Three-dimensional point cloud-based global deformation monitoring method and device for coal mine tunnel

Abstract

The application provides a coal mine tunnel global deformation monitoring method and device based on a three-dimensional point cloud. The method comprises the following steps: obtaining a first point cloud of a tunnel at a first time point and a second point cloud of the tunnel at a second time point, the first time point and the second time point being different, the first point cloud comprising a plurality of first coordinate points, and the second point cloud comprising a plurality of second coordinate points; performing registration processing on the first point cloud and the second point cloud to construct a target coordinate system; performing downsampling processing on the first point cloud after the registration processing to obtain a core point cloud, the core point cloud comprising a plurality of core coordinate points in the target coordinate system; performing cylindrical search on the core coordinate points as the geometric center of a cylinder to determine a first sub-point cloud and a second sub-point cloud; and determining a deformation data set of the tunnel at the core point cloud according to the first sub-point cloud and the second sub-point cloud. Through the application, long-distance and large-range tunnel surface reconstruction can be realized, so that the purpose of global deformation monitoring of tunnel surrounding rock deformation is achieved.

Description

Technical Field

[0001] This application relates to the field of surrounding rock monitoring technology, and more specifically, to a method for monitoring the deformation of coal mine roadways in the entire region based on three-dimensional point clouds, a device for monitoring the deformation of coal mine roadways in the entire region based on three-dimensional point clouds, a computer-readable storage medium, and an electronic device. Background Technology

[0002] Coal mining remains a primary energy source in my country's current development. During coal mining, due to harsh environments and uncontrollable factors, surrounding rock deformation frequently occurs, limiting safe and efficient production. Therefore, comprehensive deformation monitoring of the surrounding rock in roadways is of great significance. In actual production, due to the long length of coal mine roadways, traditional methods such as laser ranging and optical ranging, which measure only a small area, are insufficient for comprehensive deformation monitoring of the entire roadway. Summary of the Invention

[0003] The main objective of this application is to provide a method for monitoring the deformation of a coal mine roadway across the entire area based on three-dimensional point clouds, a device for monitoring the deformation of a coal mine roadway across the entire area based on three-dimensional point clouds, a computer-readable storage medium, and an electronic device, so as to at least solve the problem that it is difficult to achieve deformation monitoring of the entire roadway area in the prior art.

[0004] To achieve the above objectives, according to one aspect of this application, a method for monitoring the overall deformation of coal mine roadways based on three-dimensional point clouds is provided, comprising: acquiring a first point cloud of the roadway at a first time point and a second point cloud of the roadway at a second time point, wherein the first time point and the second time point are different, the first point cloud includes multiple first coordinate points, and the second point cloud includes multiple second coordinate points; performing registration processing on the first point cloud and the second point cloud to construct a target coordinate system; performing downsampling processing on the registered first point cloud to obtain a core point cloud, wherein the core point cloud includes multiple core coordinate points located in the target coordinate system; performing a cylinder search with the core coordinate points as the geometric center of the cylinder to determine a first sub-point cloud and a second sub-point cloud, wherein the first sub-point cloud is the set of coordinates of the first nearest neighbors of the coordinate points corresponding to each core coordinate point in the first point cloud, and the second sub-point cloud is the set of coordinates of the first nearest neighbors of the coordinate points corresponding to each core coordinate point in the second point cloud; and determining the deformation dataset of the roadway at the core point cloud based on the first sub-point cloud and the second point cloud.

[0005] Further, a cylinder search is performed with the core coordinate point as the geometric center of the cylinder to determine the first sub-point cloud and the second sub-point cloud, including: determining multiple first coordinate points in the first point cloud other than the first coordinate point corresponding to each core coordinate point as the first target point cloud; determining multiple second coordinate points in the second point cloud other than the second coordinate point corresponding to each core coordinate point as the second target point cloud; calculating multiple first distances between the multiple first target coordinate points in the first target point cloud and the first coordinate point corresponding to each core coordinate point, and calculating multiple second distances between the multiple second target coordinate points in the second target point cloud and the second coordinate point corresponding to each core coordinate point; determining the first nearest neighbor point cloud based on the first distance and a first threshold, and determining the second nearest neighbor point cloud based on the second distance and the first threshold, wherein the first nearest neighbor point cloud is the set of coordinates of the second nearest neighbors of the coordinate point corresponding to each core coordinate point in the first point cloud, and the second nearest neighbor point cloud is the set of coordinates of the second nearest neighbors of the coordinate point corresponding to each core coordinate point in the second point cloud; projecting the first nearest neighbor point cloud onto a first preset plane to obtain multiple first projected coordinate points in the first preset plane corresponding to the first nearest neighbor point cloud, and then... Projecting the second nearest neighbor point cloud onto a first preset plane yields multiple second projection coordinate points in the first preset plane corresponding to the second nearest neighbor point cloud. A first projection point cloud is generated based on these multiple first projection coordinate points, and a second projection point cloud is generated based on these multiple second projection coordinate points. Multiple first target distances are calculated between the multiple first projection coordinate points in the first projection point cloud and the coordinate points corresponding to each core coordinate point. Based on the first target distances and the radius of the cylinder's base, a first target nearest neighbor point cloud is determined. The index of each first projection coordinate point in the first target nearest neighbor point cloud is used to find the first coordinate point corresponding to each first projection coordinate point in the first nearest neighbor point cloud, and the coordinate set of the found multiple first coordinate points is determined as a first sub-point cloud. Multiple second target distances are calculated between the multiple second projection coordinate points in the second projection point cloud and the coordinate points corresponding to each core coordinate point. Based on the second target distances and the base radius, a second target nearest neighbor point cloud is determined. The index of each second projection coordinate point in the second target nearest neighbor point cloud is used to find the second coordinate point corresponding to each second projection coordinate point in the second nearest neighbor point cloud, and the coordinate set of the found multiple second coordinate points is determined as a second sub-point cloud.

[0006] Further, the first nearest neighbor point cloud is projected onto a first preset plane to obtain multiple first projected coordinate points in the first preset plane corresponding to the first nearest neighbor point cloud, and the second nearest neighbor point cloud is projected onto the first preset plane to obtain multiple second projected coordinate points in the first preset plane corresponding to the second nearest neighbor point cloud. This includes: obtaining the target normal vector at each core coordinate point; determining the first plane equation of the first preset plane based on the target normal vector; determining the first collinearity equation based on the first projected point cloud, the first nearest neighbor point cloud, and the target normal vector; determining the second collinearity equation based on the second projected point cloud, the second nearest neighbor point cloud, and the target normal vector; determining the first projected point cloud based on the first plane equation and the first collinearity equation; and determining the second projected point cloud based on the first plane equation and the second collinearity equation.

[0007] Further, the target normal vector at each core coordinate point is obtained, including: determining the third nearest neighbor point cloud based on the first distance and the second threshold; determining the fourth nearest neighbor point cloud based on the first distance and the second threshold; the third nearest neighbor point cloud is the set of coordinates of the third nearest neighbors of the coordinate points corresponding to each core coordinate point in the first point cloud; the fourth nearest neighbor point cloud is the set of coordinates of the third nearest neighbors of the coordinate points corresponding to each core coordinate point in the second point cloud; calculating the centroid coordinates and covariance matrix of the third nearest neighbor point cloud at each core coordinate point using the principal component analysis algorithm; and determining the target normal vector at each core coordinate point based on the minimum eigenvalue of the covariance matrix.

[0008] Further, based on the minimum eigenvalue of the covariance matrix, the target normal vector at each core coordinate point is determined, including: determining the first normal vector at each core coordinate point based on the minimum eigenvalue of the covariance matrix; performing a bounding box algorithm on the first point cloud to determine the coordinates of the bounding box center; calculating the difference between the coordinates of the bounding box center and the coordinates of the core coordinate points to obtain the first vector; determining whether the dot product of the first normal vector and the first normal vector is greater than zero, and obtaining the determination result; if the determination result indicates yes, determining the first normal vector as the target normal vector; if the determination result indicates no, reversing the first normal vector to obtain the target normal vector.

