Underground roadway laser point cloud denoising method, device and equipment and storage medium

Abstract

The invention relates to the technical field of laser point cloud data processing, and discloses an underground roadway laser point cloud denoising method, device and equipment and a storage medium. The method comprises the following steps: acquiring laser point cloud data and positioning track data of a roadway by utilizing a mobile three-dimensional laser scanning technology; segmenting the laser point cloud data along the trend direction of the roadway according to the positioning track data to form multi-section section laser point cloud data; segmenting each section of section laser point cloud data on a two-dimensional plane according to the positioning track data to form a plurality of local target point cloud ranges; and traversing all laser points in each local target point cloud range, calculating the Euclidean distance between each laser point and the positioning trajectory data, and eliminating noise points according to the Euclidean distance. According to the method, a large amount of laser point cloud data can be efficiently processed, the interior work data processing time is greatly shortened, the accuracy and reliability of the data are improved, and powerful support is provided for subsequent roadway structure recognition, three-dimensional modeling, square calculation and other applications.

Description

Technical Field

[0001] The present invention relates to the technical field of laser point cloud data processing, and in particular to an underground tunnel laser point cloud denoising method, device, equipment and storage medium. Background Art

[0002] Mobile 3D laser scanning technology can be used to quickly and continuously acquire laser point cloud data of underground tunnels. However, the acquired tunnel laser point cloud data often contains many noise points, such as smear points caused by dynamic pedestrians or vehicles, outliers caused by water vapor or dust, etc. These noise point clouds seriously affect the subsequent point cloud application effects, such as 3D modeling, over-excavation and under-excavation analysis, and volume calculation.

[0003] There are currently two mainstream denoising methods, the first is through point cloud filtering, and the second is through manual interaction. The disadvantage of denoising through point cloud filtering is that it requires traversing each laser point, the operation speed is slow, the denoising effect is highly dependent on parameters, and effective feature points of interest to the user are often deleted. The disadvantage of denoising through manual interaction is that it is time-consuming and labor-intensive, and the level of automation is low. Summary of the invention

[0004] In view of this, the purpose of the present invention is to overcome the deficiencies in the prior art and to provide a method, device, equipment and storage medium for denoising laser point cloud of underground tunnels.

[0005] The present invention provides the following technical solutions: In a first aspect, an embodiment of the present disclosure provides a method for denoising a laser point cloud of an underground tunnel, the method comprising: Use mobile 3D laser scanning technology to obtain laser point cloud data and positioning trajectory data of the tunnel; According to the positioning trajectory data, the laser point cloud data is divided along the direction of the lane to form multiple sections of profile laser point cloud data; Dividing each section of the profile laser point cloud data on a two-dimensional plane according to the positioning trajectory data to form a plurality of local target point cloud ranges; All laser points within the range of each local target point cloud are traversed, the Euclidean distance between each laser point and the positioning trajectory data is calculated, and noise points are eliminated according to the Euclidean distance.

[0006] Optionally, the laser point cloud data are discrete laser points, the positioning trajectory data are time-sequential positioning trajectory points, and the positioning trajectory points are distributed along the direction of the lane.

[0007] Optionally, the laser point cloud data is segmented along the direction of the lane according to the positioning trajectory data to form multiple sections of profile laser point cloud data, including: Starting from the starting or ending side of the positioning trajectory point, all laser point cloud data within a preset number of the positioning trajectory points are sequentially intercepted along the direction of the lane to form multi-segment profile laser point cloud data.

[0008] Optionally, the section laser point cloud data of each segment is segmented on a two-dimensional plane according to the positioning trajectory data to form a plurality of local target point cloud ranges, including: In each section of the cross-sectional laser point cloud data, projecting each section of the cross-sectional laser point cloud data according to the positioning trajectory data according to a two-dimensional plane; Taking the positioning trajectory data as endpoints, the projected sections of the profile laser point cloud data are divided into equal angles on a two-dimensional plane to form a plurality of local target point cloud ranges.

[0009] Optionally, in each section of the cross-section laser point cloud data, projecting each section of the cross-section laser point cloud data according to the positioning trajectory data according to a two-dimensional plane includes: Determine a normal vector according to the positioning trajectory data, and construct a projection plane according to the positioning trajectory data and the normal vector; Project each segment of the cross-section laser point cloud data onto the projection plane, and determine the point cloud coordinates of each laser point according to the distance from each laser point in each segment of the cross-section laser point cloud data to the projection plane.

