Coal mine tunnel point cloud data simplification method and device, storage medium and electronic equipment

Abstract

The invention provides a coal mine roadway point cloud data simplification method and device, a storage medium and electronic equipment, and the method comprises the steps: constructing a point cloud topological structure for roadway original point cloud data through a kd tree, setting a domain radius, selecting core points, recording index values, and then estimating a normal vector of each core point through a principal component analysis method and a plane fitting method; the method comprises the following steps: constructing a cylinder field at a core point by using a normal vector, then accelerating the search of a ball field of the core point by using a kd tree, calculating whether each point in the ball field is a point in the cylinder field, finally calculating the center of mass of the points in the cylinder field, and keeping the point closest to the center of mass, so that a constructed new point cloud is a simplified point cloud. The thickness of the point cloud is reduced while the point cloud is simplified, so that the problem that an existing roadway point cloud simplification method does not consider the thickness of the point cloud during point cloud simplification and cannot meet the precision requirement of similar deformation monitoring based on the roadway point cloud is solved.

Description

Technical Field

[0001] The present application relates to the field of point cloud processing technology, and in particular to a method, device, storage medium and electronic device for simplifying point cloud data of coal mine tunnels. Background Art

[0002] In coal mining projects, tunnels are important channels for coal mining and transportation. Structural deformation of tunnels caused by mining often occurs. Compared with traditional measurement technologies, 3D laser scanning technology is fast, accurate, and simple in data collection, and is widely used in various fields. With the development and improvement of ground 3D laser scanning technology, its application in deformation monitoring has also been promoted and gradually applied to coal mine tunnel detection.

[0003] Since underground coal mine tunnels are narrow and long with similar characteristics, and there is usually water vapor and dust in the tunnels, it is easy to cause redundancy in the point cloud data collected by mobile laser scanning equipment and thick point cloud thickness, which will have a certain impact on subsequent point cloud alignment and deformation monitoring. The existing point cloud simplification method does not take the point cloud thickness into consideration when simplifying the point cloud, which will directly affect the deformation monitoring accuracy based on the tunnel point cloud.

[0004] Based on the above-mentioned existing technical problems, it can be seen that a novel method for streamlining coal mine tunnel surface point cloud data is urgently needed to meet the above-mentioned technical requirements. Summary of the invention

[0005] The present invention provides a method, device, storage medium and electronic equipment for simplifying point cloud data of a coal mine tunnel, so as to at least achieve the technical effect of improving the deformation monitoring accuracy of the tunnel point cloud.

[0006] In order to achieve the above object, according to one aspect of the present application, a method for simplifying point cloud data of a coal mine tunnel is provided, the method comprising:

[0007] Acquire an initial lane point cloud set, pre-process the initial lane point cloud set, and obtain a lane point cloud set to be streamlined after cropping and denoising;

[0008] Constructing a kd-tree index structure in the lane point cloud set to be simplified, so as to divide the lane point cloud to be simplified into a plurality of subspaces, selecting the required core points in each of the subspaces and calculating the normal vector of each core point;

[0009] According to the core points and the normal vectors of each core point, the normal vectors of each core point are used as the central axis direction of the cylindrical domain, the height and radius of the cylinder are set, and the cylindrical domains are constructed respectively;

[0010] Retrieving and calculating to determine the points in each of the cylindrical domains, and selecting the point closest to the centroid of each of the points in the cylindrical domain to replace all the points in the cylindrical domain;

[0011] Determine the closest point to the center of mass of each cylindrical area, retain the point and delete other points in each area, and finally gather all the closest points together to construct a simplified point cloud set.

