Method for measuring geometric shape and position parameters of turnout section

Abstract

The invention provides a method for measuring geometric shape and position parameters of a turnout section, and belongs to the technical field of three-dimensional point cloud vision measurement. The method comprises the following steps: preprocessing acquired point cloud data of section profile shapes of left and right rails of a turnout, and establishing a sliding window based on the left and right rails; coarse-grained frame differences are calculated and classified; if the frame difference is the effective frame difference, recalculating the frame difference by fine granularity; judging the forking direction; processing waiting queues of the left / right rail and updating a sliding window if reverse forking is carried out; if the frame difference is an invalid frame difference, judging a left / right track processing identifier; if the left / right rail processing identifier is empty, executing a point cloud enqueue operation; if the left / right rail processing identifier is not empty, judging whether the left / right rail processing identifier is a switch rail close attachment identifier or not; and if the left / right rail processing identifier is a switch rail close identifier, point cloud rematching and non-positioning key frame information extraction are carried out. According to the invention, diversification of detection objects is realized, the sensitivity of monitoring data to ambient light is reduced, and the monitoring accuracy is improved.

Description

Technical Field

[0001] The invention relates to the technical field of three-dimensional point cloud visual measurement, and in particular to a method for measuring geometric shape and position parameters of a turnout section. Background Art

[0002] In the railway transportation system, the geometry of the track and turnout system is kept in good condition, which is the core element to ensure the overall safety and smoothness of railway operation. Especially for the turnout system, any degradation of its geometry may immediately affect the smooth operation of the train, the comfort of passengers and the overall safety. Therefore, regular professional inspection and maintenance work is very important.

[0003] At present, the measurement methods for the geometric parameters of turnouts are mainly divided into two directions: mobile measurement and in-situ measurement. In the scope of mobile measurement, there are both manual handheld track rulers, chords, rail profile rulers, steel plate rulers and rail grinders and other traditional tools for fine measurement. This method is mature in technology and the results are intuitive, but it takes a long time and is limited by the skylight operation period. At the same time, it is easily disturbed by the external environment and human operation errors. In the face of massive data, its processing efficiency is also insufficient. On the other hand, as an automated detection tool, the inspection vehicle can improve efficiency, but its high operating cost and the fact that it is also limited by the skylight period and external environmental conditions cannot meet the needs of real-time monitoring, which also restricts its wide application. In-situ measurement, that is, fixed in-situ detection technology, directly performs non-contact measurement of the turnout structure by integrating multiple sensors and visual imaging technology. For example, the boundary features of key components are extracted based on the turnout image and the geometric parameters are calculated using pixel differences. The three-dimensional point cloud data of the turnout is constructed and the geometric parameters of the turnout are calculated with the help of binocular structured light imaging technology. Labels are attached to the key components of the turnout and position recognition is performed. However, these methods often face challenges such as single detection object, high sensitivity to ambient light and low accuracy. Summary of the invention

[0004] The object of the present invention is to provide a method for measuring the geometric shape and position parameters of a turnout section, so as to solve at least one technical problem existing in the above-mentioned background technology.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] In a first aspect, the present invention provides a method for measuring geometric parameters of a turnout section, comprising:

[0007] Pre-process the collected point cloud data of the left and right rail profiles of the specified model of turnout;

[0008] A sliding window based on the left and right tracks is established, the coarse-grained frame difference is calculated using the KDtree algorithm, and the coarse-grained frame difference profile is classified;

[0009] If the classification result is a valid frame difference, the frame difference is recalculated at a fine granularity; the key frame information is extracted based on the recalculated frame difference; the diverging direction is determined based on the extracted key frame information; if the current diverging direction is reverse, the waiting queue of the left / right track is processed; and the sliding window is updated to calculate the coarse granularity frame difference;

[0010] If the classification result is an invalid frame difference, the left / right track processing flag is judged; if the left / right track processing flag is empty, the point cloud enqueue operation is performed and the sliding window is updated; if the left / right track processing flag is not empty, it is determined whether it is a sharp track close-fitting flag; if the left / right track processing flag is a sharp track close-fitting flag, the point cloud is re-matched, non-key frame information is extracted, and the sliding window is updated.

[0011] Furthermore, the collected point cloud data of the left and right rail profiles of the specified model of turnout are preprocessed, including: using the threshold screening method to eliminate invalid data in the point cloud; using the PCL radius filtering technology to denoise the noise data in the point cloud; using the point cloud data of the next frame to fill in the data missing problems in continuous frames to ensure the integrity and continuity of the time series data; and performing precise position calibration and alignment processing on the point cloud data of the left and right rails to ensure that all subsequent related data are compared and analyzed under the same benchmark.

[0012] Furthermore, a sliding window based on the left and right tracks is established, including: setting the size m of the sliding window and constructing a left / right track sliding window of corresponding length; enqueuing m consecutive point cloud data; dividing the point cloud data of the sliding window into two time periods, which are used for subsequent point cloud frame difference calculation.

