Non-contact online visual measurement method and device for rail displacement and inclination

Abstract

The present invention provides a non-contact online visual measurement method and device for rail displacement and inclination, wherein the method includes the following steps: arranging a line laser and a high-resolution industrial camera on the outside of the rail to obtain an image of the cross-sectional area illuminated by the line laser on the outside of the rail, and reconstructing the rail cross-sectional profile point cloud using the principle of triangulation; aligning the reconstructed static rail cross-sectional profile point cloud with a standard rail model; extracting and screening multiple feature points from the cross-sectional profile point cloud reconstructed when a train passes, and performing feature point matching on the point cloud data reconstructed at different times; and calculating the vertical displacement, lateral displacement, and inclination of the rail at different times based on the matched multiple feature points. The method and device provided by the present invention can simply, accurately, and safely measure the lateral displacement, vertical displacement, and inclination of the rail during train operation. This technology provides fast, accurate, and reliable theoretical and technical support for non-contact measurement of rail inclination and displacement.

Description

Technical Field

[0001] The present invention relates to the technical field of three-dimensional point cloud visual measurement, and in particular to a non-contact online visual measurement method and device for rail displacement and inclination. Background Art

[0002] With the rapid development of rail transit and the increasing number of rail lines coming into operation, track inspection and maintenance workloads have increased dramatically, placing significant pressure on maintaining the health of rails. During train operation, wheel pressure on rails causes them to deform and tilt slightly to the side. Online monitoring of rail deformation is beneficial for understanding and maintaining the health of the track and ensuring the safe operation of rail transit. This method projects a line laser onto the surface of the target, captures the projection area with a camera, and performs a three-dimensional reconstruction of the projected target using triangulation principles. This method generates a point cloud of the cross-sectional profile where the laser plane intersects the target, and then calculates the relevant physical parameters. This is a non-contact measurement method with widespread applications in a variety of fields, including 3D imaging, industrial product quality inspection, and rail flaw detection. Existing technologies for detecting subtle rail deformation during train operation mostly rely on contact measurement, which requires numerous components, a complex measurement process, and poses certain safety risks. Therefore, providing a simple, accurate, and secure non-contact online measurement device and method based on computer vision is of great practical significance. Summary of the Invention

[0003] The embodiments of the present invention provide a resource management method in a multimedia communication system, which is used to solve the problems existing in the prior art.

[0004] In order to achieve the above-mentioned purpose, the present invention adopts the following technical solutions.

[0005] A non-contact online visual measurement method for rail displacement and inclination, comprising:

[0006] S1 uses a line laser and a camera on the outside of the rail to collect rail images in the laser-illuminated area, and constructs point clouds of the static rail cross-section profile and dynamic rail cross-section profile at different moments during the train passing process through triangulation.

[0007] S2 performs registration processing on the static rail cross-section profile point cloud and the standard rail model to obtain a measurement benchmark;

[0008] S3 obtains multiple feature points based on the static rail cross-section profile point cloud and the dynamic rail cross-section profile point cloud, and performs feature point matching between the static rail cross-section profile point cloud and the dynamic rail cross-section profile point cloud at different times;

[0009] Based on the measurement benchmark and combined with multiple matched feature points, S4 calculates the vertical displacement, lateral displacement and inclination of the rail at the moment the train passes. Based on the vertical displacement, lateral displacement and inclination of the rail at multiple consecutive moments, the continuous displacement and inclination changes of the rail when the train passes can be calculated.

[0010] Preferably, step S1 includes:

[0011] The S11 determines the installation distance and fixing method of the camera and line laser based on the line width and length of the line laser, the camera's resolution, pixels, depth of view, and field of view, and the environmental factors of the rail area.

[0012] S12 adjusts the irradiation angle of the line laser so that the laser plane of the line laser intersects the target area of ​​the rail to be measured, and the track direction of the rail to be measured is perpendicular to the laser plane of the line laser;

[0013] S13 adjusts the camera shooting angle;

[0014] S14 calibrates the camera's shooting angle and the line laser's laser surface, collects rail images in the laser surface illumination area through the line laser and camera, and constructs static rail cross-sectional profile point clouds and dynamic rail cross-sectional profile point clouds at different times during the train's passage through triangulation methods.