[0012] According to another aspect of the present application, a device for reducing point cloud data of a coal mine tunnel is provided, the device comprising:

[0013] An acquisition unit is used to acquire an initial lane point cloud set, pre-process the initial lane point cloud set, and obtain a lane point cloud set to be streamlined after clipping and denoising;

[0014] A first processing unit is used to construct a kd-tree index structure in the lane point cloud set to be simplified, so as to divide the lane point cloud to be simplified into a plurality of subspaces, select required core points in each of the subspaces and calculate the normal vector of each core point;

[0015] The second processing unit is used to set the height and radius of the cylinder according to the core point and the normal vector of each core point, and to construct the cylindrical domain respectively by taking the normal vector of each core point as the central axis direction of the cylindrical domain;

[0016] A third processing unit is used for searching and calculating to determine the points in each of the cylindrical areas, and selecting the points closest to the centroid of each of the points in the cylindrical area to replace all the points in the cylindrical area;

[0017] The determination unit is used to determine the closest point to the center of mass of each cylindrical area, retain the point and delete other points in each area, and finally gather all the closest points together to construct a simplified point cloud set.

[0018] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute any of the aforementioned methods for reducing point cloud data of coal mine tunnels.

[0019] According to another aspect of the present application, an electronic device is provided, which includes one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for executing any of the aforementioned coal mine tunnel point cloud data simplification methods.

[0020] Beneficial effects:

[0021] The present application is used to solve the problem that the tunnel point cloud collected by mobile laser scanning equipment is relatively thick, and the existing tunnel point cloud simplification method cannot reduce the point cloud thickness, which will directly affect the deformation monitoring accuracy based on the tunnel point cloud.

[0022] By constructing a kd-tree index structure in the tunnel point cloud to be simplified, core points are selected and the normal vectors of the core points are calculated. The normal vectors are used to construct a cylindrical field at each core point position, redundant data is eliminated and the thickness of the point cloud is reduced. The points in the cylindrical field are screened out, and the tunnel point cloud is simplified by retaining the original point closest to the center of mass in the cylindrical field. The final tunnel point cloud set is obtained, thereby solving the problem that the existing tunnel point cloud simplification method cannot reduce the point cloud thickness, which will directly affect the deformation monitoring accuracy based on the tunnel point cloud. It is of great significance to promote the intelligent construction of mines, ensure national energy security, ensure stable coal production and sustainable development, and drive local economic growth. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The drawings constituting part of the present application are used to provide a further understanding of the present application. The exemplary embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0024] Figure 1 A schematic diagram of a process of a method for simplifying point cloud data of a coal mine tunnel provided in accordance with an embodiment of the present application is shown;

[0025] Figure 2 A schematic diagram of constructing a cylindrical field according to an embodiment of the present application is shown;

[0026] Figure 3 A schematic diagram showing the closest point to the center of mass within the reserved cylindrical field provided according to an embodiment of the present application is shown;

[0027] Figure 4 A schematic diagram of a process of another method for streamlining point cloud data of a coal mine tunnel provided according to an embodiment of the present application is shown;

[0028] Figure 5 A structural block diagram of a coal mine tunnel point cloud data simplification device provided according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0029] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0030] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0031] It should be noted that the terms "first", "third", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0032] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution 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 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.

[0033] As introduced in the background technology, the point cloud set collected by the three-dimensional laser scanning technology is usually a spatial three-dimensional point set. Since underground coal mine tunnels are narrow and long with similar features, and there is usually water vapor and dust in the tunnels, it is easy to cause the point cloud data collected by the mobile laser scanning equipment to be redundant and the point cloud thickness is thick, which will have a certain impact on the subsequent point cloud alignment, deformation monitoring, etc. In order to solve the problem that the existing point cloud simplification method does not take the point cloud thickness into consideration when simplifying the point cloud, the embodiments of the present application provide a tunnel point cloud data simplification method, device, computer-readable storage medium and electronic device.

[0034] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0035] In this embodiment, a method for simplifying coal mine tunnel point cloud data is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0036] Figure 1 1 is a flow chart of a method for simplifying coal mine tunnel point cloud data according to an embodiment of the present application. Figure 1 As shown, the method comprises the following steps:

[0037] Step S101, obtaining an initial lane point cloud set, preprocessing the initial lane point cloud set, and obtaining a lane point cloud set to be simplified after clipping and denoising;

[0038] Specifically, that is, before determining the target feature vector of the lane point cloud set, the method further includes: obtaining an initial lane point cloud set; preprocessing the initial lane point cloud set to obtain the lane point cloud set to filter out noise in the initial lane point cloud set.

