Sleeper-level track gauge measuring method, device, equipment and medium

Abstract

The invention provides a sleeper-level track gauge measurement method, device and equipment and a medium. The method comprises the steps that full-section three-dimensional point cloud data, collected by a laser radar at the first moment, of a railhead and a sleeper are acquired; identifying the positions of a railhead and a sleeper through a template matching algorithm; acquiring the three-dimensional coordinate data of the railhead and the sleeper collected by the linear structured light sensor at the first moment; converting the three-dimensional point cloud data and the three-dimensional coordinate data into a unified reference coordinate; position data, collected by the laser radar at the first moment, of rail heads and sleepers are aligned with three-dimensional coordinate data, collected by the linear structure light sensor, of the rail heads and the sleepers, and coordinates of the rail heads at the two ends of the sleepers under unified reference coordinates are obtained; and calculating the sleeper-level gauge at the first moment based on the coordinates of the rail heads at the two ends of the sleeper. The problem of inaccurate gauge measurement in the prior art can be solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of track measurement, in particular to a sleeper-level track gauge measurement method, device, equipment and medium. BACKGROUND

[0002] Railway infrastructure such as steel rails and sleepers is the basis for safe train operation. Sleepers are concrete or wooden support structures laid transversely below the track. Track gauge, the distance between the inner sides of two steel rails, is one of the core indicators of track condition. Small deviations in track gauge can cause increased train sway and even derailment risks. Therefore, the railway department needs to regularly detect track gauge and adjust the position of the steel rails based on the detection results.

[0003] Sleepers are the basic support structure of the track and the key node of track stress. Abnormalities such as deformation of the track gauge are often directly related to the displacement, settlement or damage of the sleepers, which can cause changes in local track gauge. Sleeper-level track gauge measurement can precisely locate the root cause of the problem by binding the track gauge value to a specific sleeper, allowing targeted maintenance measures such as reinforcement or replacement, reducing maintenance costs, and avoiding blind repair of the entire track. In addition, by combining the sleeper state (such as settlement and cracks) and track gauge changes, potential risks can be predicted, and customized maintenance and repair strategies can be designed.

[0004] Existing measurement methods mainly include automated equipment such as laser carts and track detection vehicles. These methods typically use single-line laser scanning of the rail section and combine encoder mileage recording to output a curve of track gauge changes with respect to mileage. However, there are two major drawbacks. First, the sampling is coarse. Most devices use equal-distance interval sampling and equal-distance result output, such as outputting track gauge data every 1 meter or 10 meters. However, the actual sleeper spacing is fixed (0.6 meters in China), which causes the detection results to be disconnected from the sleeper positions and unable to accurately lock the root cause of the problem. Second, there is a speed bottleneck. Limited by sensor accuracy and data processing capacity, dynamic detection speeds are generally lower than 5 km / h. Otherwise, the laser sampling rate is insufficient, leading to distorted data. For busy railway lines, low-speed detection can occupy the track for a long time, affecting normal operations.

[0005] In addition, there are automated detection methods based on vision. These methods use industrial cameras to capture steel rail images, extract rail head positions through edge detection algorithms, and pre-set marker points on the track for spatial calibration. Track gauge is calculated in combination with the odometer. This method is sensitive to light. Strong light, shadows or night environments can increase image noise, causing track gauge calculation errors. At the same time, the camera's viewing angle is limited to the upper part of the steel rail, making it difficult to obtain sleeper point cloud data and analyze the causes of track gauge abnormalities.

[0006] The prior art has two core problems due to the single sensor, asynchronous data, algorithm lag and other bottlenecks: one is "inaccurate measurement", in the high-speed dynamic measurement scene, the track gauge measurement accuracy and speed cannot be considered; the other is "unclear", the track gauge anomaly cannot be associated with the specific sleeper, resulting in lack of pertinence of maintenance decision. SUMMARY

[0007] The present application provides a sleeper-level track gauge measurement method, device, equipment and medium to solve the inaccurate track gauge measurement and the inability to accurately associate the measurement results of each sleeper in the prior art.