[0013] Furthermore, the KDtree algorithm is used to calculate the coarse-grained frame difference, including: setting the Euclidean distance threshold threshold1; calculating the union cloudA of the first X frames of the sliding window, and constructing a KD tree accordingly; calculating the union cloudB of the last mX frames of the sliding window, and for each point in cloudB, using the KDtree algorithm to obtain its nearest point in cloudA, if the Euclidean distance to the nearest point is greater than threshold1, the point is stored in the difference set of cloudB relative to cloudA; constructing a KDtree with cloudB, and constructing the difference set of cloudA relative to cloudB in the above manner; executing the contour coarse segmentation algorithm on the two difference sets, and using the one with larger point cloud data volume as the frame difference point cloud data.

[0014] Furthermore, the frame difference profile classification includes: setting 6 frame difference profile categories: point rail close frame difference, point rail repulsive frame difference, guard rail frame difference, movable center rail frame difference, fixed center rail frame difference, and invalid frame difference; and using a frame difference classification algorithm to classify the profile.

[0015] Furthermore, the frame difference is recalculated with fine granularity, including: setting the Euclidean distance threshold threshold2; taking threshold2 as the benchmark, calling the KDtree algorithm again to calculate the point cloud frame difference; executing the contour coarse segmentation algorithm on the two point cloud frame differences, performing secondary denoising on the point cloud frame difference, and using the point cloud data with a larger amount as the frame difference point cloud data.

[0016] Furthermore, the key frame information extraction includes: determining the diverging direction with the help of prior information; positioning the key frame; extracting corresponding feature points according to the silhouette type of the key frame; and calculating parameters according to the extracted feature points.

[0017] Furthermore, if the current judgment is a forward divergence, the sliding window is directly updated; if the current judgment is a reverse divergence, the point cloud data in the left / right track waiting queue needs to be subjected to corresponding feature point extraction and parameter calculation, and the sliding window is updated.

[0018] Furthermore, after determining that the point cloud frame difference is an invalid frame difference, determine whether the current left / right track processing flag is empty; if the left / right track processing flag is empty, the current point cloud data cannot directly determine the type of contour, and it will be added to the waiting queue of the left / right track; if the left / right track processing flag is not empty, determine whether the current one is a sharp track close-fitting flag.

[0019] Furthermore, if the left / right rail processing mark is a sharp rail close-fitting mark, the point cloud rematching algorithm is executed to extract the sharp rail profile point cloud data; if the left / right rail processing mark is not a sharp rail close-fitting mark, the information of non-key frames in the sliding window is extracted.

[0020] The beneficial effects of the present invention are as follows: the efficiency and accuracy are improved, the detection objects are diversified, the sensitivity of the monitoring data to the ambient light is reduced, and the monitoring accuracy is improved.

[0021] Additional advantages of the present invention will be more clearly given in the following description or learned through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0023] Figure 1 The present invention is a flowchart of a method for measuring geometric parameters of a turnout section according to an embodiment of the present invention.

[0024] Figure 2 It is a schematic diagram of the visualization result of part of the point cloud outline after the point cloud data is preprocessed according to an embodiment of the present invention.

[0025] Figure 3 It is a schematic diagram of the visualization effect of the sharp track repulsion frame difference according to an embodiment of the present invention.

[0026] Figure 4 It is a schematic diagram of the visualization effect of the sharp track close frame difference according to an embodiment of the present invention.

[0027] Figure 5 It is a schematic diagram of the visual effect of the guardrail frame difference according to an embodiment of the present invention.

[0028] Figure 6 This is a schematic diagram of the visualization effect of the movable center track frame difference according to an embodiment of the present invention.

[0029] Figure 7 This is a schematic diagram of the fixed center track frame difference visualization effect according to an embodiment of the present invention.

[0030] Figure 8 This is a schematic diagram of the characteristic points to be extracted and the parameters to be calculated for the pointed rail repulsion described in an embodiment of the present invention.

[0031] Fig. 9 This is a schematic diagram of the characteristic points to be extracted and the parameters to be calculated for the sharp track close fitting described in an embodiment of the present invention.

[0032] Fig.10 This is a schematic diagram of the feature points that need to be extracted and the parameters that need to be calculated for the guardrail according to the embodiment of the present invention.

[0033] Fig.11 This is a schematic diagram of the feature points that need to be extracted and the parameters calculated for the center track described in an embodiment of the present invention.

[0034] Fig.12 This is a schematic diagram of the feature points that need to be extracted and the parameters calculated for the center track described in an embodiment of the present invention. DETAILED DESCRIPTION

[0035] The embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements with the same or similar functions. The embodiments described below by the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be interpreted as limiting the present invention.

[0036] It should 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 to which this invention belongs.

[0037] It should also be understood that terms, such as those defined in commonly used dictionaries, should be understood to have a meaning consistent with that in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless as defined herein.

[0038] Those skilled in the art will appreciate that, unless otherwise stated, the singular forms "a", "an", "said" and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification 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 and / or groups thereof.

[0039] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. Different embodiments or examples described in this specification and features of different embodiments or examples may be combined and combined by those skilled in the art without contradiction.