[0039] Point cloud processing software is used to manually crop the tunnel point cloud to remove the incompletely scanned tunnel point cloud and large-scale noise point cloud; radius filter denoising method is used to remove individual discrete point clouds to complete point cloud preprocessing.

[0040] Step S102, constructing a kd-tree index structure in the lane point cloud set to be simplified, so as to divide the lane point cloud to be simplified into multiple subspaces, selecting the required core points in each of the subspaces and calculating the normal vector of each core point.

[0041] Specifically, the variance of the point cloud data in the three directions of X, Y, and Z is used as the discrimination condition, and the dimension of the maximum variance value is used as the basis for segmenting the subspace to construct the kd tree index structure of the lane point cloud to be streamlined. The variance calculation formula is:

[0042]

[0043] Where N is the number of points in the point cloud, S x is the variance of the point cloud data in the X direction, S y is the variance of the point cloud data in the X direction, S z is the variance of the point cloud data in the X direction.

[0044] After obtaining the maximum variance dimension, the three-dimensional points are sorted and the median is taken on this dimension. The median representative point is used as the splitting node, and a hyperplane perpendicular to the coordinate axis of this dimension is constructed to split two spaces. The two spaces after segmentation are then further divided until the kd tree structure is constructed after they cannot be split.

[0045] Select core points and use principal component analysis and plane fitting to estimate the normal vector of each core point, including:

[0046] The required core point is selected by using the R neighborhood method in the kd tree. It can be considered that the core point replaces the set of all points within the radius of the center point. Then the principal component analysis method is used to calculate the normal vector of the core point, and the domain radius of the estimated core point normal vector is set. i (x p ,y p , z p )'s neighboring points Then, substitute the coordinates of these points into the following formula to obtain the neighborhood centroid point a z (x z ,y z , z z );

[0047]

[0048] Among them, n L is the number of points in the domain. Then the covariance matrix is ​​obtained by combining the following formula:

[0049]

[0050] After decomposing the covariance matrix, three eigenvalues ​​{λ1≥λ2≥λ3} and corresponding three eigenvectors {ν1, ν2, ν3} are obtained. The vectors corresponding to the two larger eigenvalues ​​constitute the fitting plane, and the vector corresponding to the largest eigenvalue is the normal vector of the point in the calculation field.

[0051] Step S103, according to the core point and the normal vector of each core point, taking the normal vector of each core point as the center axis direction of the cylindrical domain, setting the height and radius of the cylinder, and constructing the cylindrical domains respectively;

[0052] Specifically, the normal vector of the core point is used as the central axis direction of the cylindrical domain, and the starting point p of the cylindrical domain is calculated on both sides of the core point. s (x s ,y s , z s ) and the end point p e (x e ,y e , z e ), which is calculated as follows:

[0053]

[0054] The vector formed by the start point and the end point is the central axis of the cylindrical area. Its length is the height of the cylindrical area, which is generally the thickness of the point cloud to be simplified. The radius of the bottom circle of the cylindrical area can be slightly larger than that of the core point area.

[0055] Step S104, searching and calculating to determine the points in each cylindrical area, and selecting the point closest to the centroid of each point in the cylindrical area to replace all the points in the cylindrical area;

[0056] Specifically, in order to speed up the search, a kd tree is used to search the sphere domain, and a cylindrical domain search is performed in each point obtained from the sphere domain search. This sphere domain needs to include the entire cylindrical domain. According to the spatial structure of the cylinder, points that meet the following two conditions are determined as points within the cylindrical domain:

[0057] 1) The distance from this point to the center axis of the cylinder is not greater than the radius of the bottom circle of the cylinder. The distance from this point to the center axis of the cylinder is:

[0058]

[0059] Where l is the distance from the search point to the center axis of the cylinder, P c is the searched point, P s is the starting point of the cylinder, v p It is the median axis vector formed by the starting point of the bottom surface and the ending point of the top surface of the cylinder.

