Method and system for segmenting segments of a shield tunnel

Abstract

The application discloses a shield tunnel segment division method and system, which is applied to the field of shield tunnels and comprises the following steps: obtaining original point cloud data of a shield tunnel and preprocessing the original point cloud data to obtain tunnel point cloud data; identifying each ring joint of the shield tunnel according to the tunnel point cloud data to obtain a fitting plane of the ring joint and target point cloud data of the ring joint; dividing the tunnel point cloud data into independent point cloud data of multiple segment rings of the shield tunnel according to the fitting planes of the ring joints; identifying a longitudinal joint of each segment ring according to the independent point cloud data of the segment ring to obtain longitudinal joint point cloud data of the segment ring; and segmenting the shield tunnel according to the target point cloud data of the ring joints and the longitudinal joint point cloud data of the segment rings to obtain multiple segment areas of the shield tunnel. The application can effectively improve the segment division precision of the shield tunnel.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of shield tunneling, in particular to a segment segmentation method and system for shield tunneling. BACKGROUND

[0002] A shield tunnel is a tunnel obtained by using a shield machine to perform tunnel excavation and lining work. The shield tunnel is usually sequentially connected by a plurality of segment rings. The segment ring is the main body of the lining of the shield tunnel and is assembled by prefabricated reinforced concrete segments. The segments include standard blocks, abutting blocks and capping blocks. A ring joint refers to a connecting joint between two adjacent segment rings. A longitudinal joint refers to a connecting joint between segments in a segment ring. In the related art, point cloud data of a shield tunnel is captured by using a laser radar scanning technology, and geometric information of each segment ring is extracted from the point cloud data of the shield tunnel. Then, segment segmentation is performed on the shield tunnel based on the geometric information of each segment ring, so that segment distribution information of the shield tunnel is obtained. The segment distribution information can be used to analyze the structure of the shield tunnel. However, the implementation of the related art relies on data fitting methods or spatial distance measurement methods, such as Hough transformation, region growing, random sample consensus and fast point feature histogram. This results in low processing efficiency and high spatial complexity of the related art when facing large-scale tunnel point cloud data. As a result, important point cloud features are lost, and the segment segmentation accuracy of the related art needs to be improved. SUMMARY

[0003] The present application provides a segment segmentation method and system for shield tunneling, which can improve the segment segmentation accuracy of the shield tunneling.

[0004] In one aspect, the present application provides a segment segmentation method for shield tunneling, which includes the following steps:

[0005] Obtaining original point cloud data of a shield tunnel and preprocessing the original point cloud data to obtain tunnel point cloud data;

[0006] For each ring joint of the shield tunnel, identifying the ring joint based on the tunnel point cloud data to obtain a fitting plane and target point cloud data of the ring joint;

[0007] Dividing the tunnel point cloud data into independent point cloud data of a plurality of segment rings of the shield tunnel according to the fitting planes of the ring joints;

[0008] For each longitudinal joint of the segment rings, identifying the longitudinal joint of the segment ring based on the independent point cloud data of the segment ring to obtain longitudinal joint point cloud data of the segment ring;

[0009] Segmenting the shield tunnel based on the target point cloud data of each ring joint and the longitudinal joint point cloud data of each segment ring to obtain a plurality of segment regions of the shield tunnel.

[0010] In another aspect, the embodiments of the present application provide a segment division system of a shield tunnel, comprising:

[0011] a point cloud scanning module, configured to obtain original point cloud data of the shield tunnel and perform preprocessing to obtain tunnel point cloud data;

[0012] a ring joint identification module, configured to identify each ring joint of the shield tunnel according to the tunnel point cloud data to obtain a fitting plane and target point cloud data of the ring joint;

[0013] a division processing module, configured to divide the tunnel point cloud data into independent point cloud data of a plurality of segment rings of the shield tunnel according to the fitting plane of each ring joint;

[0014] a longitudinal joint identification module, configured to identify a longitudinal joint of each segment ring according to the independent point cloud data of the segment ring to obtain longitudinal joint point cloud data of the segment ring;

[0015] a segment division module, configured to divide the shield tunnel into a plurality of segment regions according to the target point cloud data of each ring joint and the longitudinal joint point cloud data of each segment ring.

[0016] According to the segment division method and system of the shield tunnel, the original point cloud data of the shield tunnel is first obtained and preprocessed to obtain the tunnel point cloud data; then, each ring joint of the shield tunnel is identified according to the tunnel point cloud data to obtain the fitting plane and the target point cloud data of the ring joint; then, the tunnel point cloud data is divided into independent point cloud data of a plurality of segment rings of the shield tunnel according to the fitting plane of each ring joint; then, the longitudinal joint of each segment ring is identified according to the independent point cloud data of the segment ring to obtain the longitudinal joint point cloud data of the segment ring; finally, the shield tunnel is divided into a plurality of segment regions according to the target point cloud data of each ring joint and the longitudinal joint point cloud data of each segment ring. In this way, the processing efficiency and the spatial complexity can be improved when facing large-scale tunnel point cloud data, the influence of feature loss on segment division can be reduced, and the segment division accuracy of the shield tunnel can be improved. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 is a flowchart of the segment division method of the shield tunnel provided by the present application;

[0018] Figure 2 is a structure diagram of a three-dimensional column coordinate system provided by the present application;

[0019] Figure 3is a graph of the relationship between the radial distance and the cross-sectional width at different azimuth angles provided in the present application;

[0020] Figure 4 is a schematic diagram of the principle of ring seam identification provided in the present application;

[0021] Figure 5 is a schematic diagram of the principle of ring seam plane fitting provided in the present application;

[0022] Figure 6 is a structure development diagram of a pipe segment ring provided in the present application;

[0023] Figure 7 is a graph of the relationship between the azimuth angle and the radial distance provided in the present application;

[0024] Figure 8 is an effect example diagram of pipe segment segmentation provided in the present application. DETAILED DESCRIPTION

[0025] The present application will be further described below in conjunction with the accompanying drawings and specific embodiments. The described embodiments should not be regarded as limiting the present application, and all other embodiments obtained by those of ordinary skill in the art without making creative efforts fall within the scope of protection of the present application.

[0026] In view of the defects in the related art, the present application provides a pipe segment segmentation method and system for a shield tunnel, aiming to accurately extract relevant point clouds of ring seams and relevant point clouds of longitudinal seams from point cloud data of the shield tunnel, and then use the relevant point clouds of the ring seams and the relevant point clouds of the longitudinal seams to realize pipe segment segmentation of the shield tunnel, thereby improving the pipe segment segmentation accuracy of the shield tunnel.

[0027] It should be noted that the shield tunnel in the embodiments of the present application adopts single-layer flat slab type pipe segments for lining, and the outer diameter, inner diameter and ring width of the pipe segments can be flexibly set according to actual conditions; the line fitting and deviation correction adopt general double-face wedge control, and the wedge amount can be flexibly set according to actual conditions; for each pipe segment ring, the pipe segments are assembled in a block mode with staggered joints, i.e. each pipe segment ring includes a plurality of standard blocks, 2 adjacent blocks and 1 top block, the number of standard blocks is flexibly set according to actual conditions, and the pipe segments are connected with each other by a plurality of bent bolts; a plurality of bent bolts are used to connect between each pipe segment ring; the number of bent bolts is flexibly set according to actual conditions.

[0028] Firstly, the implementation steps of the pipe segment segmentation method for the shield tunnel provided in the present application will be described in detail below in conjunction with the accompanying drawings.

[0029] The segmentation method for shield tunnels provided in this application can be applied to terminals, servers, or software running on either terminal or server. Terminals can be tablets, laptops, desktop computers, etc., but are not limited to these. Servers can be independent physical servers, server clusters or distributed systems composed of multiple physical servers, or cloud servers providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms. Furthermore, a server can also be a node server in a blockchain network, but is not limited to this. Blockchain is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms.

[0030] Reference Figure 1 , Figure 1 This is a flowchart of the segment segmentation method for shield tunnels provided in this application, which may include the following steps S101-S105.

[0031] S101: Obtain the raw point cloud data of the shield tunnel and perform preprocessing to obtain the tunnel point cloud data.

[0032] In this step, firstly, a three-dimensional laser scan is performed on the interior of the shield tunnel to obtain the raw point cloud data of the shield tunnel; then, the raw point cloud data of the shield tunnel is preprocessed to improve the accuracy of the point cloud data, thereby obtaining the tunnel point cloud data, so that the circumferential joint identification and longitudinal joint identification of the shield tunnel can be realized in subsequent steps.

[0033] S102, for each annular joint of the shield tunnel, the annular joint is identified based on the tunnel point cloud data to obtain the fitting plane and target point cloud data of the annular joint.

[0034] In this step, circumferential joint identification is performed on the shield tunnel. A circumferential joint refers to the connecting joint between different tunnel segment rings. Specifically, circumferential joint identification involves using tunnel point cloud data to identify each circumferential joint, obtaining a fitting plane and target point cloud data for each joint. The fitting plane refers to the plane containing the circumferential joint, used for longitudinal joint identification and tunnel point cloud data segmentation. The target point cloud data refers to point cloud data correlated with the height of the circumferential joint, indicating its distribution within the shield tunnel. This target point cloud data is used for segmentation.

[0035] S103, based on the fitting plane of each annular joint, divides the tunnel point cloud data into independent point cloud data of multiple segment rings of the shield tunnel.

[0036] In this step, since the longitudinal joint of the shield tunnel refers to the connecting joint between the segments in a single segment ring, before the longitudinal joint recognition is realized, the tunnel point cloud data needs to be divided into independent point cloud data of multiple segment rings, so as to realize the longitudinal joint recognition of a single segment ring in the subsequent steps, and improve the accuracy of the longitudinal joint recognition. Specifically, the tunnel point cloud data is divided by using the fitting plane of the girth joint obtained in the foregoing step. The fitting plane of the girth joint can indicate the plane where the girth joint is located, so that the independent point cloud data of multiple segment rings can be accurately divided. The independent point cloud data of the segment ring refers to the point cloud data highly related to the segment ring.

[0037] S104, for the longitudinal joint of each segment ring, the longitudinal joint of the segment ring is recognized according to the independent point cloud data of the segment ring, and the longitudinal joint point cloud data of the segment ring is obtained.

[0038] In this step, the longitudinal joint of the shield tunnel is recognized. The longitudinal joint of the segment ring refers to the connecting joint between the segments in the segment ring. Since the segment ring is composed of multiple segments, the segment ring has multiple longitudinal joints. The longitudinal joint recognition specifically refers to recognizing the longitudinal joint of each segment ring by using the independent point cloud data of each segment ring, and obtaining the longitudinal joint point cloud data of each segment ring. The longitudinal joint point cloud data of the segment ring is highly related to the longitudinal joint of the segment ring, and the longitudinal joint point cloud data of each segment ring indicates the distribution of the longitudinal joint of each segment ring in the shield tunnel. The longitudinal joint point cloud data of each segment ring is used for segment segmentation.

