and vehicle vibration compensation are performed, so that the geometric parameters of each point on the wire can be obtained, and the measurement precision is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of contact network measurement, and in particular to a method, device, equipment and medium for measuring geometric parameters of contact network conductors. Background Art

[0002] The catenary is a specialized transmission line used to supply power to electric locomotives. It is erected overhead along railway lines and consists of contact suspensions, support devices, positioning devices, pillars, and foundations. Conductors are a key component of the catenary and are deployed in a "Z"-shaped, exposed configuration above the locomotive lines. Electric locomotives receive power through pantographs, which contact the conductors. During high-speed operation, the pantographs vibrate vertically, which can easily cause the conductors to shift position. Furthermore, the conductors are exposed to the elements for extended periods, creating a harsh environment and susceptible to interference and even damage. To mitigate safety hazards, railway operators must regularly monitor the conductor geometry to develop targeted maintenance plans.

[0003] Existing non-contact wire measurement methods mainly include laser ranging method, image processing method, etc., but these existing methods have very high requirements on the installation accuracy and operating environment of the equipment, and are easily affected by the environment and cause large measurement errors. Summary of the Invention

[0004] The purpose of the present invention is to provide a method, device, equipment and medium for measuring the geometric parameters of overhead wires to improve the above-mentioned problems. In order to achieve the above-mentioned purpose, the technical solution adopted by the present invention is as follows:

[0005] In a first aspect, the present application provides a method for measuring geometric parameters of a contact network conductor, comprising:

[0006] Acquire the contact network image, extract the conductor based on image recognition and preset geometric constraints, and obtain the first position information of the conductor in the camera coordinate system;

[0007] Obtaining the closest point on the wire to the center point of the camera baseline, and obtaining a rotation angle based on a vector from the origin of the camera coordinate system to the closest point; transforming the first position information based on the rotation angle to obtain second position information;

[0008] Acquiring a roll angle of the vehicle body, and transforming the second position information based on the roll angle to obtain third position information;

[0009] The geometric parameters of the wire are calculated based on the third position information.

[0010] In a second aspect, the present application provides a system for measuring geometric parameters of a contact network conductor, comprising:

[0011] The first module is used to obtain the contact network image, extract the conductor based on image recognition and preset geometric constraints, and obtain the first position information of the conductor in the camera coordinate system;

[0012] The second module is used to obtain the closest point on the wire to the center point of the camera baseline, obtain a rotation angle based on the vector from the origin of the camera coordinate system to the closest point; and transform the first position information based on the rotation angle to obtain second position information;

[0013] a third module, configured to obtain a roll angle of the vehicle body, and transform the second position information based on the roll angle to obtain third position information;

[0014] The fourth module is used to calculate the geometric parameters of the conductor based on the third position information.

[0015] In a third aspect, the present application also provides a device for measuring the geometric parameters of contact network conductors, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method for measuring the geometric parameters of contact network conductors as described above when executing the computer program.

[0016] In a fourth aspect, the present application further provides a readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the method for measuring the geometric parameters of the contact network conductor are implemented as described above.

[0017] The beneficial effects of the present invention are:

[0018] This method uses stereoscopic vision for line detection and utilizes a priori geometric constraints, such as wire direction and length, for wire identification. A set of tilt sensors captures the vehicle's roll angle. The system requires no special imaging environment, and does not require the camera's optical axis to be strictly perpendicular to the vehicle's roof plane. The algorithm is stable and reliable, with high recognition accuracy. By sequentially correcting the vertical angle of the captured wire and compensating for vehicle vibration, the geometric parameters of each point on the wire are determined, effectively improving measurement accuracy.