[0015] Preferably, step S2 includes:

[0016] S21 generates a rail CAD model by establishing a working interface through modeling software, samples the rail CAD model to obtain point cloud data, and selects in the working interface that the x-axis is parallel to the rail surface and perpendicular to the rail direction, the y-axis is perpendicular to the rail surface, the z-axis is parallel to the rail extension direction, and the origin is located at the center of the rail bottom;

[0017] S22 cuts the rail point cloud along the direction perpendicular to the rail to obtain the point cloud S1 corresponding to the standard rail cross-section profile registration;

[0018] S23 calculates the chamfer distance d between the static rail cross-section profile point cloud S2 and the standard rail cross-section profile point cloud. CD (S1, S2), repeat this process for iterative adjustment so that the chamfer distance between the point cloud corresponding to the static rail section profile point cloud and the standard rail section profile registration is less than the preset threshold δ, and obtain the translation and rotation parameters.

[0019] Preferably, the chamfer distance d CD The calculation formula for (S1, S2) is:

[0020]

[0021] Preferably, step S3 includes:

[0022] S31 transforms the dynamic rail cross-section profile point cloud at each moment into the coordinate system of the working interface established by the modeling software in step S21 by translation and rotation parameters based on the dynamic rail cross-section profile point cloud;

[0023] S32 calculates the curvature of each point of the dynamic rail cross-section profile point cloud after executing sub-step S31, selects the first N points of the dynamic rail cross-section profile point cloud after executing sub-step S31 with the largest curvature, and obtains feature points;

[0024] S33 performs feature point matching operations on the dynamic rail cross-section profile point cloud at different times and the static rail cross-section profile point cloud in descending order of curvature of each point.

[0025] Preferably, step S4 includes:

[0026] S41 assumes that the characteristic points of the static rail profile line point cloud are P1, P2, ..., P N , let the characteristic points of the dynamic rail cross-section profile point cloud corresponding to the train passing at time t be P1', P2', ..., P N ', calculate the difference P of each pair of matching feature points at time t i -P i ', N is the number of feature points; based on the difference P of each pair of matching feature points at time t i -P i ', obtain the lateral displacement X of N feature points at time t t and vertical displacement Y t ;

[0027] S42 is based on the origin O and the characteristic points P1, P2, ..., P N , obtain the stationary eigenvectors OP1, OP2, ..., OP N , based on the feature points P1', P2', ..., P of the dynamic rail profile point cloud corresponding to the train passing at time t N ', calculate and obtain the characteristic vectors OP1, OP2, ..., OP of the static state at time t N Matching N dynamic feature vectors OP1', OP2', ..., OP N ';

[0028] S43 calculates the dynamic characteristic vectors OP1', OP2', ..., OP N ' and calculate the average value to obtain the rail inclination angle α at time t t .

[0029] In a second aspect, the present invention provides a non-contact online visual measurement device for rail displacement and inclination, comprising a line laser, a camera, and a processing module;

[0030] The line laser is used to illuminate the rail area to be measured with a laser surface; the camera is used to capture the rail image in the area illuminated by the laser surface and transmit it to the processing module;

[0031] The processing module is used to: construct the static rail cross-section profile point cloud and the dynamic rail cross-section profile point cloud at different moments during the train passing process based on the rail image of the laser surface irradiation area through triangulation method;

[0032] The static rail cross-section profile point cloud is registered with the standard rail model to obtain a measurement benchmark;

[0033] A plurality of feature points are obtained based on the dynamic rail cross-section profile point cloud, and feature point matching is performed on the point cloud data of the dynamic rail cross-section profile point cloud at the corresponding moment;

[0034] Based on the measurement benchmark, the vertical displacement, lateral displacement and inclination of the rail at the time the train passes are calculated in combination with the matched multiple feature points. The registration data at multiple consecutive moments can be used to calculate the continuous displacement and inclination changes of the rail when the train passes.