[0039] S105, according to the target point cloud data of each girth joint and the longitudinal joint point cloud data of each segment ring, the segment of the shield tunnel is segmented, and multiple segment regions of the shield tunnel are obtained.

[0040] In this step, the target point cloud data of each girth joint obtained in the foregoing step is used to indicate the distribution of each girth joint in the shield tunnel, and the longitudinal joint point cloud data of each segment ring obtained in the foregoing step is used to indicate the distribution of each longitudinal joint in the shield tunnel. According to the distribution of each girth joint in the shield tunnel and the distribution of each longitudinal joint in the shield tunnel, the multiple segments of the shield tunnel are segmented, and multiple segment regions of the shield tunnel are obtained. The multiple segment regions of the shield tunnel can be understood as the segment distribution information of the shield tunnel, which is used to indicate the distribution of each segment in the shield tunnel.

[0041] Therefore, the embodiment of the application first performs ring joint identification and longitudinal joint identification on the shield tunnel based on point cloud data of the shield tunnel, so as to fully mine the distribution and morphological characteristics of the ring joint and the longitudinal joint in the shield tunnel, thereby obtaining point cloud data related to the height of the ring joint and point cloud data related to the height of the longitudinal joint, and then using the point cloud data related to the height of the ring joint and the point cloud data related to the height of the longitudinal joint to realize segmenting of the segments of the shield tunnel. In this way, the processing efficiency when facing large-scale tunnel point cloud data can be effectively improved and the spatial complexity can be reduced, and the influence of feature loss on segmenting of the segments can be effectively reduced, thereby improving the segmenting accuracy of the segments of the shield tunnel.

[0042] In some embodiments, the implementation process of obtaining the original point cloud data of the shield tunnel and preprocessing to obtain the tunnel point cloud data in the above step S101 can include the following steps:

[0043] The inside of the shield tunnel is scanned by a plurality of preset stations to obtain station point cloud data of the plurality of stations;

[0044] The station point cloud data of the plurality of stations is spliced to obtain the original point cloud data of the shield tunnel;

[0045] The original point cloud data is denoised to obtain denoised original point cloud data;

[0046] The denoised original point cloud data is converted from a Cartesian coordinate system to a three-dimensional cylindrical coordinate system to obtain the tunnel point cloud data.

[0047] In the embodiment, since the shield tunnel has the characteristics of long and narrow structure and non-obvious feature surface, and the three-dimensional laser scanner can only ensure to scan high-quality point cloud data within a short distance, before scanning the shield tunnel, a reasonable station spacing is selected and a corresponding scanning mode is set in the inside of the shield tunnel. Specifically, a plurality of stations are pre-set along the axial direction of the shield tunnel, and the inside of the shield tunnel is scanned by continuously setting the three-dimensional laser scanner at the stations to obtain station point cloud data of the plurality of stations. Optionally, the distance between the two adjacent stations, the model of the three-dimensional laser scanner of each station, the scanner resolution of the three-dimensional laser scanner of each station, and the coordinate control point of each station can be flexibly set according to actual conditions. After obtaining the station point cloud data of each station, the station point cloud data of all stations is spliced to accurately obtain the original point cloud data for describing the internal structure of the shield tunnel. For example, the point cloud station splicing is performed by using the Leica Cyclone software matched with the three-dimensional laser scanner, thereby obtaining the original point cloud data of the shield tunnel.

[0048] Since there are a large number of noise point cloud data in the original point cloud data, the noise point cloud data usually includes point cloud data associated with pedestrians, point cloud data associated with tunnel construction equipment, and point cloud data associated with the inverted arch backfill layer of the shield tunnel, etc., therefore, in order to ensure the accuracy of the point cloud data, it is necessary to perform denoising processing on the original point cloud data to remove the noise point cloud data in the original point cloud data, thereby obtaining the original point cloud data after denoising, so as to improve the accuracy of the original point cloud data, thereby ensuring the accuracy of the subsequent ring seam identification and longitudinal seam identification. It can be understood that each point in the original point cloud data after denoising is in the Cartesian coordinate system, and the coordinates of each point in the original point cloud data after denoising are expressed as .

[0049] After completing the noise point cloud removal processing, in order to facilitate the implementation of ring seam identification, it is necessary to convert each point in the original point cloud data after denoising from the Cartesian coordinate system to the three-dimensional cylindrical coordinate system to obtain tunnel point cloud data, so as to improve the accuracy of the original point cloud data, thereby ensuring the accuracy of the subsequent ring seam identification and longitudinal seam identification. Wherein, each point in the tunnel point cloud data is located in the three-dimensional cylindrical coordinate system, and the coordinates of each point in the tunnel point cloud data are expressed as , As shown in Figure 2 , represents the rotation angle of the projection point of any point in the tunnel point cloud data on the XOY plane relative to the positive direction of the axis, which is referred to as the azimuth angle in the embodiment of the application; represents the distance between the projection point of any point in the tunnel point cloud data on the XOY plane and the coordinate origin O , which can be understood as the measured radius of any point in the tunnel point cloud data relative to the axis, which is referred to as the radial distance in the embodiment of the application; the meaning of in the three-dimensional cylindrical coordinate system is the same as that of in the Cartesian coordinate system, which is referred to as the axial distance in the embodiment of the application. In addition, the conversion relationship between the Cartesian coordinate system and the three-dimensional cylindrical coordinate system satisfies the formula (1) as follows:

[0050] (1).

[0051] In some embodiments, in the step S102, the implementation process of identifying the ring seam according to the tunnel point cloud data to obtain the fitting plane of the ring seam and the target point cloud data mainly includes the following steps S1021-S1024.

[0052] S1021. Based on the axial direction, number of rings, and segment width of the shield tunnel, and combined with the preset cross-sectional width, the point cloud data associated with the ring joint is extracted from the tunnel point cloud data as the ring joint cross-sectional point cloud data.

[0053] In this step, firstly, along the three-dimensional cylindrical coordinate system... The axial direction is selected to roughly define the area where the annular joint is located; that is, along the axial direction of the shield tunnel, a pre-defined cross-sectional area of ​​a certain width is intercepted near the annular joint as the identification area of ​​the annular joint. It can be understood that the axial direction of the shield tunnel refers to the direction of the shield tunnel in a three-dimensional cylindrical coordinate system. Axial direction; then, from the tunnel point cloud data, the point cloud data of the identification area of ​​the ring joint is selected as the point cloud data associated with the ring joint, that is, the point cloud data of the ring joint section, so as to improve the accuracy and efficiency of subsequent ring joint identification. It should be noted that the point set of the ring joint section point cloud data refers to the set of points in the ring joint section point cloud data. Since the ring joint is the connecting joint between the segment rings, the point set mainly includes the ring joint points and their adjacent segment points. That is, the ring joint section point cloud data includes multiple initial ring joint point cloud data and multiple segment point cloud data. The initial ring joint point cloud data refers to the point cloud data that is moderately related to the ring joint, and the segment point cloud data refers to the point cloud data that is related to the segment height. Among them, the point set of the ring joint section point cloud data satisfies the following formula (2):

[0054] , (2);

[0055] In equation (2), This indicates the width of the tunnel segments in a shield tunnel. It refers to the width of a single segment ring, which can be pre-defined according to actual conditions. This indicates the preset cross-sectional width, which can be flexibly set according to the actual situation; This represents the axial distance between each point on the circumferential joint section in the point cloud data of the circumferential joint section. This indicates the number of rings in a shield tunnel, which refers to the total number of segment rings.

[0056] S1022, the segment point cloud data in the circumferential joint section point cloud data is removed to obtain the initial circumferential joint point cloud data.

[0057] In this step, since this embodiment aims to extract point cloud data related to the circumferential joint height from the circumferential joint cross-section point cloud data, the segment point cloud data in the circumferential joint cross-section point cloud data is useless point cloud data. This useless point cloud data should be removed before circumferential joint identification to improve the accuracy and efficiency of subsequent circumferential joint identification. Specifically, by removing the segment point cloud data from the circumferential joint cross-section point cloud data, initial circumferential joint point cloud data can be obtained.

[0058] S1023, feature point recognition processing is performed on the ring joint according to the initial ring joint point cloud data, to obtain an average width value of the ring joint and a plurality of feature points.

[0059] S1024, plane fitting processing is performed on the ring joint according to the average width value and the plurality of feature points, to obtain a fitting plane of the ring joint and target point cloud data.

[0060] In the above steps, according to the prior shield tunnel point cloud image, the initial ring joint point cloud data along the cross-sectional ring distribution of the shield tunnel can be regarded as the intersection of a certain thickness plane and the tunnel point cloud data. Based on this idea, the ring joint recognition can be converted into solving the plane parameters of the initial ring joint point cloud data. Among them, solving the plane parameters of the initial ring joint point cloud data mainly includes feature point extraction and plane fitting. Specifically, in the process of feature point extraction, the initial ring joint point cloud data obtained in the foregoing steps is used to identify the feature points associated with the ring joint, so as to obtain a plurality of feature points of the ring joint, and then the average width value of the ring joint is obtained by using the plurality of feature points of the ring joint, wherein the plurality of feature points of the ring joint jointly constitute the morphological features of the ring joint; and the average width value of the ring joint is used to indicate the width feature of the ring joint, which is mainly obtained by processing the plurality of feature points of the ring joint. In the process of plane fitting, the average width value and the plurality of feature points obtained in the foregoing steps are used to perform plane fitting on the ring joint, aiming to determine the plane where the ring joint is located, i.e., the fitting plane of the ring joint, and determine the point cloud data related to the height of the ring joint, i.e., the target point cloud data of the ring joint, so as to realize the ring joint recognition. In this way, by converting the ring joint recognition into solving the plane parameters of the initial ring joint point cloud data, the accuracy of the ring joint recognition can be effectively improved, and a better ring joint recognition effect can be achieved.

[0061] In some embodiments, in the ring joint cross-sectional point cloud data, the point cloud data at positions The point cloud data in the range of is selected, and a first two-dimensional coordinate system is constructed with the cross-sectional width as the horizontal axis and the radial distance as the vertical axis, and then the selected point cloud data under the first two-dimensional coordinate system is plotted, as shown in Figure 3 From Figure 3 it can be seen that the radial distance of the point cloud data at different positions increases obviously at the position close to the midpoint of the cross-sectional width, and has a certain width of irregular sharp angle, and the points densely distributed outside the sharp angle have very small vertical coordinate changes, which are approximately linearly distributed. As can be seen from the above, among the point cloud data at the same position, the points with obvious vertical coordinate changes are the initial ring joint points, and the points which are relatively smooth and approximately linearly distributed along the cross-sectional width direction are the segment points. According to Figure 3The geometric relationship between the initial circumferential joint point and the segment point is shown in this embodiment. This embodiment provides a segment point cloud extraction method based on the Hough transform line detection method. In this method, the mapping rule based on the Hough transform parameter space is applied to the line detection of the circumferential joint section point cloud data with the form of discrete point cloud.