[0009] Further, based on the first sub-point cloud and the second sub-point cloud, the deformation dataset of the tunnel at the core point cloud is determined, including: projecting the first sub-point cloud onto the axis of the cylinder to obtain the first axis point cloud; projecting the second sub-point cloud onto the axis of the cylinder to obtain the second axis point cloud; determining the first average value of multiple coordinate points in the first axis point cloud; determining the second average value of multiple coordinate points in the second axis point cloud; and determining the deformation dataset based on the first average value and the second average value.

[0010] Further, determining the first average value of multiple coordinate points in the first axis point cloud and the second average value of multiple coordinate points in the second axis point cloud includes: determining the first axis coordinate points in the first axis point cloud that are in the same positive direction as the target normal vector of the cylinder and the second axis coordinate points in the first axis point cloud that are in the same negative direction as the target normal vector; calculating the first cumulative value of the coordinate values ​​of multiple first axis coordinate points and the second cumulative value of the coordinate values ​​of multiple second axis coordinate points; determining the third axis coordinate points in the second axis point cloud that are in the same positive direction as the target normal vector of the cylinder and the fourth axis coordinate points in the second axis point cloud that are in the same negative direction as the target normal vector; calculating the third cumulative value of the coordinate values ​​of multiple third axis coordinate points and the fourth cumulative value of the coordinate values ​​of multiple fourth axis coordinate points; determining the first average value based on the first cumulative value, the second cumulative value, and the number of multiple first axis coordinate points and the number of multiple second axis coordinate points; and determining the second average value based on the third cumulative value, the fourth cumulative value, and the number of multiple third axis coordinate points and the number of fourth axis coordinate points.

[0011] Further, based on the first average value and the second average value, the deformation dataset is determined, including: calculating the difference between the first average value and the second average value to obtain the deformation value corresponding to each core coordinate point. The deformation dataset includes multiple deformation values.

[0012] To achieve the above objectives, according to another aspect of this application, a coal mine roadway deformation monitoring device based on three-dimensional point clouds is provided, comprising: an acquisition module for acquiring a first point cloud of the roadway at a first time point and a second point cloud of the roadway at a second time point, wherein the first time point and the second time point are different, the first point cloud includes multiple first coordinate points, and the second point cloud includes multiple second coordinate points; a registration module for registering the first point cloud and the second point cloud to construct a target coordinate system; a sampling module for downsampling the registered first point cloud to acquire a core point cloud, wherein the core point cloud includes multiple core coordinate points located in the target coordinate system; a search module for performing a cylindrical search with the core coordinate points as the geometric center of the cylinder to determine a first sub-point cloud and a second sub-point cloud, wherein the first sub-point cloud is the set of coordinates of the first nearest neighbors of the coordinate points corresponding to each core coordinate point in the first point cloud, and the second sub-point cloud is the set of coordinates of the first nearest neighbors of the coordinate points corresponding to each core coordinate point in the second point cloud; and a determination module for determining the deformation dataset of the roadway at the core point cloud based on the first sub-point cloud and the second point cloud.

[0013] According to another aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium including a stored program, wherein, when the program is running, it controls the device where the computer-readable storage medium is located to execute the above-described method for monitoring the full-area deformation of coal mine roadways based on three-dimensional point clouds.

[0014] According to another aspect of this application, an electronic device is provided, 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 performing the above-described method for monitoring the global deformation of coal mine roadways based on three-dimensional point clouds.

[0015] By applying the technical solution of this application, firstly, a first point cloud of the roadway at a first time point and a second point cloud at a second time point are obtained. Then, by registering the first and second point clouds, they can be constructed in a unified coordinate system (target coordinate system). Next, by downsampling the first point cloud, a core point cloud is obtained. A cylindrical search is then performed with each core coordinate point in this core point cloud as the center of a cylinder, thereby obtaining the coordinate set of the first nearest neighbors of each core coordinate point in the first point cloud (first sub-point cloud) and the coordinate set of each core coordinate point in the second point cloud (second sub-point cloud). Based on these first and second sub-point clouds, the deformation of the roadway at each core coordinate point in the core point cloud can be determined. In other words, through the above embodiments, long-distance and large-scale roadway surface reconstruction can be achieved, thereby achieving the purpose of full-domain deformation monitoring of the roadway surrounding rock. Attached Figure Description

[0016] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0017] Figure 1 A hardware structure block diagram of a mobile terminal for a method of monitoring the full-area deformation of a roadway based on three-dimensional point clouds, provided in an embodiment of this application, is shown.

[0018] Figure 2 A flowchart illustrating a method for monitoring the full-area deformation of a roadway based on three-dimensional point clouds, according to an embodiment of this application, is shown.

[0019] Figure 3 A schematic diagram of a cylinder search in an embodiment of this application is shown;

[0020] Figure 4 A schematic diagram illustrating the calculation method of Δe in an embodiment of this application is shown;

[0021] Figure 5 A structural block diagram of a tunnel deformation monitoring device based on three-dimensional point cloud provided according to an embodiment of this application is shown. Detailed Implementation

[0022] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0023] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0024] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0025] For ease of description, the following explains some of the nouns or terms used in the embodiments of this application:

[0026] Point cloud is a collection of point data on the surface of a product obtained through measuring instruments in reverse engineering.

[0027] Registration is the matching of geographic coordinates between different images obtained using different imaging techniques within the same region.

[0028] Cylindrical search projects the point cloud onto a specified plane, then performs a circular neighborhood search based on that plane, and then backprojects the search results back to obtain the point cloud within the cylindrical neighborhood.

[0029] Downsampling involves taking samples from a sequence of samples at intervals of several samples to obtain a new sequence, which is a downsampled version of the original sequence.

[0030] As described in the background section, in actual production, due to the long roadways of coal mines, traditional laser ranging and optical ranging methods, which measure small areas, are difficult to use to monitor deformation across the entire roadway. To solve the problem of difficulty in monitoring deformation across the entire roadway, embodiments of this application provide a method for monitoring deformation across the entire coal mine roadway based on three-dimensional point clouds, a device for monitoring deformation across the entire coal mine roadway based on three-dimensional point clouds, a computer-readable storage medium, and an electronic device.

[0031] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0032] The methods and embodiments provided in this application can be executed on a mobile terminal, computer terminal, or similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for a method of monitoring the full-area deformation of coal mine roadways based on three-dimensional point clouds, according to an embodiment of the present invention. Figure 1 As shown, a mobile terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0033] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the method for monitoring the full-domain deformation of coal mine roadways based on three-dimensional point clouds in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of the aforementioned networks may include wireless networks provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0034] This embodiment provides a method for monitoring the full-domain deformation of coal mine roadways based on three-dimensional point clouds, which runs on a mobile terminal, computer terminal, or similar computing device. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Also, although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than that shown here.

[0035] Figure 2 This is a flowchart of a method for monitoring the overall deformation of coal mine roadways based on three-dimensional point clouds, according to an embodiment of this application. Figure 2 As shown, the method includes the following steps:

[0036] Step S201: Obtain the first point cloud of the tunnel at the first time point and the second point cloud of the tunnel at the second time point. The first time point and the second time point are different. The first point cloud includes multiple first coordinate points and the second point cloud includes multiple second coordinate points.

[0037] Specifically, a 3D laser scanner can be used to acquire point cloud data of the same section of roadway at different times. These different times can be a first time point and a second time point, with a time interval between them. The point cloud data of the roadway acquired by the laser scanner at the first time point is denoted as the first point cloud, and the point cloud data of the same roadway acquired by the laser scanner at the second time point is denoted as the second point cloud. It is understood that since a point cloud is a collection of multiple points in three-dimensional space, and includes at least the location of each point (i.e., the x, y, z coordinates of each point in three-dimensional space), the first point cloud can include multiple first coordinate points, and the second point cloud can include multiple second coordinate points.

[0038] More specifically, the operator uses a handheld 3D laser scanner to walk along one side of the tunnel, and holds the scanning device at a 45-degree angle to the other side of the tunnel to scan it. The scanner is kept stable during the scan to obtain a first point cloud of uniformly dense tunnel surface data. After a preset time interval, the operator uses the handheld 3D laser scanner to generate surface data at the same location as before, obtaining a second point cloud. Optionally, the 3D point cloud of the sensor in the 3D laser scanner has three values ​​(x, y, z), where x represents the x-value in the sensor coordinate system, y represents the y-value in the sensor coordinate system, and z represents the z-value in the sensor coordinate system.