[0035] Preferably, the device comprises a line laser and a camera, and the camera is a high-resolution industrial camera.

[0036] As can be seen from the technical solutions provided by the above-mentioned embodiments of the present invention, the present invention provides a non-contact online visual measurement method and device for rail displacement and inclination, wherein the method includes the following steps: S1: arranging a line laser and a high-resolution industrial camera on the outside of the rail to obtain an image of the cross-sectional area illuminated by the line laser on the outside of the rail, and reconstructing the rail cross-sectional profile point cloud using the triangulation principle; S2: aligning the reconstructed static (when the train is not passing) rail cross-sectional profile point cloud with the standard rail model; S3: extracting and screening multiple feature points from the cross-sectional profile point cloud reconstructed when the train passes, and performing feature point matching on the point cloud data reconstructed at different times; S4: calculating the vertical displacement, lateral displacement, and inclination of the rail at different times based on the matched multiple feature points. The method and device provided by the present invention can simply, accurately, and safely measure the lateral displacement, vertical displacement, and inclination of the rail during train operation. This technology provides fast, accurate, and reliable theoretical and technical support for non-contact measurement of rail inclination and displacement.

[0037] Additional aspects and advantages of the present invention will be set forth in part in the following description, will become apparent from the following description, or may be learned by practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] 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 description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0039] Figure 1 A schematic flow chart of the non-contact visual measurement method for rail displacement and inclination provided by the present invention;

[0040] Figure 2 A schematic diagram of the working state of the non-contact visual measurement device for rail displacement and inclination provided by the present invention;

[0041] Figure 3 Schematic diagram of measurement parameters of the non-contact visual measurement method for rail displacement and inclination provided by the present invention (X t 、Y t 、a t are the lateral displacement, vertical displacement and inclination angle of a certain feature point at time t). DETAILED DESCRIPTION

[0042] The embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and are not to be construed as limiting the present invention.

[0043] It will be understood by those skilled in the art that, unless expressly stated otherwise, the singular forms "a", "an", "said" and "the" used herein may also include the plural forms. It should be further understood that the term "comprising" used in the description of the present invention refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. It should be understood that when we refer to an element as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be intermediate elements. In addition, "connected" or "coupled" as used herein may include wireless connections or couplings. The term "and / or" used herein includes any unit and all combinations of one or more associated listed items.

[0044] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those skilled in the art in the art to which the present invention pertains. It should also be understood that terms such as those defined in common dictionaries should be understood to have meanings consistent with their meanings in the context of the prior art and, unless defined as such herein, will not be interpreted in an idealized or overly formal sense.

[0045] To facilitate understanding of the embodiments of the present invention, several specific embodiments will be further explained below with reference to the accompanying drawings. However, each embodiment does not constitute a limitation on the embodiments of the present invention.

[0046] See also Figure 1 The present invention discloses a non-contact visual measurement method for rail displacement and inclination, comprising the following steps:

[0047] Step S1: Using a line laser and a camera on the outside of the rail to capture rail images of the laser surface irradiation area, and constructing a static rail cross-sectional profile point cloud and a dynamic rail cross-sectional profile point cloud at different moments during the train passing process through a triangulation method;

[0048] Step S2: registering the static rail cross-section profile point cloud with the standard rail model to obtain a measurement benchmark;

[0049] Step S3: obtaining a plurality of feature points based on the static rail cross-section profile point cloud and the dynamic rail cross-section profile point cloud, and matching the feature points of the static rail cross-section profile point cloud with the dynamic rail cross-section profile point cloud at different times;

[0050] Step S4: Using the static rail cross-sectional profile point cloud obtained in step S2 as the measurement reference, the vertical displacement, lateral displacement, and inclination of the rail at the moment the train passes are calculated by combining the matched feature points. Based on the registration data at multiple consecutive moments, the continuous displacement and inclination changes of the rail during the train passage can be calculated. The registration data includes the vertical displacement, lateral displacement, and inclination of the rail.