[0062] Specifically, in step S1022 above, the process of removing segment point cloud data from the circumferential joint cross-section point cloud data to obtain the initial circumferential joint point cloud data mainly includes the following steps S01-S04.

[0063] S01, the Hough transform line detection method is used to perform line detection processing on the circumferential joint section point cloud data, and the line associated with the segment point cloud data in the circumferential joint section point cloud data is used as the first line.

[0064] In this step, for ease of understanding, the following will be explained: Figure 3 The horizontal axis of the first two-dimensional coordinate system shown (i.e., the width of the cross section) Named The axis, and its longitudinal axis (i.e., radial distance) Named Axis, then as Figure 3 The first two-dimensional coordinate system shown can be named Coordinate system. If In order to be in The first point cloud data of the circumferential joint section in the coordinate system The coordinates of the points on the circumferential joint section are then passed through the point Countless straight lines can be expressed as cosine curves in Hough space. The set of cosine curves mapped from the point cloud data of the circumferential joint section to the Hough space is represented as follows: , Here are the parameters of the Hough space. This represents the total number of points on the circumferential joint section in the point cloud data of the circumferential joint section. It can be understood that points on the circumferential joint section refer to the points in the point cloud data of the circumferential joint section. If the intersection points of the curves in the cosine curve set are... If the point cloud data of the circumferential joint section is obtained in Hough space, the set of intersection point coordinates satisfies the following formula (3), and this set of intersection point coordinates can be understood as the Hough space parameter set of the point cloud data of the circumferential joint section:

[0065] , (3);

[0066] In equation (3), Indicates the first The Hough space parameters at the intersection points include the axial angle parameters. Distance parameter from origin Equation (3) shows that the number of straight lines detected based on Hough transform in the point cloud data of the circumferential joint section is... However, the purpose of this step is to eliminate segment point cloud data from the circumferential joint section point cloud data through straight line detection. Which of these straight lines is most relevant to the segment point cloud data still needs to be further determined. Therefore, certain constraints need to be added to determine the optimal straight line.

[0067] Based on this, this step proposes an improved Hough transform line detection method to determine the optimal line associated with the segment point cloud data, thereby improving the efficiency and accuracy of line detection. Its implementation process may include the following steps S011-S013.

[0068] S011, Determine the possible parameter values ​​of the segment point cloud data in Hough space. And select the range of values ​​for the point cloud data of the pipe segment from the possible parameter values.

[0069] Specifically, firstly, the origin distance parameters of multiple circumferential joint cross-section points in the point cloud data of the circumferential joint cross-section are obtained as a distance set. It is understandable that the circumferential joint section point refers to a point in the circumferential joint section point cloud data, and the origin distance parameter of the circumferential joint section point refers to... The distance between the points on the circumferential joint section and the origin of the coordinate system. Simultaneously, the axial angle parameters of multiple circumferential joint section points in the point cloud data of the circumferential joint section are obtained as an angle set. The axial included angle parameter of the circumferential joint section point refers to the angle parameter at the circumferential joint section point The line segment connecting the cross-section point of the circumferential joint and the origin of the coordinate system is relative to the coordinate system. The angle between the positive axes. Wherein, through the distance set... and included angle set We can obtain the initial Hough space parameter set and distance set. and included angle set It can be expressed as the following formula (4):

[0070] , (4);

[0071] In equation (4), Indicates in The first coordinate system The coordinates of the cross-section points of the circumferential joint express The origin of the coordinate system. In order to be in The minimum value among the ordinates of all points on the circumferential joint section in the coordinate system. In order to be in The minimum value among the x-coordinates of all points on the circumferential joint section in the coordinate system.

[0072] Then, based on the distribution characteristics of the segment point cloud data, the distance set... The range of values ​​is narrowed to The distance set obtained after the range is reduced is used as the distance set. At the same time, the included angle set The range of values ​​for is narrowed to The angle set obtained after narrowing the range is called the angle set. Then based on the distance set The range of values ​​and the set of included angles The value range is selected from the point cloud data of the circumferential joint section as a two-dimensional point set, which can be represented as: , ,in Represents the first point in a two-dimensional point set. Two-dimensional points in Coordinates in a coordinate system; This represents the total number of points in a two-dimensional point set.

[0073] S012, based on the distance set and included angle set This yields the Hough space parameter set for multiple uniform intervals. Specifically, the distance set... and included angle set Divided into from smallest to largest as follows: , A uniform interval, that is, dividing the Hough space into 3 uniform intervals. A grid, thus obtaining The Hough space parameter set of a uniform interval and All parameters can be flexibly set according to the actual situation. The Hough space parameter set of each uniform interval includes multiple origin distance parameters and axial angle parameters located within the uniform interval. Among them, the Hough space parameter set of each uniform interval can be expressed as the following formula (5):

[0074] (5);

[0075] In equation (5), , , , ; To fall into the included angle set at the same time The intervals and distance sets The The parameter set of each interval, i.e., the set of included angles. The intervals and distance sets The The Hough space parameter set of a uniform interval consisting of several intervals; is the minimum value in the angle set , is the maximum value in the angle set ; is the minimum value in the distance set , is the maximum value in the distance set ; is the normalized parameter of the angle set , is the normalized parameter of the distance set .

[0076] S013, since the number of points in the discrete point cloud is huge, it is difficult to select an optimal line parameter from numerous parameters mapped to the Hough space. In this regard, according to the principle of the Hough transform, it is considered to determine the optimal line parameter in the form of voting, that is, according to the Hough space parameter set of the uniform interval, the Hough space parameter set of the annular seam cross-section point cloud data and the preset accumulator, the line associated with the pipe piece point cloud data in the annular seam cross-section point cloud data is obtained as the first line.

[0077] Specifically, first, a two-dimensional matrix of is obtained as the accumulator , the initial value of each element in the accumulator is 0, and each element corresponds to the Hough space parameter set of each uniform interval. Then, each cross-section point in the Hough space parameter set of the annular seam cross-section point cloud data as shown in the above formula (3) is traversed, that is, , if the Hough space parameter of the cross-section point in the Hough space parameter set of the annular seam cross-section point cloud data belongs to the Hough space parameter set of any uniform interval, the value of the element in the accumulator corresponding to the Hough space parameter set of the uniform interval to which the Hough space parameter of the cross-section point belongs is increased by 1. For example, if , the element in the accumulator is increased by 1. The final obtained accumulator reflects the parameter distribution of lines. Obviously, the Hough space parameter set corresponding to the position of the maximum element in the accumulator is the optimal line parameter obtained. Therefore, after obtaining the final accumulator , the accumulator ​The element with the largest median value is determined as the target element. The average of the upper and lower bounds of the Hough space parameter set corresponding to the target element is taken as the average of the uniform intervals within which it resides, resulting in the target Hough space parameter set for the target element. Finally, the target Hough space parameter set of the target element is converted into corresponding linear parameters. Based on these linear parameters, a straight line is constructed that is associated with the segment point cloud data in the circumferential joint section point cloud data, serving as the first straight line. For example, when the accumulator... medium elements When the value is at its maximum, then the element is... Element taking from the corresponding Hough space parameter set The average of the upper and lower bounds of the uniform interval is used to obtain the element. Target Hough space parameter set Target Hough space parameter set Including elements Target axial angle parameters and elements Target origin distance parameter As shown in the following formula (6):

[0078] (6).

[0079] Further simplifying the above formula (6), we can obtain the following formula (7):

[0080] (7).

[0081] elements Target Hough space parameter set Convert to linear parameters Formula (8) is as follows:

[0082] , (8);

[0083] In equation (8), Indicates in The slope of the straight line detected in the coordinate system. Indicates in The line intercept detected in the coordinate system. Based on the slope and line intercept shown in formula (8), a system is constructed... The first straight line in the coordinate system. For ease of understanding, in... The first straight line in the coordinate system can be represented as .

[0084] The specific implementation process of the above step S01 can effectively improve the efficiency and accuracy of line detection and enhance the accuracy of the optimal line associated with the segment point cloud data.

[0085] S02, based on the first straight line, the segment point cloud data in the circumferential joint section point cloud data is removed to obtain the remaining section point cloud data.

[0086] In this step, each 2D point in the 2D point set is traversed. If the distance from a 2D point to the first straight line is less than a preset distance threshold (which can be flexibly set according to actual conditions), then the 2D point is considered a segment point and is removed. Otherwise, the 2D point is not a segment point and is retained. After traversing all 2D points in the 2D point set, the remaining 2D points in the set are output as the remaining cross-sectional point cloud data. This process removes shallow segment point clouds. The remaining cross-sectional point cloud data can be represented as... , , This represents the total number of remaining two-dimensional points in the two-dimensional point set. Furthermore, the distance from each two-dimensional point to the first straight line satisfies the following formula (9):

[0087] (9);

[0088] In equation (9), ; Indicates the first From a two-dimensional point to the first straight line The distance; Represents the first point in a two-dimensional point set. Two-dimensional points in Coordinates in a coordinate system.

[0089] S03, the Hough transform line detection method is used to perform line detection processing on the remaining cross section point cloud data to obtain the line associated with the segment point cloud data in the remaining cross section point cloud data as the second line.

[0090] In this step, if the point clouds of the segments on both sides of the circumferential joint are detected as the same straight line, meaning there is essentially no misalignment between the point clouds of the segments on both sides, then this process can completely separate the segment point cloud data from the initial circumferential joint point cloud data. However, in the actual acquired point cloud data of the circumferential joint section, in most cases the point cloud is... In-plane distribution pattern as follows Figure 4 As shown, the segments on both sides of the circumferential joint are not on the same straight line. To address this, this step uses the Hough transform line detection method to perform a second line detection on the remaining cross-sectional point cloud data, so as to further eliminate the segment point cloud data, thereby ensuring that all segment point cloud data are eliminated. Specifically, the Hough space parameter set of the remaining cross-sectional point cloud data is obtained according to the above formula (3) as the new Hough space parameter set of the circumferential joint cross-sectional point cloud data, and then the accumulator... All elements in the equation are set to 0, and step S013 is executed once to generate a new first line as the second line.

[0091] S04, performing a rejection processing on the pipe segment point cloud data in the remaining cross-section point cloud data according to the second straight line, to obtain initial girth joint point cloud data.

[0092] In this step, after completing the second straight line detection, each remaining two-dimensional point in the remaining cross-section point cloud data is traversed again. If the distance from the remaining two-dimensional point to the second straight line is less than a preset distance threshold, it is indicated that the remaining two-dimensional point is a pipe segment point, and the remaining two-dimensional point is rejected at this time. Otherwise, it is indicated that the remaining two-dimensional point is not a pipe segment point, and the remaining two-dimensional point is retained at this time. After traversing all two-dimensional points in the remaining cross-section point cloud data, the remaining two-dimensional points in the remaining cross-section point cloud data are output as initial girth joint point cloud data, so that the deep pipe segment point cloud can be rejected, and the rejection efficiency and rejection accuracy of the pipe segment point cloud data can be improved. The initial girth joint point cloud data is represented as , and the total number of initial girth joint points in the initial girth joint point cloud data is represented as N. It can be understood that the distance from the two-dimensional point to the second straight line can be calculated by the above formula (9), and details are not described herein.