[0039] Step S202: Perform registration processing on the first point cloud and the second point cloud to construct the target coordinate system;

[0040] Specifically, since the first and second point clouds are point cloud data collected from the same section of the roadway at different times, there will be differences between the collected first and second point clouds. As a result, the first and second point clouds each correspond to an independent coordinate system. In order to integrate the first and second point clouds into a unified coordinate system, the first and second point clouds are uploaded to a computer and registered. The target coordinate system constructed during the registration process is the unified coordinate system of the first and second point clouds.

[0041] Step S203: Perform downsampling on the first point cloud after registration to obtain a core point cloud, which includes multiple core coordinate points located in the target coordinate system.

[0042] Specifically, since the first and second point clouds contain a massive set of points representing the surface characteristics of the tunnel, the density and number of coordinate point data are too high, and some coordinate points are not very useful for subsequent data processing. Therefore, while meeting certain accuracy requirements and preserving the geometric features of the tunnel, the registered first point cloud is uniformly downsampled to obtain a more concise core point cloud W, thereby improving the speed of subsequent data processing. Optionally, the core point cloud can be a single cloud containing multiple core coordinate points. Optionally, skin color can be applied to the core point cloud W as the basis for final change recognition.

[0043] Step S204: Perform a cylinder search with the core coordinate point as the geometric center of the cylinder to determine the first sub-point cloud and the second sub-point cloud. The first sub-point cloud is the set of coordinates of the first nearest neighbor points of each core coordinate point in the first point cloud, and the second sub-point cloud is the set of coordinates of the first nearest neighbor points of each core coordinate point in the second point cloud.

[0044] Specifically, the base radius and height of the cylinder corresponding to the cylinder search can be set. Then, using the base radius, cylinder height, and a core coordinate point, the nearest neighbor points at that core coordinate point can be determined. Furthermore, the multiple first nearest neighbor points at each core coordinate point can include the coordinate set (first sub-point cloud) of multiple first nearest neighbor points corresponding to each core coordinate point, and can also include the coordinate set (second sub-point cloud) of multiple first nearest neighbor points corresponding to each core coordinate point. Further, since the core point cloud includes multiple core coordinate points, different nearest neighbor points corresponding to different core coordinate points can be determined; that is, the core point cloud corresponds to multiple first sub-point clouds and multiple second sub-point clouds.

[0045] Step S205: Based on the first sub-point cloud and the second sub-point cloud, determine the deformation of the tunnel at the core coordinate point.

[0046] Specifically, since each core coordinate point corresponds to a first sub-point cloud and a second sub-point cloud, and since the core point cloud includes multiple core coordinate points, after determining multiple first sub-point clouds and multiple second sub-point clouds based on the multiple core coordinate points in the core point cloud, multiple deformation amounts of the aforementioned roadway at the core point cloud can be determined based on the aforementioned multiple first sub-point clouds and multiple second sub-point clouds, thereby obtaining the roadway deformation amount dataset.

[0047] This embodiment first acquires a first point cloud of the roadway at a first time point and a second point cloud at a second time point. Then, by registering the first and second point clouds, they can be constructed in a unified coordinate system (target coordinate system). Next, the first point cloud is downsampled to obtain a core point cloud. A cylindrical search is then performed using each core coordinate point in this core point cloud as the center of a cylinder, resulting in the coordinate set of the first nearest neighbors (first sub-point cloud) of each core coordinate point in the first point cloud, and the coordinate set of the first nearest neighbors (second sub-point cloud) of each core coordinate point in the second point cloud. Based on these first and second sub-point clouds, the deformation of the roadway at each core coordinate point in the core point cloud can be determined. In other words, this embodiment enables long-distance and large-scale roadway surface reconstruction, thereby achieving the goal of comprehensive deformation monitoring of the surrounding rock in the roadway.

[0048] Specifically, in some optional embodiments, a cylinder search is performed with the core coordinate points as the geometric center of the cylinder to determine the first sub-point cloud, including: determining a plurality of first coordinate points in the first point cloud other than the first coordinate points corresponding to each of the core coordinate points as a first target point cloud; calculating a plurality of first distances between the plurality of first target coordinate points in the first target point cloud and the first points corresponding to each of the core coordinate points; determining a first nearest neighbor point cloud based on the first distances and a first threshold, wherein the first nearest neighbor point cloud is the set of coordinates of the second nearest neighbors of the coordinate points corresponding to each of the core coordinate points in the first point cloud; and projecting the first nearest neighbor point cloud onto a first preset plane. The process involves obtaining multiple first projected coordinate points in the first preset plane that correspond to the first nearest neighbor point cloud, generating a first projected point cloud based on these multiple first projected coordinate points, calculating multiple first target distances between the multiple first projected coordinate points in the first projected point cloud and the coordinate points corresponding to each of the core coordinate points, determining the first target nearest neighbor point cloud based on the first target distances and the base radius of the cylinder, searching for the first coordinate points in the first nearest neighbor point cloud that correspond to each of the first projected coordinate points based on the index of each of the first projected coordinate points in the first target nearest neighbor point cloud, and determining the coordinate set of the multiple first coordinate points obtained as the first sub-point cloud.

[0049] In the above implementation, to reduce the computational load, some coordinate points in the roadway are removed, and the first coordinate points within a certain range are retained for cylindrical calculation. Specifically, multiple first coordinate points in the first point cloud, excluding the first coordinate points corresponding to each of the aforementioned core coordinate points, are determined as the first target point cloud. Each core coordinate point is used as the center of the sphere corresponding to the cylinder. Then, the first distance between each core coordinate point and any first coordinate point in the first point cloud is calculated. If the first distance is less than a first threshold, multiple first coordinate points within multiple spheres centered at each core coordinate point and with the first threshold as the radius can be searched. The set of coordinates of the multiple first coordinate points within the sphere corresponding to each core coordinate point is the first nearest neighbor point cloud. Each core coordinate point corresponds to a sphere, thus the first target point cloud corresponds to multiple first nearest neighbor point clouds. It can be understood that the multiple first coordinate points corresponding to the first nearest neighbor point cloud are the multiple second nearest neighbor points.

[0050] Specifically, the coordinates of the aforementioned core coordinate points are (x core ,y core ,z core The first coordinate point is (x i ,y i ,z i If ), then the first distance is: The aforementioned first threshold can be calculated using the base radius and height of the cylinder. For example, if the base radius of the cylinder is r and the height is h, then the aforementioned first threshold is determined as follows:

[0051]

[0052] Furthermore, in order to search for the second nearest neighbor points in each of the aforementioned first nearest neighbor point clouds, the corresponding multiple second nearest neighbor points in each of the aforementioned first nearest neighbor point clouds are first projected onto a first preset plane. This allows multiple first projected coordinate points corresponding to the multiple second nearest neighbor points in each of the aforementioned first nearest neighbor point clouds to be obtained in the first preset plane. Then, by calculating the distance between each core coordinate point and the multiple first projected coordinate points, a first target distance between each first projected coordinate point and each core coordinate point can be determined. If the first target distance is less than the radius of the bottom surface of the cylinder, it is determined that the first projected coordinate point is a nearest neighbor point of the corresponding core coordinate point in the first preset plane. Since each second nearest neighbor point and each first projected coordinate point has a corresponding index, by using the index as the cylinder search index, the second nearest neighbor point corresponding to each of the aforementioned first projected coordinate points in the aforementioned first nearest neighbor point cloud can be found according to the index of each of the aforementioned first projected coordinate points in the aforementioned first target nearest neighbor point cloud. The coordinate set of the multiple second nearest neighbor points found is determined as the aforementioned first sub-point cloud.

[0053] Specifically, the first projection coordinate point is (x 3i ,y 3i z 3i The core coordinate point is (x core ,y core ,z core If the distance to the first target is:

[0054] In some optional embodiments, the above-mentioned projection of the first nearest neighbor point cloud onto a first preset plane to obtain a plurality of first projected coordinate points in the first preset plane corresponding to the first nearest neighbor point cloud includes: obtaining the target normal vector at each of the core coordinate points; determining the first plane equation of the first preset plane based on the target normal vector; determining the first collinearity equation based on the first projected point cloud, the first nearest neighbor point cloud, and the target normal vector; and determining the first projected point cloud based on the first plane equation and the first collinearity equation.