[0040] To facilitate understanding of the present invention, the present invention is further explained below with reference to specific embodiments in conjunction with the accompanying drawings, and the specific embodiments do not constitute a limitation on the embodiments of the present invention.

[0041] Those skilled in the art should understand that the drawings are merely schematic diagrams of embodiments, and the components in the drawings are not necessarily necessary for implementing the present invention.

[0042] Example 1

[0043] In this embodiment 1, a method for measuring the geometric shape and position parameters of a turnout section is provided, wherein the main method comprises the following steps:

[0044] Step S1: pre-process the collected left and right rail profile point cloud data of the specified model of the turnout; Step S2: establish a sliding window based on the left and right rails; Step S3: use the KDtree algorithm to calculate the coarse-grained frame difference; Step S4: classify the frame difference profile obtained in step S3; Step S5: if the result of step S4 is a valid frame difference, recalculate the frame difference with fine granularity; Step S6: extract key frame information; Step S7: determine the direction of the turnout; Step S8: if the current turnout is reverse, process the waiting queue of the left / right rail Processing; Step S9: Sliding window update, and execute step S3; Step S10: If step S4 determines that the frame difference is invalid, the left / right track processing mark is determined; Step S11: If the left / right track processing mark is empty, the point cloud is queued, and step S9 is executed; Step S12: If the left / right track processing mark is not empty, it is determined whether it is a sharp track close-fitting mark; Step S13: If the left / right track processing mark is a sharp track close-fitting mark, point cloud rematching is performed; Step S14: Non-key frame information is extracted, and step S9 is executed.

[0045] Among them, in step S1, the threshold screening method is used to eliminate invalid data in the point cloud; the PCL radius filtering technology is used to denoise the noise data in the point cloud; for the data missing problem in the continuous frame, the point cloud data of the next frame is used to fill the data to ensure the integrity and continuity of the time series data. The point cloud data of the left and right tracks are accurately calibrated and aligned to ensure that all subsequent related data are compared and analyzed under the same benchmark.

[0046] In the step S2, the size m of the sliding window is manually set, and a left / right track sliding window of corresponding length is constructed; the m consecutive point cloud data are queued; and the point cloud data of the sliding window is divided into two time periods, front and back, for subsequent point cloud frame difference calculation.

[0047] The step S3 includes the following steps: step S3.1: artificially set the Euclidean distance threshold threshold1; step S3.2: calculate the union cloudA of the first X frames of point cloud data of the sliding window, and construct a KD tree accordingly; step S3.3: calculate the union cloudB of the last mX frames of point cloud data of the sliding window, and for each point in cloudB, use the KDtree algorithm to quickly obtain its nearest point in cloudA, and if the Euclidean distance to the nearest point is greater than threshold1, store the point in the difference set of cloudB relative to cloudA. Step S3.4: construct a KDtree with cloudB, and construct the difference set of cloudA relative to cloudB in the manner of step S3.3. Step S3.5: perform a rough contour segmentation algorithm on the two difference sets, and use the one with the larger point cloud data volume as the frame difference point cloud data.

[0048] In step S4, the frame difference profile categories are manually set, which are divided into 6 categories: point rail close frame difference, point rail repulsive frame difference, guard rail frame difference, movable center rail frame difference, fixed center rail frame difference, and invalid frame difference; and the frame difference classification algorithm is used to perform profile classification.

[0049] Specifically, using the frame difference classification algorithm to perform silhouette classification includes:

[0050] The frame difference of the point rail mainly includes the close-fitting frame difference of the point rail and the repulsive frame difference of the point rail. Therefore, the frame difference of the aligned left and right rail point cloud data will be determined as the initial frame of the close-fitting and repulsive frame of the point rail only when it meets the characteristics of close-fitting and repulsive, and thus used for the subsequent measurement of the parameter calculation results at x meters behind the tip of the point rail.

[0051] For the point track repulsion frame difference, such as Figure 4 As shown in the figure, the frame difference data calculated by the Kdtree algorithm is the entire contour of the tip of the sharp rail. In order to identify the contour features of this part, the main direction of the point cloud is calculated with the help of the point cloud covariance matrix, and whether the characteristics of the sharp rail repulsion are met is determined based on the change in the main direction. The covariance matrix describes the data distribution of the point cloud, and is obtained by calculating the distance and direction relationship between each point in the point cloud and its surrounding K neighboring points. The calculation formula is as follows:

[0052]

[0053] where x ki Represents the information of the kth point in a set of point clouds in the i-th dimension, σ ij is the covariance between the i-th dimension and the j-th dimension in the point cloud group, and Σ is the 3*3 symmetric covariance matrix of the point cloud group.

[0054] By calculating the eigenvalues ​​and eigenvectors of the point cloud group covariance matrix, we can find the maximum eigenvalue λ max The corresponding eigenvector X max And as the main direction of the point cloud, calculate X max The angle α with the horizontal positive direction L.