[0060] 2) The projection length of the vector formed by this point and the starting point of the cylindrical area on the central axis of the cylinder is greater than zero and not greater than the height of the cylinder. The projection length is calculated as follows:

[0061]

[0062] Among them, h is the projection length of the vector formed by the searched point and the starting point of the cylindrical field on the central axis of the cylinder.

[0063] In order to reduce the thickness of the point cloud while simplifying it, and at the same time not making major changes to the point cloud features, the point closest to the centroid of the points in the cylindrical domain is selected to replace all the points in the cylindrical domain.

[0064] Figure 2 A schematic diagram of constructing a cylindrical field at the core point position with the core point normal vector as the center axis direction of the cylindrical field. Figure 3 Schematic diagram for selecting the point closest to the centroid of the points in the cylindrical field to replace all the points in the cylindrical field.

[0065] Step S105, determining the closest point to the center of mass of each cylindrical area, retaining the point and deleting other points in each area, and finally gathering all the closest points together to construct a simplified point cloud set.

[0066] In order to enable those skilled in the art to more clearly understand the technical solution of the present application, the implementation process of the tunnel point cloud data simplification method of the present application will be described in detail below in combination with specific embodiments.

[0067] This implementation process involves a specific method for streamlining roadway point cloud data, such as Figure 4 As shown, the following steps are included:

[0068] Step S1: obtaining the original data of the roadway point cloud, preprocessing the initial roadway point cloud, and filtering the noise in the initial roadway point cloud set;

[0069] Step S2: Divide the point cloud of the laneway to be simplified into multiple subspaces, select the required core points, and then use the principal component analysis method to calculate the normal vectors of the core points;

[0070] Step S3: Taking the normal vector of the core point as the center axis direction of the cylindrical domain, setting the height and radius of the cylinder, and constructing the cylindrical domain;

[0071] Step S4: Retrieve and calculate the points in the cylindrical domain, and select the point closest to the centroid of the points in the cylindrical domain to replace all the points in the cylindrical domain;

[0072] Step S5: gather the points closest to the centroid and construct a new point cloud, which is the simplified point cloud.

[0073] By constructing a kd-tree index structure in the alley point cloud to be simplified, core points are selected and the normal vectors of the core points are calculated. A cylindrical field is constructed at each core point position using the normal vector, and the points in the cylindrical field are screened out. By retaining the original point closest to the center of mass in the cylindrical field, the alley point cloud is simplified to obtain the final alley point cloud set, thereby solving the problem that the existing alley point cloud simplification method cannot reduce the point cloud thickness, which will directly affect the deformation monitoring accuracy based on the alley point cloud.

[0074] The embodiment of the present application also provides a device for simplifying coal mine roadway point cloud data. It should be noted that the device for simplifying roadway point cloud data of the embodiment of the present application can be used to execute the method for simplifying coal mine roadway point cloud data provided by the embodiment of the present application. The device is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0075] The following is an introduction to the coal mine tunnel point cloud data simplification device provided in an embodiment of the present application.

[0076] Figure 5 It is a structural block diagram of a coal mine tunnel point cloud data simplification device provided according to an embodiment of the present application.

[0077] like Figure 5 As shown, the device comprises:

[0078] An acquisition unit 51 is configured to acquire an initial lane point cloud set, pre-process the initial lane point cloud set, and obtain a lane point cloud set to be simplified after clipping and denoising;

[0079] The first processing unit 52 is used to construct a kd-tree index structure in the to-be-streamlined lane point cloud set, so as to divide the to-be-streamlined lane point cloud into a plurality of subspaces, select required core points in each of the subspaces and calculate the normal vector of each core point;

[0080] The second processing unit 53 is used to set the height and radius of the cylinder according to the core point and the normal vector of each core point, and to construct the cylindrical domain respectively by taking the normal vector of each core point as the central axis direction of the cylindrical domain;

[0081] The third processing unit 54 is used to retrieve and calculate to determine the points in each of the cylindrical areas, and select the points closest to the centroid of each of the points in the cylindrical area to replace all the points in the cylindrical area;

[0082] The determination unit 55 is used to determine the closest point to the center of mass of each cylindrical area, retain the point and delete other points in each area, and finally gather all the closest points together to construct a simplified point cloud set.