[0055] In the above embodiments, in order to project each second nearest neighbor point in the first nearest neighbor point cloud onto the first preset plane, the target normal vector at each core coordinate point is first obtained. Based on the target normal vector, the first plane equation of the first preset plane at each core coordinate point can be determined. Since the first projected coordinate point must satisfy the first plane equation, and the second nearest neighbor point, the first projected coordinate point and the target normal vector must be collinear, the first projected coordinate point is calculated.

[0056] Specifically, the core coordinate point is (x core ,ycore ,z core The obtained target normal vector is Then, the equation of the first plane at the core coordinate point can be determined by the target normal vector as A(xx). core )+B(yy core )+C(zz core Given that ) = 0, and that the first projected coordinate point must satisfy the above-mentioned first plane equation and that the second nearest neighbor point, the first projected coordinate point, and the target normal vector must be collinear, the following system of equations is obtained:

[0057]

[0058] Wherein, the first projection coordinate point corresponds to (x 3i ,y 3i z 3i The coordinates of the second nearest neighbor are (x...). 2i ,y 2i ,z 2i ).

[0059] For example, such as Figure 3 As shown, 1 represents a portion of the first point cloud, 2 represents any core coordinate point, 3 corresponds to the cylinder for the cylinder search, 4 represents the mean point of the first and second point clouds after the cylinder search, 5 represents a portion of the second point cloud, n is the target normal vector, d is the diameter of the base of the cylinder, and s is the deformation amount.

[0060] In some optional implementations, the above-mentioned cylindrical search with the core coordinate point as the geometric center of the cylinder to determine the second sub-point cloud includes: determining a plurality of second coordinate points in the second point cloud other than the second coordinate point corresponding to each of the core coordinate points as the second target point cloud; calculating a plurality of second distances between the plurality of second target coordinate points in the second target point cloud and the second point corresponding to each of the core coordinate points; determining a second nearest neighbor point cloud based on the second distances and the first threshold, wherein the second nearest neighbor point cloud is the set of coordinates of the second nearest neighbors of the coordinate point corresponding to each of the core coordinate points in the second point cloud; and projecting the second nearest neighbor point cloud onto a first preset... The planar method obtains multiple second projected coordinate points in the first preset plane that correspond to the second nearest neighbor point cloud. A second projected point cloud is generated based on these multiple second projected coordinate points. Multiple second target distances are calculated between the multiple second projected coordinate points in the second projected point cloud and the coordinate points corresponding to each core coordinate point. Based on the second target distances and the base radius of the cylinder, a second target nearest neighbor point cloud is determined. The index of each second projected coordinate point in the second target nearest neighbor point cloud is used to find the second coordinate points in the second nearest neighbor point cloud that correspond to each second projected coordinate point. The coordinate set of the multiple found second coordinate points is then determined as the second sub-point cloud.

[0061] In the above implementation, to reduce the computational load, some coordinate points in the roadway are removed, and second coordinate points within a certain range are retained for cylindrical calculation. Specifically, multiple second coordinate points in the second point cloud, excluding the second coordinate points corresponding to each of the aforementioned core coordinate points, are determined as the second target point cloud. Each core coordinate point is used as the center of the sphere corresponding to the cylinder. The second distance between each core coordinate point and any second coordinate point in the second point cloud is then calculated. If the second distance is less than a first threshold, multiple second coordinate points within multiple spheres centered at each core coordinate point and with the first threshold as the radius can be searched. The set of coordinates of the multiple second coordinate points within the sphere corresponding to each core coordinate point is the second nearest neighbor point cloud. Each core coordinate point corresponds to a sphere, thus the first target point cloud corresponds to multiple second nearest neighbor point clouds. It can be understood that the multiple second coordinate points corresponding to the second nearest neighbor point cloud are the multiple second nearest neighbor points.

[0062] Specifically, the coordinates of the aforementioned core coordinate points are (x core ,y core ,z core The second coordinate point is (x i ,y i ,z i If ), then the second distance is: The aforementioned first threshold can be calculated from the base radius and height of the cylinder. For example, if the base radius of the cylinder is r and the height is h, then the aforementioned first threshold is determined as:

[0063]

[0064] Furthermore, in order to search for the second nearest neighbor point in each of the above-mentioned second nearest neighbor point clouds, the multiple second nearest neighbor points corresponding to each of the above-mentioned second nearest neighbor point clouds are first projected onto a first preset plane. This allows multiple second projected coordinate points corresponding to the multiple second nearest neighbor points in each of the above-mentioned second nearest neighbor point clouds to be obtained in the first preset plane. Then, by calculating the distance between each core coordinate point and the multiple second projected coordinate points, the second target distance between each second projected coordinate point and each core coordinate point can be determined. If the second target distance is less than the radius of the bottom surface of the cylinder, it is determined that the second projected coordinate point is a nearest neighbor point of each corresponding core coordinate point in the first preset plane. Since each second nearest neighbor point and each second projected coordinate point has a corresponding index, by using the index as the cylinder search index, the second nearest neighbor point corresponding to each of the above-mentioned second projected coordinate points in the second nearest neighbor point cloud can be found according to the index of each of the above-mentioned second projected coordinate points in the second target nearest neighbor point cloud. The coordinate set of the multiple second nearest neighbor points found is determined as the second sub-point cloud.

[0065] Specifically, the second projection coordinate point is (x 3i ,y 3i z 3i The core coordinate point is (x core ,y core ,z core If the distance to the second target is:

[0066] For example, such as Figure 4 As shown, 6 represents a portion of the point cloud in the first point cloud, 7 represents any core coordinate point, h represents the height of the cylinder corresponding to the cylinder search, r is the radius of the cylinder's base, and Δe is the first threshold.

[0067] In some optional implementations, the second nearest neighbor point cloud is projected onto a first preset plane to obtain a plurality of second projected coordinate points in the first preset plane corresponding to the second nearest neighbor point cloud, including: obtaining the target normal vector at each of the core coordinate points; determining the second collinearity equation based on the second projected point cloud, the second nearest neighbor point cloud and the target normal vector; and determining the second projected point cloud based on the first plane equation and the second collinearity equation.

[0068] In the above embodiments, in order to project each of the second nearest neighbor points in the second nearest neighbor point cloud onto the first preset plane, the target normal vector at each core coordinate point is first obtained. Based on the target normal vector, the first plane equation of the first preset plane at each core coordinate point can be determined. Since the second projected coordinate point must satisfy the first plane equation, and the second nearest neighbor point, the second projected coordinate point and the target normal vector must be collinear, the second projected coordinate point is calculated.

[0069] Specifically, the core coordinate point is (x core ,y core ,z core The obtained target normal vector is The equation of the first plane at the core coordinate point can then be determined using the target normal vector: A(xx) core )+B(yy core )+C(zz core Given that ) = 0, and that the second projected coordinate point must satisfy the above-mentioned first plane equation and that the second nearest neighbor point, the second projected coordinate point, and the target normal vector must be collinear, the following system of equations is obtained:

[0070]

[0071] Wherein, the second projection coordinate point corresponds to (x 3i ,y 3i z 3i The coordinates of the second nearest neighbor are (x...). 2i ,y 2i ,z 2i ).

[0072] In some optional implementations, obtaining the target normal vector at each of the aforementioned core coordinate points includes: determining a third nearest neighbor point cloud based on the first distance and a second threshold; determining a fourth nearest neighbor point cloud based on the first distance and the second threshold; wherein the third nearest neighbor point cloud is the set of coordinates of the third nearest neighbors of the coordinate points corresponding to each of the aforementioned core coordinate points in the first point cloud; and the fourth nearest neighbor point cloud is the set of coordinates of the third nearest neighbors of the coordinate points corresponding to each of the aforementioned core coordinate points in the second point cloud; calculating the centroid coordinates and covariance matrix of the third nearest neighbor point cloud at each of the aforementioned core coordinate points using a principal component analysis algorithm; and determining the target normal vector at each of the aforementioned core coordinate points based on the minimum eigenvalue of the covariance matrix.