[0010] Optionally, the positioning trajectory data is used as an endpoint, and each segment of the projected profile laser point cloud data is divided into equal angles on a two-dimensional plane to form a plurality of local target point cloud ranges, including: Taking the positioning trajectory data as the endpoint, dividing each segment of the projected cross-section laser point cloud data into a fan-shaped segment at every preset angle, and cutting it into a plurality of local target point cloud ranges; The polar coordinates of each laser point in the local target point cloud range are calculated.

[0011] Optionally, traversing all laser points within the range of each local target point cloud, calculating the Euclidean distance between each laser point and the positioning trajectory data, and removing noise points according to the Euclidean distance, includes: Calculating the Euclidean distance between each laser point within the local target point cloud and the positioning trajectory data, and calculating the average and standard deviation of the Euclidean distances of all laser points; The absolute value of the difference between the Euclidean distance of each laser point and the average value is calculated, and the laser points whose absolute value is greater than a preset multiple of the standard deviation are determined as the noise points, and the noise points are removed.

[0012] In a second aspect, an embodiment of the present disclosure provides a device for denoising a laser point cloud of an underground tunnel, the device comprising: An acquisition module, used to acquire laser point cloud data and positioning trajectory data of the lane by using mobile 3D laser scanning technology; The first segmentation module is used to segment the laser point cloud data along the direction of the lane according to the positioning trajectory data to form multiple sections of profile laser point cloud data; A second segmentation module is used to segment each section of the profile laser point cloud data on a two-dimensional plane according to the positioning trajectory data to form a plurality of local target point cloud ranges; The elimination module is used to traverse all laser points within the range of each local target point cloud, calculate the Euclidean distance between each laser point and the positioning trajectory data, and eliminate noise points according to the Euclidean distance.

[0013] In a third aspect, a computer device is provided in an embodiment of the present disclosure, wherein the computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the underground tunnel laser point cloud denoising method described in the first aspect are implemented.

[0014] In a fourth aspect, a computer-readable storage medium is provided in an embodiment of the present disclosure, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the underground tunnel laser point cloud denoising method described in the first aspect are implemented.

[0015] Beneficial effects of this application: The embodiment of the present application provides a method for denoising underground tunnel laser point cloud, which includes: using mobile three-dimensional laser scanning technology to obtain tunnel laser point cloud data and positioning trajectory data; dividing the laser point cloud data along the tunnel direction according to the positioning trajectory data to form multiple sections of profile laser point cloud data; dividing each section of the profile laser point cloud data on a two-dimensional plane according to the positioning trajectory data to form multiple local target point cloud ranges; traversing all laser points within each local target point cloud range, calculating the Euclidean distance between each laser point and the positioning trajectory data, and eliminating noise points according to the Euclidean distance. The present application can efficiently process a large amount of laser point cloud data, greatly reducing the internal data processing time, improving the accuracy and reliability of the data, and providing strong support for subsequent tunnel structure recognition, three-dimensional modeling, volume calculation and other applications.

[0016] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and understandable, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work. In each of the drawings, similar components are numbered similarly.

[0018] Figure 1 One of the flow charts of a method for denoising a laser point cloud of an underground tunnel provided in an embodiment of the present application is shown; Figure 2 A schematic diagram of multi-segment profile laser point cloud data provided by an embodiment of the present application is shown; Figure 3 The second flowchart of a method for denoising a laser point cloud of an underground tunnel provided in an embodiment of the present application is shown; Figure 4 A third flowchart of a method for denoising a laser point cloud of an underground tunnel provided in an embodiment of the present application is shown; Figure 5 A schematic diagram of dividing profile laser point cloud data on a two-dimensional plane according to positioning trajectory data provided in an embodiment of the present application is shown; Figure 6 A schematic diagram showing a local target point cloud range provided by an embodiment of the present application is shown; Figure 7 A schematic structural diagram of a laser point cloud denoising device for an underground tunnel provided in an embodiment of the present application is shown; Figure 8 A schematic diagram of the structure of a computer device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0019] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0020] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. In contrast, when an element is referred to as being "directly on" another element, there is no intermediate element. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0021] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0022] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0023] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of the template are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0024] Example 1 like Figure 1 FIG. 1 is a flow chart of a method for denoising a laser point cloud of an underground tunnel in an embodiment of the present application. The method for denoising a laser point cloud of an underground tunnel provided in an embodiment of the present application comprises the following steps: Step S110, using mobile 3D laser scanning technology to obtain laser point cloud data and positioning trajectory data of the lane.