[0019] Other features and advantages of the present invention will be set forth in the following description, and in part will be apparent from the description, or may be learned by practicing embodiments of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 Flowchart of the method for measuring geometric parameters of contact wires in an embodiment of the present application;

[0022] Figure 2 This is a schematic diagram of the arrangement of the binocular camera and the tilt sensor group in an embodiment of the present application;

[0023] Figure 3 This is a schematic diagram of the binocular camera ranging principle in an embodiment of the present application;

[0024] Figure 4 The edge detection result diagram in the embodiment of this application, where the left image is the original image and the right image is the binary edge image;

[0025] Figure 5 This is a line detection diagram based on Houh transformation in the embodiment of the present application;

[0026] Figure 6 The diagrams of line screening and wire judgment in the embodiment of the present application are shown, wherein the left diagram shows the line screening result, and the right diagram shows the wire judgment result;

[0027] Figure 7 This is a schematic diagram of the camera coordinate system in the embodiment of the present application;

[0028] Figure 8 Schematic diagram of the vertical deflection of the Z axis of the camera coordinate system in the embodiment of the present application;

[0029] Figure 9 This is a schematic diagram of the vehicle body roll in the embodiment of the present application;

[0030] Figure 10 This is a schematic structural diagram of a device for measuring geometric parameters of a contact network conductor in an embodiment of the present application;

[0031] Figure 11 Schematic diagram of the structure of the equipment for measuring the geometric parameters of the contact network conductor in the embodiment of the present application.

[0032] Markings in the figure: 1-camera; 2-flash; 3-locomotive; 4-first inclination sensor; 5-second inclination sensor; 100-first module; 110-first unit; 120-second unit; 130-third unit; 140-fourth unit; 200-second module; 210-fifth unit; 220-sixth unit; 230-seventh unit; 300-third module; 400-fourth module; 800-device for measuring geometric parameters of contact network conductors; 801-processor; 802-memory; 803-multimedia component; 804-I / O interface; 805-communication component. DETAILED DESCRIPTION

[0033] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0034] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0035] The geometric parameters of the catenary conductor include lead height and pullout. Lead height refers to the vertical distance from the bottom of the catenary conductor to the track plane and is a key indicator for evaluating the operating condition of the catenary. If the lead height is too large, the pantograph will be offline, causing arcing and wear on the pantograph and conductor. If the lead height is too small, it can easily lead to bow drilling and bow scraping accidents. Pullout refers to the offset of the catenary conductor from the pantograph centerline at the suspension point. If the pullout is too small, excessive wear will occur in the center area of the pantograph's carbon plate, shortening the pantograph's service life. If the pullout is too large, the conductor will easily exceed the limit in severe weather such as strong winds, leading to bow-off accidents. The required lead height measurement range for my country's railway catenary conductors is 5100-6600mm with an accuracy of 10mm; the required pullout measurement range is -600 to 600mm with an accuracy of 25mm; and the interval between adjacent sampling points should be no greater than 250mm.

[0036] There are currently two main methods for measuring the geometric parameters of overhead wires: contact and non-contact. The contact method uses tools such as an insulated measuring rod, plumb line, and steel tape measure to measure the distance from the conductor to the two rails, then calculates the conductor height and pullout values based on triangulation. The non-contact method relies primarily on advanced sensing technologies and equipment such as laser ranging and image processing, and is often used in conjunction with dedicated inspection vehicles. Compared to contact methods, non-contact methods offer a wider measurement range, higher efficiency, and safe and convenient dynamic testing, resulting in increasingly widespread application on railway sites.

[0037] The laser ranging method uses a laser and optical scanner mounted on the roof of a test vehicle. Using the phase scanning principle, it measures conductor geometry in real time. The laser continuously emits an uninterrupted laser beam, which is reflected by the optical scanner to form a sector-shaped scanning area. The reflected laser beam then reflects again upon encountering the conductor, with the return beam being received by the laser. Phase analysis reveals the actual distance from the optical scanner to the conductor. Based on this distance and the corresponding laser scanning angle, the conductor height and pullout can be calculated. This method places high demands on the equipment's installation precision and operating environment; even small installation errors or external vibrations can cause significant measurement errors.

[0038] The image processing method utilizes two linear array cameras, specialized fill-light equipment, and specialized filtering devices to achieve real-time measurement of target points on conductors. This method uses a high-power laser light source to illuminate the conductor surface. Based on the characteristics of the contact wire material and the light source, specialized wavelength filters sensitive to the corresponding wavelength band are employed to eliminate interference from daytime sunlight, line lights, and signal lights. The two linear array cameras capture linear images of the contact wire cross-section and determine the conductor position based on light intensity. The conductor's geometric parameters are then calculated using triangulation principles. This method places strict requirements on the mounting position of the two linear cameras, requiring them to be located in the same detection plane perpendicular to the vehicle roof. Otherwise, significant measurement errors can occur. Furthermore, this method determines the conductor position based solely on the brightest point in the linear image, making it prone to misjudgment.

