Roadway / tunnel pipeline extraction method based on point cloud curvature and geometric feature fusion

Abstract

The invention discloses a roadway / tunnel pipeline extraction method based on point cloud curvature and geometric feature fusion, and the method comprises the steps: calculating the curvature value of each point in a roadway through the local curvature change of point cloud data in combination with a point cloud normal vector and a spatial distribution feature; a curvature threshold value is set, a clustering algorithm is combined, the point cloud data are classified, and a point cloud area conforming to pipeline features is identified; the pipeline extraction precision is optimized by combining the geometrical morphology and curvature characteristics of the pipeline; and the curvature features and the geometric features are fused, and the pipeline is segmented and labeled through a semantic segmentation and labeling algorithm based on deep learning. The method reduces the influence of noise and interference points, improves the recognition precision of the pipeline, achieves the accurate segmentation and marking of the pipeline, and provides more efficient and more accurate data support for the intelligent detection, maintenance and management of mine facilities.

Description

Technical Field

[0001] The invention relates to a lane / tunnel pipeline extraction method based on the fusion of point cloud curvature and geometric features, belonging to the technical field of pipeline facility three-dimensional point cloud processing. Background Art

[0002] During mining, pipeline facilities in the tunnel, such as power supply pipelines, water supply pipelines, communication lines, etc., are important parts to support the safe operation of the mine. These pipeline facilities are usually buried in complex terrain and may be deformed and damaged during the mining process, so regular inspection and maintenance are required.

[0003] Traditional pipeline inspection methods mainly rely on manual inspection or simple machine equipment, which cannot meet the needs of high efficiency and accuracy. Manual inspection has problems such as low efficiency, high missed detection rate and easy to be affected by human factors. In recent years, with the rapid development of deep learning and point cloud processing technology, three-dimensional point cloud data has become an important means of obtaining spatial information. In complex environments such as underground spaces, mine tunnels, and tunnels, point cloud data can provide rich three-dimensional geometric information, overcoming the limitations of traditional two-dimensional images in processing complex scenes. Point cloud-based deep learning technology, especially semantic segmentation and target detection methods, can extract effective geometric features from point clouds and classify and annotate them. This makes it possible to intelligently identify and accurately detect pipeline facilities in tunnels. However, the existing point cloud-based pipeline recognition technology still has the following problems: (1) In complex environments such as mine tunnels, point cloud data contains a lot of noise, overlap and irregular geometric shapes, especially the spatial features of pipeline facilities and the surrounding environment are highly overlapped, resulting in unclear edge features of facilities. Existing point cloud segmentation methods often have difficulty in accurately extracting pipelines. Traditional point cloud processing methods mostly rely on global or single features and cannot effectively handle these complexities and noises; (2) Traditional point cloud processing methods usually focus on local features such as normal vectors, geometric shapes, etc., but ignore important geometric information such as curvature and cannot effectively distinguish pipelines from other types of facilities or environments. Summary of the invention

[0004] The purpose of the present invention is to provide a lane / tunnel pipeline extraction method based on the fusion of point cloud curvature and geometric features, which can reduce the influence of noise and interference points, improve the recognition accuracy of pipelines, and realize accurate segmentation and labeling of pipelines, thereby providing more efficient and accurate data support for intelligent detection, maintenance and management of mining facilities.

[0005] In order to achieve the above object, the present invention provides a lane / tunnel pipeline extraction method based on the fusion of point cloud curvature and geometric features, comprising the following steps:

[0006] S1. Using the local curvature change of point cloud data, combined with the point cloud normal vector and spatial distribution characteristics, the curvature value of each point in the tunnel is calculated;

[0007] S2. Set the curvature threshold and combine it with the clustering algorithm to classify the point cloud data and identify the point cloud area that meets the pipeline characteristics;

[0008] S3, combining the geometric shape and curvature characteristics of the pipeline to optimize the pipeline extraction accuracy;

[0009] S4. The curvature features and geometric features are integrated to segment and label the pipeline through a semantic segmentation and labeling algorithm based on deep learning.