[0008] According to an aspect of the present application, a sleeper-level track gauge measurement method is provided, comprising: acquiring full-section three-dimensional point cloud data of a rail head and a sleeper collected by a laser radar at a first time; identifying the positions of the rail head and the sleeper by a template matching algorithm; acquiring three-dimensional coordinate data of the rail head and the sleeper collected by a line structured light sensor at the first time; converting the three-dimensional point cloud data and the three-dimensional coordinate data to a unified reference coordinate; aligning the position data of the rail head and the sleeper collected by the laser radar at the first time with the three-dimensional coordinate data of the rail head and the sleeper collected by the line structured light sensor to obtain the coordinates of the rail head at both ends of the sleeper under the unified reference coordinate; calculating the sleeper-level track gauge at the first time based on the coordinates of the rail head at both ends of the sleeper.

[0009] Optionally, the identification of the positions of the rail head and the sleeper by the template matching algorithm comprises: determining the point cloud shape features of the rail head and the sleeper; identifying the positions of the rail head and the sleeper in the full-section three-dimensional point cloud data of the rail head and the sleeper collected by the laser radar based on the point cloud shape features of the rail head and the sleeper by the template matching algorithm.

[0010] Optionally, the conversion of the three-dimensional point cloud data and the three-dimensional coordinate data to the unified reference coordinate comprises: calibrating the line structured light sensor to determine a first conversion relationship from the line structured light sensor coordinate system to the reference coordinate system, and calculating the first reference coordinate of the three-dimensional coordinate data collected by the line structured light sensor at the first time based on the first conversion relationship; calibrating the laser radar to determine a second conversion relationship from the laser radar coordinate system to the reference coordinate system, and calculating the second reference coordinate of the three-dimensional point cloud data collected by the laser radar at the first time based on the second conversion relationship.

[0011] Optionally, the position alignment is performed by aligning the position data of the rail head and the sleeper collected by the laser radar at the first time with the three-dimensional coordinate data of the rail head and the sleeper collected by the line structured light sensor, to obtain the coordinates of the rail head at both ends of the sleeper under the unified reference coordinate. convert the full-section three-dimensional point cloud data of the rail head and the sleeper collected by the laser radar at the first time to the reference coordinate system based on the first conversion relationship, to obtain the first reference coordinate of the rail head and the sleeper; obtain the second reference coordinate of the rail head and the sleeper based on the second conversion relationship; align the first reference coordinate and the second reference coordinate of the rail head and the sleeper to obtain the coordinates of the rail head at both ends of the sleeper under the unified reference coordinate.

[0012] Optionally, the method further comprises denoising and fusing the first reference coordinate and the second reference coordinate of the rail head and the sleeper by using a Kalman filtering method, to obtain the coordinates of the rail head at both ends of the sleeper under the unified reference coordinate.

[0013] Optionally, the method further comprises numbering each sleeper in a time sequence and a running direction, and sequentially calculating the track gauge of the rail head at both ends of each numbered sleeper.

[0014] Optionally, the method further comprises obtaining the center coordinate of the sleeper, and judging the state of the sleeper based on the difference between the center coordinate of the sleeper and a preset elevation.

[0015] According to another aspect of the present application, a sleeper-level track gauge measuring device is provided, comprising: a first acquisition unit configured to acquire full-section three-dimensional point cloud data of a rail head and a sleeper collected by a laser radar at a first time; a matching unit configured to identify the position of the rail head and the sleeper by using a template matching algorithm; a second acquisition unit configured to acquire three-dimensional coordinate data of the rail head and the sleeper collected by a line structured light sensor at the first time; a coordinate conversion unit configured to convert the three-dimensional point cloud data and the three-dimensional coordinate data to a unified reference coordinate; a fusion unit configured to align the position data of the rail head and the sleeper collected by the laser radar at the first time with the three-dimensional coordinate data of the rail head and the sleeper collected by the line structured light sensor, to obtain the coordinates of the rail head at both ends of the sleeper under the unified reference coordinate; a track gauge calculation unit configured to calculate the sleeper-level track gauge at the first time based on the coordinates of the rail head at both ends of the sleeper.

[0016] According to another aspect of the present application, an electronic device is provided, comprising: at least one processor; and a memory in communication with the at least one processor; wherein The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the tie-level track gauge measurement according to any one of the embodiments of the present application.

[0017] According to another aspect of the present application, a computer readable storage medium is provided, which stores computer instructions for enabling a processor to implement the tie-level track gauge measurement according to any one of the embodiments of the present application when executed.