[0039] For non-contact methods, the influence of vehicle body vibration should also be considered. The detection device is fixed to the locomotive roof, and the obtained parameter values are based on the vehicle body coordinate system. Therefore, the vibration state of the locomotive at different speeds is also different, which will lead to inconsistent detection data. To solve this problem, the vehicle body vibration state must be detected so that the detection parameters can be mapped to the same coordinate system. Currently, lidar is mainly used to measure vehicle body vibration. LiDAR is installed on both sides of the bottom of the locomotive. During travel, the surrounding environment is continuously scanned to obtain point cloud data, from which the contour features of the rails are identified. The vibration state is determined based on the distance between the bottom of the vehicle and the two rails. This method has a complex algorithm, is expensive, and has poor applicability.

[0040] like Figure 1 As shown, this embodiment provides a method for measuring geometric parameters of a contact network conductor, including steps S100, S200, S300 and S400.

[0041] S100, acquiring a contact network image, extracting the conductor based on image recognition and preset geometric constraints, and obtaining first position information of the conductor in a camera coordinate system;

[0042] In the present invention, a binocular camera is used to acquire images of the contact network. The binocular camera module consists of two cameras 1 and a flash 2, and is mounted on the roof. The optical axis of the camera does not need to be strictly perpendicular to the roof plane, and the structure is simple and easy to install. The two cameras 1 are connected by a rigid rod, and the relative distance and posture remain unchanged. The rigid rod spans the roof and the center point is aligned with the center line of the locomotive 3. The optical axis of the camera 1 is symmetrical and points upward from the locomotive 3. To increase the common viewing area between the two cameras 1, the optical axes on both sides can be deflected to the center line at the same angle, such as Figure 2 As shown. The flash 2 is used in nighttime and tunnel operation scenes, and is matched with the shutter of camera 1 to improve the brightness at the moment of shooting. The binocular camera uses two cameras 1 to shoot the same scene at the same time to generate two images; when the same object appears in the two images, the position of the object on the image will be offset due to the baseline distance, where the baseline distance refers to the distance between the two cameras 1; by calculating the distance difference between the corresponding pixel points in the two images, the parallax can be measured; using the principle of triangulation, the three-dimensional coordinates of the object can be calculated through parallax, baseline distance and focal length. Each camera 1 has its own internal and external parameters; the internal parameters include focal length and principal point coordinates, which are determined when a single camera 1 is calibrated; the external parameters are the relationship between the camera 1 and the world coordinate system, which changes with the height and angle at which the camera 1 is installed. In the present invention, it is necessary to obtain the relative position relationship between the two cameras 1 for binocular calibration.

[0043] The present invention first needs to calculate spatial coordinates based on the principles of stereo vision, that is, to calculate the coordinates of key positions in the camera coordinate system. The key position of the present invention is the wire area. The solution process is divided into five steps: distortion correction, epipolar correction, stereo matching, parallax calculation and three-dimensional coordinate solution. Distortion correction is used to process the original image and eliminate the tangential distortion and radial distortion caused by lens imaging according to the distortion parameters. Epipolar correction is used to obtain a strictly parallel binocular structure, that is, to define a new image plane based on the relative position parameters between the two cameras 1, so that the epipolar line pairs are collinear and parallel to the horizontal axis of the image plane. The epipolar line refers to the intersection of the plane formed by the target point and the optical center of the two cameras 1 (episode plane) and the imaging plane of a single camera, and the epipolar line pair refers to the intersection of the same epipolar plane and the two imaging planes of the binocular camera. After the epipolar correction is completed, the same matching point pair is located in the same row of the two views, and the only difference between the two is the horizontal coordinate. Stereo matching is used to determine the corresponding points on the two views. Different similarity measurement functions, matching windows and matching algorithms can be selected according to the application scenario. Disparity calculation is used to calculate the position difference of the same target point in the left and right images, expressed as the horizontal pixel distance. 3D coordinate solution is used to calculate the position information of the target point in the camera coordinate system.