[0073] In the above implementation, in order to fit the plane that determines the target normal vector, a suitable second threshold is first determined according to actual needs. Then, it is determined whether the first distance is less than the second threshold. If it is less, multiple first coordinate points in the first point cloud corresponding to the first distance less than the second threshold are retained, and the set of coordinates of the retained multiple first coordinate points is recorded as the third nearest neighbor point cloud. Then, principal component analysis (PCA) is used to calculate the centroid coordinates of multiple third nearest neighbors at each core coordinate point and the covariance matrix of multiple third nearest neighbors at each core coordinate point. By calculating the covariance matrix, multiple eigenvalues ​​and the eigenvectors corresponding to each eigenvalue can be obtained. The target normal vector is determined according to the smallest eigenvalue among the multiple eigenvalues. The multiple first coordinate points corresponding to the third nearest neighbor point cloud are the multiple third nearest neighbors.

[0074] Specifically, let N be the third nearest neighbor point cloud mentioned above. p (w j (j=1,2,3,......k), where k>3, calculate the centroid coordinates of multiple third nearest neighbors at each core coordinate point as follows:

[0075]

[0076] Thus, the centroid coordinates are obtained as w0(x0,y0,z0). The covariance matrix C of multiple third nearest neighbors at each core coordinate point is calculated as follows:

[0077]

[0078] In some optional implementations, determining the target normal vector at each of the core coordinate points based on the minimum eigenvalue of the covariance matrix includes: determining a first normal vector at each of the core coordinate points based on the minimum eigenvalue of the covariance matrix; performing a bounding box algorithm on the first point cloud to determine the bounding box center coordinates; calculating the difference between the bounding box center coordinates and the coordinates of the core coordinate points to obtain a first vector; determining whether the dot product of the first normal vector and the first normal vector is greater than zero, and obtaining a determination result; if the determination result indicates yes, determining the first normal vector as the target normal vector; if the determination result indicates no, reversing the first normal vector to obtain the target normal vector.

[0079] In the above implementation, in order to use the target normal vector as the axial direction of the cylinder at each core coordinate point, multiple eigenvalues ​​of the covariance matrix are first calculated, and then the smallest eigenvalue among these eigenvalues ​​is determined. The eigenvector corresponding to this smallest eigenvalue is then the first normal vector of the centroid coordinate w0. For example, the covariance matrix C is decomposed into eigenvalues ​​to obtain three eigenvalues ​​λ0, λ1, and λ2, and their corresponding eigenvectors v0, v1, and v2. At this point, the first normal vector of the centroid coordinate w0 is... Where v min This is the eigenvector corresponding to the smallest eigenvalue.

[0080] Furthermore, to unify the direction of the first normal vector and obtain the target normal vector, the first point cloud is subjected to minimum bounding box calculation, and the center coordinates of the minimum bounding box are obtained. For example, these center coordinates are (x... 中心 ,y 中心 ,z 中心 Then, through the aforementioned center coordinates and core coordinate points (x... core ,y core ,z core The difference between the coordinates of (x) yields the first vector as (x) 中心 -x core y 中心 -y core , z 中心 -z core Then, by determining whether the dot product of the first vector and the first normal vector is greater than 0 (i.e., A(x)), we can determine whether the dot product of the first vector and the first normal vector is greater than 0 (i.e., A(x)). 中心 -x core )+B(y 中心 -y core )+C(z 中心 -z core If the first normal vector is positive or negative, and if it is greater than 0, the first normal vector at the core coordinate point is determined to be the target normal vector. If it is less than 0, the first normal vector at the core coordinate point is reversed to obtain the target normal vector. The direction of the target normal vector is the axis direction of the cylinder.

[0081] In some optional implementations, determining the deformation dataset of the alleyway at the core point cloud based on the first sub-point cloud and the second sub-point cloud includes: projecting the first sub-point cloud onto the axis of the cylinder to obtain a first axis point cloud; projecting the second sub-point cloud onto the axis of the cylinder to obtain a second axis point cloud; determining a first average value of multiple coordinate points in the first axis point cloud; determining a second average value of multiple coordinate points in the second axis point cloud; and determining the deformation dataset based on the first average value and the second average value.

[0082] Specifically, the first and second sub-point clouds are first projected onto the axes of the corresponding cylinders, respectively.

[0083] Specifically,

[0084] Among them, the above (x) i y i , z i The coordinate point can be any point in either the first or second sub-point cloud. Parametric equations can then be used to calculate multiple first projected coordinate points projected from the first sub-point cloud onto the axis of the cylinder. These multiple first projected coordinate points generate a first axis point cloud. Similarly, multiple second projected coordinate points projected from the second sub-point cloud onto the axis of the cylinder generate a second axis point cloud. A first average value of the multiple coordinate points in the first axis point cloud is then determined; a second average value of the multiple coordinate points in the second axis point cloud is also determined; and based on the first and second average values, the deformation dataset is determined.

[0085] In some optional embodiments, determining the first average value of multiple coordinate points in the first axis point cloud includes: determining the first axis coordinate points in the first axis point cloud that are in the same positive direction as the target normal vector of the cylinder and the second axis coordinate points in the first axis point cloud that are in the same negative direction as the target normal vector; calculating a first cumulative value of the coordinate values ​​of the multiple first axis coordinate points and a second cumulative value of the coordinate values ​​of the multiple second axis coordinate points; and determining the first average value based on the first cumulative value, the second cumulative value, the number of the multiple first axis coordinate points, and the number of the multiple second axis coordinate points.

[0086] In the above embodiments, the following formula is used to determine the coordinates of points in the first axis point cloud that are in the same or opposite direction to the axis of the cylinder:

[0087]

[0088] Where (x,y,z) is any coordinate point in the point cloud of the first axis, (x core ,y core ,z core ) represents the corresponding core coordinate point. If any coordinate point in the first axis point cloud satisfies the above formula, then the coordinate point whose direction is consistent with the direction of the target normal vector is determined as the first axis coordinate point; otherwise, the coordinate point whose direction is opposite to the direction of the target normal vector is considered as the second axis coordinate point, and this process continues until all coordinate points in the first axis point cloud have been searched according to the above formula.

[0089] Furthermore, after determining the coordinate points that are in the same positive direction as the target normal vector and the coordinate points that are in the opposite direction to the target normal vector, a first cumulative value of the coordinate values ​​of the multiple first axis coordinate points that are in the same positive direction as the target normal vector and a second cumulative value of the coordinate values ​​of the multiple second axis coordinate points that are in the same opposite direction to the target normal vector are calculated; based on the first cumulative value, the second cumulative value, the number of multiple first axis coordinate points, and the number of multiple second axis coordinate points, the first average value is determined.

[0090] In some optional embodiments, determining the second average value of multiple coordinate points in the second axis point cloud includes: determining the coordinate points of a third axis in the second axis point cloud that are in the same positive direction as the target normal vector of the cylinder, and the coordinate points of a fourth axis in the second axis point cloud that are in the same negative direction as the target normal vector; calculating the third cumulative value of the coordinate values ​​of the multiple third axis coordinate points and the fourth cumulative value of the coordinate values ​​of the multiple fourth axis coordinate points; and determining the second average value based on the third cumulative value, the fourth cumulative value, and the number of the multiple third axis coordinate points and the number of the multiple fourth axis coordinate points.

[0091] Similarly, in the above embodiments, the following formula is used to determine the coordinates of points in the second axis point cloud that are in the same or opposite direction to the axis of the cylinder:

[0092]

[0093] Where (x,y,z) is any coordinate point in the point cloud of the second axis, (x core ,y core ,z core ) represents the corresponding core coordinate point. If any coordinate point in the second axis point cloud satisfies the above formula, then the coordinate point whose direction is consistent with the direction of the target normal vector is determined as the third axis coordinate point; otherwise, the coordinate point whose direction is opposite to the direction of the target normal vector is considered as the fourth axis coordinate point, and this process continues until all coordinate points in the second axis point cloud have been searched according to the above formula.

[0094] Furthermore, after determining the coordinate points that are in the same positive direction as the target normal vector and the coordinate points that are in the opposite direction to the target normal vector, the third accumulated value of the coordinate values ​​of the multiple third axis coordinate points that are in the same positive direction as the target normal vector and the fourth accumulated value of the coordinate values ​​of the multiple fourth axis coordinate points that are in the same opposite direction to the target normal vector are calculated; based on the third accumulated value, the fourth accumulated value, the number of multiple third axis coordinate points, and the number of multiple fourth axis coordinate points, the second average value is determined.

