A method, device, medium and equipment for segmenting leaky cable point cloud in tunnel

Abstract

The present invention discloses a method, device, medium and equipment for segmenting a leaky communication cable point cloud in a tunnel. The method comprises: obtaining tunnel point cloud data and point cloud data at one end point of a leaky communication cable to be segmented; segmenting the tunnel point cloud data into a plurality of sub-tunnel point cloud data according to a preset distance; obtaining the tunnel ground plane equation and tunnel direction vector of each sub-tunnel point cloud data; segmenting the leaky communication cable point cloud data from the tunnel point cloud data according to the tunnel direction vector and the point cloud data at one end point of the leaky communication cable to be segmented. The present invention can adapt to the direction of complex tunnels, has strong anti-interference ability, and can achieve stable and accurate leaky cable point cloud segmentation.

Description

Technical Field

[0001] The present invention relates to the technical field of point cloud segmentation, and in particular to a method, device, medium and equipment for segmenting a point cloud of a leaky communication cable in a tunnel. Background Art

[0002] In the modern transportation system, the scale of tunnel construction is constantly expanding, and the stability of its internal communication has become the key to ensuring traffic safety and operational efficiency. As the core component of the tunnel communication system, the communication leaky cable bears the heavy responsibility of signal transmission and coverage, and its operating status is directly related to the communication quality. With the increase in traffic flow and the increase in communication demand, the accurate monitoring and maintenance of the leaky cable status has become increasingly important.

[0003] However, the traditional methods for detecting and analyzing leaky communication cables in tunnels have obvious shortcomings. Conventional detection methods rely on manual inspections or simple equipment measurements, which make it difficult to fully and accurately obtain the spatial position and complex morphological information of leaky cables. Especially in tunnel environments with dim light and complex structures, the existing methods have poor segmentation efficiency and accuracy when processing point cloud data of leaky communication cables, resulting in delayed diagnosis and positioning of leaky cable faults and large deviations, which seriously affects the reliability and stability of tunnel communication systems. Summary of the invention

[0004] The purpose of the present invention is to overcome the deficiencies in the prior art and provide a method, device, medium and equipment for segmenting the point cloud of a leaky cable in a tunnel. To achieve the above purpose, the present invention is implemented by adopting the following technical solutions:

[0005] In a first aspect, the present invention provides a method for segmenting a leaky cable point cloud in a tunnel, comprising:

[0006] Acquire the tunnel point cloud data and the point cloud data at one end point of the communication leaky cable to be segmented;

[0007] According to a preset distance, the tunnel point cloud data is divided into a plurality of sub-tunnel point cloud data;

[0008] Obtaining the tunnel ground plane equation and tunnel direction vector of each sub-tunnel point cloud data;

[0009] According to the tunnel direction vector and the point cloud data at one end point of the communication leaky cable to be segmented, the communication leaky cable point cloud data is segmented from the tunnel point cloud data; the step of segmenting the communication leaky cable point cloud data from the tunnel point cloud data according to the tunnel direction vector and the point cloud data at one end point of the communication leaky cable to be segmented includes:

[0010] Acquire sub-tunnel point cloud data corresponding to the tunnel direction vector;

[0011] Calculating the average density distance value of the sub-tunnel point cloud data;

[0012] Taking the point cloud coordinates at the endpoint as the starting point, and taking 1 / 10 of the average density distance value as the step length along the tunnel direction vector, a reference point cloud data is generated;

[0013] Calculating the distance between the sub-tunnel point cloud data and the reference point cloud data;

[0014] Determine that the point cloud data whose distance value is less than the average density distance value is the communication leaky cable point cloud data corresponding to the sub-tunnel;

[0015] The communication leaky cable point cloud data corresponding to all the sub-tunnels are superimposed to obtain the communication leaky cable point cloud data.

[0016] In combination with the first aspect, optionally, the obtaining of the tunnel point cloud data and the point cloud data at an end point of the leaky communication cable to be segmented includes:

[0017] Use laser point cloud scanning equipment to collect tunnel point cloud data;

[0018] Importing the tunnel point cloud data into point cloud viewing software;

[0019] A point cloud at the endpoint of the communication leaky cable to be segmented is selected, and the coordinate information of the point cloud at the endpoint is recorded.