[0083] The lane data simplification method and device include a processor and a memory, wherein the acquisition unit, the first processing unit, the second processing unit, the third processing unit and the determination unit are stored in the memory as program units, and the processor executes the program units stored in the memory to implement corresponding functions. The modules are all located in the same processor; or, the modules are located in different processors in any combination.

[0084] The processor includes a kernel, and the kernel retrieves the corresponding program unit from the memory. One or more kernels can be set, and the kernel parameters can be adjusted to solve the problem that the existing roadway point cloud simplification method has large errors and cannot meet the accuracy requirements of deformation monitoring based on roadway point clouds.

[0085] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0086] An embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the method for simplifying the lane point cloud data.

[0087] An embodiment of the present invention provides a processor, and the processor is used to run a program, wherein the method for simplifying the lane point cloud data is executed when the program is run.

[0088] The embodiment of the present invention provides a device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, at least the following steps are implemented: constructing a kd-tree index structure in the point cloud of the lane to be streamlined; setting a domain radius, selecting core points and recording their index values, and estimating the normal vector v of each core point by using a principal component analysis method and a plane fitting method. i ; Use the normal vector to construct a cylindrical domain at each core point position. The height of the constructed cylinder is generally the thickness of the roadway surface point cloud, and the bottom circle radius is generally consistent with the set domain radius. At the same time, the vector from the starting point to the end point of the cylindrical domain is obtained; Use the kd tree neighborhood to search the spherical domain of the core point, and construct a vector with each point in the spherical domain and the starting point of the cylindrical domain. Calculate the projection length h of this vector on the cylindrical direction vector and the distance l from the point to this direction vector, and select the points in the cylindrical domain; Calculate the centroid of the points in the cylindrical domain and select the original point closest to the centroid, retain this point and delete other points, complete the simplification of the roadway point cloud, and obtain the final roadway point cloud set. The devices in this article can be servers, PCs, PADs, mobile phones, etc.

[0089] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that initializes at least the following method steps: constructing a kd-tree index structure in the point cloud of the lane to be streamlined; setting a domain radius, selecting core points and recording their index values, and estimating the normal vector v of each core point using principal component analysis and plane fitting method. i; Use the normal vector to construct a cylindrical domain at each core point position. The height of the constructed cylinder is generally the thickness of the roadway surface point cloud, and the bottom circle radius is generally consistent with the set domain radius. At the same time, the vector from the starting point to the end point of the cylindrical domain is obtained; Use the kd tree neighborhood to search the spherical domain of the core point, and construct a vector with each point in the spherical domain and the starting point of the cylindrical domain. Calculate the projection length h of this vector on the cylindrical direction vector and the distance l from the point to this direction vector, and select the points in the cylindrical domain; Calculate the centroid of the points in the cylindrical domain and select the original point closest to the centroid, retain this point and delete other points, complete the simplification of the roadway point cloud, and obtain the final roadway point cloud set.

[0090] The present application also provides an electronic device, the electronic device comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include methods for executing any of the above-mentioned lane point cloud data simplification methods. By first constructing a kd tree index structure in the lane point cloud to be simplified, selecting core points and calculating the normal vectors of the core points, and using the normal vectors to construct a cylindrical field at each core point position, filtering out points in the cylindrical field, and completing the lane point cloud simplification by retaining the original point closest to the center of mass in the cylindrical field, the final lane point cloud set is obtained, thereby solving the problem that the existing lane point cloud simplification method cannot reduce the point cloud thickness, which will directly affect the deformation monitoring accuracy based on the lane point cloud.

[0091] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0092] 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.

[0093] 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.

[0094] 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.

[0095] 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.

