Underground engineering characteristic section characteristic area deformation monitoring method

Abstract

The invention relates to an underground engineering characteristic section characteristic area deformation monitoring method. The method comprises the following steps: firstly, acquiring feature section point cloud data by adopting a depth camera; then, preprocessing the feature section point cloud data to obtain initial point cloud data; then, performing fine registration based on the initial point cloud data; then, calculating a point deformation value of the feature region based on the initial point cloud data after fine registration; and finally, generating global deformation field information based on the point deformation, and performing visual display to obtain a deformation monitoring result. That is to say, underground engineering point cloud data are collected through the depth camera with high cost performance, the cost is low, the environmental interference is small, local area deformation monitoring of the feature section is focused, large-scene and global deformation monitoring is abandoned, the model generation speed is higher, the advantages of the depth camera are fully utilized, manpower and material resources are saved, and the operation is convenient.

Description

Technical Field

[0001] This application relates to the technical field of deformation monitoring for underground engineering, and particularly to a method for monitoring the deformation of characteristic regions of characteristic cross-sections in underground engineering. Background Art

[0002] In recent years, more and more underground engineering related to coal mine development has been built. Different from other fields of civil engineering, underground engineering is usually built in natural rock and soil masses. The construction period involves the excavation of rock and soil masses, and there are more unforeseeable risk factors. During the construction period, the actual information of the dynamic changes of the structure and the surrounding environment can be obtained in real time through monitoring. Therefore, monitoring is one of the most effective means to ensure the safe construction of underground engineering.

[0003] As one of the important monitoring items for the construction safety monitoring of underground engineering, in traditional technologies, non-contact measurement methods represented by digital photogrammetry and three-dimensional laser scanning technology can efficiently, automatically, safely and accurately collect information of rock masses. However, digital photogrammetry technology is greatly affected by environmental lighting conditions. Although a three-dimensional laser scanner can generate a high-precision point cloud model, the hardware cost is expensive. Since the diameters of roadways in coal mines and mine shafts are small, and during the construction process, only the easily deformable characteristic regions on those dangerous characteristic cross-sections need to be concerned, and high-precision deformation monitoring similar to subway tunnels is not required.

[0004] Therefore, in related technologies, there is an urgent need for a method that can improve the stability, flexibility and efficiency of deformation monitoring. Summary of the Invention

[0005] Based on this, in view of the above technical problems, it is necessary to provide a method for monitoring the deformation of characteristic regions of characteristic cross-sections in underground engineering that can improve the stability, flexibility and efficiency of deformation monitoring.

[0006] In a first aspect, this application provides a method for monitoring the deformation of characteristic regions of characteristic cross-sections in underground engineering. The method includes:

[0007] Obtaining point cloud data of a characteristic cross-section by using a depth camera;

[0008] Preprocessing the point cloud data of the characteristic cross-section to obtain initial point cloud data;

[0009] Performing fine registration based on the initial point cloud data;

[0010] Calculating the point deformation value of the characteristic region based on the initially point cloud data after fine registration;

[0011] Generating global deformation field information based on the point deformation and performing visual display to obtain the deformation monitoring result.

[0012] Optionally, in an embodiment of the present application, the preprocessing includes:

[0013] Voxel filtering is used to downsample the feature cross-section point cloud data, and statistical filtering is used to remove outliers.

[0014] Optionally, in an embodiment of the present application, the fine registration based on the initial point cloud data includes:

[0015] The iterative closest point method ICP is used for fine registration.

[0016] Optionally, in an embodiment of the present application, the calculation of the point deformation value of the feature region based on the initially fine-registered point cloud data includes:

[0017] Select the original point cloud and the target point cloud from the initial point cloud data;

[0018] Determine the normal vector of each point in the original point cloud, and use the K-nearest neighbor algorithm to determine the neighboring points of each point in the target point cloud;

[0019] Based on the normal vector and the corresponding neighboring points, determine the corresponding point pairs, and calculate the spatial distance between the corresponding point pairs as the point deformation value.