[0051] In a preferred embodiment provided by the present invention, step S1 includes:

[0052] Step S11: Determine the installation distance and fixing method of the camera and the line laser based on the line width, line length, camera resolution, pixel size, field of view depth, and size, and other parameter information of the line laser, combined with the on-site environment;

[0053] Step S12: adjusting the irradiation angle of the line laser so that the laser plane of the line laser intersects the target area of ​​the rail to be measured, and the track direction of the rail to be measured is perpendicular to the laser plane of the line laser;

[0054] Step S13: adjusting the camera shooting angle so that the camera can capture a clear laser line image;

[0055] Step S14: Calibrate the camera's shooting angle and the line laser's laser surface, collect rail images in the laser surface illumination area using the line laser and camera, and construct the static rail cross-sectional profile point cloud and the dynamic rail cross-sectional profile point cloud at different times during the train's passage using a triangulation method.

[0056] Step S2 includes:

[0057] Step S21: Generate a rail CAD model by establishing a working interface through modeling software, sample the rail CAD model to obtain point cloud data, and in the working interface, select the x-axis direction to be parallel to the rail surface and perpendicular to the rail direction, the y-axis direction to be perpendicular to the rail surface, the z-axis to be parallel to the rail extension direction, and the origin to be the center position of the rail bottom;

[0058] Step S22: cutting the rail point cloud along the direction perpendicular to the rail to obtain a point cloud corresponding to the standard rail cross-section profile registration;

[0059] Step S23: Based on the stationary rail cross-section profile point cloud, calculate the chamfer distance between the stationary rail cross-section profile point cloud and the point cloud corresponding to the standard rail cross-section profile alignment, repeat this process for iterative adjustment, so that the chamfer distance between the stationary rail cross-section profile point cloud and the point cloud corresponding to the standard rail cross-section profile alignment is less than a preset threshold δ, and obtain the translation and rotation parameters.

[0060] The calculation formula of the chamfer distance is:

[0061]

[0062] Step S3 includes:

[0063] Step S31: Based on the reconstructed dynamic rail cross-section profile point cloud, the dynamic rail cross-section profile point cloud at each moment is transformed into the coordinate system of the working interface established by the modeling software in step S21 by using the translation and rotation parameters;

[0064] Step S32: Calculate the curvature of each point in the dynamic rail cross-section profile point cloud after executing sub-step S31, and select the first N points with the largest curvature as feature points;

[0065] S33 performs feature point matching operations on the dynamic rail cross-section profile point cloud at different times and the static rail cross-section profile point cloud in descending order of curvature of each point.

[0066] Step S4 includes:

[0067] Step S41: Figure 3As shown, let the characteristic points of the static rail profile line point cloud be P1, P2, ..., P N (i.e., measurement benchmark), let the characteristic points of the dynamic rail cross-section profile point cloud corresponding to the train passing at time t be P1', P2', ..., P N ', calculate the difference between each pair of matching feature points at time t, where N is the number of feature points, i (i = 1, 2, ..., N); based on the difference between each pair of matching feature points at time t, obtain the lateral and vertical displacements of the N feature points at time t. N pairs of feature points can obtain N differences, and their components in the x-axis and y-axis directions are the lateral and vertical displacements of the N feature points at time t.

[0068] Step S42: Figure 3 As shown, based on the origin and the characteristic points P1, P2, ..., P N , obtain the stationary eigenvectors OP1, OP2, ..., OP N , based on the characteristic points P1', P2', ..., P of the dynamic rail profile point cloud corresponding to the train passing at time t N ', calculate and obtain N dynamic feature vectors OP1', OP2', ..., OP N ';

[0069] Step S43 calculates the angle of the dynamic characteristic vector and takes the average value to obtain the rail inclination angle α at time t t .