[0044] Consider the binocular imaging scene after epipolar correction, where the epipolar pairs are collinear and parallel to the horizontal axis of the image plane, as shown in Figure 3 As shown. The left and right optical centers of the binocular camera are O and O respectively.r The camera baseline is the line connecting the left and right optical centers; the intersection points of the left and right optical axes and the left and right imaging planes are C and C respectively. r The intersection points of the target point P and the left and right imaging planes are P l With P r The left camera coordinate system is used as the measurement coordinate system, that is, the X axis of the camera coordinate system is from O to O r The Z axis is from O to C, and the Y axis is perpendicular to the X axis and the Z axis and is consistent with the longitudinal axis on the imaging plane. For the left and right imaging planes, the upper left corner is the origin of the pixel coordinates, and C and C are respectively r The coordinates of are (x c ,y c ) and (x rc ,y rc ), P l With P r The coordinates of are (x l ,y l ) and (xr,yr), then according to the polar correction principle, the vertical coordinates on the left and right sides satisfy:

[0045] yl-y c =y r -y rc (1)

[0046] In pixels, the parallax d of the left and right imaging planes about point P is defined as:

[0047] d=x l -x r +(x rc -x c ) (2)

[0048] Define f as focal length and B as baseline length, where f is in pixels and B is in meters, then:

[0049]

[0050] Let the coordinates of point P be (x, y, z), then according to the geometric relationship we can get:

[0051]

[0052] Through the above steps, the coordinates of any point in the contact network image in the camera coordinate system can be obtained.

[0053] The steps to extract wires from an image are as follows:

[0054] S110, extracting lines from the contact network image using an edge detection algorithm;

[0055] Edge detection is used to identify pixels with obvious grayscale changes in the original image. After this processing step, the amount of data to be processed can be greatly reduced, irrelevant information can be eliminated, and important structural attributes can be retained. This embodiment uses the Canny edge detection algorithm, and the detection effect is as follows: Figure 4 As shown, the left image is the original image and the right image is the detected binary edge image.

[0056] S120, using a Hough transform algorithm to filter the lines to obtain a first filtering result;

[0057] The contact wire is straight. Line detection can only retain the linear area and filter out the curves and noise points, which can further reduce the amount of data to be processed. The present invention uses the Hough transform algorithm to obtain a two-dimensional matrix of distance and angle. The point with a larger value in the matrix corresponds to a line. Figure 5 Line Filtering is an option used to select suspected wires from all line segments.

[0058] S130, calculating the angle between each line in the first screening result and the image height direction, and calculating the length of the line, and performing screening based on the calculated results to obtain a second screening result;

[0059] The first screening results may include, in addition to the wires, linear structural components such as slings, arms, positioning tubes, positioners, support connectors, and catenary cables. The wires have a slight angle with the direction of locomotive 3 and should span the entire height of the image. Therefore, this step performs another screening based on angle and length constraints. The angle constraint is that the angle between the line and the image height direction is no more than 20 degrees, and the length constraint is that the line length should not be less than 40% of the image height. The results after screening are as follows: Figure 6 (Left) shown.

[0060] S140 , calculating the distance from each line in the second screening result to the center point of the camera baseline to obtain the closest point, and identifying the line where the closest point is located as a guide wire.

[0061] Because the catenary and adjacent conductors are close to the conductor being measured, it is difficult to distinguish them using a single image. This method uses the binocular camera's measurement results to determine the spatial coordinates of each line. It then calculates the distance from each point on the line to the center of the camera's baseline. The point with the closest distance is then identified as the conductor.

[0062] For the application scenario of the present invention, the X-axis of the camera coordinate system is perpendicular to the running direction of the locomotive 3, the Y-axis points to the running direction of the locomotive 3, and the Z-axis points to the top of the locomotive 3. Figure 7 As shown. The coordinates of the camera baseline center point M are (x m, 0,0), the coordinates of any point P on the line are (x, y, z), then the distance between the two D(P, M) is defined as:

[0063]

[0064] The set Φ includes all the points on the candidate lines, and the nearest point is recorded as P opt , then:

[0065] P opt =argmin{D(P,M)|P∈Φ} (6)

[0066] Then P opt The line where it is located can be identified as a wire. The judgment result is as follows Figure 6 (right) shown.