[0020] Optionally, in an embodiment of the present application, the method further includes:

[0021] Multiple depth cameras are used to obtain the feature cross-section point cloud data and perform calibration processing.

[0022] Optionally, in an embodiment of the present application, the calibration processing includes:

[0023] Based on the transformation matrix, the data of the sub-depth camera and the main depth camera are fused.

[0024] In a second aspect, the present application further provides an underground engineering feature cross-section feature region deformation monitoring device. The device includes:

[0025] A data acquisition module for obtaining the feature cross-section point cloud data by using a depth camera;

[0026] A preprocessing module for preprocessing the feature cross-section point cloud data to obtain initial point cloud data;

[0027] A point cloud fine registration module for performing fine registration based on the initial point cloud data;

[0028] A point deformation calculation module for calculating the point deformation value of the feature region based on the initially fine-registered point cloud data;

[0029] A visualization analysis module, which is used to generate global deformation field information based on the point deformation, perform visualization display, and obtain the deformation monitoring result.

[0030] In a third aspect, the present application also provides a computer device. The computer device includes a memory and a processor. The memory stores a computer program, and the processor executes the steps of the methods described in the above respective embodiments.

[0031] In a fourth aspect, the present application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, and when the computer program is executed by a processor, the steps of the methods described in the above respective embodiments are implemented.

[0032] For the above-mentioned method for monitoring the deformation of the characteristic region of the characteristic section of an underground project, first, a depth camera is used to obtain the point cloud data of the characteristic section; then, the point cloud data of the characteristic section is preprocessed to obtain the initial point cloud data; then, fine registration is performed based on the initial point cloud data; then, the point deformation value of the characteristic region is calculated based on the initially point cloud data after fine registration; finally, global deformation field information is generated based on the point deformation, and visualization display is performed to obtain the deformation monitoring result. That is to say, by using a cost-effective depth camera to collect the point cloud data of the underground project, the cost is low and the environmental interference is small. It focuses on the local area deformation monitoring of the characteristic section, abandons the monitoring of the large scene and global deformation, and the generation model is faster. It makes full use of the advantages of the depth camera, saves manpower and material resources, and is easy to operate. The whole work is completed semi-automatically. Only by fixing the device to the section of interest and marking the control points can it automatically scan and export the results, which is more efficient than traditional manual monitoring. By registering the point clouds of two periods and using the normal information of the points to find the corresponding points, and using the Euclidean distance as the deformation value, the volumetric measurement advantage of the three-dimensional point cloud data is fully utilized. Description of the Drawings

[0033] Figure 1 It is an application environment diagram of a method for monitoring the deformation of the characteristic region of the characteristic section of an underground project in an embodiment;

[0034] Figure 2 It is a schematic flow chart of a method for monitoring the deformation of the characteristic region of the characteristic section of an underground project in an embodiment;

[0035] Figure 3 It is a schematic flow chart of using a depth camera to collect point cloud data in an embodiment;

[0036] Figure 4 It is a schematic flow chart of calculating the deformation of the point clouds of two periods in an embodiment;

[0037] Figure 5 It is a schematic diagram of the deformation monitoring effect of an underground project in an embodiment;

[0038] Figure 6 It is a structural block diagram of a deformation monitoring device for a characteristic area of a characteristic section of an underground project in an embodiment;

[0039] Figure 7 It is an internal structure diagram of a computer device in an embodiment. Specific embodiments

[0040] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0041] A method for monitoring the deformation of a characteristic area of a characteristic section of an underground project provided by an embodiment of the present application can be applied to, for example, Figure 1 the application environment shown. Among them, the terminal 102 communicates with the server 104 through a network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or placed in the cloud or other network servers. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart vehicle-mounted devices, etc. The portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0042] In one embodiment, as Figure 2 shown, a method for monitoring the deformation of a characteristic area of a characteristic section of an underground project is provided. Taking the method applied to the Figure 1 server as an example, the method includes the following steps:

[0043] S201: Obtain the point cloud data of the characteristic section by using a depth camera.