[0070] In a second aspect, the present invention provides a device for executing the above method, comprising a line laser, a camera and a processing module; the line laser is used to irradiate a laser surface onto a rail area to be measured; the camera is used to collect rail images in the area irradiated by the laser surface and transmit them to the processing module; the processing module is used to: construct a stationary rail cross-sectional profile point cloud and a dynamic rail cross-sectional profile point cloud at different moments during the passage of a train based on the rail images in the area irradiated by the laser surface, and through a triangulation method; align the stationary rail cross-sectional profile point cloud with a standard rail model to obtain a measurement reference; obtain multiple feature points based on the dynamic rail cross-sectional profile point cloud, and perform feature point matching on the point cloud data of the dynamic rail cross-sectional profile point cloud at the corresponding moment; calculate the vertical displacement, lateral displacement and inclination of the rail at the moment the train passes based on the matched multiple feature points, and the alignment data at multiple consecutive moments can calculate the continuous displacement and inclination changes of the rail when the train passes.

[0071] Furthermore, in some preferred embodiments, the device includes a line laser and a camera, and the camera is a high-resolution industrial camera.

[0072] In summary, the present invention provides a non-contact online visual measurement method and device for rail displacement and inclination, wherein the method comprises the following steps: S1: arranging a line laser and a high-resolution industrial camera on the outside of the rail, obtaining an image of the cross-sectional area illuminated by the line laser on the outside of the rail, and reconstructing the rail cross-sectional profile point cloud using the triangulation principle; S2: aligning the reconstructed static (when the train is not passing) rail cross-sectional profile point cloud with the standard rail model; S3: extracting and screening multiple feature points from the cross-sectional profile point cloud reconstructed when the train passes, and performing feature point matching on the point cloud data reconstructed at different times; S4: calculating the vertical displacement, lateral displacement and inclination of the rail at different times based on the matched multiple feature points. The method and device provided by the present invention can simply, accurately and safely measure the lateral displacement, vertical displacement and inclination of the rail during train operation. This technology provides fast, accurate and reliable theoretical and technical support for non-contact measurement of rail inclination and displacement.

[0073] Those skilled in the art will appreciate that the accompanying drawings are merely schematic diagrams of an embodiment, and the modules or processes in the accompanying drawings are not necessarily required to implement the present invention.

[0074] From the above description of the embodiments, it can be seen that those skilled in the art can clearly understand that the present invention can be implemented by means of software plus the necessary general-purpose hardware platform. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various embodiments of the present invention or certain parts of the embodiments.

[0075] Each embodiment in this specification is described in a progressive manner. The same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the device or system embodiments, since they are basically similar to the method embodiments, the description is relatively simple. For the relevant parts, refer to the partial description of the method embodiments. The device and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. A person of ordinary skill in the art can understand and implement it without making any creative efforts.

[0076] The above description is merely a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes 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 in 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 non-contact online visual measurement method for rail displacement and inclination, characterized in that: include: S1 uses a line laser and a camera on the outside of the rail to collect rail images in the laser-illuminated area, and constructs point clouds of the static rail cross-section profile and dynamic rail cross-section profile at different moments during the train passing process through triangulation. S2 performs registration processing on the static rail cross-section profile point cloud and the standard rail model to obtain a measurement benchmark; S3: obtaining a plurality of feature points based on the static rail cross-section profile point cloud and the dynamic rail cross-section profile point cloud, and matching the static rail cross-section profile point cloud with the dynamic rail cross-section profile point cloud at different times; S4 calculates the vertical displacement, lateral displacement and inclination of the rail at the moment the train passes based on the measurement benchmark and the matched multiple feature points. The continuous displacement and inclination changes of the rail when the train passes can be calculated based on the vertical displacement, lateral displacement and inclination of the rail at multiple consecutive moments.

2. The method according to claim 1, characterized in that Step S1 includes: The S11 determines the installation distance and fixing method of the camera and line laser based on the line width and length of the line laser, the camera's resolution, pixels, depth of view, and field of view, and the environmental factors of the rail area. S12 adjusts the irradiation angle of the line laser so that the laser plane of the line laser intersects the target area of ​​the rail to be measured, and the track direction of the rail to be measured is perpendicular to the laser plane of the line laser; S13 adjusts the camera shooting angle; S14 calibrates the shooting angle of the camera and the laser surface of the line laser, collects the rail image of the laser surface irradiation area through the line laser and the camera, and constructs the static rail cross-sectional profile point cloud and the dynamic rail cross-sectional profile point cloud at different times during the train passing through the method of triangulation.