[0020] In combination with the first aspect, optionally, dividing the tunnel point cloud data into a plurality of sub-tunnel point cloud data according to a preset distance includes:

[0021] Obtain a directional bounding box of the tunnel point cloud data;

[0022] Determining a direction category of the tunnel point cloud data according to the directional bounding box, the direction category including an x-axis direction and a y-axis direction;

[0023] Determining a segmentation bounding box according to the direction category, the preset distance and the directional bounding box;

[0024] According to the segmentation bounding box, the tunnel point cloud data is segmented into a plurality of sub-tunnel point cloud data.

[0025] In combination with the first aspect, optionally, determining the direction category of the tunnel point cloud data according to the directional bounding box includes:

[0026] Obtain the coordinates of two endpoints of a longest side of the oriented bounding box;

[0027] Calculate the angle between the longest side and the x-axis and the y-axis according to the coordinates of the two endpoints of the longest side;

[0028] If the x-axis angle is greater than the y-axis angle, the direction category is determined to be the y-axis direction; otherwise, the direction category is determined to be the x-axis direction.

[0029] In combination with the first aspect, optionally, determining the segmentation bounding box according to the direction category, the preset distance and the directional bounding box includes:

[0030] Obtain the coordinates of the two endpoints of the longest side of the oriented bounding box;

[0031] If the direction category is the x-axis direction, the endpoint with the smaller x value among the two endpoints of the longest side is selected as the starting point; otherwise, the endpoint with the smaller y value among the two endpoints of the longest side is selected as the starting point;

[0032] According to the starting point and the preset distance, sampling is performed on the longest side to obtain a plurality of segmentation points;

[0033] The segmentation bounding box is determined according to the segmentation points.

[0034] In combination with the first aspect, optionally, the obtaining of the tunnel ground plane equation and the tunnel direction vector of each sub-tunnel point cloud data includes:

[0035] Performing plane fitting on the sub-tunnel point cloud data to determine tunnel ground point cloud data and the tunnel ground plane equation;

[0036] According to the tunnel ground plane equation, segmenting the running track point cloud data;

[0037] A straight line fitting is performed on the running track point cloud data, and a direction vector of the fitting line is determined as the tunnel direction vector.

[0038] In a second aspect, the present invention provides a device for segmenting a leaky cable point cloud in a tunnel, comprising:

[0039] Point cloud acquisition module: acquires the point cloud data of the tunnel and the point cloud data at one end point of the communication leaky cable to be segmented;

[0040] Sub-tunnel segmentation module: segmenting the tunnel point cloud data into a plurality of sub-tunnel point cloud data according to a preset distance;

[0041] Direction vector acquisition module: obtains the tunnel ground plane equation and tunnel direction vector of each sub-tunnel point cloud data;

[0042] Leaky cable point cloud segmentation module: segmenting the communication leaky cable point cloud data from the tunnel point cloud data according to the tunnel direction vector and the point cloud data at one end point of the communication leaky cable to be segmented; segmenting the communication leaky cable point cloud data from the tunnel point cloud data according to the tunnel direction vector and the point cloud data at one end point of the communication leaky cable to be segmented, including:

[0043] Acquire sub-tunnel point cloud data corresponding to the tunnel direction vector;

[0044] Calculating the average density distance value of the sub-tunnel point cloud data;

[0045] Taking the point cloud coordinates at the endpoint as the starting point, and taking 1 / 10 of the average density distance value as the step length along the tunnel direction vector, a reference point cloud data is generated;

[0046] Calculating the distance between the sub-tunnel point cloud data and the reference point cloud data;

[0047] Determine that the point cloud data whose distance value is less than the average density distance value is the communication leaky cable point cloud data corresponding to the sub-tunnel;

[0048] The communication leaky cable point cloud data corresponding to all the sub-tunnels are superimposed to obtain the communication leaky cable point cloud data.

[0049] In a third aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for segmenting a leaky cable point cloud for communication in a tunnel as described in any one of the first aspects is implemented.