[0055]

[0056] The source point cloud data corresponding to the frame difference are arranged in order along the x-axis, and then a predefined distance threshold is used to identify potential contour boundaries. When the lateral distance |x2-x1| between two adjacent points P1=(x1,y1,z1) and P2=(x2,y2,z2) on the x-axis exceeds the distance threshold, P1 and P2 are considered to be potential cutting points of the contour boundary and constitute the contour segmentation boundary set E={{P 1x ,P 2x},{P 3x ,P4x}...{P ix ,P jx}}, where P ix Indicates P i The x-coordinate value of the point.

[0057] If there is a certain index, the proportion of 0°<α<90° on the left side and the proportion of 180°>α>90° on the right side are both greater than 95% and the x-axis boundary of this part of the frame difference {P ix ,P jx}∈E and #E=2, it is considered to meet the characteristics of the sharp track repelling the initial frame.

[0058] For the frame difference of the point track close contact state, such as Figure 5 As shown, this part is the partial profile of the tip of the sharp rail. This is because the other side of the sharp rail tip is closely attached to the basic rail, so the single-line structured light cannot be illuminated and cannot be reconstructed in three dimensions. Therefore, the outline of the frame difference of the sharp rail closely attached shows a monotonically increasing or decreasing trend in the y-axis direction. That is, if the sharp rail is closely attached to the right rail, its frame difference outline shows a monotonically increasing trend in the y-axis direction. If the sharp rail is closely attached to the left rail, its frame difference outline shows a monotonically decreasing trend in the y-axis direction. In order to utilize this part of the features and not be affected by the noise data of the frame difference, the MK (Mann-Kendall) trend verification algorithm is used.

[0059] The MK trend check algorithm is a non-parametric test that does not require the sample to follow a certain distribution and is not disturbed by a few outliers. The algorithm mainly tests whether to reject the null hypothesis H0 and accept the alternative hypothesis H1. H0 means that there is no obvious trend in the sample data, and H1 means that there is a trend in the sample data. The point cloud frame difference data is sorted in the x-axis direction, and the difference function f(p iy ,p jy ), S value, S value variance and the final Z value of the MK algorithm.

[0060]

[0061] If for a given confidence level (significance level) α, Then the null hypothesis H0 is rejected, that is, at the confidence level α (significance test level), the point cloud frame difference data has an obvious upward or downward trend. MK A positive value indicates an upward trend, and a negative value indicates a decreasing trend.

[0062] In addition to judging the trend, the boundary of the frame difference must also be judged. tx ,P rx}, if the contour segmentation boundary set E = {{P 1x ,P2x},{P 3x ,P 4x}...{P ix ,P jx There exists a set of boundaries {P ix ,P jx}, satisfying P tx =P ix And P rx <P jx At the same time, the MK trend check result is an upward trend and #E=1 or satisfies P rx =P jx And P ix <P tx At the same time, if the MK trend check result is a downward trend and #E=1, it is considered to meet the characteristics of the point track being closely attached to the initial frame.

[0063] The linear structure of the grooved guardrail is an important criterion for judging the profile. Figure 6 As shown, this part uses the relative angle judgment mechanism to judge the frame difference. Sort the points in the frame difference data according to the x-axis, calculate the m points on the left and right sides of each index point, use the RANSAC algorithm to perform straight line fitting, and obtain the direction vector L of the straight line left With L right . Calculate the angle α between the two direction vectors and normalize it to the interval [0°, 90°].

[0064] If the case of 0°<α<2° accounts for the largest proportion in the entire angle distribution and the x-axis boundary of the frame difference {P tx ,P rx}∈E and #E=2. In addition, combined with the geometric characteristics that the guardrail is higher than the basic rail, if the y-value maximum point in the frame difference is also the y-value maximum point in the source point cloud, it is considered to meet the characteristics of the toe end of the grooved guardrail.

[0065] For the movable center rail frame difference, such as Figure 7 As shown in Figure 2. The frame difference contour judgment mechanism of this part is similar to the sharp rail close frame difference, and point cloud rematching is also required. The MK trend verification algorithm is used to judge the trend of the point cloud on the y-axis. For the x-axis boundary of the frame difference {P tx ,P rx}, if the contour segmentation boundary set E = {{P 1x ,P 2x},{P 3x ,P 4x}...{P ix ,P jx There exists a set of boundaries {P ix ,P jx}, satisfying P tx =P ixAnd P rx <P jx At the same time, the MK trend check result is an upward trend and #E=2 or satisfies P rx =P jx And P ix <P tx At the same time, if the MK trend check result is a downward trend and #E=2, it is considered to meet the characteristics of the movable center rail initial frame.

[0066] For a fixed center track frame difference, such as Figure 8 As shown. The frame difference profile judgment mechanism of this part is similar to the point track repulsion frame difference. The covariance matrix of the point cloud group is decomposed by eigenvalue to obtain the main direction of the point cloud and calculate the angle α with the horizontal direction of the x-axis. If the proportion of 0°<α<90° on the left side and 180°>α>90° on the right side of a certain index is greater than 95% and the x-axis boundary of this part of the frame difference {P ix ,P jx}∈E and #E=3, it is considered to meet the characteristics of the initial frame of the fixed center track.