[0093] In some embodiments, in the step S1023, the feature point recognition processing is performed on the initial girth joint point cloud data to obtain the average width value of the girth joint and a plurality of feature points, and the implementation process mainly includes the following steps S11-S14:

[0094] S11, obtaining a plurality of first feature points of the girth joint in the three-dimensional cylindrical coordinate system according to the maximum value of the radial distance of all initial girth joint points in the initial girth joint point cloud data;

[0095] S12, obtaining a plurality of second feature points of the girth joint in the three-dimensional cylindrical coordinate system according to the median of the radial distance of all initial girth joint points in the initial girth joint point cloud data;

[0096] S13, converting the plurality of first feature points and the plurality of second feature points from the three-dimensional cylindrical coordinate system to the three-dimensional rectangular coordinate system to obtain a plurality of converted first feature points and a plurality of converted second feature points as a plurality of feature points of the girth joint;

[0097] S14, obtaining the average width value of the girth joint according to the plurality of feature points of the girth joint.

[0098] In this embodiment, with reference to Figure 4 , the initial girth joint point cloud data and the pipe segment point cloud data are in ​​In a coordinate system, there are generally two scenarios. The first scenario shows the area closer to the 3D laser scanner, where the laser beam can fully penetrate the width of the circumferential gap, and the radial distance of the initial circumferential gap point cloud data is significantly greater than that of the segment point cloud data. The second scenario shows the location farther from the 3D laser scanner, where, due to the scanning angle, the laser beam cannot penetrate the width of the circumferential gap, resulting in the radial distance of the initial circumferential gap point cloud data falling between that of the segment point cloud data on both sides.

[0099] For the two different types of initial annular seam point cloud data, this embodiment uses two different methods to determine the feature points and coordinates of the annular seam. The first type of initial annular seam point cloud data is often a pointed point cloud with a certain width. Therefore, for the first type of initial annular seam point cloud data, each initial annular seam point in the first type of initial annular seam point cloud data is first taken as the first feature point of the annular seam. Then, the radial distance of all initial annular seam points in the initial annular seam point cloud data is calculated. The maximum value is used as the first feature point The axis coordinates are used to obtain multiple first feature points of the circumferential joint and their coordinates in a three-dimensional cylindrical coordinate system. The initial circumferential joint point cloud data of the second type transitions gently between the segment point cloud data on both sides. Therefore, for the initial circumferential joint point cloud data of the second type, each initial circumferential joint point in the initial circumferential joint point cloud data of the second type is first used as the second feature point of the circumferential joint. Then, the radial distances of all initial circumferential joint points in the initial circumferential joint point cloud data are calculated. The median is used as the second feature point The coordinates of the axes can be used to obtain multiple second feature points of the annular seam and their coordinates in the three-dimensional cylindrical coordinate system. Thus, by fully considering the morphological features of the initial annular seam point cloud data, accurately extracting multiple first feature points and multiple second feature points from the initial annular seam point cloud data and determining the coordinates of the first and second feature points in the three-dimensional cylindrical coordinate system can effectively improve the feature point extraction accuracy. The coordinate set of the first feature points and the coordinate set of the second feature points can be expressed as the following formula (10):

[0100] ,

[0101] (10);

[0102] In equation (10), This represents the coordinate set of the first feature points, which includes the coordinates of multiple first feature points in a three-dimensional cylindrical coordinate system. Represents the radial distance of all initial circumferential joint points in the initial circumferential joint point cloud data. The maximum value; Indicates the first The coordinates of the first feature point in the three-dimensional cylindrical coordinate system; a total number of points of the initial girth point cloud data in the first form; a coordinate set of the second feature points, including coordinates of the plurality of second feature points in the three-dimensional cylindrical coordinate system; a median of radial distances of all initial girth points in the initial girth point cloud data ; a coordinate of the th second feature point in the three-dimensional cylindrical coordinate system; , a total number of points of the initial girth point cloud data in the second form.

[0103] Then, for the purpose of directly performing plane fitting and identifying target girth point cloud data in the point cloud data, the plurality of first feature points and the plurality of second feature points are converted from the three-dimensional cylindrical coordinate system to a three-dimensional rectangular coordinate system, so as to obtain a plurality of converted first feature points and a plurality of converted second feature points as a plurality of feature points of the girth, as shown in the following formula (11):

[0104] (11);

[0105] In formula (11), denotes coordinates of the feature points of the girth in the three-dimensional rectangular coordinate system; denotes coordinates of the first feature points and the second feature points of the girth in the three-dimensional cylindrical coordinate system.

[0106] Finally, according to the plurality of feature points and the coordinates thereof, an average width value of the girth can be obtained for subsequent plane fitting processing, so as to ensure the accuracy of the plane fitting, and the average width value of the girth is shown in the following formula (12):

[0107] (12);

[0108] In formula (12), denotes the average width value of the girth; denotes an axis coordinate of the th feature point in the three-dimensional rectangular coordinate system, .

[0109] In some embodiments, the process of performing plane fitting processing on the girth according to the average width value and the plurality of feature points to obtain a fitting plane of the girth and target point cloud data in step S1024 can include the following steps S21-S23.

[0110] S21, selecting a plurality of feature points at a preset azimuth angle from the plurality of feature points as to-be-fitted feature points.

[0111] ​It should be noted that the feature points to be fitted refer to the feature points at the preset azimuth angle.

[0112] In this step, feature points at a preset azimuth angle are obtained as feature points to be fitted. These feature points at the preset azimuth angle can fully reflect the distribution of the annular joints in the shield tunnel. It can be understood that the feature points to be fitted are the objects of planar fitting processing.

[0113] Optionally, the preset azimuth angle can be set according to actual conditions, and this embodiment does not specifically limit it. For example, the preset azimuth angle is... However, it is not limited to this.

[0114] S22, the M-estimation sample consistency method is used to perform plane fitting on the feature points to be fitted, and the fitting plane of the circumferential seam is obtained.

[0115] In this step, refer to Figure 5 Several feature points are fitted to a plane. The intersection of the fitted plane with the tunnel point cloud data within a certain thickness constitutes the complete circumferential joint point cloud, i.e., the target point cloud data of the circumferential joint. In terms of plane fitting, this step employs the M-Estimate Sample Consensus (MSAC) method, which effectively improves the fitting accuracy and efficiency of the circumferential joint plane. MSAC is an improved method of random sample consensus, and its specific implementation is shown in steps S221-S225.

[0116] S221, randomly select three feature points from multiple feature points to be fitted as the first three feature points. The target feature points for round fitting.

[0117] The coordinates of the three target feature points in the three-dimensional Cartesian coordinate system can be expressed as follows: , and .

[0118] S222, assuming the fitted target plane equation is... According to the The coordinates of the target feature points in the three-dimensional Cartesian coordinate system are obtained by fitting the first round. The initial fitting plane and its parameters for round fitting. The initial fitting plane parameters may include the first plane parameters. Second plane parameters Third plane parameters and fourth plane parameters It is understandable that, in a three-dimensional Cartesian coordinate system, the parameters of the first plane... The plane is determined in Variation in the axial direction, second plane parameter The plane is determined in Changes in the axial direction, third plane parameters The plane is determined in Changes in the axial direction, fourth plane parameters Once the position of the plane at the origin is determined, the initial fitted plane can be represented as: For ease of understanding, the initial fitting plane parameters are expressed as follows: (13)

[0119] (13).

[0120] S223, traverse each feature point to be fitted. If the feature point to be fitted reaches the... If the distance between the initial fitting planes in the first round of fitting is less than the preset fitting distance threshold, it indicates that the feature point to be fitted is an interior point. In this case, the feature point to be fitted is added to the first round of fitting. If the preset interior point set for the first round of fitting is not found, it indicates that the feature point to be fitted is an outlier, and in this case, the feature point to be fitted is added to the first round of fitting. A preset set of outliers for round-robin fitting. Optionally, the fitting distance threshold can be flexibly set according to the actual situation. It can be understood that inliers are data points that can be correctly described by the model; outliers are data points that deviate significantly from the model.

[0121] S224, if No. If the number of elements in the preset interior set of the round fitting is greater than three, then the first round fitting will be... The preset interior point set of the round fitting is determined as the target interior point set, and the first round fitting is used as the target interior point set. The initial fitting plane parameters for round fitting are determined as the target plane parameters, and then proceed to step S225; otherwise, proceed directly to step S225.

[0122] S225, Judgment Is it equal to , Let be the total number of fitting iterations; otherwise, let . Then return to step S221 to iteratively fit; if so, construct the fitting plane of the circumferential seam based on the target plane parameters. The total number of fitting iterations satisfies the following condition. , Indicates the process The probability that the three feature points to be fitted after the second selection will be selected as interior points is generally set to a value close to 1, such as 0.99. This represents the probability that an interior point is selected in the entire dataset, and its value can be flexibly set according to the actual situation.

[0123] Optionally, the cost function of the MSAC method Satisfy the following formula (14):

[0124] , , (14);

[0125] In formula (14), is a loss function of the MSAC method, represents a distance threshold value; represents an error function of the MSAC method.

[0126] S23, target point cloud data of the girth joint is obtained according to the average width value and the distance of each feature point to the fitting plane of the girth joint.

[0127] In this step, after the fitting plane of the girth joint and the target plane parameters thereof are determined, if the plane thickness is set as the average width value of the girth joint, the points within the plane thickness range are the points of the girth joint, wherein the plane thickness range refers to less than or equal to half of the average width value of the girth joint. Based on this, the target point cloud data of the girth joint can be extracted according to the condition shown in the following formula (15), that is, the feature points satisfying the following formula (15) are retained, and the feature points not satisfying the following formula (15) are screened out, so as to obtain the target point cloud data of the girth joint, which can effectively improve the extraction accuracy and extraction efficiency of the girth joint point cloud:

[0128] (15);

[0129] In formula (15), represents the fitting plane of the girth joint; respectively represent the target plane parameters of the fitting plane of the girth joint; represents the coordinates of the feature point of the girth joint in the three-dimensional rectangular coordinate system.

[0130] In some embodiments, in the step S103, the implementation process of dividing the tunnel point cloud data into independent point cloud data of multiple segment rings of the shield tunnel according to the fitting planes of the girth joints can include the following steps:

[0131] Iterate through the multiple girth joints of the shield tunnel, and according to the fitting planes of two adjacent girth joints in the axial direction of the shield tunnel, obtain the tunnel point cloud data located between the fitting planes of the two girth joints as the independent point cloud data of the segment ring, so as to obtain the independent point cloud data of the multiple segment rings.