[0095] Specifically, the formulas for calculating the first, second, third, and fourth accumulated values ​​are as follows:

[0096]

[0097] Among them, K j (When j = 1, d) 正向j This represents the first accumulated value. When j = 2, d 正向j K represents the third accumulated value. p (When p = 1, it represents d) 反向p This represents the second accumulated value. When p = 2, d 反向p (Represents the fourth accumulated value).

[0098] In some optional implementations, determining the deformation dataset based on the first average value and the second average value includes: calculating the difference between the first average value and the second average value to obtain the deformation value corresponding to each of the core coordinate points, wherein the deformation dataset includes multiple deformation values.

[0099] Specifically, if the total number of the aforementioned first axis coordinate points and the aforementioned second axis coordinate points is determined to be m, and the total number of the aforementioned third axis coordinate points and the aforementioned fourth axis coordinate points is determined to be n, then the deformation at each core coordinate point is:

[0100]

[0101] Where, d 正向1 The first accumulated value, d 反向1 This is the second accumulated value;

[0102] Where, d 正向2 The third accumulated value, d 反向2 This is the fourth accumulated value.

[0103] Specifically, it can also be based on the deformation amount d 变形 Color the corresponding points in the core point cloud.

[0104] This application also provides a tunnel deformation monitoring device based on 3D point clouds. It should be noted that this tunnel deformation monitoring device based on 3D point clouds can be used to execute the tunnel deformation monitoring method based on 3D point clouds provided in this application. This device is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0105] The following describes the tunnel deformation monitoring device based on three-dimensional point cloud provided in the embodiments of this application.

[0106] Figure 5 This is a schematic diagram of a coal mine roadway deformation monitoring device according to an embodiment of this application. Figure 5 As shown, the device includes:

[0107] The acquisition module 10 is used to acquire the first point cloud of the roadway at the first time point and the second point cloud of the roadway at the second time point. The first time point and the second time point are different. The first point cloud includes multiple first coordinate points, and the second point cloud includes multiple second coordinate points.

[0108] The registration module 20 is used to register the first point cloud and the second point cloud to construct the target coordinate system;

[0109] The sampling module 30 is used to perform downsampling on the first point cloud after registration to obtain the core point cloud, which includes multiple core coordinate points located in the target coordinate system.

[0110] Search module 40 is used to perform a cylindrical search with the core coordinate point as the geometric center of the cylinder to determine the first sub-point cloud and the second sub-point cloud. The first sub-point cloud is the set of coordinates of the first nearest neighbor points of the coordinate point corresponding to each core coordinate point in the first point cloud, and the second sub-point cloud is the set of coordinates of the first nearest neighbor points of the coordinate point corresponding to each core coordinate point in the second point cloud.

[0111] The determination module 50 is used to determine the deformation dataset of the alleyway at the core point cloud based on the first sub-point cloud and the second sub-point cloud.

[0112] Optionally, the search module includes: a first processing module, configured to determine multiple first coordinate points in the first point cloud, excluding the first coordinate point corresponding to each core coordinate point, as a first target point cloud; a second processing module, configured to determine multiple second coordinate points in the second point cloud, excluding the second coordinate point corresponding to each core coordinate point, as a second target point cloud; and a third processing module, configured to calculate multiple first distances between the multiple first target coordinate points in the first target point cloud and the first coordinate point corresponding to each core coordinate point, and calculate multiple second distances between the multiple second target coordinate points in the second target point cloud and the second coordinate point corresponding to each core coordinate point. The fourth processing module is used to determine a first nearest neighbor point cloud based on a first distance and a first threshold, and to determine a second nearest neighbor point cloud based on a second distance and a first threshold. The first nearest neighbor point cloud is the set of coordinates of the second nearest neighbors of the coordinates of the coordinates of the coordinates corresponding to each core coordinate point in the first point cloud, and the second nearest neighbor point cloud is the set of coordinates of the second nearest neighbors of the coordinates of the coordinates of the coordinates corresponding to each core coordinate point in the second point cloud. The fifth processing module is used to project the first nearest neighbor point cloud onto a first preset plane to obtain multiple first projected coordinate points corresponding to the first nearest neighbor point cloud in the first preset plane, and to project the second nearest neighbor point cloud onto the first preset plane. The first processing module obtains multiple second projection coordinate points in the first preset plane corresponding to the second nearest neighbor point cloud, generates a first projection point cloud based on the multiple first projection coordinate points, and generates a second projection point cloud based on the multiple second projection coordinate points; the sixth processing module is used to calculate multiple first target distances between the multiple first projection coordinate points in the first projection point cloud and the coordinate points corresponding to each core coordinate point, and determines the first target nearest neighbor point cloud based on the first target distance and the base radius of the cylinder; the seventh processing module is used to search for the corresponding first projection coordinate points in the first nearest neighbor point cloud based on the index of each first projection coordinate point in the first target nearest neighbor point cloud. The first coordinate point is determined, and the set of coordinates of the multiple first coordinate points obtained is determined as the first sub-point cloud; the eighth processing module is used to calculate the multiple second target distances between the multiple second projected coordinate points in the second projected point cloud and the coordinate points corresponding to each core coordinate point; the ninth processing module is used to determine the second target nearest neighbor point cloud based on the second target distance and the bottom radius; the tenth processing module is used to find the second coordinate point corresponding to each second projected coordinate point in the second nearest neighbor point cloud based on the index of each second projected coordinate point in the second target nearest neighbor point cloud, and determine the set of coordinates of the multiple second coordinate points obtained is determined as the second sub-point cloud.

[0113] Optionally, the fifth processing module includes: a first processing submodule for obtaining the target normal vector at each core coordinate point; a second processing submodule for determining the first plane equation of the first preset plane based on the target normal vector; a third processing submodule for determining the first collinearity equation based on the first projected point cloud, the first nearest neighbor point cloud, and the target normal vector; a fourth processing submodule for determining the second collinearity equation based on the second projected point cloud, the second nearest neighbor point cloud, and the target normal vector; a fifth processing submodule for determining the first projected point cloud based on the first plane equation and the first collinearity equation; and a sixth processing submodule for determining the second projected point cloud based on the first plane equation and the second collinearity equation.

[0114] Optionally, the first processing submodule includes: a seventh processing submodule, used to determine a third nearest neighbor point cloud based on a first distance and a second threshold, and to determine a fourth nearest neighbor point cloud based on the first distance and the second threshold, wherein the third nearest neighbor point cloud is the set of coordinates of the third nearest neighbor points of the coordinate points corresponding to each core coordinate point in the first point cloud, and the fourth nearest neighbor point cloud is the set of coordinates of the third nearest neighbor points of the coordinate points corresponding to each core coordinate point in the second point cloud; an eighth processing submodule, used to calculate the centroid coordinates and covariance matrix of the third nearest neighbor point cloud at each core coordinate point using a principal component analysis algorithm; and a ninth processing submodule, used to determine the target normal vector at each core coordinate point based on the minimum eigenvalue of the covariance matrix.

[0115] Optionally, the ninth processing submodule includes: a tenth processing submodule, used to determine the first normal vector at each core coordinate point based on the minimum eigenvalue of the covariance matrix; an eleventh processing submodule, used to perform bounding box algorithm calculation on the first point cloud to determine the center coordinates of the bounding box; a twelfth processing submodule, used to calculate the difference between the coordinates of the center coordinates of the bounding box and the coordinates of the core coordinate points to obtain the first vector; a thirteenth processing submodule, used to determine whether the dot product of the first normal vector and the first normal vector is greater than zero, and obtain a judgment result; a fourteenth processing submodule, used to determine the first normal vector as the target normal vector if the judgment result indicates yes; and a fifteenth processing submodule, used to reverse the first normal vector if the judgment result indicates no, to obtain the target normal vector.

[0116] Optionally, the determining module includes: an eleventh processing module for projecting a first sub-point cloud onto the axis of the cylinder to obtain a first axis point cloud; a twelfth processing module for projecting a second sub-point cloud onto the axis of the cylinder to obtain a second axis point cloud; a thirteenth processing module for determining a first average value of multiple coordinate points in the first axis point cloud; a fourteenth processing module for determining a second average value of multiple coordinate points in the second axis point cloud; and a fifteenth processing module for determining a deformation dataset based on the first and second average values.