[0018] The technical scheme of the embodiment of the present application comprises the following steps: acquiring full-section three-dimensional point cloud data of a rail head and a tie at a first time point collected by a laser radar; identifying the positions of the rail head and the tie through a template matching algorithm; acquiring three-dimensional coordinate data of the rail head and the tie collected by a line structured light sensor at the first time point; converting the three-dimensional point cloud data and the three-dimensional coordinate data to a unified reference coordinate; aligning the position data of the rail head and the tie collected by the laser radar at the first time point with the three-dimensional coordinate data of the rail head and the tie collected by the line structured light sensor to obtain the coordinates of the rail heads at both ends of the tie under the unified reference coordinate; and calculating the tie-level track gauge at the first time point based on the coordinates of the rail heads at both ends of the tie. The present application utilizes the joint data of the three-dimensional laser radar and the line structured light sensor, the laser radar provides full-section point cloud data for coarse positioning of the center of the tie and the rail head, and then the data provided by the line structured light sensor is combined to realize accurate positioning and data fusion of the tie-level track gauge measurement and to complete accurate extraction of three-dimensional information of the rail head. In a high-speed dynamic environment, the track gauge value is quickly and accurately calculated.

[0019] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become apparent through the following description. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0021] Figure 1 is a flowchart of a tie-level track gauge measurement method according to the first embodiment of the present application; Figure 2 is a structural entity diagram of a detection device according to an embodiment of the present application; Figure 3It is a structural schematic diagram of a sleeper-level track gauge measuring device provided according to an embodiment of the present application. Figure 4 It is a structural schematic diagram of an electronic device for implementing a sleeper-level track gauge measuring method of the present application. DETAILED DESCRIPTION

[0022] In order for those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should fall within the scope of protection of the present application.

[0023] It should be noted that the terms "first", "second", and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product, or device that includes a series of steps or units does not have to be limited to only those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0024] Embodiment one Figure 1 A flowchart of a sleeper-level track gauge measuring method is provided for the first embodiment of the present application. As shown in the figure, the method comprises: Figure 1 S101, acquiring full-section three-dimensional point cloud data of a rail head and a sleeper collected by a laser radar at a first time.

[0025] In the present embodiment, a laser radar with a higher sampling frequency is used, for example, a frequency of 2.5k~20kHz; and a 360° rotary scanning laser radar can be selected, so as to acquire full-section three-dimensional point cloud data of the track and the sleeper in the running direction of the detection device in real time.

[0026] In the present embodiment, the first time can be any sampling time, that is, the laser radar can acquire full-section three-dimensional point cloud data of the rail head and the sleeper at a higher sampling frequency, so that the measuring tool can still acquire high-precision measurement data when running at a high speed.

[0027] ​In addition, in this embodiment, a preset algorithm can be used to denoise, register and optimize the full-section three-dimensional point cloud data collected by the lidar in order to generate the three-dimensional geometric shape of the track.

[0028] The detection equipment used in this embodiment can be as follows: Figure 2 As shown, the detection equipment can be a trolley running on the track, equipped with a 360° three-dimensional lidar and a line structured light sensor. Two line structured light sensors are symmetrically fixed on both sides of the trolley chassis, vertically aligned with the inner working edge of the rail head (i.e., the track gauge measurement reference plane). The three-dimensional lidar is installed at the center of the top of the trolley. During operation, the three-dimensional lidar rotates 360° to scan and acquire the point cloud of the entire track and sleeper cross-section. Through feature extraction and other processing methods, it achieves coarse positioning of the sleeper center and rail head three-dimensional coordinates. The line structured light sensor acquires laser stripe images, extracts and outputs the coordinates of the laser center point, completing the fine extraction of the rail head three-dimensional information and calculating the track gauge value.

[0029] S102. Identify the positions of railheads and sleepers using a template matching algorithm.

[0030] In one embodiment, step S102 includes: determining the point cloud shape features of the rail head and the sleeper; Based on the point cloud shape features of the rail head and sleeper, a template matching algorithm is used to identify the position of the rail head and sleeper in the full-section three-dimensional point cloud data of the rail head and sleeper collected by lidar.

[0031] First, the full-section 3D point cloud data of the rail head and sleepers collected by the lidar can be denoised. For example, isolated noise points in the point cloud collected by the lidar can be removed, and voxel grid downsampling can be used to reduce the point cloud density (such as reducing the point cloud resolution to 5-10mm), thereby improving matching efficiency while ensuring geometric features.