[0067] S200, obtaining the closest point on the wire to the center point of the camera baseline, and obtaining a rotation angle based on a vector from the origin of the camera coordinate system to the closest point; and transforming the first position information based on the rotation angle to obtain second position information;

[0068] When the binocular camera is installed, the optical axis cannot be guaranteed to be perpendicular to the roof plane; the roof plane cannot be strictly parallel to the track surface; and the vibration during the movement of locomotive 3 may cause slight changes in the posture of camera 1. The above reasons can make the Z axis of the camera coordinate system not strictly perpendicular to the conductor plane, where the conductor plane is the plane formed by the "Z" shape distribution of the conductors and is parallel to the track plane. Therefore, this step requires vertical angle correction to correct the measurement deviation caused by the Z axis of the camera coordinate system not being strictly perpendicular to the conductor plane. The specific steps are as follows:

[0069] S210, calculating the vector from the origin of the camera coordinate system to the nearest point to obtain a first vector;

[0070] The closest point P is obtained in step S140 opt , the origin of the camera coordinate system is O, so the first vector OP1 can be obtained;

[0071] S220, calculating the angle between the first vector and the Z axis of the camera coordinate system to obtain a rotation angle, where the Z axis is perpendicular to the top surface of the vehicle body;

[0072] like Figure 8 As shown, analyze the spatial geometric relationship and note the midpoint P in the previous step. opt The plane formed by the X axis is P opt -X, according to P opt From the definition of , we know that this plane is strictly perpendicular to the conductor plane. o ,y o ,z o ) is P opt The coordinates of point P1(0,y o ,z o ) is also located in plane Popt -X. Move the Z axis to the plane P opt -X vertical projection, then point P1 is located on the projection line. Therefore, the rotation angle σ required for vertical correction is also the angle between the straight line OP1 and the Z axis. According to the coordinates of point P1, we can get:

[0073]

[0074] S230: Construct a first rotation matrix according to the rotation angle, and transform the first position information based on the first rotation matrix to obtain second position information.

[0075] For any point (x, y, z) in the camera coordinate system, its coordinates in the new coordinate system O-X'Y'Z' are recorded as (x', y', z'). The new coordinate system O-X'Y'Z' maintains the X-axis of the camera coordinate system unchanged, while rotating the Z and Y axes clockwise around the X-axis by σ degrees. Therefore, the X-axis coordinate of the same point remains unchanged, while the Z and Y axes satisfy a planar rotation relationship of angle σ. The transformation relationship between the two can be determined by a 3x3 unit orthogonal rotation matrix R1:

[0076]

[0077] Thus, the position information of the wire in the O-X'Y'Z' coordinate system, ie, the second position information, can be obtained.

[0078] S300, obtaining a roll angle of the vehicle body, and transforming the second position information based on the roll angle to obtain third position information;

[0079] During locomotive 3's operation, the wheelset is in direct contact with the rail surface, while the vehicle body and wheelset are connected by a suspension system consisting of bogies, springs, and shock absorbers, effectively suppressing vibration shock. When locomotive 3 travels on a curved track, the vehicle body will vibrate in the rolling direction relative to the wheel axle due to track irregularities and the locomotive's own inertia. Therefore, this step performs vehicle vibration compensation to address measurement deviations caused by vehicle body vibration. The specific steps are as follows:

[0080] S310, obtaining wheel axle inclination data through a first inclination sensor 4, wherein the first inclination sensor 4 is disposed on the wheel axle surface and parallel to the wheel axle direction;

[0081] The inclination sensor is a long, linear structure, utilizing a highly sensitive acceleration sensor chip. Through data processing, it achieves real-time measurement of the horizontal inclination along its longitudinal direction, achieving an accuracy of less than 0.001 degrees and a response time of less than 0.1 seconds. The first inclination sensor 4 is secured to the wheel axle surface, its longitudinal direction strictly parallel to the axle's axis. During locomotive 3 operation, it rotates synchronously with the wheel axle along its axis, providing real-time output of the inclination angle between the wheel axle and the horizontal plane.