[0044] In the embodiment of the present application, first, a depth camera is deployed and turned on, and the depth camera Azure Kinect is used to obtain the point cloud data of the characteristic section. Specifically, as Figure 3As shown in the figure, the depth camera is installed on the camera bracket, and the installation location is at the center of the cross-section of interest. Affected by the parameters of the depth camera itself, the camera is facing the area to be monitored, and the distance is about 1.5m to 2m. One end of the camera is connected to the computer via USB, and the other end is connected to the power supply. To turn on the camera, files in the development kit are required. In Microsoft's Azure Kinect DK, k4a_device_open is defined to turn on the device, and then the capture interval time is defined. In each frame, a depth map, an RGB map, and an infrared map are generated respectively. Finally, the Generate Fast point cloud module in the DK package is used to quickly generate point cloud data.

[0045] S203: Preprocess the point cloud data of the feature cross-section to obtain the initial point cloud data.

[0046] In the embodiment of the present application, after obtaining the point cloud data of the feature cross-section, it needs to be further preprocessed, such as data reduction and noise reduction, to eliminate the possible negative impact of the original point cloud data on the results and facilitate better deformation monitoring.

[0047] Specifically, in an embodiment of the present application, the preprocessing includes:

[0048] Voxel filtering is used to downsample the point cloud data of the feature cross-section, and statistical filtering is used to remove outliers.

[0049] In an embodiment of the present application, first, since the generated point cloud data is very large, voxel filtering is used for downsampling to reduce the data as much as possible while retaining the structural features and reducing the computational load of subsequent algorithms. The principle of voxel filtering is as follows: First, the point cloud is divided into spatial voxels. For all points in a voxel, the centroid coordinates are calculated as the feature points to replace all points in the voxel to reduce the point cloud data. Suppose a non-empty voxel contains n points, then the calculation formula for the centroid coordinates of the feature points is:

[0050]

[0051] At the same time, statistical filtering is used to remove outliers to generate smooth and accurate point cloud data. In statistical filtering, it is assumed that the overall point cloud shows a relatively uniform distribution, and the distances of all points form a Gaussian distribution. The shape of the point cloud is determined by the mean u and the standard deviation σ. Suppose the coordinates of point n in the point cloud are (x n , y n , z n ), and the distance to any point m(x m , y m , z m ) is:

[0052]

[0053] The average distance and standard deviation from this point to any point are as follows:

[0054]

[0055] Finally, outlier points are removed based on the Gaussian distribution and the σ value:

[0056]

[0057] S205: Perform fine registration based on the initial point cloud data.

[0058] In the embodiment of the present application, although the fixed method can keep the position of the depth camera unchanged, due to external interference (such as vibration, human activities, etc.) and internal errors (such as the action of gravity), the positions of the depth cameras at two different acquisition times cannot remain absolutely stationary, and there will be slight changes. However, generally, the initial poses of the point clouds are very consistent. Therefore, it is necessary to perform fine registration on them to eliminate error interference.

[0059] Specifically, in an embodiment of the present application, the performing fine registration based on the initial point cloud data includes:

[0060] Perform fine registration using the Iterative Closest Point (ICP) method.

[0061] In an embodiment of the present application, the Iterative Closest Point (ICP) method is introduced for fine registration. On the premise that the initial poses are very consistent, ICP is not easily trapped in a local optimal solution, and the registration result has great advantages. The principle of the ICP algorithm is to minimize the objective function using the least squares method, where the objective function E is defined as:

[0062]

[0063] where q i and p i respectively represent a point in the source point cloud and the target point cloud, and n is the number of points in the source point cloud. The least squares method is used to minimize the objective function to solve the pose transformation matrix R and t with the smallest difference between the two point clouds.

[0064] Point cloud registration highly depends on the features of the point cloud data collected at two different times. The rock trend in the roadway and obvious markers can be regarded as registration features. In the absence of the above conditions, a relatively deep anchor bolt can be driven into the surrounding rock deep, regarded as a fixed reference object, and regarded as the absolute reference object for the registration of two-phase point clouds.