[0050] In a fourth aspect, the present invention provides a device, comprising:

[0051] A memory for storing instructions;

[0052] A processor is used to execute the instructions so that the device performs operations to implement the method for segmenting the leaky cable point cloud in a tunnel as described in any one of the first aspects.

[0053] Compared with the prior art, the method, device, medium and equipment for segmenting the point cloud of a leaky cable in a tunnel provided by the embodiment of the present invention have the following beneficial effects:

[0054] The present invention obtains tunnel point cloud data and point cloud data at one end point of the communication leaky cable to be segmented; according to a preset distance, the tunnel point cloud data is segmented into a plurality of sub-tunnel point cloud data; the tunnel ground plane equation and tunnel direction vector of each sub-tunnel point cloud data are obtained; according to the tunnel direction vector and the point cloud data at one end point of the communication leaky cable to be segmented, the communication leaky cable point cloud data is segmented from the tunnel point cloud data. The present invention can adapt to the direction of complex tunnels, has strong anti-interference ability, and can achieve stable and accurate leaky cable point cloud segmentation. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 A flowchart of a method for segmenting a leaky cable point cloud for communication in a tunnel provided in Example 1 of the present invention. DETAILED DESCRIPTION

[0056] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of this embodiment can be combined with each other. The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0057] Embodiment 1:

[0058] like Figure 1 As shown, an embodiment of the present invention provides a method for segmenting a leaky cable point cloud in a tunnel, comprising:

[0059] S1: Obtaining the tunnel point cloud data and the point cloud data at one end point of the communication leaky cable to be segmented;

[0060] In a specific embodiment, the step of obtaining the tunnel point cloud data and the point cloud data at one end point of the leaky communication cable to be segmented includes:

[0061] S1-1: Use laser point cloud scanning equipment to collect tunnel point cloud data;

[0062] S1-2: Importing the tunnel point cloud data into the point cloud viewing software;

[0063] S1-3: Select a point cloud at the endpoint of the communication leaky cable to be segmented, and record the coordinate information of the point cloud at the endpoint.

[0064] S2: dividing the tunnel point cloud data into a plurality of sub-tunnel point cloud data according to a preset distance;

[0065] In a specific embodiment, the tunnel point cloud data is divided into a plurality of sub-tunnel point cloud data according to a preset distance, including:

[0066] S2-1: Obtain a directional bounding box of the tunnel point cloud data;

[0067] Specifically, the bounding box of the point cloud includes an axial bounding box and an oriented bounding box. The axial bounding box is the smallest bounding box aligned with the coordinate axis. It is a simple model but has poor compactness. The oriented bounding box is a bounding box aligned with the direction of the object. It is no longer limited to the alignment of the coordinate axis, so it is more compact when enclosing the point cloud. Since the tunnel point cloud data in the present invention is not necessarily parallel to the coordinate axis, it is more suitable to use an oriented bounding box. The calculation of the oriented bounding box of the point cloud can be obtained using get_oriented_bounding_box() in the open3d library.

[0068] S2-2: determining a direction category of the tunnel point cloud data according to the directional bounding box, where the direction category includes an x-axis direction and a y-axis direction;

[0069] In a specific embodiment, determining the direction category of the tunnel point cloud data according to the directional bounding box includes:

[0070] S2-2-1: Obtain the coordinates of two endpoints of the longest side of the oriented bounding box;

[0071] S2-2-2: Calculate the angle between the longest side and the x-axis and the angle between the longest side and the y-axis according to the coordinates of the two endpoints of the longest side;

[0072] S2-2-3: If the x-axis angle is greater than the y-axis angle, the direction category is determined to be the y-axis direction; otherwise, the direction category is determined to be the x-axis direction.

[0073] Specifically, assuming that the coordinates of the two endpoints of the longest side are (0.0, 0.0, 0.0) and (1.0, 0.5, 0.0), the angle between this longest side and the x-axis is 26.56 degrees, and the angle between this longest side and the y-axis is 63.44 degrees. Therefore, the y-axis angle is greater than the x-axis angle, and the direction category of the longest side is the x-axis direction.