[0067] Each determined frame difference needs to be checked for accuracy, that is, the current frame difference is calculated in a sliding window containing m frames of continuous point cloud data. In order to avoid the randomness of the frame difference, an accuracy check is required.

[0068] For the sliding window W = {P1, P2, P3, ... P n}, P i represents the i-th point cloud in the sliding window, and is also the dividing point of the data in the sliding window. That is, W1={P1,P2,P3...P i}, W2={P i+1 ,P i+2 ,P i+3 ...P n}and W=W1∪W2.

[0069] The position where the effective frame difference appears is P n or P i+1 , if the position of the frame difference is P n , then let W2={P i+1 ,P i+2 ,P i+3 ...P n-1 ,P n+1}, recalculate the difference set between W1 and W2, if the frame difference classification result does not change, it is considered to have passed the accuracy check. Similarly, if the position of the frame difference is P i+1 , then let W1={P1,P2,P3...P i-1}, recalculate the difference set of W1 and W2, if the frame difference classification result does not change, it is considered to have passed the accuracy check.

[0070] The above are the five ways to judge valid frame differences. If the current frame difference is judged as a valid frame difference, the classification result of the frame difference is set as the processing mark of the left / right track for subsequent processing of other point cloud data belonging to non-positioning keyframes. If the calculated frame difference does not meet the above five frame difference profiles, it is judged as an invalid frame difference.

[0071] In step S5, a Euclidean distance threshold threshold2 is set; based on threshold2, the KDtree algorithm is called again to calculate the point cloud frame difference; a contour coarse segmentation algorithm is performed on the two point cloud frame differences to perform secondary denoising on the point cloud frame difference, and the point cloud data with a larger amount of data is used as the frame difference point cloud data.

[0072] In the step S6, the diverging direction is determined with the help of prior information; the key frame is located; the corresponding feature points are extracted according to the type of the silhouette of the key frame; and the parameters are calculated according to the extracted feature points.

[0073] In step S7, if the current judgment is a forward divergence, the sliding window is directly updated; if the current judgment is a reverse divergence, the point cloud data in the left / right track waiting queue needs to be subjected to corresponding feature point extraction and parameter calculation, and the sliding window is updated.

[0074] In the step S10, after determining that the point cloud frame difference is an invalid frame difference, determine whether the current left / right track processing identifier is empty; if the left / right track processing identifier is empty, the current point cloud data cannot be directly used to determine the type of profile, and it will be added to the waiting queue of the left / right track; if the left / right track processing identifier is not empty, determine whether the current one is a sharp track close-fitting identifier.

[0075] In step S12, if the left / right rail processing mark is a sharp rail close-fitting mark, the point cloud rematching algorithm is executed to extract the sharp rail profile point cloud data; if the left / right rail processing mark is not a sharp rail close-fitting mark, the information of the non-key frame in the sliding window is extracted.

[0076] In the step 14, corresponding feature points are extracted according to the silhouette type of the non-positioned key frame; and parameters are calculated according to the extracted feature points.

[0077] Example 2

[0078] like Figures 1 to 11As shown, in this embodiment 2, a method for measuring the geometric shape and position parameters of a turnout is provided, which can calculate the key geometric parameters of the turnout area more simply, safely and accurately. This method uses spatiotemporal correlation to classify point cloud frame differences, and includes the following steps: Step S1: preprocessing the collected point cloud data of the left and right rail profiles of a specified model of turnout; Step S2: establishing a sliding window based on the left and right rails; Step S3: using the KDtree algorithm to calculate the coarse-grained frame difference; Step S4: classifying the frame difference profile obtained in step S3; Step S5: if the result of step S4 is a valid frame difference, recalculate the frame difference at a fine granularity; Step S6: extract positioning key frame information; Step S7: determine whether it is a forward turnout; Step S8: if it is currently a reverse turnout , then process the waiting queue of the left / right track; step S9: update the sliding window and execute step S3; step S10: if step S4 determines that the frame difference is invalid, then determine the left / right track processing mark; step S11: if the left / right track processing mark is empty, execute the point cloud queue operation and execute step S9; step S12: if the left / right track processing mark is not empty, determine whether it is a sharp track close-fitting mark; step S13: if the left / right track processing mark is a sharp track close-fitting mark, perform point cloud re-matching; step S14: extract non-positioning key frame information and execute step S9.

[0079] In this embodiment, the step S1 includes: step S1.1: using the threshold screening method to eliminate invalid data in the point cloud; step S1.2: using the PCL radius filtering technology to perform data denoising on the noise data in the point cloud; step S1.3: for the problem of missing data in continuous frames, the point cloud data of the next frame is used to fill the data to ensure the integrity and continuity of the time series data; step S1.4: performing precise position calibration and alignment processing on the point cloud data of the left and right tracks to ensure that all subsequent related data are compared and analyzed under the same benchmark.

[0080] In this embodiment, step S2 includes: step S2.1: manually setting the size m of the sliding window and constructing a left / right track sliding window of corresponding length; step S2.2: enqueuing m consecutive points of point cloud data; step S2.3: dividing the point cloud data of the sliding window into two parts, front and back, for subsequent point cloud frame difference calculation.