[0096] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0097] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0098] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM) digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0099] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of further restrictions, the elements defined by the sentence "comprising a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0100] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

[0101] 1) The tunnel point cloud data simplification method of the present application selects core points and calculates the normal vectors of the core points by constructing a kd-tree index structure in the tunnel point cloud to be simplified, and constructs a cylindrical field at each core point position using the normal vector, screens out the points in the cylindrical field, and completes the tunnel point cloud simplification by retaining the original point closest to the center of mass in the cylindrical field to obtain the final tunnel point cloud set, thereby solving the problem that the existing tunnel point cloud simplification method cannot reduce the point cloud thickness, which will directly affect the deformation monitoring accuracy based on the tunnel point cloud.

[0102] 2) The tunnel point cloud data simplification device of the present application first obtains the original point cloud data, filters the noise in the initial tunnel point cloud set according to the tunnel point cloud preprocessing method, then constructs a kd-tree index structure in the tunnel point cloud to be simplified, selects core points and calculates the normal vectors of the core points, and constructs a cylindrical field at each core point position using the normal vector, screens out the points in the cylindrical field, and completes the tunnel point cloud simplification by retaining the original point closest to the center of mass in the cylindrical field to obtain the final tunnel point cloud set, thereby solving the problem that the existing tunnel point cloud simplification method cannot reduce the point cloud thickness, which will directly affect the deformation monitoring accuracy based on the tunnel point cloud.

[0103] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for simplifying point cloud data of coal mine tunnels, characterized in that: include: Acquire an initial lane point cloud set, pre-process the initial lane point cloud set, and obtain a lane point cloud set to be streamlined after cropping and denoising; Constructing a kd-tree index structure in the lane point cloud set to be simplified, so as to divide the lane point cloud to be simplified into a plurality of subspaces, selecting the required core points in each of the subspaces and calculating the normal vector of each core point; According to the core points and the normal vectors of each core point, the normal vectors of each core point are used as the central axis direction of the cylindrical domain, the height and radius of the cylinder are set, and the cylindrical domains are constructed respectively; Retrieving and calculating to determine the points in each of the cylindrical domains, and selecting the points closest to the centroid of each of the points in the cylindrical domain to replace all the points in the cylindrical domain; Determine the closest point to the center of mass of each cylindrical area, retain the point and delete other points in each area, and finally gather all the closest points together to construct a simplified point cloud set.

2. The method for simplifying coal mine tunnel point cloud data according to claim 1, characterized in that: The step of constructing a kd-tree index structure in the to-be-streamlined lane point cloud set to divide the to-be-streamlined lane point cloud into a plurality of subspaces comprises: The variance of the point cloud data in the three directions of X, Y, and Z is used as a discrimination condition, and the dimension of the maximum variance value is used as the basis for segmenting the subspace to construct the kd tree index structure. After obtaining the maximum variance dimension, the three-dimensional points are sorted and the median is taken on this dimension. The median representative point is used as the segmentation node, and a hyperplane perpendicular to the coordinate axis of the dimension is constructed to segment two spaces. The two segmented spaces are then further divided until the kd tree structure is completed after they cannot be segmented.