[0065] S207: Calculate the point deformation value of the feature region based on the initially registered point cloud data.

[0066] In the embodiments of the present application, corresponding point pairs of point cloud data collected at two different times are obtained by using the normal information of points, and the point deformation values of the feature region are calculated based on the corresponding point pairs.

[0067] Specifically, in one embodiment of the present application, calculating the point deformation value of the feature region based on the initially registered point cloud data includes:

[0068] S301: Select the original point cloud and the target point cloud from the initially registered point cloud data.

[0069] S303: Determine the normal vector of each point in the original point cloud, and use the K-nearest neighbor algorithm to determine the neighboring points of each point in the target point cloud.

[0070] S305: Determine the corresponding point pairs based on the normal vector and the corresponding neighboring points, and calculate the spatial distance between the corresponding point pairs as the point deformation value.

[0071] In one embodiment of the present application, as Figure 4 shown, the point cloud data of the unified feature region to be focused is selected by enclosing it in two point clouds. The data in the original point cloud is P S ′ , and the data in the target point cloud is P ′ T . Traverse each point in P S ′ . Use the module for solving point normals in the PCL library to solve the normal vector of each point, and find the K nearest points of each point in the target point cloud through the K-nearest neighbor algorithm. Find the neighboring point corresponding to the minimum included angle along the normal direction of the current point and use it as the corresponding point pair of the current point. Calculate the Euclidean distance between the corresponding point pairs as the point deformation value. Loop through all the points in the required region to obtain the deformation values of all the points in this region.

[0072] S209: Generate global deformation field information based on the point deformation, and perform visual display to obtain the deformation monitoring result.

[0073] In the embodiment of the present application, based on the cross-platform C++ development platform QT6, PCL 1.12.1 and VTK 9.0 are configured. The interaction mechanism between QT and PCL is used to display point cloud data on the GUI of QT through VTK. The signal and slot function response mechanism of QT is adopted to design the functions of various buttons, including basic file saving, point cloud filtering, registration calculation, deformation calculation, and visualization of deformation values. The Lookuptable color bar module in VTK is used to render the deformation value of each point into the point cloud color through a color mapper. Finally, the RenderWindow is displayed through the Renderer to generate global deformation field information, which is displayed on the GUI of QT using the interaction mechanism. The size of the deformation and the spread trend of the deformation can be fully seen through the generated global deformation field information. By comparing the deformation conditions between different days, the deformation trend of the characteristic area can be obtained, providing a basis for the design of the support method. As Figure 5 shown, it is the effect of the deformation monitoring of the underground project.

[0074] In one embodiment of the present application, the method further includes:

[0075] Multiple depth cameras are used to obtain point cloud data of the characteristic section and perform calibration processing.

[0076] In one embodiment of the present application, compared with the 3D laser scanner, the field of view of the depth camera is limited. If the cross-section area is large and the working range of a single depth camera cannot cover the entire area, multiple depth camera arrays can be used to expand the working vision. Compared with the hardware cost, the multi-camera array method can ensure a relatively low price on the premise of collecting data over a large range. The Azure Kinect device can synchronize input and output through the synchronization port using a 3.5mm standard audio cable. This depth camera can synchronize at most one master device and eight slave devices, and is connected in a daisy chain. To avoid interference between multiple cameras, the time offset of the camera to capture images is set to 160 milliseconds, which can be set through depth_delay_off_color_usec in the development kit. After determining that multiple cameras can be normally turned on, they need to be calibrated, that is, calibration processing, so that the images obtained by all cameras are fused in a single domain. For a single camera, calibration has been performed during production. For multiple cameras, the relative pose between the cameras needs to be obtained through an external calibration method. The external parameter matrix between the cameras can be accurately obtained through the method of OpenCV.

[0077] Specifically, in one embodiment of the present application, the calibration processing includes:

[0078] Fusing the data of the sub-depth camera and the master-depth camera based on the transformation matrix.