[0074] S2-3: determining a segmentation bounding box according to the direction category, the preset distance and the directional bounding box;

[0075] In a specific embodiment, determining the segmentation bounding box according to the direction category, the preset distance and the directional bounding box includes:

[0076] S2-3-1: Obtain the coordinates of the two endpoints of the longest side of the oriented bounding box;

[0077] S2-3-2: If the direction category is the x-axis direction, select the endpoint with the smaller x value among the two endpoints of the longest side as the starting point; otherwise, select the endpoint with the smaller y value among the two endpoints of the longest side as the starting point;

[0078] S2-3-3: sampling on the longest side to obtain a plurality of segmentation points according to the starting point and the preset distance;

[0079] Specifically, combined with actual scenarios, tunnels generally do not have bends within a range of 3 meters, so the preset distance can be set to 3. Assuming that the coordinates of the two endpoints of the longest side are (0.0, 0.0, 0.0) and (10.0, 5.0, 0.0), the segmentation points are sampled on this longest side (2.68, 1.34, 0.0), (5.36, 2.68, 0.0), and (8.04, 4.02, 0.0).

[0080] S2-3-4: Determine the segmentation bounding box according to the segmentation point.

[0081] S2-4: According to the segmentation bounding box, the tunnel point cloud data is divided into a plurality of sub-tunnel point cloud data.

[0082] S3: Obtaining the tunnel ground plane equation and tunnel direction vector of each sub-tunnel point cloud data;

[0083] In a specific embodiment, the step of obtaining the tunnel ground plane equation and the tunnel direction vector of each sub-tunnel point cloud data includes:

[0084] S3-1: performing plane fitting on the sub-tunnel point cloud data to determine the tunnel ground point cloud data and the tunnel ground plane equation;

[0085] Specifically, the plane fitting of the sub-tunnel point cloud data uses the segment_plane function in the open3d library, and the fitting method uses the RANSAC algorithm. The RANSAC algorithm is an iterative method that can effectively identify the plane equation from noisy data and output it in the form of a general expression Ax+By+Cz+D=0.

[0086] S3-2: Segmenting the running track point cloud data according to the tunnel ground plane equation;

[0087] Specifically, the distance from all point cloud coordinates in the sub-tunnel point cloud to the ground plane equation is calculated. Then, according to the actual scenario, the track is generally located between 0.15 meters and 0.35 meters above the ground, so all point clouds with a distance between 0.15 and 0.35 are determined as running track point cloud data.

[0088] S3-3: Perform straight line fitting on the running track point cloud data, and determine the direction vector of the fitting line as the tunnel direction vector.

[0089] Specifically, the straight line fitting of the running track point cloud is implemented using the pyransac3d library. The fitting method also uses the RANSAC algorithm and is output in the form of y=Ax+B, where A and B are not a scalar but a vector.

[0090] S4: Segment the communication leaky cable point cloud data from the tunnel point cloud data according to the tunnel direction vector and the point cloud data at one end point of the communication leaky cable to be segmented.

[0091] In a specific embodiment, segmenting the communication leaky cable point cloud data from the tunnel point cloud data according to the tunnel direction vector and the point cloud data at one end point of the communication leaky cable to be segmented includes:

[0092] S4-1: Acquire sub-tunnel point cloud data corresponding to the tunnel direction vector;

[0093] S4-2: Calculate the average density distance value of the sub-tunnel point cloud data;

[0094] S4-3: Taking the point cloud coordinates at the endpoint as the starting point, and taking 1 / 10 of the average density distance value as the step length along the tunnel direction vector, generating reference point cloud data;

[0095] S4-4: Calculating the distance between the sub-tunnel point cloud data and the reference point cloud data;

[0096] S4-5: Determine that the point cloud data whose distance value is less than the average density distance value is the communication leaky cable point cloud data corresponding to the sub-tunnel;

[0097] S4-6: Superimpose the communication leaky cable point cloud data corresponding to all the sub-tunnels to obtain the communication leaky cable point cloud data.

[0098] The method for segmenting the leaky cable point cloud of communication in a tunnel provided by the present invention can adapt to the direction of a complex tunnel and has strong anti-interference ability, thereby realizing stable and accurate leaky cable point cloud segmentation.