[0081] The step S3 includes: step S3.1: artificially set the Euclidean distance threshold threshold1; step S3.2: calculate the union cloudA of the first X frames of the sliding window point cloud data, and construct a KD tree accordingly; step S3.3: calculate the union cloudB of the last mX frames of the sliding window point cloud data, and for each point in cloudB, quickly obtain its nearest point in cloudA with the help of the KDtree algorithm. If the Euclidean distance to the nearest point is greater than threshold1, the point is stored in the difference set of cloudB relative to cloudA. Step S3.4: construct a KDtree with cloudB, and construct the difference set of cloudA relative to cloudB in the manner of step S3.3. Step S3.5: Since the obtained frame difference data may be noisy, the two difference sets are subjected to secondary denoising by the rough segmentation algorithm of the contour, and the one with a larger amount of point cloud data is used as the frame difference point cloud data. The core of the rough segmentation algorithm of the contour is to effectively identify and eliminate those noise points that may interfere with the correct classification of the frame difference contour, so as to improve the effectiveness of subsequent analysis. The algorithm performs detailed data processing in two dimensions, the X-axis and the Y-axis. First, the algorithm sorts the point cloud data according to the X-axis coordinates, and then uses a predefined distance threshold to identify potential contour boundaries. When the distance between two adjacent points exceeds this threshold, these points are considered potential cutting points of the contour boundary. Next, the algorithm will further evaluate the point cloud data within these candidate boundaries, and determine which boundaries are real and valid by checking the number of point clouds and the variance of the Y values. Only when the number of points reaches a certain threshold and the variance of the Y values ​​shows sufficient difference, these boundaries will be retained as part of the valid contour, and the remaining data that does not meet the conditions will be eliminated. In the Y-axis direction, the algorithm will repeat a similar process, namely sorting, boundary identification and data evaluation. This step is designed to further clean up the point cloud data and ensure that there is no noise interference in the vertical direction, thereby enhancing the purity of the data and the accuracy of subsequent analysis.

[0082] The step S4 includes: step S4.1: manually set the frame difference profile category, which is divided into 6 categories: point rail close frame difference, point rail repulsion frame difference, guard rail frame difference, movable center rail frame difference, fixed center rail frame difference, invalid frame difference, and the visualization results of the first 5 types of frame differences are shown in the attached figure. Step S4.2: Use the frame difference classification algorithm to perform profile classification. The profile classification algorithm is the same as the profile classification algorithm in Example 1, and will not be repeated here. If it is currently judged to be a valid frame difference, the classification result of the frame difference is set as the processing identifier of the left / right track for subsequent processing of other point cloud data belonging to non-positioning key frames.

[0083] The step S5 includes: step S5.1: Since there is an obvious change trend in the width at the beginning and end of the guardrail, if fine-grained frame difference calculation and profile classification are used at the beginning, it is easy to cause misjudgment of key frames. In order to improve the accuracy of profile classification, step S3 uses coarse-grained frame difference calculation. In order to make the feature point extraction after classification more accurate, this step uses fine-grained frame difference recalculation and sets the Euclidean distance threshold threshold2; step S5.2: based on threshold2, the KDtree algorithm is called again to calculate the point cloud frame difference; step S5.3: the profile coarse segmentation algorithm is executed on the two point cloud frame differences, and the point cloud frame difference is secondary denoised, and the point cloud data with a larger amount is used as the frame difference point cloud data.

[0084] The step S6 includes: step S6.1: determine the direction of divergence with the help of prior information. For the frame difference of the point rail or the center rail, if the frame difference appears in the first x frames, it is judged as reverse divergence, otherwise it is judged as forward divergence. For the guard rail frame difference, if the frame difference appears in the first x frames and the point rail has been visited, it is judged as the end of the forward divergence guard rail, and if the point rail has not been visited, it is the end of the reverse divergence guard rail; if the frame difference appears after mx frames and the point rail has been visited, it is judged as the beginning of the forward divergence guard rail, and if the point rail has not been visited, it is the beginning of the reverse divergence guard rail. Step S6.2: positioning of the key frame, for forward divergence, the key frame is located in the last frame of the sliding window, and for reverse divergence, the key frame is located in the xth frame of the sliding window; step S6.3: extract corresponding feature points according to the profile type of the positioned key frame, the main feature points include the basic rail vertex, the point rail vertex, the guard rail vertex, the gauge point, and the auxiliary point for calculating the wheel flange groove width; the visualization of some feature point extraction results is shown in the attached figure. Step S6.4: Parameters are calculated based on the extracted feature points. The main parameters include reduction value-point rail (the height difference between the vertex of the basic rail and the vertex of the point rail), reduction value-long center rail (the height difference between the vertex of the wing rail and the vertex of the center rail), reduction value-short center rail (the height difference between the vertex of the wing rail and the vertex of the center rail), flange groove width-point rail (the lateral distance between the point on the same horizontal line of the gauge point and the point rail profile), flange groove width-long center rail (the lateral distance between the point on the same horizontal line of the gauge point and the wing rail profile), flange groove width-guard rail (the lateral distance between the point on the same horizontal line of the gauge point and the guard rail profile), guard rail height difference (the height difference between the vertex of the guard rail and the vertex of the basic rail). The visualization of the parameter calculation method is shown in the attached figure.