[0032] By utilizing the linear characteristics of the orbit (continuous distribution along the orbit's extension direction), straight lines in the point cloud are detected through Hough Transform, which initially determines the approximate direction and range of the orbit, thus narrowing down the search area for template matching.

[0033] Subsequently, the typical geometric features (size, shape) of the rail head and sleepers are obtained, which can be constructed in the following way: the sleepers are rectangular structures arranged regularly along the direction of travel; the rail head is the upper structure of the track, with a cross-section in the shape of "I" or "T", a rounded top, and slopes on both sides.

[0034] According to the characteristic difference between the rail head and the sleeper, a suitable matching algorithm is selected to search for a matching area in the point cloud after denoising processing: in the point cloud after denoising processing, a sliding window (the window size is slightly larger than the sleeper size, such as 3m*0.5m*0.3m) is used to traverse the possible sleeper area. For the point cloud in each window, registration is performed with the sleeper three-dimensional template (such as using the ICP algorithm to iteratively optimize the average distance between the template and the window point cloud to be the minimum). A matching threshold is set (such as the average distance after registration <10mm, and the matching point ratio >70%), if the threshold is met, it is determined that the sleeper is matched, and the center point position is recorded.

[0035] In addition, the spatial continuity of the sleeper can also be verified, that is, the sleepers are continuously distributed along the longitudinal direction of the track. If a rail head is matched at a position, a rail head feature should also exist at the adjacent position (such as 100mm before and after), otherwise it is considered as a false match. The matched sleeper positions are uniformly spaced along the longitudinal direction of the track (such as a standard interval of 600-650mm). If the interval deviation of the matched sleeper positions exceeds the threshold (such as ±50mm), the abnormal points need to be removed.

[0036] S103, acquire three-dimensional coordinate data of the rail head and the sleeper collected by the line structure light sensor at the first time.

[0037] In this embodiment, a line structure light sensor with a higher sampling frequency is used, for example, the frequency can be 2.5k-20kHz; and two line structure light sensors can be arranged on the sampling device at positions above the left and right rail heads to respectively collect data in the areas near the rail heads, so as to acquire three-dimensional coordinate data of the rail head and part of the sleepers in the advancing direction of the detection device in real time.

[0038] The line structure light sensor includes a laser and an image sensor. The line structure light emitted by the laser forms a light plane in space, is projected onto the surface of the rail head and the sleeper, is diffusely reflected, and is received by the image sensor. The laser line is deformed on the surface of the object to form a laser stripe with a width of several pixels on the image sensor. The shape of the object is reflected in the deformation and displacement of the laser stripe. If the measured object changes in shape or position, the stripe collected by the image sensor will also change or move. Since there is a specific geometric relationship between the shape and displacement of the object and the shape and displacement of the stripe, the object space and the image space of the optical lens form a similar relationship. The shape of the laser stripe reflects the contour features of the surface of the measured object, and the three-dimensional data is calculated through the deformation and displacement in the image. After filtering and denoising processing of the image data, the point cloud data is transmitted to the computing unit. Since the cross-sectional light intensity of the laser stripe on the imaging plane approximately obeys the Gaussian distribution, the distribution formula is:

[0039] Wherein, I(x) is the pixel value of the pixel point x in the image, I0 is the central peak intensity of the fringe, μ is the ordinate of the actual fringe center point, and σ is the fringe width. By using the Gaussian fitting algorithm, the natural logarithm of the above formula is taken, and , the square term is expanded to obtain:

[0040] Then, the imaging coordinates of the laser fringe center in the image sensor are calculated.

[0041] Through the system preset calibration algorithm, the object side three-dimensional coordinates (X, Y, Z) corresponding to the image side coordinates in the image sensor are obtained. The laser line uses the extraction algorithm to obtain the imaging coordinates in the sensor. Through the system preset calibration algorithm, a mapping calibration table of the imaging coordinates and the object side coordinates is established, and the imaging coordinates are converted to the object side three-dimensional coordinates of the object to be measured in the real world through the table lookup mode, and the high-precision three-dimensional depth information of each point on the object surface is calculated. S104, convert the three-dimensional point cloud data and the three-dimensional coordinate data to a unified reference coordinate.