3. The method for simplifying coal mine tunnel point cloud data according to claim 2, characterized in that: The step of selecting the required core points in each of the subspaces and calculating the normal vectors of the core points comprises: Set the domain radius, select the core points and record their index values, and use principal component analysis and plane fitting to estimate the normal vector v of each core point. i ;in, The required core point is selected by using the R neighborhood method in the kd tree. It can be considered that the core point replaces the set of all points within the radius of the center point. Then the principal component analysis method is used to calculate the normal vector of the core point, and the domain radius of the estimated core point normal vector is set. i (x p ,y p , z p )'s neighboring points Then, substitute the coordinates of these points into the following formula to obtain the neighborhood centroid point a z (x z ,y z , z z ); Among them, n L is the number of points in the domain. Then the covariance matrix is ​​obtained by combining the following formula: After decomposing the covariance matrix, three eigenvalues ​​{λ1≥λ2≥λ3} and corresponding three eigenvectors {ν1, ν2, ν3} are obtained. The vectors corresponding to the two larger eigenvalues ​​constitute the fitting plane, and the vector corresponding to the largest eigenvalue is the normal vector of the point in the calculation field. The required core point is selected by using the R neighborhood method in the kd tree. It can be considered that the core point replaces the set of all points within the radius of the center point. Then the principal component analysis method is used to calculate the normal vector of the core point, and the domain radius of the estimated core point normal vector is set. i (x p ,y p , z p )'s neighboring points Then, substitute the coordinates of these points into the following formula to obtain the neighborhood centroid point a z (x z ,y z , z z ); Among them, n L is the number of points in the domain. Then the covariance matrix is ​​obtained by combining the following formula: After decomposing the covariance matrix, three eigenvalues ​​{λ1≥λ2≥λ3} and corresponding three eigenvectors {ν1, ν2, ν3} are obtained. The vectors corresponding to the two larger eigenvalues ​​constitute the fitting plane, and the vector corresponding to the largest eigenvalue is the normal vector of the point in the calculation field.

4. The method for simplifying coal mine tunnel point cloud data according to claim 3, characterized in that: The steps of constructing cylindrical areas respectively by setting the height and radius of the cylinder according to the core points and the normal vectors of the core points and taking the normal vectors of the core points as the central axis direction of the cylindrical area include: The normal vector of the core point is used as the central axis direction of the cylindrical domain, and the starting point p of the cylindrical domain is calculated on both sides of the core point. s (x s ,y s , z s ) and the end point p e (x e ,y e , z e ), which is calculated as follows: The vector formed by the start point and the end point is the central axis of the cylindrical field. Its length is the height of the cylindrical field and the thickness of the point cloud to be simplified. The radius of the bottom circle of the cylindrical field is larger than that of the core point field.

5. The method for simplifying coal mine tunnel point cloud data according to claim 4, characterized in that: The steps of retrieving and calculating to determine the points in each cylindrical area include: A kd tree is used to search the spherical domain. A cylindrical domain search is performed in each point obtained from the spherical domain search. This spherical domain includes the entire cylindrical domain. A vector is constructed between each point in the spherical domain and the starting point of the cylindrical domain. The projection length h of this vector on the cylindrical direction vector and the distance l from the point to this direction vector are calculated, and points in the circular domain are selected.

6. The method for simplifying coal mine tunnel point cloud data according to claim 1, characterized in that: The steps of obtaining an initial lane point cloud set, preprocessing the initial lane point cloud set, and obtaining a lane point cloud set to be streamlined after clipping and denoising include: Point cloud processing software is used to manually crop the tunnel point cloud to remove the incompletely scanned tunnel point cloud and large-scale noise point cloud; radius filter denoising method is used to remove individual discrete point clouds to complete point cloud preprocessing.

7. A coal mine tunnel point cloud data simplification device, characterized in that: include: An acquisition unit is used to acquire an initial lane point cloud set, pre-process the initial lane point cloud set, and obtain a lane point cloud set to be streamlined after clipping and denoising; A first processing unit is used to construct a kd-tree index structure in the lane point cloud set to be simplified, so as to divide the lane point cloud to be simplified into a plurality of subspaces, select required core points in each of the subspaces and calculate the normal vector of each core point; The second processing unit is used to set the height and radius of the cylinder according to the core point and the normal vector of each core point, and to construct the cylindrical domain respectively by taking the normal vector of each core point as the central axis direction of the cylindrical domain; A third processing unit is used for searching and calculating to determine the points in each of the cylindrical areas, and selecting the points closest to the centroid of each of the points in the cylindrical area to replace all the points in the cylindrical area; The determination unit is used to determine the closest point to the center of mass of each cylindrical area, retain the point and delete other points in each area, and finally gather all the closest points together to construct a simplified point cloud set.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the method for reducing coal mine tunnel point cloud data as described in any one of claims 1 to 6.

9. An electronic device, characterized in that: It comprises: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for executing the coal mine tunnel point cloud data simplification method described in any one of claims 1 to 6.

Images