[0085] The step S7 includes: step S7.1: if the current judgment is a forward divergence, directly update the sliding window; step S7.2: if the current judgment is a reverse divergence, it is necessary to perform corresponding feature point extraction and parameter calculation on the point cloud data in the left / right track waiting queue, and update the sliding window.

[0086] The step S10 includes: step S10.1: after determining that the point cloud frame difference is an invalid frame difference, determine whether the current left / right track processing identifier is empty; step S10.2: if the left / right track processing identifier is empty, the current point cloud data cannot be directly used to determine the type of contour, and it is added to the waiting queue of the left / right track; step S10.3: if the left / right track processing identifier is not empty, determine whether the current one is a sharp track close-fitting identifier.

[0087] The step S12 includes: step S12.1: if the left / right rail processing mark is a sharp rail close-fitting mark, execute the point cloud re-matching algorithm to extract the sharp rail profile point cloud data; step S12.2: if the left / right rail processing mark is not a sharp rail close-fitting mark, extract the information of non-key frames in the sliding window.

[0088] The step S13 includes: in the first frame where the switch rail is closely attached, the profile of the switch rail is obtained by calculating the fine-grained frame difference, and for all frames from the third frame where the switch rail is closely attached to the base rail before the switch rail is separated from the base rail, it is difficult to directly extract the profile data of the switch rail from the source point cloud data. For this reason, a rematching algorithm for the switch rail is proposed: step S13.1: for the switch rail profile obtained by fine-grained frame difference, a KDtree is constructed with the switch rail, and the source point cloud data of the frame where the switch rail is located is used to calculate the difference set about the switch rail, and the point cloud data of the base rail profile in the source point cloud data is obtained; step S13.2: Since the profile data of the switch section is collected at every 5mm section, the difference between two adjacent frames is weak. Therefore, the stock rail is used to approximate the base rail profile point cloud data of the second frame where the switch rail is closely attached. Construct a KDtree with stock rail, use the source point cloud data of the second frame with the point rail closely attached to calculate the difference set about stockrail, obtain the point rail profile data of the second frame with the point rail closely attached to, and update the basic rail point cloud data stock rail.

[0089] Taking the point cloud rematch of the point rail as an example, for the point rail profile obtained by fine-grained frame difference, a KDtree is constructed with this part, and the source point cloud data of the frame where the point rail is located is used to calculate the difference set about the point rail profile, and the point cloud data belonging to the basic rail profile in the source point cloud data is obtained. The contour of the point rail is changing with the increase of mileage, while the contour of the basic rail remains unchanged under ideal conditions. To this end, based on the feature that the basic rail contour remains unchanged, the ICP point cloud registration algorithm is performed on the point cloud data belonging to the basic rail part of the initial frame of the point rail and the xth frame of the point rail, and the objective function is as follows:

[0090]

[0091] Among them, q is the point cloud data set belonging to the basic track part of the initial frame of the sharp track, and p is the set of the nearest neighbor points of each point in q in the point cloud data of the xth frame of the sharp track. After multiple iterations, the rotation and translation matrix of q to the point cloud data of the xth frame of the sharp track is obtained, and the unmatched point set part in the xth frame of the sharp track is considered to be the sharp track profile, so as to obtain the corresponding feature points of the sharp track profile.

[0092] The step 14 comprises: step S14.1: extracting corresponding feature points according to the silhouette type of the non-positioned key frame; step S14.2: calculating parameters according to the extracted feature points.

[0093] In this embodiment, the proposed method is applied to the cross-sectional profile point cloud data of No. 18 single-opening turnout collected by the equipment, and the obtained parameter calculation results are compared with the results measured manually at designated points using tools such as a track ruler and a vernier caliper. The experimental results are shown in Tables 1, 2, 3, 4, 5, and 6, respectively.

[0094] Table 1 Measurement results of the point rail reduction value (unit: mm)

[0095]

[0096] Table 2 Measurement results of long center rail reduction value (unit: mm)

[0097]

[0098] Table 3 Measurement results of short center rail reduction value (unit: mm)

[0099]

[0100] Table 4 Measurement results of long center rail-wheel flange groove width (unit: mm)

[0101]

[0102] Table 5 Guardrail-wheel flange groove width measurement results (unit: mm)

[0103]

[0104] Table 6 Guardrail height difference measurement results (unit: mm)

[0105]

[0106]

[0107] After on-site measurement and comparison with manual measurement results, the key frame positioning accuracy of this method reached 99%, the average error of geometric parameter measurement was less than 0.3mm, and the detection speed reached 28.9 frames / second, meeting the real-time, high-precision and high-reliability engineering requirements.