[0099] Embodiment 2:

[0100] The embodiment of the present invention provides a device for segmenting a leaky cable point cloud in a tunnel, comprising:

[0101] Point cloud acquisition module: acquires the point cloud data of the tunnel and the point cloud data at one end point of the communication leaky cable to be segmented;

[0102] Sub-tunnel segmentation module: segmenting the tunnel point cloud data into a plurality of sub-tunnel point cloud data according to a preset distance;

[0103] Direction vector acquisition module: obtains the tunnel ground plane equation and tunnel direction vector of each sub-tunnel point cloud data;

[0104] Leaky cable point cloud segmentation module: segmenting the communication leaky cable point cloud data from the tunnel point cloud data according to the tunnel direction vector and the point cloud data at one end point of the communication leaky cable to be segmented; segmenting the communication leaky cable point cloud data from the tunnel point cloud data according to the tunnel direction vector and the point cloud data at one end point of the communication leaky cable to be segmented, including:

[0105] Acquire sub-tunnel point cloud data corresponding to the tunnel direction vector;

[0106] Calculating the average density distance value of the sub-tunnel point cloud data;

[0107] Taking the point cloud coordinates at the endpoint as the starting point, and taking 1 / 10 of the average density distance value as the step length along the tunnel direction vector, a reference point cloud data is generated;

[0108] Calculating the distance between the sub-tunnel point cloud data and the reference point cloud data;

[0109] Determine that the point cloud data whose distance value is less than the average density distance value is the communication leaky cable point cloud data corresponding to the sub-tunnel;

[0110] The communication leaky cable point cloud data corresponding to all the sub-tunnels are superimposed to obtain the communication leaky cable point cloud data.

[0111] The leaky cable point cloud segmentation device for communication in a tunnel provided by the present invention can adapt to the direction of a complex tunnel and has a strong anti-interference ability, thereby realizing stable and accurate leaky cable point cloud segmentation.

[0112] Embodiment three:

[0113] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, a method for segmenting a leaky cable point cloud for communication in a tunnel as described in Embodiment 1 is implemented.

[0114] Embodiment 4:

[0115] An embodiment of the present invention provides a device, including:

[0116] A memory for storing instructions;

[0117] A processor is used to execute the instructions so that the device performs operations to implement the method for segmenting the point cloud of a leaky cable for communication in a tunnel as described in any one of the first embodiments.

[0118] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0119] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0120] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0121] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0122] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for segmenting leaky cable point clouds in tunnels, characterized in that: include: Acquire the tunnel point cloud data and the point cloud data at one end point of the communication leaky cable to be segmented; According to a preset distance, the tunnel point cloud data is divided into a plurality of sub-tunnel point cloud data; Obtaining the tunnel ground plane equation and tunnel direction vector of each sub-tunnel point cloud data; Segmenting the communication leaky cable point cloud data from the tunnel point cloud data according to the tunnel direction vector and the point cloud data at one end point of the communication leaky cable to be segmented; The step of segmenting the communication leaky cable point cloud data from the tunnel point cloud data according to the tunnel direction vector and the point cloud data at one end point of the communication leaky cable to be segmented comprises: Acquire sub-tunnel point cloud data corresponding to the tunnel direction vector; Calculating the average density distance value of the sub-tunnel point cloud data; Taking the point cloud coordinates at the endpoint as the starting point, and taking 1 / 10 of the average density distance value as the step length along the tunnel direction vector, a reference point cloud data is generated; Calculating the distance between the sub-tunnel point cloud data and the reference point cloud data; Determine that the point cloud data whose distance value is less than the average density distance value is the communication leaky cable point cloud data corresponding to the sub-tunnel; The communication leaky cable point cloud data corresponding to all the sub-tunnels are superimposed to obtain the communication leaky cable point cloud data.

2. According to claim 1, a method for segmenting leaky cable point cloud in a tunnel, characterized in that: The step of obtaining the tunnel point cloud data and the point cloud data at one end point of the leaky communication cable to be segmented includes: Use laser point cloud scanning equipment to collect tunnel point cloud data; Importing the tunnel point cloud data into point cloud viewing software; A point cloud at the endpoint of the communication leaky cable to be segmented is selected, and the coordinate information of the point cloud at the endpoint is recorded.