[0117] Optionally, the thirteenth and fourteenth processing modules include: a sixteenth processing submodule, used to determine the coordinate points of the first axis in the first axis point cloud that are in the same positive direction as the target normal vector of the cylinder, and the coordinate points of the second axis in the first axis point cloud that are in the same negative direction as the target normal vector; a seventeenth processing submodule, used to calculate the first accumulated value of the coordinate values ​​of multiple first axis coordinate points and the second accumulated value of the coordinate values ​​of multiple second axis coordinate points; an eighteenth processing submodule, used to determine the coordinate points of the third axis in the second axis point cloud that are in the same positive direction as the target normal vector of the cylinder, and the coordinate points of the fourth axis in the second axis point cloud that are in the same negative direction as the target normal vector; a nineteenth processing submodule, used to calculate the third accumulated value of the coordinate values ​​of multiple third axis coordinate points and the fourth accumulated value of the coordinate values ​​of multiple fourth axis coordinate points; a twentieth processing submodule, used to determine the first average value based on the first accumulated value, the second accumulated value, and the number of multiple first axis coordinate points and the number of multiple second axis coordinate points; and a twenty-first processing submodule, used to determine the second average value based on the third accumulated value, the fourth accumulated value, and the number of multiple third axis coordinate points and the number of fourth axis coordinate points.

[0118] Optionally, the fifteenth processing module includes a twenty-second processing submodule, which calculates the difference between the first average value and the second average value to obtain the deformation amount corresponding to each core coordinate point. The deformation amount dataset includes multiple deformation amounts.

[0119] The aforementioned coal mine roadway full-area deformation monitoring device based on 3D point clouds includes a processor and a memory. The acquisition module 10, registration module 20, sampling module 30, search module, and determination module 50 are all stored as program units in the memory. The processor executes these program units stored in the memory to achieve the corresponding functions. All of the above modules are located in the same processor; alternatively, the modules may be located in different processors in any combination.

[0120] The processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and by adjusting kernel parameters, long-distance and large-scale roadway surface reconstruction can be achieved, thereby enabling comprehensive deformation monitoring of the roadway surrounding rock.

[0121] The memory may include non-permanent memory in computer-readable media, such as 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.

[0122] This invention provides a computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to perform the above-described method for monitoring the full-area deformation of a roadway based on three-dimensional point clouds.

[0123] This invention provides an apparatus including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs at least the following steps: acquiring a first point cloud of a roadway at a first time point and a second point cloud of the roadway at a second time point, wherein the first and second time points are different; the first point cloud includes multiple first coordinate points, and the second point cloud includes multiple second coordinate points; performing registration processing on the first and second point clouds to construct a target coordinate system; performing downsampling processing on the registered first point cloud to obtain a core point cloud, which includes multiple core coordinate points located in the target coordinate system; performing a cylinder search with the core coordinate points as the geometric center of the cylinder to determine a first sub-point cloud and a second sub-point cloud, wherein the first sub-point cloud is the set of coordinates of the first nearest neighbors of each core coordinate point in the first point cloud, and the second sub-point cloud is the set of coordinates of the first nearest neighbors of each core coordinate point in the second point cloud; and determining the deformation dataset of the roadway at the core point cloud based on the first and second sub-point clouds.

[0124] This application also provides a computer program product, which, when executed on a data processing device, is adapted to execute a program that initializes a method for monitoring the full-domain deformation of a tunnel based on a 3D point cloud, having at least the steps described above.

[0125] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0126] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0127] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0128] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0129] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0130] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0131] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0132] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, 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 technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0133] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0134] As can be seen from the above description, the embodiments of this application achieve the following technical effects:

[0135] This application first obtains a first point cloud of the roadway at a first time point and a second point cloud at a second time point. Then, by registering the first and second point clouds, they can be constructed in a unified coordinate system (target coordinate system). Next, by downsampling the first point cloud, a core point cloud is obtained. A cylindrical search is then performed with each core coordinate point in this core point cloud as the center of a cylinder, resulting in the coordinate set of the first nearest neighbors (first sub-point cloud) of each core coordinate point in the first point cloud, and the coordinate set of the corresponding coordinate points (second sub-point cloud) of each core coordinate point in the second point cloud. Based on these first and second sub-point clouds, the deformation of the roadway at each core coordinate point in the core point cloud can be determined. In other words, through the above embodiments, long-distance and large-scale roadway surface reconstruction can be achieved, thereby achieving the purpose of full-domain deformation monitoring of the roadway surrounding rock.

[0136] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for monitoring the overall deformation of coal mine roadways based on three-dimensional point clouds, characterized in that, include: Obtain a first point cloud of the tunnel at a first time point and a second point cloud of the tunnel at a second time point. The first time point and the second time point are different. The first point cloud includes multiple first coordinate points, and the second point cloud includes multiple second coordinate points. The first point cloud and the second point cloud are registered to construct a target coordinate system; The first point cloud after registration is downsampled to obtain a core point cloud, which includes multiple core coordinate points located in the target coordinate system. A cylinder search is performed with the core coordinate point as the geometric center of the cylinder to determine the first sub-point cloud and the second sub-point cloud. The first sub-point cloud is the set of coordinates of the first nearest neighbor points of the coordinate point corresponding to each core coordinate point in the first point cloud, and the second sub-point cloud is the set of coordinates of the first nearest neighbor points of the coordinate point corresponding to each core coordinate point in the second point cloud. Based on the first sub-point cloud and the second sub-point cloud, determine the deformation dataset of the alleyway at the core point cloud; The step of performing a cylindrical search with the core coordinate point as the geometric center of the cylinder to determine the first sub-point cloud and the second sub-point cloud includes: determining a plurality of first coordinate points in the first point cloud, excluding the first coordinate point corresponding to each core coordinate point, as the first target point cloud; determining a plurality of second coordinate points in the second point cloud, excluding the second coordinate point corresponding to each core coordinate point, as the second target point cloud; calculating a plurality of first distances between the plurality of first target coordinate points in the first target point cloud and the first coordinate point corresponding to each core coordinate point; and calculating a plurality of second coordinate points between the plurality of second target coordinate points in the second target point cloud and the second coordinate point corresponding to each core coordinate point. Multiple second distances between punctuation marks; based on the first distance and a first threshold, a first nearest neighbor point cloud is determined; based on the second distance and the first threshold, a second nearest neighbor point cloud is determined; the first nearest neighbor point cloud is the set of coordinates of the second nearest neighbors of the coordinate points corresponding to each core coordinate point in the first point cloud; the second nearest neighbor point cloud is the set of coordinates of the second nearest neighbors of the coordinate points corresponding to each core coordinate point in the second point cloud; the first nearest neighbor point cloud is projected onto a first preset plane to obtain multiple first projected coordinate points corresponding to the first nearest neighbor point cloud in the first preset plane, and the second nearest neighbor point cloud is... Projecting onto the first preset plane yields multiple second projected coordinate points in the first preset plane corresponding to the second nearest neighbor point cloud. A first projected point cloud is generated based on these multiple first projected coordinate points, and a second projected point cloud is generated based on these multiple second projected coordinate points. Multiple first target distances are calculated between the multiple first projected coordinate points in the first projected point cloud and the coordinate points corresponding to each core coordinate point. Based on the first target distances and the base radius of the cylinder, a first target nearest neighbor point cloud is determined. The index of each first projected coordinate point in the first target nearest neighbor point cloud is used to find the first coordinate point corresponding to each first projected coordinate point in the first nearest neighbor point cloud, and the coordinate set of the found multiple first coordinate points is determined as the first sub-point cloud. Multiple second target distances are calculated between the multiple second projected coordinate points in the second projected point cloud and the coordinate points corresponding to each core coordinate point. Based on the second target distances and the base radius, a second target nearest neighbor point cloud is determined. The index of each second projected coordinate point in the second target nearest neighbor point cloud is used to find the second coordinate point corresponding to each second projected coordinate point in the second nearest neighbor point cloud, and the coordinate set of the found multiple second coordinate points is determined as the second sub-point cloud.