[0010] Furthermore, the specific method of S1 is: according to the different importance of local curvature changes, point cloud normal vectors and spatial distribution features of point cloud data, multi-dimensional feature fusion is performed through a splicing method to obtain the comprehensive feature value of each point cloud data, which is expressed as:

[0011] f i =[n i ,K i ,ρ(p i )];

[0012] Among them, n i is the normal vector, K i is the local curvature value, ρ(p i ) is the spatial distribution characteristic;

[0013] The spatial distribution characteristics are expressed as the distance between point clouds, which is divided into the distance between the pipeline and the inner wall of the lane / tunnel and the distance between the pipeline and the pipeline facilities. The calculation methods are as follows:

[0014] Distance d between pipeline and inner wall of lane / tunnel i It is expressed as:

[0015]

[0016] Among them, a point in the point cloud is P i (x i ,y i ,z i ), the equation of the tunnel wall is f(x,y,z)=0;

[0017] The relative distance between pipeline and pipeline facilities d facility It is expressed as:

[0018] d facility =‖P i -P facility ‖;

[0019] Among them, ‖P i -Pfacility ‖ is point P i To pipeline facility point P facility The Euclidean distance.

[0020] Furthermore, the method of S2 is as follows: the curvature threshold is selected based on the geometric features of the pipeline structure through the local curvature calculation of the point cloud to select the curvature range; similar points are grouped into a cluster through the clustering algorithm, and the point cloud area that meets the pipeline characteristics is identified, and the cluster that meets the pipeline characteristics is screened out through the clustering results; the local curvature of the point cloud is calculated by PCA, and the specific calculation process is as follows:

[0021] S2.1. Use PCA to calculate the covariance matrix of the point cloud in a local neighborhood: For each point p in the point cloud, select a local neighborhood N(p) containing the point and organize the coordinate information of the neighborhood points into a matrix X:

[0022]

[0023] Where n is the number of points in the neighborhood, x i ,y i , z i is the spatial coordinate of the i-th point in the point cloud;

[0024] S2.2. Calculate the covariance matrix C:

[0025]

[0026] in, is the mean vector of the neighborhood points;

[0027] S2.3. Calculate the eigenvalues ​​of the covariance matrix, perform eigenvalue decomposition on the covariance matrix C, and obtain the eigenvalues ​​λ1, λ2, and λ3:

[0028] C.v j =λ j ·v j (j=1,2,3);

[0029] Among them, v j is the corresponding eigenvector, representing the main changes of the point cloud in the three main directions; λ1 is the variance along the direction of maximum variance, λ2 is the variance along the direction of the second largest variance, and λ3 is the variance along the direction of minimum variance;

[0030] S2.4, the principal curvatures k1 and k2 correspond to the minimum and maximum eigenvalues ​​of the covariance matrix, respectively, which describe the curvature of the local surface of the point cloud in the two main directions:

[0031] k1=λ1,k2=λ2;

[0032] Gaussian curvature K is the product of two principal curvatures:

[0033] K = k1·k2 = λ1·λ2;

[0034] If K = 0, it means that the point is in a flat or straight area; if K>0, it means that the point is on a convex surface; if K<0, the point is on a concave surface;

[0035] S2.5, similar points are grouped into a cluster through clustering algorithm, focusing on neighborhood calculation, core point definition, cluster expansion and density reachability. Through the neighborhood radius ∈ and the minimum number of points MinPts, the algorithm can automatically identify and expand clusters and handle complex data with large density changes;

[0036] S2.5.1. The method of neighborhood calculation is: for a data point p, its neighborhood N(p) is defined as all points within a given neighborhood radius ε, that is:

[0037] N(p)={q∈D|||pq||≤ε};

[0038] Where D is the set of data points, p and q are two points in the point cloud, ||pq|| is the Euclidean distance between point p and point q, and ε is the neighborhood radius, which indicates the maximum distance that p can affect;

[0039] The Euclidean distance calculation formula is:

[0040]

[0041] Where p = (x p ,y p ,z p ) and q=(x q ,y q ,z q ) are the coordinates of the three-dimensional point;

[0042] S2.5.2. The definition of a core point is: If a point p is a core point, if and only if its neighborhood N(p) contains at least MinPts points:

[0043] |N(p)|≥MinPts;