[0079] In one embodiment of the present application, taking the calibration between two cameras as an example, the pose transformation of multiple cameras can be obtained through pairwise conversion. For two cameras of a master-slave device, by setting the viewing angles so that there is a certain overlapping part in the fields of view of the two cameras, a calibration board is placed in the overlapping field of view, multiple frames of images are captured by the cameras, the corner points of the calibration board are detected using OpenCV, and then the transformation matrices of the multiple cameras relative to the calibration board are obtained. Taking the calibration board as a medium, the relative matrix of the slave device relative to the master device is obtained. The data of the slave device is converted into the camera coordinate system of the master device through matrix transformation for data fusion. In practical applications, calibration errors will lead to unsatisfactory data fusion results. When the gap is large, methods such as image registration and point cloud ICP fine registration can be introduced to optimize the fusion results.

[0080] In the above-mentioned method for monitoring the deformation of the characteristic region of the characteristic section of underground engineering, first, a depth camera is used to obtain the point cloud data of the characteristic section; then, the point cloud data of the characteristic section is preprocessed to obtain the initial point cloud data; then, fine registration is performed based on the initial point cloud data; then, the point deformation value of the characteristic region is calculated based on the initially point cloud data after fine registration; finally, the global deformation field information is generated based on the point deformation and visually displayed to obtain the deformation monitoring result. That is to say, the point cloud data of underground engineering is collected by a cost-effective depth camera, which has low cost and is less affected by the environment. It focuses on the local area deformation monitoring of the characteristic section, abandons the monitoring of large scenes and global deformation, and the generation model is faster. It makes full use of the advantages of the depth camera, saves manpower and material resources, and is easy to operate. The whole work is completed semi-automatically. Only by fixing the device to the section of interest and marking the control points can it automatically scan and export the results, which is more efficient than traditional manual monitoring. By registering the point clouds of two periods and using the normal information of the points to find the corresponding points, and using the Euclidean distance as the deformation value, the volumetric measurement advantage of the three-dimensional point cloud data is fully utilized.

[0081] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or steps or stages in other steps.

[0082] Based on the same inventive concept, an embodiment of the present application also provides an underground engineering characteristic cross-section characteristic area deformation monitoring device for implementing the underground engineering characteristic cross-section characteristic area deformation monitoring method involved above. The solution provided by this device to solve the problem is similar to the solution recorded in the above method. Therefore, the specific limitations in one or more embodiments of the underground engineering characteristic cross-section characteristic area deformation monitoring device provided below can refer to the limitations on the underground engineering characteristic cross-section characteristic area deformation monitoring method in the above text, and will not be repeated here.

[0083] In one embodiment, as Figure 6 shown, an underground engineering characteristic cross-section characteristic area deformation monitoring device 600 is provided, including: a data acquisition module 601, a preprocessing module 603, a point cloud fine registration module 605, a point deformation calculation module 607, and a visualization analysis module 609, where:

[0084] The data acquisition module 601 is used to acquire characteristic cross-section point cloud data by using a depth camera.

[0085] The preprocessing module 603 is used to preprocess the characteristic cross-section point cloud data to obtain initial point cloud data.

[0086] The point cloud fine registration module 605 is used to perform fine registration based on the initial point cloud data.

[0087] The point deformation calculation module 607 is used to calculate the point deformation value of the characteristic area based on the initial point cloud data after fine registration.

[0088] The visualization analysis module 609 is used to generate global deformation field information based on the point deformation, perform visualization display, and obtain the deformation monitoring result.

[0089] In one embodiment of the present application, the preprocessing module is further used for:

[0090] Performing downsampling on the characteristic cross-section point cloud data by using voxel filtering, and removing outliers by using statistical filtering.

[0091] In one embodiment of the present application, the point cloud fine registration module is further used for:

[0092] Performing fine registration by using the iterative closest point method ICP.