2. The method for monitoring the deformation of the entire coal mine roadway according to claim 1, characterized in that, The step of projecting the first nearest neighbor point cloud onto a first preset plane to obtain multiple first projected coordinate points in the first preset plane corresponding to the first nearest neighbor point cloud, and projecting the second nearest neighbor point cloud onto the first preset plane to obtain multiple second projected coordinate points in the first preset plane corresponding to the second nearest neighbor point cloud, includes: Obtain the target normal vector at each of the core coordinate points; Based on the target normal vector, determine the first plane equation of the first preset plane; The first collinearity equation is determined based on the first projected point cloud, the first nearest neighbor point cloud, and the target normal vector; The second collinearity equation is determined based on the second projected point cloud, the second nearest neighbor point cloud, and the target normal vector; The first projected point cloud is determined based on the first plane equation and the first collinearity equation; The second projected point cloud is determined based on the first plane equation and the second collinearity equation.

3. The method for monitoring the deformation of the entire coal mine roadway according to claim 2, characterized in that, The step of obtaining the target normal vector at each of the core coordinate points includes: Based on the first distance and the second threshold, a third nearest neighbor point cloud is determined, and based on the first distance and the second threshold, a fourth nearest neighbor point cloud is determined. The third nearest neighbor point cloud is the set of coordinates of the third nearest neighbor points of the coordinate points corresponding to each core coordinate point in the first point cloud, and the fourth nearest neighbor point cloud is the set of coordinates of the third nearest neighbor points of the coordinate points corresponding to each core coordinate point in the second point cloud. The principal component analysis algorithm is used to calculate the centroid coordinates and covariance matrix of the third nearest neighbor point cloud at each of the core coordinate points; The target normal vector at each core coordinate point is determined based on the minimum eigenvalue of the covariance matrix.

4. The method for monitoring the deformation of the entire coal mine roadway according to claim 3, characterized in that, Determining the target normal vector at each core coordinate point based on the minimum eigenvalue of the covariance matrix includes: Based on the minimum eigenvalue of the covariance matrix, determine the first normal vector at each of the core coordinate points; The bounding box algorithm is used to calculate the center coordinates of the bounding box for the first point cloud. Calculate the difference between the coordinates of the bounding box center and the coordinates of the core point to obtain the first vector; Determine whether the dot product of the first normal vector and the first vector is greater than zero, and obtain the determination result; If the determination result indicates yes, the first normal vector is determined to be the target normal vector; If the judgment result indicates no, the first normal vector is reversed to obtain the target normal vector.

5. The method for monitoring the deformation of a coal mine roadway across its entire area according to any one of claims 1 to 4, characterized in that, The step of determining the deformation dataset of the alleyway at the core point cloud based on the first sub-point cloud and the second sub-point cloud includes: The first sub-point cloud is projected onto the axis of the cylinder to obtain the first axis point cloud; The second sub-point cloud is projected onto the axis of the cylinder to obtain the second axis point cloud; Determine the first average value of multiple coordinate points in the first axis point cloud; Determine the second average value of multiple coordinate points in the second axis point cloud; The deformation dataset is determined based on the first average value and the second average value.

6. The method for monitoring the deformation of the entire coal mine roadway according to claim 5, characterized in that, Determining the first average value of multiple coordinate points in the first axis point cloud and determining the second average value of multiple coordinate points in the second axis point cloud includes: Determine the coordinates of the first axis point in the first axis point cloud that is in the same positive direction as the target normal vector of the cylinder, and the coordinates of the second axis point in the first axis point cloud that is in the same negative direction as the target normal vector; Calculate the first cumulative value of the coordinate values ​​of multiple first axis coordinate points and the second cumulative value of the coordinate values ​​of multiple second axis coordinate points; Determine the coordinates of the third axis point in the second axis point cloud that is in the same positive direction as the target normal vector of the cylinder, and the coordinates of the fourth axis point in the second axis point cloud that is in the same negative direction as the target normal vector; Calculate the third cumulative value of the coordinate values ​​of multiple third axis coordinate points and the fourth cumulative value of the coordinate values ​​of multiple fourth axis coordinate points; The first average value is determined based on the first accumulated value, the second accumulated value, the number of multiple first axis coordinate points, and the number of multiple second axis coordinate points; The second average value is determined based on the third accumulated value, the fourth accumulated value, the number of multiple third axis coordinate points, and the number of fourth axis coordinate points.

7. The method for monitoring the deformation of a coal mine roadway across its entire area according to claim 5, characterized in that, Determining the deformation dataset based on the first average value and the second average value includes: The difference between the first average value and the second average value is calculated to obtain the deformation amount corresponding to each core coordinate point, and the deformation amount dataset includes multiple deformation amounts.

8. A coal mine roadway deformation monitoring device based on three-dimensional point cloud, characterized in that, include: The acquisition module is used to acquire a first point cloud of the tunnel at a first time point and a second point cloud of the tunnel at a second time point. The first time point and the second time point are different. The first point cloud includes multiple first coordinate points, and the second point cloud includes multiple second coordinate points. The registration module is used to register the first point cloud and the second point cloud to construct a target coordinate system; The sampling module is used to perform downsampling processing on the first point cloud after registration to obtain a core point cloud, wherein the core point cloud includes multiple core coordinate points located in the target coordinate system. The search module is used to perform a cylindrical search with the core coordinate point as the geometric center of the cylinder to determine a first sub-point cloud and a second sub-point cloud. The first sub-point cloud is the set of coordinates of the first nearest neighbor points of each coordinate point corresponding to the core coordinate point in the first point cloud, and the second sub-point cloud is the set of coordinates of the first nearest neighbor points of each coordinate point corresponding to the core coordinate point in the second point cloud. The determination module is used to determine the deformation dataset of the alleyway at the core point cloud based on the first sub-point cloud and the second sub-point cloud; The search module includes: a first processing module, configured to determine a plurality of first coordinate points in the first point cloud, excluding the first coordinate point corresponding to each core coordinate point, as a first target point cloud; a second processing module, configured to determine a plurality of second coordinate points in the second point cloud, excluding the second coordinate point corresponding to each core coordinate point, as a second target point cloud; a third processing module, configured to calculate a plurality of first distances between the plurality of first target coordinate points in the first target point cloud and the first coordinate point corresponding to each core coordinate point, and to calculate a plurality of second distances between the plurality of second target coordinate points in the second target point cloud and the second coordinate point corresponding to each core coordinate point; and a fourth processing module, configured to... Based on the first distance and the first threshold, a first nearest neighbor point cloud is determined; based on the second distance and the first threshold, a second nearest neighbor point cloud is determined. The first nearest neighbor point cloud is the set of coordinates of the second nearest neighbors of the coordinate points corresponding to each core coordinate point in the first point cloud; the second nearest neighbor point cloud is the set of coordinates of the second nearest neighbors of the coordinate points corresponding to each core coordinate point in the second point cloud. A fifth processing module is used to project the first nearest neighbor point cloud onto a first preset plane to obtain multiple first projected coordinate points corresponding to the first nearest neighbor point cloud in the first preset plane, and to project the second nearest neighbor point cloud onto the first preset plane to obtain the first nearest neighbor point cloud. A sixth processing module is used to calculate multiple first target distances between multiple first projection coordinates in the first projection point cloud and the coordinates corresponding to each core coordinate point, and to determine the first target nearest neighbor point cloud based on the multiple first projection coordinates and the base radius of the cylinder; a seventh processing module is used to search for the first target nearest neighbor point cloud corresponding to each first projection coordinate point in the first target nearest neighbor point cloud based on the index of each first projection coordinate point in the first target nearest neighbor point cloud. The first processing module is used to: 1) find multiple second target distances between multiple second projected coordinate points in the second projected point cloud and the coordinate points corresponding to each core coordinate point; 2) determine the second target nearest neighbor point cloud based on the second target distances and the bottom radius; and 3) find the second coordinate points corresponding to each second projected coordinate point in the second nearest neighbor point cloud based on the index of each second projected coordinate point in the second target nearest neighbor point cloud, and determine the coordinate set of multiple second coordinate points obtained from the search as the second sub-point cloud.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to perform the method for monitoring the full-area deformation of coal mine roadways based on three-dimensional point clouds as described in any one of claims 1 to 7.

10. An electronic device, characterized in that, include: 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, the one or more programs comprising methods for performing a three-dimensional point cloud-based method for monitoring the global deformation of coal mine roadways as described in any one of claims 1 to 7.

Images