[0082] S320, obtaining vehicle bottom inclination data through a second inclination sensor 5, wherein the second inclination sensor 5 is provided at the bottom of the vehicle body and is perpendicular to the running direction of the locomotive 3;

[0083] The second inclination sensor 5 is located directly above the wheel axle and is strictly perpendicular to the running direction of the locomotive 3. It outputs the inclination angle between the two sides of the vehicle body and the horizontal plane in real time. The present invention can obtain the vibration angle of the vehicle body roll through two inclination sensors, which is simple, reliable and low-cost.

[0084] S330, calculating the difference between the wheel axle inclination angle data and the vehicle bottom inclination angle data to obtain the roll angle;

[0085] The output of the first inclination sensor 4 is θ d , the output of the second inclination sensor 5 is θ u ;

[0086] Then the vehicle body roll angle θ is:

[0087] θ=θ u -θ d (9)

[0088] Obviously, when the track is laid horizontally and the locomotive 3 is stationary, the output inclination angles of the two inclination sensors are both 0 degrees.

[0089] S340: Construct a second rotation matrix based on the roll angle, and transform the second position information according to the second rotation matrix to obtain third position information.

[0090] like Figure 9 As shown, with the midpoint of the bottom of the vehicle body as the origin, the wheel axis direction as the X'Y axis, the locomotive 3 running direction as the "Y"Z axis, and the direction perpendicular to the rail surface as the Z" axis, a new coordinate system O"-X"Y"Z" is constructed. The distance between the origins of the O"-X"Y"Z and O-X'Y'Z' coordinate systems is x translation along the X' and Z' directions respectively. c The Y' axis and the Y" axis are in the same direction as the -h vector, and the X' / Z' axis and the X" / Z" axis satisfy a plane rotation relationship of angle θ. Therefore, for any point (x', y', z') in the O-X'Y'Z' coordinate system, its coordinates in the coordinate system O"-X"Y"Z" are (x", y", z"), and the transformation relationship between the two can be determined by a 3x3 unit orthogonal rotation matrix R2 and a translation vector:

[0091]

[0092] In the above formula, x c is the coordinate value of the midpoint M of the binocular camera baseline on the X' axis, where M is also located on the center line of the vehicle body; h is the height of the vehicle body.

[0093] S400: Calculate and obtain geometric parameters of the conductor based on the third position information.

[0094] The final geometric parameter calculation determines the lead height and pullout of the conductor relative to the rail surface. The position of point O" relative to the wheel axle remains unchanged, and thus its distance from the rail surface remains unchanged. The distance from O" to the rail surface is denoted by l. For any point P on the conductor, whose coordinates in the new coordinate system are (x", y", z"), the lead height G and pullout L at that point are:

[0095]

[0096] By traversing all points on the wire in the image, the geometric parameters of the wire at different distances in the moving direction of the locomotive 3 can be obtained.

[0097] For subsequent troubleshooting, it is necessary to record the conductor geometry parameters together with its location; therefore, the method further includes:

[0098] Determine whether the vehicle is currently in a satellite obstruction area based on the environment. If so, use the vehicle's onboard speed sensor to obtain speed data, and calculate the kilometer mark information by integrating the speed relative to time. When locomotive 3 passes through areas such as tunnels and trenches, it can be determined that the vehicle is currently in a satellite obstruction area.

[0099] If not, the longitude and latitude of locomotive 3 are obtained using the Beidou satellite antenna, and kilometer marker information is obtained in combination with the electronic map;

[0100] Alternatively, the kilometer marker information can be obtained by using the GYK or LKJ device on locomotive 3;

[0101] The kilometer mark information is associated with the conductor geometric parameters to obtain a conductor information record table.

[0102] Example 2

[0103] See also Figure 10 This embodiment provides a system for measuring geometric parameters of a contact network conductor, including:

[0104] The first module 100 is used to obtain a contact network image, extract the conductor based on image recognition and preset geometric constraints, and obtain first position information of the conductor in the camera coordinate system;

[0105] The second module 200 is configured to obtain the closest point on the wire to the center point of the camera baseline, obtain a rotation angle based on a vector from the origin of the camera coordinate system to the closest point, and transform the first position information based on the rotation angle to obtain second position information;

[0106] The third module 300 is configured to obtain a roll angle of the vehicle body and transform the second position information based on the roll angle to obtain third position information;

[0107] The fourth module 400 is configured to calculate geometric parameters of the conductor based on the third position information.