[0042] In this embodiment, the laser radar and the line structured light sensor can be calibrated by the pre-calibration method to obtain the transformation matrix of the coordinate system of the laser radar to the reference coordinate system and the transformation matrix of the coordinate system of the line structured light sensor to the reference coordinate system, and then the point cloud data collected by the laser radar and the three-dimensional data collected by the line structured light sensor can be converted to the reference coordinate system.

[0043] S105, by aligning the position of the position data of the rail head and the rail tie collected by the laser radar at the first time with the three-dimensional coordinate data of the rail head and the rail tie collected by the line structured light sensor, the coordinates of the rail head at both ends of the rail tie in the unified reference coordinate are obtained.

[0044] The three-dimensional coordinate value of the rail head collected by the line structured light sensor and the center coordinate of the rail tie synchronously obtained by the laser radar can be paired through position alignment. The synchronization calibration based on the mileage encoder is adopted to realize the correspondence between the track gauge data and the rail tie position.

[0045] The physical connection between the rail head and the sleeper determines the spatial correlation between the two, which can be used as the core constraint for pairing. Specifically, sleepers are spaced along the longitudinal direction of the track (e.g., standard spacing 600-650mm), while rail heads are continuously laid above sleepers, with each sleeper typically corresponding to a local area of the rail head (e.g., the position of the rail head above the center of the sleeper). Define the "mileage coordinate" along the longitudinal direction of the track (e.g., 0 at the starting point of the track, distance along the center line of the track), and the mileage values of the rail head and the sleeper should approximately correspond (rail head mileage ≈ sleeper mileage). In addition, the rail head is located above the transverse center line of the sleeper with minimal lateral offset (usually <50mm, determined by track laying accuracy); in the transverse coordinate system (perpendicular to the center line of the track), the x-coordinate of the center of the rail head and the x-coordinate of the center of the corresponding sleeper should deviate by less than a threshold value (e.g., ±100mm). There is a fixed height difference between the bottom of the rail head and the top surface of the sleeper (determined by the track structure, e.g., sleeper thickness + track underlayer thickness ≈ 200-300mm). The difference between the z-coordinate (height) of the rail head and the z-coordinate of the sleeper should be within a reasonable range (e.g., 200±50mm, which can be adjusted according to the actual track type).

[0046] Based on the above spatial constraints, the one-to-one pairing of the rail head and the sleeper is achieved through "rough matching - fine screening - verification" in three steps: First, extract the key coordinates of the rail head and the sleeper. The line structured light sensor usually scans along the transverse direction of the track, and can extract the feature point coordinates of the rail head, such as the center point of the top surface of the rail head (x1, y1, z1). The center coordinates of the sleeper extracted by the laser radar are (x2, y2, z2), where y2 is the longitudinal mileage of the sleeper. Sort the rail head and sleeper data along the longitudinal direction of the track (according to the y value from small to large). For each sleeper (y2 = y_pillow), search for a candidate rail head with similar longitudinal mileage in the rail head data. For the candidate rail head matched in the rough, calculate it through the above spatial constraints. When the above constraints are satisfied at the same time, it is preliminarily determined as a matched pair. One sleeper can only correspond to one rail head. If a sleeper matches multiple rail heads, select the pair with the smallest constraint deviation. In addition, along the longitudinal direction of the track, the pairing relationship between the rail head and the sleeper should be continuous (e.g., the nth sleeper matches the nth rail head, and the n+1th sleeper matches the n+1th rail head). If there is a skip pairing (e.g., the nth sleeper matches the n+2th rail head), it is considered abnormal and corrected.

[0047] S106, calculate the sleeper-level track gauge at the first time based on the coordinates of the rail heads at both ends of the sleeper.

[0048] Based on the coordinates of the rail heads at both ends of the sleeper, the edge point coordinates of the rail heads at both ends of the sleeper can be obtained 、 Calculate the track gauge:

[0049] The technical scheme of the embodiment of the present application comprises the following steps: acquiring full-section three-dimensional point cloud data of a rail head and a rail tie collected by a laser radar at a first moment; identifying the positions of the rail head and the rail tie through a template matching algorithm; acquiring three-dimensional coordinate data of the rail head and the rail tie collected by a line structured light sensor at the first moment; converting the three-dimensional point cloud data and the three-dimensional coordinate data to a unified reference coordinate; aligning the position data of the rail head and the rail tie collected by the laser radar at the first moment with the three-dimensional coordinate data of the rail head and the rail tie collected by the line structured light sensor to obtain the coordinates of the rail head at both ends of the rail tie under the unified reference coordinate; and calculating the rail tie level track gauge at the first moment based on the coordinates of the rail head at both ends of the rail tie. The present application uses the joint data of a three-dimensional laser radar and a line structured light sensor, the laser radar provides full-section point cloud data, and the center of the rail tie and the rail head are coarsely positioned, and then the data provided by the line structured light sensor is combined to realize accurate positioning and data fusion of the rail tie level track gauge measurement and complete accurate extraction of three-dimensional information of the rail head. In a high-speed dynamic environment, the track gauge value is quickly and accurately calculated.