[0093] In one embodiment of the present application, the point deformation calculation module is further used for:

[0094] Selecting the original point cloud and the target point cloud from the initial point cloud data;

[0095] Determine the normal vector of each point in the original point cloud, and use the K-nearest neighbor algorithm to determine the neighboring points of each point in the target point cloud;

[0096] Determine the corresponding point pairs based on the normal vector and the corresponding neighboring points, and calculate the spatial distance of the corresponding point pairs as the point deformation value.

[0097] In an embodiment of the present application, the data acquisition module is further configured to:

[0098] Use multiple depth cameras to acquire feature cross-section point cloud data and perform calibration processing.

[0099] In an embodiment of the present application, the data acquisition module is further configured to:

[0100] Fuse the data of the sub-depth camera and the main-depth camera based on the transformation matrix.

[0101] Each module in the above-mentioned underground engineering feature cross-section feature area deformation monitoring device can be implemented in whole or in part by software, hardware, and their combination. The above-mentioned modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above-mentioned modules.

[0102] In an embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as Figure 7 shown. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it realizes a method for monitoring the deformation of the feature area of the underground engineering feature cross-section. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a button, a trackball, or a touchpad provided on the shell of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0103] Those skilled in the art can understand, Figure 7The structure shown is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have a different component layout.

[0104] In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0105] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0106] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0107] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data that have been authorized by the user or fully authorized by all parties.

[0108] Those of ordinary skill in the art can understand that all or part of the processes in the above-described method embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the method embodiments as described above. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0109] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0110] The above-described embodiments only represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method for monitoring deformation of characteristic sections and characteristic areas of underground engineering, characterized in that: The method comprises: Use a depth camera to obtain feature section point cloud data; Preprocessing the characteristic section point cloud data to obtain initial point cloud data; Performing precise registration based on the initial point cloud data; Calculate the point deformation value of the feature area based on the initial point cloud data after precise registration; Based on the point deformation, global deformation field information is generated and visualized to obtain deformation monitoring results.

2. A method for monitoring deformation of characteristic sections and characteristic areas of underground engineering according to claim 1, characterized in that: The pre-processing comprises: Voxel filtering is used to downsample the characteristic section point cloud data, and statistical filtering is used to remove outliers.

3. A method for monitoring deformation of characteristic sections and characteristic areas of underground engineering according to claim 1, characterized in that: The performing precise registration based on the initial point cloud data comprises: The closest point iterative method (ICP) is used for precise registration.

4. A method for monitoring deformation of characteristic sections and characteristic areas of underground engineering according to claim 1, characterized in that: The calculation of the point deformation value of the feature area based on the initial point cloud data after precise registration includes: Selecting an original point cloud and a target point cloud from the initial point cloud data; Determine the normal vector of each point in the original point cloud, and use the K nearest neighbor algorithm to determine the neighboring points of each point in the target point cloud; A corresponding point pair is determined based on the normal vector and the corresponding neighboring point, and a spatial distance between the corresponding point pairs is calculated as a point deformation value.

5. The method for monitoring deformation of characteristic sections and characteristic areas of underground engineering according to claim 1, characterized in that: The method further comprises: Multiple depth cameras are used to obtain feature section point cloud data and perform calibration processing.

6. A method for monitoring deformation of characteristic sections and characteristic areas of underground engineering according to claim 5, characterized in that: The calibration process includes: The data of the sub-depth camera is fused with the data of the main depth camera based on the transformation matrix.

7. A deformation monitoring device for characteristic sections and characteristic areas of underground engineering, characterized in that: The device comprises: A data acquisition module, used to acquire feature cross-section point cloud data using a depth camera; A preprocessing module, used for preprocessing the characteristic section point cloud data to obtain initial point cloud data; A point cloud precision registration module, used for performing precision registration based on the initial point cloud data; A point deformation calculation module is used to calculate the point deformation value of the feature area based on the initial point cloud data after precise registration; The visualization analysis module is used to generate global deformation field information based on the point deformation, perform visualization, and obtain deformation monitoring results.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images