[0108] As an optional implementation manner, the first module includes:

[0109] The first unit 110 is configured to extract lines from the contact network image using an edge detection algorithm;

[0110] The second unit 120 is used to filter the lines using a Hough transform algorithm to obtain a first filtering result;

[0111] The third unit 130 is used to calculate the angle between each line in the first screening result and the image height direction, and calculate the length of the line, and perform screening based on the calculation results to obtain a second screening result;

[0112] The fourth unit 140 is configured to calculate the distance from each line in the second screening result to the center point of the camera baseline, obtain the closest point, and identify the line where the closest point is located as a guide wire.

[0113] As an optional implementation, the second module includes:

[0114] The fifth unit 210 is used to calculate the vector from the origin of the camera coordinate system to the nearest point to obtain a first vector;

[0115] The sixth unit 220 is configured to calculate an angle between the first vector and the Z axis of the camera coordinate system to obtain a rotation angle, wherein the Z axis is perpendicular to the top surface of the vehicle body;

[0116] The seventh unit 230 is configured to construct a first rotation matrix according to the rotation angle, and transform the first position information based on the first rotation matrix to obtain second position information.

[0117] Example 3

[0118] Corresponding to the above method embodiment, this embodiment also provides a contact network conductor geometric parameter measuring device. The contact network conductor geometric parameter measuring device described below and the contact network conductor geometric parameter measuring method described above can refer to each other.

[0119] Figure 11 FIG. 8 is a block diagram of a device 800 for measuring geometric parameters of a contact wire according to an exemplary embodiment. Figure 11As shown, the contact network conductor geometric parameter measuring device 800 includes a processor 801 and a memory 802. The contact network conductor geometric parameter measuring device 800 may also include one or more of a multimedia component 803, an input / output (I / O) interface 804, and a communication component 805. Among them, the processor 801 is used to control the overall operation of the contact network conductor geometric parameter measuring device 800 to complete all or part of the steps in the above-mentioned contact network conductor geometric parameter measuring method. The memory 802 is used to store various types of data to support the operation of the contact network conductor geometric parameter measuring device 800. These data may, for example, include commands for any application or method operating on the contact network conductor geometric parameter measuring device 800, as well as application-related data, such as contact data, messages sent and received, pictures, audio, video, etc. The memory 802 can be implemented by any type of volatile or non-volatile memory device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0120] The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals.

[0121] The received audio signal can be further stored in the memory 802 or sent through the communication component 805. The audio component also includes at least one speaker for outputting the audio signal. The I / O interface 804 provides an interface between the processor 801 and other interface modules. The above-mentioned other interface modules can be a keyboard, a mouse, buttons, etc. These buttons can be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the contact network conductor geometric parameter measuring device 800 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, near field communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 805 can include: Wi-Fi module, Bluetooth module, NFC module.

[0122] In an exemplary embodiment, the device 800 for mutual signing and verification of digital files can be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned method for measuring the geometric parameters of the contact network conductors.

[0123] Example 4

[0124] Corresponding to the above embodiment of the method for measuring the geometric parameters of the contact network conductor, this embodiment also provides a readable storage medium. The readable storage medium described below and the method for measuring the geometric parameters of the contact network conductor described above can be referenced to each other.

[0125] A readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the embodiment of the method for measuring the geometric parameters of a contact network conductor.

[0126] The readable storage medium may specifically be any readable storage medium that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0127] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0128] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A method for measuring geometric parameters of a contact wire, characterized in that: include: Acquire the contact network image, extract the conductor based on image recognition and preset geometric constraints, and obtain the first position information of the conductor in the camera coordinate system; Get the closest point on the wire to the center of the camera baseline, and get the rotation angle based on the vector from the origin of the camera coordinate system to the closest point; transforming the first position information based on the rotation angle to obtain second position information; Acquiring a roll angle of the vehicle body, and transforming the second position information based on the roll angle to obtain third position information; The geometric parameters of the conductor are calculated based on the third position information.

2. The method for measuring the geometric parameters of a contact wire according to claim 1, characterized in that: The extraction of wires based on image recognition and preset geometric constraints includes: Edge detection algorithm is used to extract lines from the contact network image; The lines are screened using the Hough transform algorithm to obtain the first screening result; Calculate the angle between each line in the first screening result and the image height direction, and calculate the length of the line, and perform screening based on the calculated results to obtain a second screening result; Calculate the distance from each line in the second screening result to the center point of the camera baseline to obtain the closest point, and identify the line where the closest point is located as a guide wire.