[0044] Among them, |N(p)| represents the number of points contained in the neighborhood of point p, and MinPts is a preset parameter, which represents the minimum number of neighborhood points required for a point to be considered as a core point;

[0045] S2.5.3. After finding the core point, the cluster is expanded based on the density-based clustering method, and the points in the neighborhood are iteratively added to the cluster. The expansion process is carried out by the following formula:

[0046] E = {p|p∈D, p is a core point or p is density-reachable};

[0047] Here, E represents the cluster being expanded, and E is a set that contains all the points currently known to belong to a cluster. The expansion of the core point continues to explore its neighborhood and add new points until there are no more points that can be added;

[0048] S2.5.4. A point p is density-reachable if and only if it is a core point or is in the neighborhood of a core point and is connected from the core point through a series of density-reachable points;

[0049] Points p and q must be density-connected if and only if there exists a core point r such that both points p and q are within the neighborhood of core point r and are connected by r.

[0050] Furthermore, the method of S3 is: using the least squares method to fit the straight line portion of the pipeline, and obtaining the direction, length and position information of the pipeline by fitting several points in the point cloud;

[0051] S3.1, the linear fitting related formula is as follows:

[0052] For a set of points P1, P2, ..., P n ,The goal of the least squares method is to find a straight line y = mx + t such that:

[0053]

[0054] Among them, x i ,y i It's point P i The coordinates of , m and t are the fitted straight line parameters;

[0055] For the curved pipe section, the least squares method is used to obtain:

[0056]

[0057] Among them, a, b, h are fitting curve parameters;

[0058] S3.2. For a portion of the pipeline corresponding to the identified point cloud cluster C, the curvature calculation formula is:

[0059]

[0060] Among them, k i is the curvature of point i, r i is the radius of curvature at that point, and are the tangent and normal of the point respectively;

[0061] S3.3. The curvature threshold is set according to the calculated curvature value. During the optimization process, the geometric morphology information is used to determine the boundary of the pipeline. The curvature information is used to determine the curved part of the pipeline. For the curved part, the curvature change trend is combined to determine whether it is a natural bend of the pipeline.

[0062] Furthermore, the specific process of S4 is as follows:

[0063] S4.1. Input the comprehensive feature value into the improved Pointnet++ network, and extract the multi-scale local features of the point cloud through the Set Abstraction layer; combine the local geometric information with the global information, and extract rich feature information by sampling and feature aggregation at different scales of the point cloud data. In this layer, the features of each point in the point cloud are processed by the MLP multi-layer perceptron to generate local features. Then the global feature representation of each sampling point is obtained through pooling operation;

[0064] S4.2, Feature Propagation layer is used to fuse local features at different levels with global features and restore the high-resolution structure of point cloud data;

[0065] S4.3. After feature extraction in the Set Abstraction and Feature Propagation layers, the improved PointNet++ classifies or segments the point cloud through the fully connected layer FC; the FC layer is used to map the fused multimodal features to the final label space for pipeline segmentation:

[0066]

[0067] Among them, y i It's point p i The classification or segmentation label, Softmax function is used to calculate the probability that each point belongs to each category;

[0068] S4.4. For each point p i , whose category probability is p i =[p1,p2,…,p k ], the loss function evaluates the segmentation effect by calculating the cross entropy of each point. The specific formula is:

[0069]

[0070] Where s is the total number of points in the point cloud, k is the number of categories, and y i,g It's point p i The true label of category g, p i,g is the probability predicted by the network that the point belongs to category g.

[0071] The present invention accurately identifies and extracts pipelines in complex tunnels by fusing the curvature features and geometric structure information of the point cloud, and further accurately segments and optimizes the pipeline area through point cloud area division based on the DBSCAN clustering algorithm; finally, through the improved deep learning network model, the curvature features and geometric features are integrated to improve the accuracy of pipeline extraction and annotation, and can achieve high-quality pipeline classification in complex environments. Among them, curvature information can effectively distinguish the geometric differences between pipelines and other facilities, while geometric features such as normal vectors and PCA features enhance the understanding of the spatial distribution and morphology of pipelines. Compared with the traditional point cloud segmentation method, the present invention realizes pipeline identification in dense and overlapping environments, improves the accuracy and robustness of pipeline extraction, reduces the phenomenon of mis-segmentation and missed segmentation, and stably outputs accurate segmentation results, especially in complex and dynamic mining environments; through the point cloud segmentation method based on deep learning, combined with curvature and geometric features, the efficiency is significantly improved in the automated pipeline identification and segmentation tasks. The present invention realizes automatic identification and annotation of pipelines in tunnels, reduces manual intervention, and improves work efficiency. The present invention is suitable for rapid processing of large-scale point cloud data, meeting the needs for real-time and accurate pipeline monitoring and protection in modern mine and urban infrastructure management. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] Figure 1 It is a work flow chart of the present invention;