[0025] In this embodiment, mobile 3D laser scanning technology can be used to obtain laser point cloud data and positioning trajectory data of a continuous lane. The laser point cloud data consists of a series of discrete laser points (x, y, z), representing the 3D coordinates of the lane surface; the positioning trajectory data consists of time-sequential positioning trajectory points (T, X, Y, Z), where T represents the timestamp, and X, Y, and Z represent the 3D coordinates of the positioning point. The positioning trajectory points are usually distributed along the lane direction, and the output frequency is relatively high (e.g., above 10 Hz).

[0026] It should be noted that in the current existing technology, to obtain laser point cloud data of a continuous area, it is necessary to first use a fixed 3D laser scanner to scan and obtain laser point cloud data of a small range, and then stitch multiple point cloud data together through internal data processing, which is time-consuming and labor-intensive. In this application, the mobile 3D laser scanner can continuously obtain laser point cloud data of a region by means of real-time laser SLAM (Simultaneous Localization and Mapping) technology: the mobile carrier is equipped with sensors such as laser radar and inertial navigation. The laser radar can obtain the geometric information of the surrounding environment in real time. The splicing (or registration) process of two frames of laser point cloud data will output the rotation and translation. The rotation constitutes the posture data, and the translation constitutes the position data. Therefore, the splicing process of two frames of laser point cloud data will form position information and posture information, that is, the "self-positioning information" (i.e., positioning trajectory points) of the mobile carrier. Then, the final splicing of the two frames of laser point cloud is completed according to the "self-positioning information". This process is called mapping. This process is repeated, positioning-mapping-positioning-mapping process, and finally completes the continuous splicing of multiple frames of laser point cloud data to form the overall laser point cloud data. The positioning and mapping processes complement each other, promote each other, and proceed synchronously, greatly improving the efficiency of surveying and mapping.

[0027] The above method uses mobile 3D laser scanning technology to obtain the 3D coordinate information of the tunnel surface and the time-series 3D coordinate information of the positioning points in real time, avoiding the tedious process of splicing multiple small-range point cloud data in the traditional method, thereby reducing the errors and omissions that may occur in the data splicing process, improving the integrity and accuracy of the data, and providing necessary and accurate original data for subsequent processing.

[0028] Step S120, dividing the laser point cloud data along the direction of the lane according to the positioning trajectory data to form multiple sections of profile laser point cloud data.

[0029] Understandably, the positioning trajectory points with timing are expressed as follows:

[0030] like Figure 2 As shown in the figure, the black dots are the positioning trajectory points. Starting from the starting or ending side of the positioning trajectory point, all laser point cloud data with a segment length of k within the range of the positioning trajectory point are intercepted in sequence along the direction of the lane. , forming multi-segment profile laser point cloud data.

[0031] It should be noted that the value of k can be adjusted according to the length of the lane, the amount of data and the processing requirements. For example, the segment length k can be dynamically selected according to the lane curvature (calculated by the second-order derivative of the positioning trajectory point). When the curvature is large, k decreases, and when the curvature is small, k increases to avoid over-segmentation of straight segments or under-segmentation of curved segments. This embodiment does not limit this.

[0032] The above method divides the entire tunnel laser point cloud data into multiple sections of profile data, reducing the complexity and computational complexity of data processing. The segmented profile data is easier to analyze and process, which helps to more accurately identify the tunnel structure in subsequent steps.

[0033] Step S130 , dividing each section of the profile laser point cloud data on a two-dimensional plane according to the positioning trajectory data to form a plurality of local target point cloud ranges.

[0034] Specifically, first, in each section of laser point cloud data, each section of laser point cloud data is projected according to the two-dimensional plane according to the positioning trajectory data, such as Figure 3 As shown, the specific steps include: Step S131, determining a normal vector according to the positioning trajectory data, and constructing a projection plane according to the positioning trajectory data and the normal vector; Step S132, projecting each segment of the cross-section laser point cloud data onto the projection plane, and determining the point cloud coordinates of each laser point according to the distance from each laser point in each segment of the cross-section laser point cloud data to the projection plane.