3. The method for measuring the geometric parameters of a contact wire according to claim 1, characterized in that: Get the closest point on the wire to the center of the camera baseline, and get the rotation angle based on the vector from the origin of the camera coordinate system to the closest point; Transforming the first position information based on the rotation angle to obtain second position information includes: Calculate the vector from the origin of the camera coordinate system to the nearest point to obtain the first vector; Calculate the angle between the first vector and the Z axis of the camera coordinate system to obtain the rotation angle, where the Z axis is perpendicular to the top surface of the vehicle body; A first rotation matrix is constructed according to the rotation angle, and the first position information is transformed based on the first rotation matrix to obtain second position information.

4. The method for measuring geometric parameters of a contact network conductor according to claim 1, characterized in that: Acquiring a roll angle of the vehicle body and transforming the second position information based on the roll angle to obtain third position information includes: Acquiring wheel axle inclination data through a first inclination sensor, wherein the first inclination sensor is arranged on the surface of the wheel axle and parallel to the direction of the wheel axle; Obtaining vehicle bottom inclination data through a second inclination sensor, wherein the second inclination sensor is arranged at the bottom of the vehicle body and is perpendicular to the running direction of the locomotive; The roll angle is obtained by calculating the difference between the wheel axle inclination angle data and the vehicle bottom inclination angle data; A second rotation matrix is constructed based on the roll angle, and the second position information is transformed according to the second rotation matrix to obtain third position information.

5. The method for measuring geometric parameters of a contact network conductor according to claim 1, characterized in that: The method further comprises: Determine whether the vehicle is currently in a satellite obstruction area based on the environment. If so, use the vehicle-mounted speed sensor to obtain speed data and calculate the kilometer mark information by integrating the speed relative to time. If not, the Beidou satellite antenna is used to obtain the longitude and latitude of the locomotive, and the kilometer mark information is obtained in combination with the electronic map; The kilometer mark information is associated with the conductor geometric parameters to obtain a conductor information record table.

6. A system for measuring geometric parameters of contact wires, characterized in that: include: The first module is used to obtain the contact network image, extract the conductor based on image recognition and preset geometric constraints, and obtain the first position information of the conductor in the camera coordinate system; The second module is used to obtain the closest point on the wire to the center of the camera baseline, and obtain the rotation angle based on the vector from the origin of the camera coordinate system to the closest point; transforming the first position information based on the rotation angle to obtain second position information; a third module, configured to obtain a roll angle of the vehicle body, and transform the second position information based on the roll angle to obtain third position information; The fourth module is used to calculate the geometric parameters of the conductor based on the third position information.

7. The system for measuring geometric parameters of overhead wire according to claim 6, characterized in that: The first module includes: The first unit is used to extract lines in the contact network image using an edge detection algorithm; The second unit is used to screen the lines using the Hough transform algorithm to obtain a first screening result; The third unit is used to calculate the angle between each line in the first screening result and the image height direction, and calculate the length of the line, and perform screening based on the calculation results to obtain a second screening result; The fourth unit is used to calculate the distance from each line in the second screening result to the center point of the camera baseline, obtain the nearest point, and identify the line where the nearest point is located as a wire.

8. The system for measuring geometric parameters of overhead wire according to claim 6, characterized in that: The second module includes: The fifth unit is used to calculate the vector from the origin of the camera coordinate system to the nearest point to obtain the first vector; a sixth unit, configured to calculate an angle between the first vector and a Z axis of the camera coordinate system to obtain a rotation angle, wherein the Z axis is perpendicular to the top surface of the vehicle body; The seventh unit is used to construct a first rotation matrix according to the rotation angle, and transform the first position information based on the first rotation matrix to obtain second position information.

9. A device for measuring geometric parameters of contact wires, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method for measuring the geometric parameters of the contact network conductor as claimed in any one of claims 1 to 5 when executing the computer program.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method for measuring the geometric parameters of the contact network conductor as claimed in any one of claims 1 to 5.

Images