[0073] Figure 2 It is a visualization diagram of local point cloud normal vectors of the present invention, wherein Figure (a) is a schematic diagram of local pipeline normal vectors, and Figure (b) is a schematic diagram of local tunnel inner wall normal vectors;

[0074] Figure 3 is a schematic diagram of point cloud curvature information of the present invention;

[0075] Figure 4 is a curvature threshold and clustering algorithm workflow diagram of the present invention;

[0076] Figure 5 It is a result diagram of the curvature information clustering algorithm of the present invention, wherein Figure (a) is an original point cloud information diagram of the pipeline, Figure (b) is a result diagram of the pipeline point cloud clustering processing, Figure (c) is an original point cloud information diagram of the working power transmission line facility, and Figure (d) is a result diagram of the working power transmission line facility point cloud clustering processing;

[0077] Figure 6 Schematic diagram of a mine tunnel point cloud data set for training a network model according to the present invention, wherein Figure (a) is a labeled pipeline, Figure (b) is a transportation track facility, Figure (c) is a lighting equipment line facility, and Figures (d) and (e) are working power transmission line facilities;

[0078] Figure 7 This is a workflow diagram of the deep learning network based on the fusion of curvature features and geometric features of the present invention. DETAILED DESCRIPTION

[0079] The present invention will be further described below in conjunction with the accompanying drawings.

[0080] like Figure 1 As shown, a lane / tunnel pipeline extraction method based on the fusion of point cloud curvature and geometric features includes the following steps:

[0081] S1. Using the local curvature change of point cloud data, combined with the point cloud normal vector and spatial distribution characteristics, the curvature value of each point in the tunnel is calculated;

[0082] S2. Set the curvature threshold and combine it with the clustering algorithm to classify the point cloud data and identify the point cloud area that meets the pipeline characteristics;

[0083] S3, combining the geometric shape and curvature characteristics of the pipeline to optimize the pipeline extraction accuracy;

[0084] S4. The curvature features and geometric features are integrated to segment and label the pipeline through a semantic segmentation and labeling algorithm based on deep learning.

[0085] As a preferred implementation, in step S1, representative geometric features in the point cloud are extracted by normal vector estimation and local curvature calculation. After loading the point cloud data, the point cloud is analyzed using PCA principal component analysis to obtain the local features of each point. In order to improve the accuracy of normal vector estimation, the least squares method based on neighborhood points is used to calculate the normal vector. On this basis, the local neighborhood of each point is analyzed by PCA to extract the main direction and curvature features of the point cloud. During the PCA calculation, the eigenvalues ​​of the covariance matrix of the neighborhood points are taken, and the minimum eigenvalue reflects the curvature information of the point in the neighborhood. Through this process, the key features in the point cloud are efficiently extracted, providing basic data for subsequent pipeline extraction and optimization. The calculated normal vector and curvature information also provide valuable input for the deep learning model, further improving the accuracy of pipeline segmentation and annotation. The specific method of S1 is: in view of the different importance of local curvature changes, point cloud normal vectors and spatial distribution features of point cloud data, multi-dimensional feature fusion is performed through the splicing method to obtain the comprehensive eigenvalues ​​of each point cloud data, expressed as:

[0086] f i =[n i ,K i ,ρ(p i )];

[0087] Among them, n i is the normal vector, Ki is the local curvature value, ρ(p i ) is the spatial distribution characteristic;

[0088] The spatial distribution characteristics are expressed as the distance between point clouds, which is divided into the distance between the pipeline and the inner wall of the lane / tunnel and the distance between the pipeline and the pipeline facilities. The calculation methods are as follows:

[0089] Distance d between pipeline and inner wall of lane / tunnel i It is expressed as:

[0090]

[0091] Among them, a point in the point cloud is P i (x i ,y i ,z i ), the equation of the tunnel wall is f(x,y,z)=0;

[0092] The relative distance between pipeline and pipeline facilities d facility It is expressed as:

[0093] d facility =‖P i -P facility ‖;

[0094] Among them, ‖P i -P facility ‖ is point P i To pipeline facility point P facility The Euclidean distance.