3. The method according to claim 1, characterized in that Step S2 includes: S21 generates a rail CAD model by establishing a working interface through modeling software, samples the rail CAD model to obtain point cloud data, and in the working interface, selects an x-axis direction parallel to the rail surface and perpendicular to the rail direction, a y-axis direction perpendicular to the rail surface, a z-axis direction parallel to the rail extension direction, and an origin at the center of the rail bottom; S22 cuts the rail point cloud along the direction perpendicular to the rail to obtain the point cloud S1 corresponding to the standard rail cross-section profile registration; S23 calculates the chamfer distance d between the point cloud corresponding to the stationary rail cross-section profile point cloud and the standard rail cross-section profile based on the stationary rail cross-section profile point cloud S2. CD (S1, S2), repeat this process for iterative adjustment so that the chamfer distance between the point cloud corresponding to the static rail section profile point cloud and the standard rail section profile registration is less than a preset threshold δ, and obtain the translation and rotation parameters.

4. The method according to claim 3, characterized in that The chamfer distance d CD The calculation formula for (S1, S2) is:

5. The method according to claim 3, characterized in that Step S3 includes: S31 transforms the dynamic rail cross-section profile point cloud at each moment into the coordinate system of the working interface established by the modeling software in step S21 by using the translation and rotation parameters based on the dynamic rail cross-section profile point cloud; S32 calculates the curvature of each point of the dynamic rail cross-section profile point cloud after executing sub-step S31, selects the first N points of the dynamic rail cross-section profile point cloud after executing sub-step S31 with the largest curvature, and obtains the feature points; S33 performs feature point matching operations on the dynamic rail section profile point clouds at different times and the static rail section profile point clouds in descending order of curvature of each point.

6. The method according to claim 5, characterized in that Step S4 includes: S41: Set the characteristic points of the static rail profile line point cloud as P1, P2, ..., P N , let the characteristic points of the dynamic rail cross-section profile point cloud corresponding to the train passing at time t be P1', P2', ..., P N ', calculate the difference P of each pair of matching feature points at time t i -P i ', N is the number of feature points, i = 1, 2, ..., N, based on the difference P of each pair of matching feature points at time t i -P i ', obtain the lateral displacement X of N feature points at time t t and vertical displacement Y t ; S42 is based on the origin O and the characteristic points P1, P2, ..., P N , obtain the stationary eigenvectors OP1, OP2, ..., OP N , based on the characteristic points P1', P2', ..., P of the dynamic rail profile point cloud corresponding to the train passing at time t N ', calculate and obtain the characteristic vectors OP1, OP2, ..., OP N Matching N dynamic feature vectors OP1', OP2', ..., OP N '; S43 calculates the dynamic characteristic vectors OP1', OP2', ..., OP N ' and calculate the average value to obtain the rail inclination angle α at time t t .

7. Non-contact online visual measurement device for rail displacement and inclination, characterized in that: Includes line laser, camera and processing module; The line laser is used to illuminate the rail area to be measured with a laser surface; the camera is used to capture the rail image in the area illuminated by the laser surface and transmit it to the processing module; The processing module is used to: construct a static rail cross-section profile point cloud and a dynamic rail cross-section profile point cloud at different moments during the train passing process based on the rail image of the laser surface irradiation area by a triangulation method; The static rail cross-section profile point cloud is registered with the standard rail model to obtain a measurement benchmark; Obtaining a plurality of feature points based on the dynamic rail section profile point cloud, and performing feature point matching on the point cloud data of the dynamic rail section profile point cloud at a corresponding moment; Based on the measurement benchmark, the vertical displacement, lateral displacement and inclination of the rail at the time the train passes are calculated in combination with the matched multiple feature points. The registration data of multiple consecutive moments can be used to calculate the continuous displacement and inclination changes of the rail when the train passes.

8. The device according to claim 7, characterized in that The device includes a line laser and a camera, and the camera is a high-resolution industrial camera.

Images