[0132] In this embodiment, the longitudinal seam refers to the connecting seam between each segment of the segment ring, which means that the point cloud data of the longitudinal seam is highly related to the point cloud data of the segment ring. Based on this, before the longitudinal seam identification, the tunnel point cloud data is divided into independent point cloud data in units of segment rings according to the fitting planes of the multiple ring seams in this embodiment, which can effectively improve the extraction efficiency of the longitudinal seam point cloud of each segment ring. Specifically, the multiple ring seams of the shield tunnel are traversed, and for the two ring seams adjacent in the axial direction of the shield tunnel in the three-dimensional column coordinate system, the fitting plane of the two ring seams is determined, and the tunnel point cloud data located between the fitting planes of the two ring seams is determined as the independent point cloud data of a single segment ring, so that the independent point cloud data of multiple segment rings can be obtained. For ease of understanding, it is assumed that the two ring seams adjacent in the axial direction of the shield tunnel in the three-dimensional column coordinate system are the first ring seam and the second ring seam, and the tunnel point cloud data located between the fitting plane of the first ring seam and the fitting plane of the second ring seam satisfies the following formula (16):

[0133] (16);

[0134] In formula (16), represents the target plane parameter of the fitting plane of the first ring seam; represents the target plane parameter of the fitting plane of the second ring seam; represents the average width value of the first ring seam; represents the average width value of the second ring seam.

[0135] In some embodiments, the implementation process of identifying the longitudinal seam of the segment ring according to the independent point cloud data of the segment ring to obtain the longitudinal seam point cloud data of the segment ring in the above step S104 can include the following steps S1041-S1043.

[0136] S1041, according to the front end axis direction and the rear end axis direction of the segment ring, in combination with the preset cross-sectional width, the point cloud data associated with the longitudinal seam of the segment ring is intercepted in the independent point cloud data as the longitudinal seam cross-sectional point cloud data of the segment ring.

[0137] ​​In this step, similar to the distribution characteristics of the target point cloud data for the circumferential joint, the longitudinal joint point cloud data obtained by scanning exhibits a shape that is significantly prominently protruding from the tunnel segment. Therefore, the longitudinal joint point cloud data can be extracted based on the difference between the location of the longitudinal joint in the independent point cloud data and the radial distance to the surrounding tunnel segments. Based on this, after completing the division of the independent point cloud data, this step first uses a preset cut-off width of point cloud data at both ends of the independent point cloud data (i.e., the front and rear axial directions of the tunnel segment ring) along the axial direction of the shield tunnel as the point cloud data associated with the longitudinal joint of the tunnel segment ring, i.e., the longitudinal joint cross-sectional point cloud data of the tunnel segment ring, for subsequent longitudinal joint identification. It is understood that the cut-off of the longitudinal joint cross-sectional point cloud data is similar to that of the aforementioned circumferential joint cross-sectional point cloud data, and this step will not elaborate further. However, it should be noted that the cut-off width used in both cut-offs is the same.

[0138] S1042, based on the preset central angle feature set of the segment ring and the fitting plane of at least one ring seam, the longitudinal seam cross-section point cloud data is processed by longitudinal seam point cloud extraction to obtain the initial longitudinal seam point cloud data of the segment ring.

[0139] It should be noted that, referring to Figure 6 In this embodiment, the design radius of the observation tunnel is... R Each segment ring is made of It is assembled from segmented tubes. Block segments include One standard block, two adjacent blocks, and one capping block. Figure 6 The number of standard blocks is 3. The standard blocks are named respectively. Name the two adjacent blocks respectively. and Name the capping block Among them, standard blocks The inner arc length is Its corresponding central angle is the standard central angle. For adjacent blocks and The inner arc length of the end with the larger arc length is the length of the first adjacent arc. The central angle corresponding to the length of the first adjacent arc is the first adjacent central angle. The inner arc length of the end with the smaller arc length is the second adjacent arc length. The central angle corresponding to the second adjacent arc length is the second adjacent central angle. For the capping block The inner arc length at the end with the smaller arc length is the first capping arc length. The central angle corresponding to the first capping arc length is the first capping central angle. The inner arc length at the end with the larger arc length is the second capping arc length. a second capping central angle corresponding to a second capping arc length The preset central angle feature set can include a standard central angle a first abutment central angle a second abutment central angle a first capping central angle a second capping central angle These central angles satisfy: .

[0140] It can be understood that the preset central angle feature set is used to indicate the positional relationship between each segment and the center of the segment ring.

[0141] In this step, after the longitudinal seam section point cloud data is intercepted, the longitudinal seam section point cloud data is preliminarily extracted using the preset central angle feature set of the segment ring and the fitting plane of at least one ring seam obtained in the foregoing step, to obtain initial longitudinal seam point cloud data of the segment ring.

[0142] S1043, screening and adding processing of the initial longitudinal seam point cloud data according to the preset central angle feature set, to obtain longitudinal seam point cloud data of the segment ring.

[0143] In this step, although most of the longitudinal seam point cloud data can be extracted through the previous step, there are still some longitudinal seam point cloud data that cannot be displayed in the tunnel point cloud data due to the shielding of objects in the tunnel and the influence of the scanning distance. In addition, there is also a phenomenon that some segment point cloud data is misjudged as longitudinal seam point cloud data. Therefore, after the initial longitudinal seam point cloud data is preliminarily extracted, the initial longitudinal seam point cloud data needs to be processed using the preset central angle feature set, aiming to screen out the segment point cloud data in the initial longitudinal seam point cloud data, and add some longitudinal seam point cloud data that is not extracted in the foregoing step, so as to effectively improve the extraction accuracy and efficiency of the longitudinal seam point cloud data, and thus improve the accuracy and efficiency of the longitudinal seam identification.

[0144] In some embodiments, the implementation process of the step S1042 of performing longitudinal seam point cloud extraction processing on the longitudinal seam section point cloud data according to the preset central angle feature set of the segment ring and the fitting plane of at least one ring seam to obtain the initial longitudinal seam point cloud data of the segment ring can include the following steps S31-S34:

[0145] S31, projecting the longitudinal seam section point cloud data to the fitting plane closest to the longitudinal seam section point cloud data to obtain projected point cloud data;

[0146] S32, converting the projected point cloud data from a three-dimensional rectangular coordinate system to a three-dimensional cylindrical coordinate system to obtain converted projected point cloud data;

[0147] S33, denoising the converted projection point cloud data to obtain denoised projection point cloud data;

[0148] S34, extracting initial longitudinal seam point cloud data of the pipe ring from the denoised projection point cloud data according to the preset circle center angle feature set and the denoised projection point cloud data.

[0149] In the embodiment, first, the longitudinal seam cross-section point cloud data is projected to the closest fitting plane of the longitudinal seam cross-section point cloud data to obtain the projection point cloud data, so that all longitudinal seam cross-section points can be unified to the same data space position, so as to improve the extraction accuracy of the initial longitudinal seam point cloud data. Assuming that the closest fitting plane of the longitudinal seam cross-section point cloud data is , the projection point cloud data obtained by projecting the longitudinal seam cross-section point cloud data to the fitting plane satisfies the following formula (17):

[0150] (17);

[0151] In formula (17), is the coordinate of the point projected into the three-dimensional plane, that is, the three-dimensional rectangular coordinate value of the projected point in the three-dimensional plane; is the coordinate of the longitudinal seam cross-section point in the three-dimensional rectangular coordinate system, which can be obtained by converting the longitudinal seam cross-section point cloud data from the three-dimensional cylindrical coordinate system to the three-dimensional rectangular coordinate system. It can be understood that the projected point refers to the point of the projected point cloud data, and the longitudinal seam cross-section point refers to the point of the longitudinal seam cross-section point cloud data.

[0152] Then, in order to express the relative position of the longitudinal seam and the pipe ring, the projected point cloud data is converted from the three-dimensional rectangular coordinate system to the three-dimensional cylindrical coordinate system according to formula (1) to obtain the converted projection point cloud data, which is beneficial to express the relative position of the longitudinal seam and the pipe ring. In the converted projection point cloud data, the three-dimensional cylindrical coordinate value of each point is expressed as , the azimuth angle and the radial distance are related as shown in Figure 7 . As can be seen from Figure 7 , the radial distance changes relatively gently with the change of the azimuth angle in most areas, but the radial distance suddenly increases or decreases greatly at some specific angles, so it can be inferred that the converted projection point cloud data includes initial longitudinal seam point cloud data and internal noise point cloud data, wherein the points with sudden increase are longitudinal seam points, and the points with sudden decrease are internal noise points of the shield tunnel, such as power lines. It can be seen that as long as the coordinates of these points with sudden increase are extracted from the converted projection point cloud data, the initial longitudinal seam point cloud data can be obtained.

[0153] Before extracting the initial longitudinal seam point cloud data, it is necessary to remove internal noise points with similar shapes. This helps to eliminate internal noise points with similar shapes to the longitudinal seam points, improving the accuracy and quality of the projected point cloud data. This denoising process mainly uses 3D... The criterion is that the transformed projected point cloud data is in a three-dimensional cylindrical coordinate system. The axis is evenly divided into M Each interval M =360, then the three-dimensional cylindrical coordinates of each point in the converted projected point cloud data within each interval satisfy the following formula (18):

[0154] (18);

[0155] In equation (18), This indicates that each point in the transformed projected point cloud data is at the [number]th [position]. A set of three-dimensional cylindrical coordinate values ​​within a given interval. This can be understood as... Axis coordinates do not satisfy Points that are internal noise points are considered outliers and removed, while points that satisfy the condition are retained. point.

[0156] After denoising, it is also based on 3 The criteria further separate the initial longitudinal joint point cloud data. This is because the radial distance of the longitudinal joint section point cloud data, when projected onto the fitting plane of the circumferential joint, is... There is a certain gap; if the M value is set too large, the evenly divided intervals will be too small; if the M value is set too small, the evenly divided intervals will be too large. In either case, multiple longitudinal seam point clouds may be contained within the same interval, which is detrimental to accurate point cloud extraction. Therefore, unlike the denoising situation, when separating the initial longitudinal seam point cloud data... The value of M in the criterion must depend on a preset central angle feature set, that is, the value of M must satisfy: By setting the M value in combination with 3 The criterion can extract the initial longitudinal seam point cloud data of the segment ring from the denoised projected point cloud data, thereby effectively improving the extraction accuracy of the initial longitudinal seam point cloud data.

[0157] In some implementations, the process of performing point cloud filtering and addition processing on the initial longitudinal seam point cloud data according to the preset central angle feature set to obtain the longitudinal seam point cloud data of the segment ring may include the following steps S41-S44.

[0158] S41, obtain the endpoint set and azimuth set of the first capping end of the segment ring, and obtain the endpoint set and azimuth set of the second capping end of the segment ring.

[0159] It should be noted that, referring toFigure 6 The first cap tip refers to the arc length of the first cap tip. At one end, the top of the first seal was named t end, t The endpoints of the longitudinal seam are respectively The second capping point refers to the arc length of the second capping point. At one end, the top of the second seal was named h end, h The endpoints of the longitudinal seam are respectively Longitudinal seams typically include two types: straight seams and diagonal seams, such as... Figure 6 As shown, standard block Between or standard blocks With two adjacent blocks , The longitudinal joint between them is perpendicular to the tunnel's cross-section, that is... h, t Azimuth angle of the end longitudinal joint point in the three-dimensional cylindrical coordinate system For ease of description, these are called straight seams; similarly, two adjacent blocks... , With capping block The longitudinal joint between points is called a diagonal joint. In a three-dimensional cylindrical coordinate system, the difference in azimuth angle between points along the longitudinal joint is essentially the difference in azimuth angle between the points along the longitudinal joint. Distance in a direction.