[0095] like Figure 2 As shown in (a) and (b), the normal vector of the point cloud is calculated and visualized through the geometric distribution information of the point cloud data; the curvature difference of the point cloud data is visualized by calculating the local curvature, as shown in Figure 3 shown.

[0096] As a preferred implementation, the method of S2 is as follows: the curvature threshold is based on the geometric features of the pipeline structure, and the curvature range is selected by calculating the local curvature of the point cloud; similar points are grouped into a cluster by a clustering algorithm, and the point cloud area that meets the pipeline characteristics is identified. The cluster that meets the pipeline characteristics is screened out by the clustering results; the local curvature of the point cloud is calculated by PCA, and the specific calculation process is as follows:

[0097] S2.1. Use PCA to calculate the covariance matrix of the point cloud in a local neighborhood: For each point p in the point cloud, select a local neighborhood N(p) containing the point and organize the coordinate information of the neighborhood points into a matrix X:

[0098]

[0099] Where n is the number of points in the neighborhood, x i ,y i , z i is the spatial coordinate of the i-th point in the point cloud;

[0100] S2.2. Calculate the covariance matrix C:

[0101]

[0102] in, is the mean vector of the neighborhood points;

[0103] S2.3. Calculate the eigenvalues ​​of the covariance matrix, perform eigenvalue decomposition on the covariance matrix C, and obtain the eigenvalues ​​λ1, λ2, and λ3:

[0104] C.v j =λ j ·v j (j=1,2,3);

[0105] Among them, v j is the corresponding eigenvector, representing the main changes of the point cloud in the three main directions; λ1 is the variance along the direction of maximum variance, λ2 is the variance along the direction of the second largest variance, and λ3 is the variance along the direction of minimum variance;

[0106] S2.4, the principal curvatures k1 and k2 correspond to the minimum and maximum eigenvalues ​​of the covariance matrix, respectively, which describe the curvature of the local surface of the point cloud in the two main directions:

[0107] k1=λ1,k2=λ2;

[0108] Gaussian curvature K is the product of two principal curvatures:

[0109] K = k1·k2 = λ1·λ2;

[0110] If K = 0, it means that the point is in a flat or straight area; if K>0, it means that the point is on a convex surface; if K<0, the point is on a concave surface;

[0111] S2.5, similar points are grouped into a cluster through clustering algorithm, focusing on neighborhood calculation, core point definition, cluster expansion and density reachability. Through the neighborhood radius ε and the minimum number of points MinPts, the algorithm can automatically identify and expand clusters and handle complex data with large density changes;

[0112] S2.5.1. The method of neighborhood calculation is: for a data point p, its neighborhood N(p) is defined as all points within a given neighborhood radius ε, that is:

[0113] N(p)={q∈D|||pq||≤ε};

[0114] Where D is the set of data points, p and q are two points in the point cloud, ||pq|| is the Euclidean distance between point p and point q, and ε is the neighborhood radius, which indicates the maximum distance that p can affect;

[0115] The Euclidean distance calculation formula is:

[0116]

[0117] Where p = (x p ,y p ,z p ) and q=(x q ,y q ,z q ) are the coordinates of the three-dimensional point;

[0118] S2.5.2. The definition of a core point is: If a point p is a core point, if and only if its neighborhood N(p) contains at least MinPts points:

[0119] |N(p)|≥MinPts;

[0120] Among them, |N(p)| represents the number of points contained in the neighborhood of point p, and MinPts is a preset parameter, which represents the minimum number of neighborhood points required for a point to be considered as a core point;