[0050] In an embodiment, step S104 further comprises: calibrating the line structured light sensor to determine a first conversion relationship of the line structured light sensor coordinate system to a reference coordinate system, and calculating first reference coordinates of the three-dimensional coordinate data collected by the line structured light sensor at the first moment based on the first conversion relationship; calibrating the laser radar to determine a second conversion relationship of the laser radar coordinate system to the reference coordinate system, and calculating second reference coordinates of the three-dimensional point cloud data collected by the laser radar at the first moment based on the second conversion relationship.

[0051] The line structured light sensor and the laser radar can be converted to the same reference coordinate system, for example, the position of the origin of the laser radar coordinate system in the reference system and the attitude matrix (usually fitted by measuring a plurality of feature points) can be measured. Similarly, the position of the origin of the line structured light coordinate system in the reference system and the attitude matrix can also be measured. Then the coordinates of the reference system points are equal to the attitude matrix multiplied by the product of the laser radar points and then added to the position of the origin of the laser radar coordinate system in the reference system; the coordinates of the reference system points are equal to the attitude matrix multiplied by the product of the line structured light points and then added to the position of the origin of the line structured light point coordinate system in the reference system.

[0052] In an embodiment, step S105 further comprises: converting the full-section three-dimensional point cloud data of the rail head and the rail tie collected by the laser radar at the first moment to the reference coordinate system based on the first conversion relationship to obtain first reference coordinates of the rail head and the rail tie; converting the three-dimensional coordinate data of the rail head and the rail tie collected by the line structured light sensor to obtain second reference coordinates of the rail head and the rail tie based on the second conversion relationship; aligning the first reference coordinates and the second reference coordinates of the rail head and the rail tie to obtain the coordinates of the rail head at both ends of the rail tie under the unified reference coordinate.

[0053] In this embodiment, based on the measured position of the laser radar coordinate system origin in the reference system and the attitude matrix, and the measured position of the line structure light coordinate system origin in the reference system and the attitude matrix, the following can be obtained respectively In an embodiment, it further comprises: using Kalman filtering method to denoise and fuse the first reference coordinates and the second reference coordinates of the rail head and the sleeper, to obtain the coordinates of the rail head at both ends of the sleeper in the unified reference coordinates.

[0054] Specifically, Kalman filtering is suitable for state estimation of linear systems, and its core is to output the optimal state estimation through the "prediction-update" cycle combined with the measurement value of the sensor and the system model. In practical application, the corresponding same target point in the laser radar point cloud and the line structured light depth map is determined through feature matching (such as ICP algorithm) first, and then Kalman filtering fusion is performed to avoid incorrect association of measurement values of different points.

[0055] In an embodiment, it further comprises: numbering each sleeper in time sequence and in the direction of travel, and sequentially calculating the gauge of the rail head at both ends of each numbered sleeper.

[0056] In this embodiment, for the multiple sleeper centers recognized by the laser radar, each sleeper center is assigned a number as an index key, thereby realizing automatic identification and numbering of the sleeper center. Since the sampling frequency of the laser radar is high, the detection device can collect point cloud data of the track and the sleeper in real time during travel, and sequentially number the sleepers. And the calculated gauge of the rail head at both ends of each sleeper is bound to the numbered sleeper, and then the detection data of each sleeper is obtained.

[0057] In an embodiment, it further comprises: obtaining the center coordinates of the sleeper, and judging the state of the sleeper based on the difference between the sleeper center coordinates and the preset elevation.

[0058] In this embodiment, the state of the sleeper includes settlement, and the track design parameters can be imported in advance, and the difference between the Z coordinate of the sleeper center point and the preset elevation in the design parameters is taken as the settlement amount, a positive number indicates upward floating, and a negative number indicates downward sinking. If it exceeds the abnormal threshold (such as 5mm), a warning signal is issued.