[0160] Understandably, the endpoint set includes several longitudinal slit-like point clusters; furthermore, h The endpoint set of the end includes h end A cluster of longitudinal suture-like dots, and t The endpoint set of the end includes t end A cluster of longitudinal suture-like dots, Azimuth angle Using the horizontal axis as the radial distance Using the vertical axis as the ordinate, construct a third two-dimensional coordinate system, which can be named... Coordinate system. Each longitudinal seam linear point cluster includes multiple longitudinal seam endpoints, in In coordinate system, h The coordinates of the longitudinal seam endpoints within each longitudinal seam linear point cluster are represented as follows: , ,Will t The coordinates of the longitudinal seam endpoints within each longitudinal seam linear point cluster are represented as follows: , ,for h End and tThe median of the azimuth angle values of all longitudinal seam end points in each longitudinal seam linear point cluster is taken as the azimuth angle of the longitudinal seam end point of the longitudinal seam linear point cluster, and each longitudinal seam linear point cluster is sorted from small to large according to the azimuth angle of the longitudinal seam end point of each longitudinal seam linear point cluster, so that h the azimuth angle set of the longitudinal seam end point of the first sealing end t the azimuth angle set of the longitudinal seam end point of the second sealing end. It can be understood that h the azimuth angle set of the longitudinal seam end point of the first sealing end includes h the azimuth angle set of the longitudinal seam end point of the second sealing end the azimuth angle of the longitudinal seam end point of the first sealing end t the azimuth angle set of the longitudinal seam end point of the first sealing end includes t the azimuth angle set of the longitudinal seam end point of the second sealing end the azimuth angle of the longitudinal seam end point of the first sealing end

[0161] the azimuth angle of the longitudinal seam end point of the second sealing end

[0162] In formula (19), the median operator is represented by the azimuth angle set of the longitudinal seam end point of the first sealing end h the azimuth angle set of the longitudinal seam end point of the second sealing end the azimuth angle set of the longitudinal seam end point of the first sealing end t the azimuth angle set of the longitudinal seam end point of the second sealing end

[0163] In this step, although most of the longitudinal seam point cloud data can be extracted through the previous step, part of the longitudinal seam point cloud data cannot be displayed in the tunnel point cloud data due to the shielding of the objects in the tunnel and the influence of the scanning distance. In addition, there is a phenomenon that part of the segment point cloud data is misjudged as longitudinal seam point cloud data. Therefore, after the initial longitudinal seam point cloud data is preliminarily extracted, the initial longitudinal seam point cloud data needs to be processed twice. In the secondary processing, the endpoint set and the azimuth angle set of the first sealing end of the segment ring are first obtained, and the endpoint set and the azimuth angle set of the second sealing end of the segment ring are obtained, so as to facilitate subsequent screening and adding processing.

[0164] S42, according to the endpoint set of the first sealing end, the azimuth angle set of the first sealing end, the endpoint set of the second sealing end and the azimuth angle set of the second sealing end, and in combination with the preset central angle feature set, the longitudinal seam end point azimuth angle of the first sealing end and the longitudinal seam end point azimuth angle of the second sealing end are obtained as the longitudinal seam end point features of the segment ring.

[0165] In this step, the azimuth angle set of the first sealing end and the azimuth angle set of the second sealing end may not contain the longitudinal seam end point azimuth angle of the entire segment ring, and there may be misjudged longitudinal seam end points in these coordinates, so the endpoint set and the azimuth angle set of the first sealing end and the endpoint set and the azimuth angle set of the second sealing end need to be further verified and screened, and the longitudinal seam end point azimuth angle not displayed in the tunnel point cloud data is calculated.

[0166] Specifically, according to the distribution characteristics of the longitudinal seam in the ring, the capping block The position of the longitudinal seam end point in the whole ring is determined by the azimuth of the oblique seam end point where the capping block is located. Therefore, when the longitudinal seam in the whole ring is positioned, the positions of the oblique seams on both sides of the capping block t should be determined first. Specifically, if there are elements h and elements in the azimuth set of the first capping end (i.e., the set as shown in formula (19) below) and the azimuth set of the second capping end (i.e., the set as shown in formula (19) below) respectively, and both the elements and the elements satisfy the azimuth condition shown in formula (20) below, where is a pre-set tolerance threshold, then the elements and the elements are determined as the oblique seam end points on both sides of the capping block . The elements are stored in the set

[0167] in ascending order, and the elements are stored in the set in ascending order:

[0168] h (20); In formula (20), t is the longitudinal seam end point azimuth of the th longitudinal seam line point cluster in the azimuth set of the th capping end.

[0169] h Then, for the th capping end, if the length of the set is 2, that is, the two longitudinal seams on both sides of the capping block are successfully identified, and if the elements contained in the set are and , then the initial longitudinal seam end point azimuth of the whole ring is obtained, which satisfies formula (21) below:

[0170] (21);

[0171] In formula (21), represents the minimum value of the azimuth of the h th capping end, represents the floor function, and represents the maximum value of the azimuth of the h th capping end.

[0172] At the same time, for t End, if set The length is 2, which is the capping block. If both longitudinal seams on both sides are successfully identified, then assume the set The elements contained therein are and Then the initial longitudinal seam endpoint azimuth angle of the entire ring is identified, which satisfies the following formula (22):

[0173] (twenty two);

[0174] In equation (22), express t Minimum azimuth angle at the end express t Maximum value of end azimuth angle.

[0175] Then, the above-identified results h The initial longitudinal seam endpoint azimuth angle is stored in h The azimuth set of the end, and the above-identified azimuth angles. t The initial longitudinal seam endpoint azimuth angle is stored in t The azimuth set of the end, updated h The set of azimuth angles at the ends t The elements within the azimuth set of the endpoint are arranged in ascending order. A certain tolerance is set; in this embodiment, the tolerance is set to [value missing]. By comparison h The redundant and duplicate longitudinal seam endpoint azimuth angles are removed by using the size of adjacent elements within the set of azimuth angles at the ends. h The set of intermediate azimuth angles of the end At the same time, through comparison t The redundant and duplicate longitudinal seam endpoint azimuth angles are removed by using the size of adjacent elements within the set of azimuth angles at the ends. t The set of intermediate azimuth angles of the end It should be noted that the principle of redundant coordinate deletion is to prioritize retaining the endpoint azimuth angle obtained through longitudinal seam identification, rather than the result obtained through geometric reasoning, when two elements are approximately equal, thus preserving as much of the original measurement information as possible. Understandably, if the difference between two elements is less than the tolerance, the two elements are considered approximately equal; furthermore, the result obtained through geometric reasoning refers to the elements in the original azimuth angle set; the endpoint azimuth angle obtained through longitudinal seam identification refers to the initial longitudinal seam endpoint azimuth angle.

[0176] Finally, after removing redundant data, it is also necessary to ensure that each longitudinal seam... t End coordinates and h The end coordinates correspond one-to-one, therefore the above formula (20) is used again for... h The set of intermediate azimuth angles of the endst the intermediate azimuth angle set of the end to verify the mapping relationship between the intermediate azimuth angle set of the end and t the intermediate azimuth angle set of the end. h For each element in the intermediate azimuth angle set of the end, if the element cannot find a corresponding element in the intermediate azimuth angle set of the end through the above formula (20), it is deleted, otherwise it is retained, so as to obtain the target azimuth angle set of the end, which includes the longitudinal seam end point azimuth angle of the end. h For each element in the intermediate azimuth angle set of the end, if the element cannot find a corresponding element in the intermediate azimuth angle set of the end through the above formula (20), it is deleted, otherwise it is retained, so as to obtain the target azimuth angle set of the end, which includes the longitudinal seam end point azimuth angle of the end. t For each element in the intermediate azimuth angle set of the end, if the element cannot find a corresponding element in the intermediate azimuth angle set of the end through the above formula (20), it is deleted, otherwise it is retained, so as to obtain the target azimuth angle set of the end, which includes the longitudinal seam end point azimuth angle of the end. h For each element in the intermediate azimuth angle set of the end, if the element cannot find a corresponding element in the intermediate azimuth angle set of the end through the above formula (20), it is deleted, otherwise it is retained, so as to obtain the target azimuth angle set of the end, which includes the longitudinal seam end point azimuth angle of the end. h For each element in the intermediate azimuth angle set of the end, if the element cannot find a corresponding element in the intermediate azimuth angle set of the end through the above formula (20), it is deleted, otherwise it is retained, so as to obtain the target azimuth angle set of the end, which includes the longitudinal seam end point azimuth angle of the end. t For each element in the intermediate azimuth angle set of the end, if the element cannot find a corresponding element in the intermediate azimuth angle set of the end through the above formula (20), it is deleted, otherwise it is retained, so as to obtain the target azimuth angle set of the end, which includes the longitudinal seam end point azimuth angle of the end. h For each element in the intermediate azimuth angle set of the end, if the element cannot find a corresponding element in the intermediate azimuth angle set of the end through the above formula (20), it is deleted, otherwise it is retained, so as to obtain the target azimuth angle set of the end, which includes the longitudinal seam end point azimuth angle of the end. t For each element in the intermediate azimuth angle set of the end, if the element cannot find a corresponding element in the intermediate azimuth angle set of the end through the above formula (20), it is deleted, otherwise it is retained, so as to obtain the target azimuth angle set of the end, which includes the longitudinal seam end point azimuth angle of the end. t For each element in the intermediate azimuth angle set of the end, if the element cannot find a corresponding element in the intermediate azimuth angle set of the end through the above formula (20), it is deleted, otherwise it is retained, so as to obtain the target azimuth angle set of the end, which includes the longitudinal seam end point azimuth angle of the end. t For each element in the intermediate azimuth angle set of the end, if the element cannot find a corresponding element in the intermediate azimuth angle set of the end through the above formula (20), it is deleted, otherwise it is retained, so as to obtain the target azimuth angle set of the end, which includes the longitudinal seam end point azimuth angle of the end. h For each element in the intermediate azimuth angle set of the end, if the element cannot find a corresponding element in the intermediate azimuth angle set of the end through the above formula (20), it is deleted, otherwise it is retained, so as to obtain the target azimuth angle set of the end, which includes the longitudinal seam end point azimuth angle of the end. For each element in the intermediate azimuth angle set of the end, if the element cannot find a corresponding element in the intermediate azimuth angle set of the end through the above formula (20), it is deleted, otherwise it is retained, so as to obtain the target azimuth angle set of the end, which includes the longitudinal seam end point azimuth angle of the end. t For each element in the intermediate azimuth angle set of the end, if the element cannot find a corresponding element in the intermediate azimuth angle set of the end through the above formula (20), it is deleted, otherwise it is retained, so as to obtain the target azimuth angle set of the end, which includes the longitudinal seam end point azimuth angle of the end. h For each element in the intermediate azimuth angle set of the end, if the element cannot find a corresponding element in the intermediate azimuth angle set of the end through the above formula (20), it is deleted, otherwise it is retained, so as to obtain the target azimuth angle set of the end, which includes the longitudinal seam end point azimuth angle of the end.