[0121] S2.5.3. After finding the core point, the cluster is expanded based on the density-based clustering method, and the points in the neighborhood are iteratively added to the cluster. The expansion process is carried out by the following formula:

[0122] E = {p|p∈D, p is a core point or p is density-reachable};

[0123] Here, E represents the cluster being expanded, and E is a set that contains all the points currently known to belong to a cluster. The expansion of the core point continues to explore its neighborhood and add new points until there are no more points that can be added;

[0124] S2.5.4. A point p is density-reachable if and only if it is a core point or is in the neighborhood of a core point and is connected from the core point through a series of density-reachable points;

[0125] Points p and q must be density-connected if and only if there exists a core point r such that both points p and q are within the neighborhood of core point r and are connected by r.

[0126] Through this step, the area that meets the pipeline characteristics can be effectively separated from the complex point cloud data. Figure 4The curvature threshold and clustering algorithm module diagram flow chart is shown in FIG. Figure 5 As shown in the figure, the original point cloud data obtained by the clustering algorithm and the point cloud data after clustering are displayed, where: Figure 5 (a) is the original point cloud information map of the pipeline, (b) is the result map of the pipeline point cloud clustering processing, (c) is the original point cloud information map of the working transmission line facilities, and (d) is the result map of the working transmission line facility point cloud clustering processing; Figure 6 FIG. 1 is a diagram of a mine tunnel point cloud data set trained by the method of the present invention, wherein: Figure 6 (a) is a marked pipeline diagram, (b) is a transportation track facility diagram, (c) is a lighting equipment line facility diagram, (d) and (e) are working power transmission line facility diagrams;

[0127] As a preferred implementation, the method of S3 is: using the least squares method to fit the straight line portion of the pipeline, and obtaining the direction, length and position information of the pipeline by fitting several points in the point cloud;

[0128] S3.1, the linear fitting related formula is as follows:

[0129] For a set of points P1, P2, ..., P n ,The goal of the least squares method is to find a straight line y = mx + t such that:

[0130]

[0131] Among them, x i ,y i It's point P i The coordinates of , m and t are the fitted straight line parameters;

[0132] For the curved pipe section, the least squares method is used to obtain:

[0133]

[0134] Among them, a, b, and h are fitting curve parameters;

[0135] S3.2. For a portion of the pipeline corresponding to the identified point cloud cluster C, the curvature calculation formula is:

[0136]

[0137] Among them, k i is the curvature of point i, r i is the radius of curvature at that point, and are the tangent and normal of the point respectively;

[0138] S3.3. The curvature threshold is set according to the calculated curvature value. During the optimization process, the geometric morphology information is used to determine the boundary of the pipeline. The curvature information is used to determine the curved part of the pipeline. For the curved part, the curvature change trend is combined to determine whether it is a natural bend of the pipeline.

[0139] This step can refine and optimize the pipeline extraction results, improve the segmentation accuracy of the pipeline, and provide a more accurate basis for subsequent pipeline labeling and identification.

[0140] As a preferred embodiment, Figure 7 As shown, the specific process of S4 is:

[0141] S4.1. Input the comprehensive feature value into the improved Pointnet++ network, and extract the multi-scale local features of the point cloud through the Set Abstraction layer; combine the local geometric information with the global information, and extract rich feature information by sampling and feature aggregation at different scales of the point cloud data. In this layer, the features of each point in the point cloud are processed by the MLP multi-layer perceptron to generate local features. Then the global feature representation of each sampling point is obtained through pooling operation;

[0142] S4.2, Feature Propagation layer is used to fuse local features at different levels with global features and restore the high-resolution structure of point cloud data;

[0143] S4.3. After feature extraction in the Set Abstraction and Feature Propagation layers, the improved PointNet++ classifies or segments the point cloud through the fully connected layer FC; the FC layer is used to map the fused multimodal features to the final label space for pipeline segmentation:

[0144]

[0145] Among them, y i It's point p i The classification or segmentation label, Softmax function is used to calculate the probability that each point belongs to each category;

[0146] S4.4. For each point p i , whose category probability is p i =[p1,p2,…,p k ], the loss function evaluates the segmentation effect by calculating the cross entropy of each point. The specific formula is:

[0147]

[0148] Where s is the total number of points in the point cloud, k is the number of categories, and y i,g It's point p i The true label of category g, p i,g is the probability predicted by the network that the point belongs to category g.