[0108] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0109] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0110] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0111] These computer program instructions can also be loaded onto a computer or other programmable data processing device, and a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0112] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art without creative work on the basis of the technical solution disclosed in the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for measuring the geometric shape and position parameters of a turnout section, characterized in that: include: Pre-process the collected point cloud data of the left and right rail profiles of the specified model of turnout; A sliding window based on the left and right tracks is established, the coarse-grained frame difference is calculated using the KDtree algorithm, and the coarse-grained frame difference profile is classified; If the classification result is a valid frame difference, the frame difference is recalculated at a fine granularity; And extract key frame information based on the recalculated frame difference; determine the diverging direction based on the extracted key frame information; if the current diverging direction is reverse, process the waiting queue of the left / right track; And update the sliding window to calculate the coarse-grained frame difference; If the classification result is an invalid frame difference, the left / right track processing flag is judged; if the left / right track processing flag is empty, the point cloud enqueue operation is performed and the sliding window is updated; if the left / right track processing flag is not empty, it is determined whether it is a sharp track close-fitting flag; if the left / right track processing flag is a sharp track close-fitting flag, the point cloud is re-matched, non-key frame information is extracted, and the sliding window is updated.

2. The method for measuring the geometric shape and position parameters of a turnout section according to claim 1, characterized in that: The collected point cloud data of the left and right rail profiles of the specified model of turnout are preprocessed, including: using the threshold screening method to eliminate invalid data in the point cloud; using the PCL radius filtering technology to denoise the noise data in the point cloud; using the point cloud data of the next frame to fill in the data missing problems in continuous frames to ensure the integrity and continuity of the time series data; and performing precise position calibration and alignment processing on the point cloud data of the left and right rails to ensure that all subsequent related data are compared and analyzed under the same benchmark.

3. The method for measuring the geometric shape and position parameters of a turnout section according to claim 1, characterized in that: A sliding window based on the left and right tracks is established, including: setting the size m of the sliding window and constructing a left / right track sliding window of corresponding length; enqueuing m consecutive point cloud data; dividing the point cloud data of the sliding window into two time periods, front and back, for subsequent point cloud frame difference calculation.

4. The method for measuring the geometric shape and position parameters of a turnout section according to claim 1, characterized in that: The KDtree algorithm is used to calculate the coarse-grained frame difference, including: setting the Euclidean distance threshold threshold1; calculating the union cloudA of the first X frames of the sliding window point cloud data, and constructing a KD tree accordingly; calculating the union cloudB of the last mX frames of the sliding window point cloud data, for each point in cloudB, using the KDtree algorithm to obtain its nearest point in cloudA, if the Euclidean distance to the nearest point is greater than threshold1, the point is stored in the difference set of cloudB relative to cloudA; constructing a KDtree with cloudB, and constructing the difference set of cloudA relative to cloudB in the above manner; executing the contour coarse segmentation algorithm on the two difference sets, and using the one with a larger amount of point cloud data as the frame difference point cloud data.

5. The method for measuring the geometric shape and position parameters of a turnout section according to claim 1, characterized in that: The frame difference profile classification includes: setting 5 frame difference profile categories: point rail close frame difference, point rail repelling frame difference, guard rail frame difference, movable center rail frame difference, and fixed center rail frame difference; and using a frame difference classification algorithm to classify the profile.

6. The method for measuring the geometric shape and position parameters of a turnout section according to claim 1, characterized in that: Recalculate the frame difference in fine granularity, including: setting the Euclidean distance threshold threshold2; using threshold2 as a benchmark, calling the KDtree algorithm again to calculate the point cloud frame difference; performing a rough contour segmentation algorithm on the two point cloud frame differences, performing secondary denoising on the point cloud frame difference, and using the point cloud data with a larger amount as the frame difference point cloud data.

7. The method for measuring the geometric shape and position parameters of a turnout section according to claim 1, characterized in that: The key frame information extraction includes: judging the diverging direction with the help of prior information; positioning the key frame; extracting corresponding feature points according to the silhouette type of the key frame; and calculating parameters according to the extracted feature points.

8. The method for measuring the geometric shape and position parameters of a turnout section according to claim 1, characterized in that: If the current judgment is a forward divergence, the sliding window is directly updated; if the current judgment is a reverse divergence, the point cloud data in the left / right track waiting queue needs to be subjected to corresponding feature point extraction and parameter calculation, and the sliding window is updated.

9. The method for measuring the geometric shape and position parameters of a turnout section according to claim 1, characterized in that: After determining that the point cloud frame difference is an invalid frame difference, determine whether the current left / right track processing flag is empty; if the left / right track processing flag is empty, the current point cloud data cannot be directly judged for the type of profile, and it will be added to the waiting queue of the left / right track; If the left / right track processing flag is not empty, determine whether the current flag is a sharp track close-fitting flag.

10. The method for measuring the geometric shape and position parameters of a turnout section according to claim 1, characterized in that: If the left / right rail processing mark is a sharp rail close-fitting mark, the point cloud rematching algorithm is executed to extract the sharp rail profile point cloud data; if the left / right rail processing mark is not a sharp rail close-fitting mark, the information of the non-key frame in the sliding window is extracted.

Images