[0035] Understandably, in each section of laser point cloud data, the positioning trajectory data As the endpoint, it is connected to the next positioning trajectory data The connecting vector between Construct a projection plane for the normal vector. The equation of the projection plane is:

[0036] In the formula, , , , .

[0037] Next, the laser point cloud data of each section is projected onto the projection plane, and the point cloud coordinates of each laser point are determined based on the distance from each laser point in the laser point cloud data of each section to the projection plane. :

[0038]

[0039]

[0040] In the formula, is the distance from the i-th laser point to the projection plane.

[0041] The above steps construct the projection plane based on the positioning trajectory data and normal vector, ensuring the accuracy and effectiveness of the projection. The three-dimensional point cloud data is converted into two-dimensional plane data through the projection plane equation, which simplifies the data processing process while retaining key information.

[0042] Furthermore, if Figure 4 As shown, taking the positioning trajectory data as the endpoint, the projected sections of the profile laser point cloud data are divided into equal angles on a two-dimensional plane to form a plurality of local target point cloud ranges. The specific steps include: Step S133, taking the positioning trajectory data as the endpoint, dividing each segment of the projected cross-section laser point cloud data into a fan-shaped segment at every preset angle, and dividing it into a plurality of local target point cloud ranges; Step S134, calculating the polar coordinates of each laser point in the local target point cloud range.

[0043] Understandably, if Figure 5 As shown, to locate the trajectory data As endpoints, the laser point cloud data of each section after projection is taken at preset angles. Divide a sector into The local target point cloud range is calculated, and the polar coordinates of all projected laser points are calculated for subsequent denoising based on Euclidean distance.

[0044] It should be noted that, in this embodiment, the preset angle of the segmentation can be dynamically adjusted according to the actual width and shape of the lane. In a wider lane, the segmentation angle can be increased to cover more areas; in a narrow lane, the segmentation angle is reduced to improve the processing accuracy. The specific value can be determined according to the actual situation, and the embodiment of the present application does not limit this.

[0045] The above steps further refine the profile laser point cloud data into multiple local target point cloud ranges, which helps to more accurately identify and process the detailed features in the roadway. The equal-angle segmentation method ensures that each local target point cloud range has a similar size and shape, which facilitates unified processing and analysis in subsequent steps.

[0046] Step S140, traversing all laser points within the range of each local target point cloud, calculating the Euclidean distance between each laser point and the positioning trajectory data, and eliminating noise points according to the Euclidean distance.

[0047] Specifically, within each local target point cloud, assuming there are m laser points, traverse each laser point and calculate With positioning trajectory data The Euclidean distance is calculated as follows:

[0048] In the formula, is the Euclidean distance between the mth laser point and the positioning trajectory data. Since the projection is performed on a two-dimensional plane, only the y and z coordinates are considered.

[0049] Next, the average Euclidean distance of all laser points is calculated and standard deviation , the calculation formula is as follows:

[0050]

[0051] Understandably, if Figure 6 As shown in Figure 1, within each local target point cloud range, the Euclidean distance between the laser point on the tunnel wall and the positioning trajectory point should obey the normal distribution, and its geometric relationship is: Noise points are outliers. Therefore, within the range of each local target point cloud, the absolute value of the difference between the Euclidean distance of each laser point and the average value is calculated, and the laser points whose absolute value is greater than a preset multiple n (such as 2 times) of the standard deviation are determined as noise points, that is:

[0052] Finally, the screened noise points are removed, such as the smears produced by dynamic pedestrians or vehicles, outliers produced by water vapor and dust, etc. Preferably, after the initial denoising, the remaining point cloud data is rechecked and denoised to remove the noise points that may be missed, aiming to improve the efficiency of in-house laser point cloud data processing.

[0053] Preferably, in this embodiment, a DQN (Deep Q-Learning) model can be constructed to dynamically optimize the segmentation parameters (k, θ), preset multiples (n), etc. according to the historical denoising effect to form an adaptive denoising closed-loop system, realize intelligent parameter adjustment, reduce manual intervention, and enhance the system's generalization ability for different lane environments.

[0054] The above method can accurately identify noise points by calculating the Euclidean distance between the laser point and the positioning trajectory data. The threshold of noise points can be determined more accurately by statistically analyzing the Euclidean distance of the laser point using the normal distribution characteristics. After eliminating the noise points, the quality and accuracy of the laser point cloud data are improved, providing a reliable data basis for subsequent processing and analysis.