Claims

1. A lane / tunnel pipeline extraction method based on the fusion of point cloud curvature and geometric features, characterized in that: The steps include: S1. Using the local curvature change of point cloud data, combined with the point cloud normal vector and spatial distribution characteristics, the curvature value of each point in the tunnel is calculated; S2. Set the curvature threshold and combine it with the clustering algorithm to classify the point cloud data and identify the point cloud area that meets the pipeline characteristics; S3, combining the geometric shape and curvature characteristics of the pipeline to optimize the pipeline extraction accuracy; S4. The curvature features and geometric features are integrated to segment and label the pipeline through a semantic segmentation and labeling algorithm based on deep learning.

2. The lane / tunnel pipeline extraction method based on the fusion of point cloud curvature and geometric features according to claim 1 is characterized in that: The specific method of S1 is: according to the local curvature change of point cloud data, the different importance of point cloud normal vector and spatial distribution features, multi-dimensional feature fusion is performed through the splicing method to obtain the comprehensive feature value of each point cloud data, which is expressed as: f i =[n i ,K i ,ρ(p i )]; Among them, n i is the normal vector, K i is the local curvature value, ρ(p i ) is the spatial distribution characteristic; The spatial distribution characteristics are expressed as the distance between point clouds, which is divided into the distance between the pipeline and the inner wall of the lane / tunnel and the distance between the pipeline and the pipeline facilities. The calculation methods are as follows: Distance d between pipeline and inner wall of lane / tunnel i It is expressed as: Among them, a point in the point cloud is P i (x i ,y i ,z i ), the equation of the tunnel wall is f(x,y,z)=0; The relative distance between pipeline and pipeline facilities d facility It is expressed as: d facility =‖P i -P facility ‖; Among them, ‖P i -P facility ‖ is point P i To pipeline facility point P facility The Euclidean distance.

3. The lane / tunnel pipeline extraction method based on the fusion of point cloud curvature and geometric features according to claim 1 or 2 is characterized in that: The method of S2 is as follows: the curvature threshold is based on the geometric characteristics of the pipeline structure, and the curvature range is selected by calculating the local curvature of the point cloud; similar points are grouped into a cluster by a clustering algorithm, and the point cloud area that meets the pipeline characteristics is identified. The cluster that meets the pipeline characteristics is screened out by the clustering results; the local curvature of the point cloud is calculated by PCA, and the specific calculation process is as follows: S2.

1. Use PCA to calculate the covariance matrix of the point cloud in a local neighborhood: For each point p in the point cloud, select a local neighborhood N(p) containing the point and organize the coordinate information of the neighborhood points into a matrix X: Where n is the number of points in the neighborhood, x i ,y i , z i is the spatial coordinate of the i-th point in the point cloud; S2.

2. Calculate the covariance matrix C: in, is the mean vector of the neighborhood points; S2.

3. Calculate the eigenvalues ​​of the covariance matrix, perform eigenvalue decomposition on the covariance matrix C, and obtain the eigenvalues ​​λ1, λ2, and λ3: C·v j =λ j ·in j (j=1,2,3); Among them, j represents a point in the point cloud or a sample in the point cloud, v j is the corresponding eigenvector, representing the main changes of the point cloud in the three main directions; λ1 is the variance along the direction of maximum variance, λ2 is the variance along the direction of the second largest variance, and λ3 is the variance along the direction of minimum variance; S2.4, the principal curvatures k1 and k2 correspond to the minimum and maximum eigenvalues ​​of the covariance matrix, respectively, which describe the curvature of the local surface of the point cloud in the two main directions: k1=λ1,k2=λ2; Gaussian curvature K is the product of two principal curvatures: K = k1·k2 = λ1·λ2; If K = 0, it means that the point is in a flat or straight area; if K>0, it means that the point is on a convex surface; if K<0, the point is on a concave surface; S2.5, similar points are grouped into a cluster through clustering algorithm, focusing on neighborhood calculation, core point definition, cluster expansion and density reachability. Through the neighborhood radius ε and the minimum number of points MinPts, the algorithm can automatically identify and expand clusters and handle complex data with large density changes; S2.5.