3. According to claim 1, a method for segmenting leaky cable point cloud in a tunnel, characterized in that: The step of dividing the tunnel point cloud data into a plurality of sub-tunnel point cloud data according to a preset distance includes: Obtain a directional bounding box of the tunnel point cloud data; Determining a direction category of the tunnel point cloud data according to the directional bounding box, the direction category including an x-axis direction and a y-axis direction; Determining a segmentation bounding box according to the direction category, the preset distance and the directional bounding box; According to the segmentation bounding box, the tunnel point cloud data is segmented into a plurality of sub-tunnel point cloud data.

4. A method for segmenting leaky cable point clouds in tunnels according to claim 3, characterized in that: The determining the direction category of the tunnel point cloud data according to the directional bounding box includes: Obtain the coordinates of two endpoints of a longest side of the oriented bounding box; Calculate the angle between the longest side and the x-axis and the y-axis according to the coordinates of the two endpoints of the longest side; If the x-axis angle is greater than the y-axis angle, the direction category is determined to be the y-axis direction; otherwise, the direction category is determined to be the x-axis direction.

5. The method for segmenting leaky cable point cloud in a tunnel according to claim 3, characterized in that: The determining of the segmentation bounding box according to the direction category, the preset distance and the directional bounding box includes: Obtain the coordinates of the two endpoints of the longest side of the oriented bounding box; If the direction category is the x-axis direction, the endpoint with the smaller x value among the two endpoints of the longest side is selected as the starting point; otherwise, the endpoint with the smaller y value among the two endpoints of the longest side is selected as the starting point; According to the starting point and the preset distance, sampling is performed on the longest side to obtain a plurality of segmentation points; The segmentation bounding box is determined according to the segmentation points.

6. The method for segmenting leaky cable point cloud in a tunnel according to claim 1, characterized in that: The step of obtaining the tunnel ground plane equation and tunnel direction vector of each sub-tunnel point cloud data comprises: Performing plane fitting on the sub-tunnel point cloud data to determine tunnel ground point cloud data and the tunnel ground plane equation; According to the tunnel ground plane equation, segmenting the running track point cloud data; A straight line fitting is performed on the running track point cloud data, and a direction vector of the fitting line is determined as the tunnel direction vector.

7. A device for segmenting leaky cable points in tunnels, characterized in that: include: Point cloud acquisition module: acquires the point cloud data of the tunnel and the point cloud data at one end point of the communication leaky cable to be segmented; Sub-tunnel segmentation module: segmenting the tunnel point cloud data into a plurality of sub-tunnel point cloud data according to a preset distance; Direction vector acquisition module: obtains the tunnel ground plane equation and tunnel direction vector of each sub-tunnel point cloud data; Leaky cable point cloud segmentation module: segmenting the communication leaky cable point cloud data from the tunnel point cloud data according to the tunnel direction vector and the point cloud data at one end point of the communication leaky cable to be segmented; The step of segmenting the communication leaky cable point cloud data from the tunnel point cloud data according to the tunnel direction vector and the point cloud data at one end point of the communication leaky cable to be segmented comprises: Acquire sub-tunnel point cloud data corresponding to the tunnel direction vector; Calculating the average density distance value of the sub-tunnel point cloud data; Taking the point cloud coordinates at the endpoint as the starting point, and taking 1 / 10 of the average density distance value as the step length along the tunnel direction vector, a reference point cloud data is generated; Calculating the distance between the sub-tunnel point cloud data and the reference point cloud data; Determine that the point cloud data whose distance value is less than the average density distance value is the communication leaky cable point cloud data corresponding to the sub-tunnel; The communication leaky cable point cloud data corresponding to all the sub-tunnels are superimposed to obtain the communication leaky cable point cloud data.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for segmenting a leaky cable point cloud for communication in a tunnel as described in any one of claims 1 to 6 is implemented.

9. A device, characterized in that: include: A memory for storing instructions; A processor is used to execute the instructions so that the device performs operations to implement the method for segmenting the point cloud of a leaky cable for communication in a tunnel as described in any one of claims 1 to 6.

Images