[0059] In addition, the state of the sleeper includes the damaged state. Among them, the surface damage condition can be obtained by analyzing the three-dimensional point cloud curvature. If the local curvature mutation area is >100cm 2 , it is marked as damaged.

[0060] Finally, the detection data of each sleeper can be obtained, as follows: { "sleeper number": N "center coordinates": [X, Y, Z], "left rail head coordinates": [X1, Y1, Z1], "right rail head coordinates": [X2, Y2, Z2], "gauge": D, "pier state": {"settlement": Xmm, "damage": false}” } The above structured data is written into a track maintenance system database in real time, which supports subsequent associated query, track gauge anomaly tracing, and track pier state analysis, etc., realizes dynamic monitoring of track and track pier geometry and real-time calculation of track gauge, and facilitates subsequent maintenance and repair management.

[0061] Embodiment Two Figure 3 A structure diagram of a track pier gauge measuring device provided by Embodiment Three of the present application is shown in the figure. Figure 3 As shown in the figure, the device comprises: A first acquisition unit 301 is configured to acquire full-section three-dimensional point cloud data of rail heads and track piers collected by a laser radar at a first time; A matching unit 302 is configured to identify the positions of the rail heads and track piers by a template matching algorithm; A second acquisition unit 303 is configured to acquire three-dimensional coordinate data of the rail heads and track piers collected by a line structured light sensor at the first time; A coordinate conversion unit 304 is configured to convert the three-dimensional point cloud data and the three-dimensional coordinate data to a unified reference coordinate; A fusion unit 305 is configured to align the positions of the rail heads and track piers collected by the laser radar at the first time with the three-dimensional coordinate data of the rail heads and track piers collected by the line structured light sensor, to obtain the coordinates of the rail heads at both ends of the track pier under the unified reference coordinate; A gauge calculation unit 306 is configured to calculate the track pier gauge at the first time based on the coordinates of the rail heads at both ends of the track pier.

[0062] The track pier gauge measuring device provided by the embodiments of the present application can execute the track pier gauge measuring method provided by any of the embodiments of the present application, and has the corresponding functional modules and beneficial effects of the execution method.

[0063] Embodiment Four Figure 4A structural diagram of an electronic device 10 that can be used to implement embodiments of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices (e.g., headsets, glasses, watches, etc.), and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application described and / or claimed in this document.

[0064] As shown, Figure 4 The electronic device 10 includes at least one processor 11, and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., communicatively connected to the at least one processor 11, where the memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer programs stored in the read-only memory (ROM) 12 or loaded into the random access memory (RAM) 13 from the storage unit 18. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0065] Various components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc., an output unit 17, such as various types of displays, speakers, etc., a storage unit 18, such as a magnetic disk, an optical disk, etc., and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0066] The processor 11 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs various methods and processes described above, such as a tie-level gauge measurement.

[0067] In some embodiments, a tie-level gauge measurement can be implemented as a computer program tangibly embodied in a computer readable storage medium, e.g., storage unit 18. In some embodiments, parts or all of the computer program can be loaded and / or installed onto electronic device 10 via, e.g., ROM 12 and / or communication unit 19. When the computer program is loaded onto RAM 13 and executed by processor 11, one or more of the steps of a tie-level gauge measurement as described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform a tie-level gauge measurement by other means, e.g., by way of firmware.

[0068] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, specially designed application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0069] Computer programs implementing methods of the present application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the computer program, when executed, implements the functions / acts specified in the flowcharts and / or block diagrams. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0070] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer-readable storage medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of a machine-readable storage medium will include one or more lines of a program of instructions in a transitory signal, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0071] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0072] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), blockchain network, and the Internet.

[0073] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0074] It should be understood that the various forms of flow shown above can be used to reorder, add or delete steps. For example, each step described in the present application can be executed in parallel, sequentially or in a different order, as long as the desired results of the technical solutions of the present application can be achieved, which is not limited herein.