1. The method of neighborhood calculation is: for a data point p, its neighborhood N(p) is defined as all points within a given neighborhood radius ε, that is: N(p)={q∈D|||pq||≤ε}; Where D is the set of data points, p and q are two points in the point cloud, ||pq|| is the Euclidean distance between point p and point q, and ε is the neighborhood radius, which indicates the maximum distance that p can affect; The Euclidean distance calculation formula is: Where p = (x p ,y p ,z p ) and q=(x q ,y q ,z q ) are the coordinates of the three-dimensional point; S2.5.

2. The definition of a core point is: If a point p is a core point, if and only if its neighborhood N(p) contains at least MinPts points: |N(p)|≥MinPts; Among them, |N(p)| represents the number of points contained in the neighborhood of point p, and MinPts is a preset parameter, which represents the minimum number of neighborhood points required for a point to be considered as a core point; S2.5.

3. After finding the core point, the cluster is expanded based on the density-based clustering method, and the points in the neighborhood are iteratively added to the cluster. The expansion process is carried out by the following formula: E = {p|p∈D, p is a core point or p is density-reachable}; Among them, E represents the cluster being expanded, which is a set containing all the points currently known to belong to a cluster; the expansion of the core point continues to explore its neighborhood and add new points until no more points can be added; S2.5.

4. A point p is density-reachable if and only if it is a core point or is in the neighborhood of a core point and is connected from the core point through a series of density-reachable points; Points p and q must be density-connected if and only if there exists a core point r such that both points p and q are within the neighborhood of core point r and are connected by r.

4. The lane / tunnel pipeline extraction method based on the fusion of point cloud curvature and geometric features according to claim 3 is characterized in that: The method of S3 is: using the least squares method to fit the straight line part of the pipeline, and obtaining the direction, length and position information of the pipeline by fitting several points in the point cloud; S3.1, the linear fitting related formula is as follows: For a set of points P1, P2, ..., P n , the goal of the least squares method is to find a straight line y = mx + t such that: Among them, x i ,y i It's point P i The coordinates of , m and t are the fitted straight line parameters; For the curved pipe section, the least squares method is used to obtain: Among them, a, b, h are fitting curve parameters; S3.

2. For a portion of the pipeline corresponding to the identified point cloud cluster C, the curvature calculation formula is: Among them, k i is the curvature of point i, r i is the radius of curvature of point i, and are the tangent and normal of point i respectively; S3.

3. The curvature threshold is set according to the calculated curvature value. During the optimization process, the geometric morphology information is used to determine the boundary of the pipeline. The curvature information is used to determine the curved part of the pipeline. For the curved part, the curvature change trend is combined to determine whether it is a natural bend of the pipeline.

5. The lane / tunnel pipeline extraction method based on the fusion of point cloud curvature and geometric features according to claim 4 is characterized in that: The specific process of S4 is as follows: S4.

1. Input the comprehensive feature value into the improved Pointnet++ network, and extract the multi-scale local features of the point cloud through the Set Abstraction layer; Combine local geometric information with global information, extract rich feature information by sampling and feature aggregation at different scales of point cloud data. In this layer, the features of each point in the point cloud are processed by the MLP multi-layer perceptron to generate local features. Then the global feature representation of each sampling point is obtained through pooling operation; S4.2, Feature Propagation layer is used to fuse local features at different levels with global features and restore the high-resolution structure of point cloud data; S4.

3. After feature extraction in the Set Abstraction and Feature Propagation layers, the improved PointNet++ classifies or segments the point cloud through the fully connected layer FC; the FC layer is used to map the fused multimodal features to the final label space for pipeline segmentation: Among them, y i It's point p i The classification or segmentation label, Softmax function is used to calculate the probability that each point belongs to each category; S4.

4. For each point p i , whose category probability is p i =[p1,p2,…,p k ], the loss function evaluates the segmentation effect by calculating the cross entropy of each point. The specific formula is: Where s is the total number of points in the point cloud, k is the number of categories, and y i,g It's point p i The true label of category g, p i,g is the point p predicted by the network i The probability of belonging to class g.

Images