[0177] S43, according to the longitudinal seam end point feature, the straight line where the longitudinal seam of the pipe segment ring is located in the second two-dimensional coordinate system is obtained as a third straight line.

[0178] In this step, the axis distance is taken as the horizontal axis, and the azimuth angle is taken as the vertical axis to construct the second two-dimensional coordinate system, which is named as the coordinate system. Since the longitudinal seam is linearly distributed between the girth seams on both sides of the pipe segment ring, the straight line equation of the longitudinal seam in the coordinate system is first determined in order to extract the final longitudinal seam point cloud data. Assuming that the longitudinal seam end point azimuth angle of the h end of the pipe segment ring is , the cylindrical coordinate value of the girth seam point cloud in the three-dimensional cylindrical coordinate system is , and the longitudinal seam end point azimuth angle of the t end of the pipe segment ring is , the cylindrical coordinate value of the girth seam point cloud in the three-dimensional cylindrical coordinate system is , then the coordinate value of the longitudinal seam end point of the h end in the coordinate system and the coordinate value of the longitudinal seam end point of the t end in the coordinate system are shown in the following formula (23):

[0179] (twenty three);

[0180] In equation (23), express h The end of the longitudinal seam is at Coordinate values ​​in a coordinate system; express t The end of the longitudinal seam is at Coordinate values ​​in a coordinate system.

[0181] Then, according to h The end of the longitudinal seam and t The end of the longitudinal seam is at The coordinate values ​​in the coordinate system are obtained in The line containing the longitudinal seam in the coordinate system is taken as the third line. .

[0182] S44. Based on the average width of the longitudinal joint of the segment ring and the distance from each initial longitudinal joint point in the initial longitudinal joint point cloud data to the third straight line, extract the longitudinal joint point cloud data of the segment ring from the initial longitudinal joint point cloud data.

[0183] In this step, it is assumed that h The number of longitudinal suture linear point clusters at the end is ,and t The number of longitudinal suture linear point clusters at the end is ,exist In coordinate system, h The coordinates of the longitudinal seam endpoints within each longitudinal seam linear point cluster are represented as follows: , ,Will t The coordinates of the longitudinal seam endpoints within each longitudinal seam linear point cluster are represented as follows: , According to h Number of longitudinal suture linear point clusters at the end t The number of longitudinal suture linear point clusters at the end, in coordinate system h The coordinates of the longitudinal seam endpoints within each longitudinal seam linear point cluster and in coordinate system t The average width of the longitudinal seam is calculated by taking the coordinates of the endpoints of the longitudinal seam within each cluster of linear points in the longitudinal seam, as shown in the following formula (24):

[0184] (twenty four);

[0185] In equation (24), This represents the average width of the longitudinal seam; express hthe maximum value of the abscissa of all the longitudinal seam end points in each longitudinal seam linear point cluster in the end; denotes h the minimum value of the abscissa of all the longitudinal seam end points in each longitudinal seam linear point cluster in the end; denotes t the maximum value of the abscissa of all the longitudinal seam end points in each longitudinal seam linear point cluster in the end; denotes t the minimum value of the abscissa of all the longitudinal seam end points in each longitudinal seam linear point cluster in the end.

[0186] After determining the average width value of the longitudinal seam, the point cloud in the initial longitudinal seam point cloud data with a linear distance to the third straight line less than half of the average width value of the longitudinal seam is regarded as the final longitudinal seam point cloud, i.e., the longitudinal seam point cloud data of the pipe ring. Specifically, first, for each initial longitudinal seam point in the initial longitudinal seam point cloud data, if the distance of the initial longitudinal seam point to the third straight line is less than half of the average width value of the longitudinal seam, i.e., , is the distance of the initial longitudinal seam point to the third straight line, it is indicated that the initial longitudinal seam point is related to the height of the longitudinal seam, and the initial longitudinal seam point is retained at this time, otherwise, it is indicated that the initial longitudinal seam point is related to the low degree of the longitudinal seam or is not related, and the initial longitudinal seam point is removed at this time, and then the longitudinal seam point cloud data of the pipe ring is obtained. Wherein, the distance of the initial longitudinal seam point to the third straight line satisfies the following formula (25):

[0187] (25);

[0188] In formula (25), denotes the coordinates of the initial longitudinal seam point in the three-dimensional cylindrical coordinate system, denotes the distance of the initial longitudinal seam point to the third straight line .

[0189] Finally, the longitudinal seam point cloud data of the pipe ring is converted from the three-dimensional cylindrical coordinate system to the three-dimensional rectangular coordinate system, and the converted longitudinal seam point cloud data is output as the final longitudinal seam point cloud data, and the final longitudinal seam point cloud data satisfies the following formula (26):

[0190] (26);

[0191] In formula (26), denotes the abscissa of the point of the final longitudinal seam point cloud data in the three-dimensional rectangular coordinate system; denotes the ordinate of the point of the final longitudinal seam point cloud data in the three-dimensional rectangular coordinate system; denotes the depth coordinate of the point of the final longitudinal seam point cloud data in the three-dimensional rectangular coordinate system.

[0192] Finally, the application also provides a segmenting system for segments of a shield tunnel, comprising a point cloud scanning module, a ring joint identification module, a division processing module, a longitudinal joint identification module, and a segment segmenting module. The point cloud scanning module is configured to obtain original point cloud data of the shield tunnel and perform preprocessing to obtain tunnel point cloud data. The ring joint identification module is configured to identify ring joints of the shield tunnel based on the tunnel point cloud data to obtain a fitting plane of the ring joints and target point cloud data of the ring joints. The division processing module is configured to divide the tunnel point cloud data into independent point cloud data of multiple segment rings of the shield tunnel based on the fitting planes of the ring joints. The longitudinal joint identification module is configured to identify longitudinal joints of the segment rings based on the independent point cloud data of the segment rings to obtain longitudinal joint point cloud data of the segment rings. The segment segmenting module is configured to segment the shield tunnel based on the target point cloud data of the ring joints and the longitudinal joint point cloud data of the segment rings to obtain multiple segment regions of the shield tunnel.

[0193] The content in the above method embodiments is applicable to the system embodiments. The system embodiments specifically implement the same functions as the above method embodiments and achieve the same beneficial effects as the above method embodiments.

[0194] The segment segmenting method and system for a shield tunnel according to the embodiments of the application will be described below with reference to an example.

[0195] In the example, the tunnel is lined with single-layer flat segments, the outer diameter of the segments is 6.2 m, the inner diameter is 5.5 m, and the ring width is 1.5 m. The line fitting and deviation correction use general double-wedge control, and the wedge amount is 40 mm. The segments are assembled in a 1+5 block mode, i.e., each segment ring includes 3 standard blocks, 2 adjacent blocks, and 1 top block. The blocks in a segment ring are connected by 12 bent bolts, and the segment rings are connected by 16 bent bolts. The ring width of the segment ring is 1.5 m, and the distance between the two ends of the segment and the nearest bolt hole is 0.2 m. To prevent the bolt hole and the ring joint point cloud from being confused in automatic identification, the identification area width is set to 0.15 m. D s d r The three-dimensional laser scanners of the stations are all Leica P40. The three-dimensional laser scanning is performed when the tunnel shield tunneling is completed, and there are no dust, vibration, and other interference factors in the tunnel. Considering the quality and scanning efficiency of the point cloud, the scanner resolution of the three-dimensional laser scanners of the stations is set to 3.1 mm, the station spacing is 10-15 m, and three Leica 4.5'' black and white targets are set as coordinate control points on the left and right sides and the bottom of the tunnel.

[0196] ​The process of segmenting the pipe segment in this example is as follows: steps S1-S5.

[0197] S1, point cloud scanning and preprocessing: The inside of the shield tunnel is scanned by several stations to obtain station point cloud data of several stations, and the station point cloud data of all stations is spliced into original point cloud data of the shield tunnel. After the original point cloud data is exported, it is subjected to denoising and coordinate system conversion processing, and the coordinate system conversion follows the above formula (1), so as to obtain tunnel point cloud data.

[0198] S2, ring joint identification: for each ring joint of the shield tunnel, first, the point cloud data associated with the ring joint is intercepted from the tunnel point cloud data as the ring joint cross section point cloud data , . Then, the target point cloud data of the ring joint and the fitting plane are obtained by the above steps S1022-S1023, and the target plane parameters of the fitting plane are shown in Table 1.

[0199] S3, pipe segment point cloud segmentation: according to the fitting planes of the multiple ring joints, the tunnel point cloud data is divided into independent point cloud data in units of pipe ring, and independent point cloud data of each pipe ring is obtained.

[0200] S4, longitudinal joint identification: for each pipe ring of the shield tunnel, under the condition that the design arc length and radius of the pipe segment are known, the corresponding central angle of each pipe segment at both ends can be calculated , and the design arc length and the corresponding central angle of the pipe segment are shown in Table 2. The possible distance between the straight joint end points at both ends of the pipe segment is calculated as ; h The possible distance between the straight joint and the inclined joint is , and the possible distance between the inclined joints is ; t The possible distance between the straight joint and the inclined joint is , and the possible distance between the inclined joints is . The value of M in formula (18) is set to 11. Combined with the fitting plane of the ring joint and the target plane parameters thereof, the theoretical distance between the longitudinal joint end points of the pipe segment and the calculation parameters are substituted into steps S1041-S1043 to obtain the longitudinal joint point cloud data of the pipe ring and the longitudinal joint end point azimuth angle, and the longitudinal joint end point azimuth angle is shown in Table 3, and NaN in Table 3 is the point coordinates not identified.

[0201] S5, segmenting the pipe piece: according to the target point cloud data of each ring joint, the target plane parameters of the fitting plane shown in Table 1, the point cloud data of the longitudinal joint of each pipe piece ring, and the azimuth angle of the longitudinal joint end point shown in Table 3, the ring joint and the longitudinal joint in the tunnel point cloud data are extracted, and the segmentation of a single pipe piece in the tunnel point cloud data can be realized by combining a preset software, and the segmentation result is shown in Figure 8 As can be seen from Figure 8 It can be seen that the embodiments of the present application can correctly identify most of the ring joints and longitudinal joints in the point cloud, and only a few areas with long scanning distances fail to be identified or the identification result is inaccurate, such as only one longitudinal joint in the longitudinal joint in the first ring is successfully identified, and the longitudinal joint between the 20th and 21st rings is obviously distorted. This is mainly due to the long scanning distance, the fewer laser beams entering the ring joint, and the corresponding reduction in the number of points in the ring joint point cloud, which affects the accuracy of the feature point coordinate extraction. If the distance between the stations can be shortened during scanning, the accuracy of the pipe piece segmentation can be effectively improved.