[0075] The above detailed description does not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method of measuring the gauge of a sleeper, characterized in that, The method comprises the following steps: acquiring full-section three-dimensional point cloud data of the rail head and the sleeper collected by the laser radar at the first time point; identifying the positions of the rail head and the sleeper by a template matching algorithm; acquiring three-dimensional coordinate data of the rail head and the sleeper collected by the line structured light sensor at the first time point; converting the three-dimensional point cloud data and the three-dimensional coordinate data to a unified reference coordinate; aligning the position data of the rail head and the sleeper collected by the laser radar at the first time point with the three-dimensional coordinate data of the rail head and the sleeper collected by the line structured light sensor to obtain the coordinates of the rail head at both ends of the sleeper in the unified reference coordinate; calculating the sleeper-level track gauge at the first time point based on the coordinates of the rail head at both ends of the sleeper.

2. The tie gauge method according to claim 1, wherein The step of identifying the positions of the rail head and the sleeper by the template matching algorithm comprises the following steps: determining the point cloud shape features of the rail head and the sleeper; identifying the positions of the rail head and the sleeper in the full-section three-dimensional point cloud data of the rail head and the sleeper collected by the laser radar based on the point cloud shape features of the rail head and the sleeper by the template matching algorithm.

3. The tie gauge method according to claim 1, wherein The step of converting the three-dimensional point cloud data and the three-dimensional coordinate data to a unified reference coordinate comprises the following steps: calibrating the line structured light sensor to determine a first conversion relationship from the line structured light sensor coordinate system to the reference coordinate system, and calculating the first reference coordinate of the three-dimensional coordinate data collected by the line structured light sensor at the first time point based on the first conversion relationship; calibrating the laser radar to determine a second conversion relationship from the laser radar coordinate system to the reference coordinate system, and calculating the second reference coordinate of the three-dimensional point cloud data collected by the laser radar at the first time point based on the second conversion relationship.

4. The tie gauge method according to claim 3, wherein The step of aligning the position data of the rail head and the sleeper collected by the laser radar at the first time point with the three-dimensional coordinate data of the rail head and the sleeper collected by the line structured light sensor to obtain the coordinates of the rail head at both ends of the sleeper in the unified reference coordinate comprises the following steps: converting the full-section three-dimensional point cloud data of the rail head and the sleeper collected by the laser radar at the first time point to the reference coordinate system based on the first conversion relationship to obtain the first reference coordinate of the rail head and the sleeper; obtaining the second reference coordinate of the rail head and the sleeper based on the three-dimensional coordinate data of the rail head and the sleeper collected by the line structured light sensor based on the second conversion relationship; aligning the first reference coordinate and the second reference coordinate of the rail head and the sleeper to obtain the coordinates of the rail head at both ends of the sleeper in the unified reference coordinate.

5. The tie gauge method according to claim 1, wherein, The method further comprises the following steps:

6. The tie gauge method of claim 1, wherein, using the Kalman filtering method to denoise and fuse the first reference coordinate and the second reference coordinate of the rail head and the sleeper to obtain the coordinates of the rail head at both ends of the sleeper in the unified reference coordinate. The method further comprises the following steps:

7. The tie gauge method according to claim 1, wherein numbering each sleeper in time sequence and in the direction of travel, and sequentially calculating the track gauge of the rail head at both ends of each numbered sleeper.

8. A tie gauge, characterized in that The method further comprises the following steps: acquiring the center coordinate of the sleeper, and determining the state of the sleeper based on the difference between the center coordinate of the sleeper and a preset elevation. The method comprises the following steps: a first acquisition unit configured to acquire full-section three-dimensional point cloud data of the rail head and the sleeper collected by the laser radar at the first time point; a matching unit configured to identify the positions of the rail head and the sleeper by a template matching algorithm; a second acquisition unit configured to acquire three-dimensional coordinate data of the rail head and the sleeper collected by the line structured light sensor at the first time point; A coordinate conversion unit is configured to convert the three-dimensional point cloud data and the three-dimensional coordinate data into a unified reference coordinate; A fusion unit is configured to obtain coordinates of the rail heads at both ends of the sleeper in the unified reference coordinate by aligning the position data of the rail heads and sleepers collected by the laser radar at the first time with the three-dimensional coordinate data of the rail heads and sleepers collected by the line structured light sensor. A gauge calculation unit is configured to calculate the sleeper-level gauge at the first time based on the coordinates of the rail heads at both ends of the sleeper.

9. An electronic device, comprising: The electronic device comprises: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the sleeper-level gauge measurement method in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for enabling the processor to implement the sleeper-level gauge measurement method in any one of claims 1-7 when executed.

Images