[0202] Table 1: example data for ring joint identification

[0203]

[0204] Table 2: example table of design arc length and center angle of pipe piece

[0205]

[0206] Table 3: example table of azimuth angle of longitudinal joint end point

[0207]

[0208] Although the embodiments of the present application have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, replacements and variations can be made to these embodiments without departing from the principles and purposes of the present application, and the scope of the present application is defined by the claims and their equivalents.

[0209] The above is a specific description of the preferred embodiments of the present application, but the present application is not limited to the described embodiments, and those skilled in the art can make various equivalent modifications or replacements without departing from the spirit of the present application, and these equivalent modifications or replacements are all included in the scope defined by the claims of the present application.

Claims

1. A method of segmenting a pipe of a shield tunnel, characterized by, The method comprises the following steps: Obtain original point cloud data of a shield tunnel and perform preprocessing to obtain tunnel point cloud data; For each ring joint of the shield tunnel, identify the ring joint according to the tunnel point cloud data to obtain a fitting plane of the ring joint and target point cloud data of the ring joint; Divide the tunnel point cloud data into independent point cloud data of multiple segment rings of the shield tunnel according to the fitting planes of the ring joints; For a longitudinal joint of each segment ring, identify the longitudinal joint of the segment ring according to the independent point cloud data of the segment ring to obtain longitudinal joint point cloud data of the segment ring; Segment the segment ring of the shield tunnel according to the target point cloud data of each ring joint and the longitudinal joint point cloud data of each segment ring to obtain multiple segment areas of the shield tunnel; The identification of the ring joint according to the tunnel point cloud data to obtain the fitting plane of the ring joint and the target point cloud data of the ring joint comprises: According to the axial direction, the number of rings, and the segment width of the shield tunnel, in combination with a preset cross-sectional width, the point cloud data associated with the ring joint is intercepted from the tunnel point cloud data as ring joint cross-sectional point cloud data; The segment point cloud data in the ring joint cross-sectional point cloud data is removed to obtain initial ring joint point cloud data; According to the initial ring joint point cloud data, feature point identification processing is performed on the ring joint to obtain an average width value of the ring joint and a plurality of feature points; According to the average width value and the plurality of feature points, plane fitting processing is performed on the ring joint to obtain the fitting plane of the ring joint and the target point cloud data of the ring joint; The identification of the longitudinal joint of the segment ring according to the independent point cloud data of the segment ring to obtain the longitudinal joint point cloud data of the segment ring comprises: According to the front end axial direction and the rear end axial direction of the segment ring, in combination with a preset cross-sectional width, the point cloud data associated with the longitudinal joint of the segment ring is intercepted from the independent point cloud data as longitudinal joint cross-sectional point cloud data of the segment ring; According to the preset circle center angle feature set of the segment ring and the fitting plane of at least one ring joint, longitudinal joint point cloud extraction processing is performed on the longitudinal joint cross-sectional point cloud data to obtain initial longitudinal joint point cloud data of the segment ring; According to the preset circle center angle feature set, the initial longitudinal joint point cloud data is screened and added to obtain the longitudinal joint point cloud data of the segment ring.

2. The segmental discission method of a shield tunnel according to claim 1, wherein, The obtaining of the original point cloud data of the shield tunnel and the preprocessing to obtain the tunnel point cloud data comprises: Scanning processing is performed on the inside of the shield tunnel by a plurality of preset stations to obtain station point cloud data of the plurality of stations; The station point cloud data of the plurality of stations is spliced to obtain the original point cloud data of the shield tunnel; The original point cloud data is denoised to obtain denoised original point cloud data; The denoised original point cloud data is converted from a Cartesian coordinate system to a three-dimensional cylindrical coordinate system to obtain the tunnel point cloud data.

3. The segmental discission method of a shield tunnel according to claim 1, wherein, The removal of the segment point cloud data in the ring joint cross-sectional point cloud data to obtain the initial ring joint point cloud data comprises: The straight line detection method of the Hough transformation is used for straight line detection processing on the ring seam cross section point cloud data, and a straight line associated with the pipe piece point cloud data in the ring seam cross section point cloud data is obtained as a first straight line; According to the first straight line, the pipe piece point cloud data in the ring seam cross section point cloud data is removed, and residual cross section point cloud data is obtained; The straight line detection method of the Hough transformation is used for straight line detection processing on the residual cross section point cloud data, and a straight line associated with the pipe piece point cloud data in the residual cross section point cloud data is obtained as a second straight line; According to the second straight line, the pipe piece point cloud data in the residual cross section point cloud data is removed, and the initial ring seam point cloud data is obtained.

4. The segmental discission method of a shield tunnel according to claim 1, wherein, The feature point recognition processing of the initial ring seam point cloud data on the ring seam is performed to obtain the average width value of the ring seam and a plurality of feature points, including: According to the maximum value of the radial distance of all initial ring seam points in the initial ring seam point cloud data, a plurality of first feature points of the ring seam under the three-dimensional cylindrical coordinate system are obtained; According to the median of the radial distance of all initial ring seam points in the initial ring seam point cloud data, a plurality of second feature points of the ring seam under the three-dimensional cylindrical coordinate system are obtained; The plurality of first feature points and the plurality of second feature points are converted from the three-dimensional cylindrical coordinate system to the three-dimensional rectangular coordinate system to obtain a plurality of converted first feature points and a plurality of converted second feature points as a plurality of feature points of the ring seam; According to the plurality of feature points of the ring seam, the average width value of the ring seam is obtained.

5. The segmental discission method of a shield tunnel according to claim 1, wherein, The plane fitting processing of the average width value and a plurality of feature points on the ring seam is performed to obtain a fitting plane of the ring seam and target point cloud data, including: A plurality of feature points at a preset azimuth angle are selected from a plurality of feature points as fitting feature points; The fitting feature points are subjected to plane fitting processing by using the M-estimation sample consistency method to obtain the fitting plane of the ring seam; According to the average width value and the distance of each feature point to the fitting plane of the ring seam, the target point cloud data of the ring seam is obtained.

6. The segmental discission method of a shield tunnel according to claim 1, wherein, The longitudinal seam point cloud extraction processing of the longitudinal seam cross section point cloud data according to the preset central angle feature set of the pipe ring and the fitting plane of at least one ring seam is performed to obtain the initial longitudinal seam point cloud data of the pipe ring, including: The longitudinal seam cross section point cloud data is projected onto the fitting plane closest to the longitudinal seam cross section point cloud data to obtain projected point cloud data; The projected point cloud data is converted from the three-dimensional rectangular coordinate system to the three-dimensional cylindrical coordinate system to obtain converted projected point cloud data; The converted projected point cloud data is subjected to denoising to obtain denoised projected point cloud data; According to the preset central angle feature set and the denoised projected point cloud data, the initial longitudinal seam point cloud data of the pipe ring is extracted from the denoised projected point cloud data.

7. The segmental discission method of a shield tunnel according to claim 1, wherein, The point cloud screening and adding processing of the initial longitudinal seam point cloud data according to the preset central angle feature set is performed to obtain the longitudinal seam point cloud data of the pipe ring, including: acquire an endpoint set and an azimuth angle set of a first capping end of the segment ring, and acquire an endpoint set and an azimuth angle set of a second capping end of the segment ring; wherein the first capping end is an end where a first capping arc length is located, the first capping arc length is an inner arc of an end with a smaller arc length in a capping block of the segment ring, the second capping end is an end where a second capping arc length is located, the second capping arc length is an inner arc of an end with a larger arc length in the capping block, the endpoint set includes a plurality of longitudinal seam line point clusters, each longitudinal seam line point cluster includes a plurality of longitudinal seam endpoints, and the azimuth angle set includes a plurality of longitudinal seam endpoint azimuth angles of the longitudinal seam line point clusters; obtain, according to the endpoint set of the first capping end, the azimuth angle set of the first capping end, the endpoint set of the second capping end, and the azimuth angle set of the second capping end, and in combination with the preset central angle feature set, a longitudinal seam endpoint azimuth angle of the first capping end and a longitudinal seam endpoint azimuth angle of the second capping end as longitudinal seam endpoint features of the segment ring; obtain, according to the longitudinal seam endpoint features, a straight line where a longitudinal seam of the segment ring is located in a second two-dimensional coordinate system as a third straight line; wherein an abscissa of the second two-dimensional coordinate system is an axis line distance and an ordinate is an azimuth angle; extract, according to an average width value of the longitudinal seam of the segment ring and distances from each initial longitudinal seam point in the initial longitudinal seam point cloud data to the third straight line, longitudinal seam point cloud data of the segment ring from the initial longitudinal seam point cloud data.

8. A segmental division system of a shield tunnel, characterized by, comprise: a point cloud scanning module configured to acquire original point cloud data of a shield tunnel and perform preprocessing to obtain tunnel point cloud data; a ring joint identification module configured to identify each ring joint of the shield tunnel according to the tunnel point cloud data to obtain a fitting plane and target point cloud data of the ring joint; a division processing module configured to divide the tunnel point cloud data into independent point cloud data of a plurality of segment rings of the shield tunnel according to the fitting plane of each ring joint; a longitudinal seam identification module configured to identify a longitudinal seam of each segment ring according to the independent point cloud data of the segment ring to obtain longitudinal seam point cloud data of the segment ring; a segment segmentation module configured to segment the shield tunnel according to the target point cloud data of each ring joint and the longitudinal seam point cloud data of each segment ring to obtain a plurality of segment regions of the shield tunnel; wherein the identification of each ring joint according to the tunnel point cloud data to obtain the fitting plane and the target point cloud data of the ring joint comprises: according to an axis direction, a ring number, and a segment width of the shield tunnel, in combination with a preset cross-sectional width, intercepting point cloud data associated with the ring joint in the tunnel point cloud data as ring joint cross-sectional point cloud data; performing rejection processing on segment point cloud data in the ring joint cross-sectional point cloud data to obtain initial ring joint point cloud data; performing feature point identification processing on the ring joint according to the initial ring joint point cloud data to obtain an average width value and a plurality of feature points of the ring joint; Fitting a plane to the ring seams according to the average width values and a plurality of the feature points, to obtain a fitting plane of the ring seams and target point cloud data; The method further comprises: According to the front end axis direction and the rear end axis direction of the segment ring, in combination with a preset cross-sectional width, the point cloud data associated with the longitudinal seam of the segment ring is intercepted from the independent point cloud data as longitudinal seam cross-sectional point cloud data of the segment ring; According to the preset central angle feature set of the segment ring and the fitting plane of at least one of the ring seams, longitudinal seam point cloud extraction processing is performed on the longitudinal seam cross-sectional point cloud data, to obtain initial longitudinal seam point cloud data of the segment ring; According to the preset central angle feature set, the initial longitudinal seam point cloud data is screened and newly added, to obtain longitudinal seam point cloud data of the segment ring.

Images