[0055] The underground tunnel laser point cloud denoising method provided in the embodiment of the present application uses mobile three-dimensional laser scanning technology to obtain the tunnel laser point cloud data and positioning trajectory data; according to the positioning trajectory data, the laser point cloud data is divided along the tunnel direction to form multiple sections of profile laser point cloud data; according to the positioning trajectory data, each section of the profile laser point cloud data is divided on a two-dimensional plane to form multiple local target point cloud ranges; all laser points within each local target point cloud range are traversed, and the Euclidean distance between each laser point and the positioning trajectory data is calculated, and noise points are eliminated according to the Euclidean distance. The present application can efficiently process a large amount of laser point cloud data, greatly reducing the internal data processing time, improving the accuracy and reliability of the data, and providing strong support for subsequent tunnel structure recognition, three-dimensional modeling, volume calculation and other applications.

[0056] Example 2 like Figure 7 FIG. 1 is a schematic diagram of the structure of a laser point cloud denoising device 700 for an underground tunnel in an embodiment of the present application, wherein the device comprises: An acquisition module 710 is used to acquire laser point cloud data and positioning trajectory data of the lane by using mobile 3D laser scanning technology; The first segmentation module 720 is used to segment the laser point cloud data along the direction of the lane according to the positioning trajectory data to form multiple sections of profile laser point cloud data; A second segmentation module 730 is used to segment each section of the profile laser point cloud data on a two-dimensional plane according to the positioning trajectory data to form a plurality of local target point cloud ranges; The elimination module 740 is used to traverse all laser points within the range of each local target point cloud, calculate the Euclidean distance between each laser point and the positioning trajectory data, and eliminate noise points according to the Euclidean distance.

[0057] The underground tunnel laser point cloud denoising device provided in the embodiment of the present application can implement each process of the underground tunnel laser point cloud denoising method corresponding to Example 1, and can achieve the same technical effect. To avoid repetition, it will not be repeated here. The underground tunnel laser point cloud denoising device provided in the embodiment of the present application can efficiently process a large amount of laser point cloud data, greatly reducing the internal data processing time, improving the accuracy and reliability of the data, and providing strong support for subsequent tunnel structure recognition, three-dimensional modeling, volume calculation and other applications.

[0058] Example 3 The present application also provides a computer device. Figure 8 , Figure 8 This is a basic structural block diagram of the computer device in this embodiment.

[0059] The computer device 8 includes a memory 81, a processor 82, and a network interface 83 that are interconnected and communicated through a system bus. It should be noted that the figure only shows a computer device 8 with a memory 81, a processor 82, and a network interface 83, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (ASIC), programmable gate arrays (FPGA), digital signal processors (DSP), embedded devices, etc.

[0060] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0061] The memory 81 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or D slot compatibility test memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 81 can be an internal storage unit of the computer device 8, such as a hard disk or memory of the computer device 8. In other embodiments, the memory 81 can also be an external storage device of the computer device 8, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the computer device 8. Of course, the memory 81 can also include both the internal storage unit of the computer device 8 and its external storage device. In this embodiment, the memory 81 is generally used to store the operating system and various application software installed on the computer device 8, such as computer-readable instructions of the slot compatibility test method, etc. In addition, the memory 81 can also be used to temporarily store various types of data that have been output or are to be output.

[0062] The processor 82 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other underground tunnel laser point cloud denoising chip in some embodiments. The processor 82 is generally used to control the overall operation of the computer device 8. In this embodiment, the processor 82 is used to run the computer-readable instructions stored in the memory 81 or process data, such as running the computer-readable instructions of the slot compatibility test method.

[0063] The network interface 83 may include a wireless network interface or a wired network interface. The network interface 83 is generally used to establish a communication connection between the computer device 8 and other electronic devices.

[0064] The computer device provided in this embodiment can execute the above-mentioned underground tunnel laser point cloud denoising method. Here, the underground tunnel laser point cloud denoising method can be the underground tunnel laser point cloud denoising method of each of the above-mentioned embodiments.

[0065] Example 4 This embodiment also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the underground tunnel laser point cloud denoising method in the embodiment are implemented.

[0066] In this embodiment, the computer-readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the computer-readable storage medium can be an internal storage unit of a computer device, such as a hard disk or memory of the computer device. In other embodiments, the computer-readable storage medium can also be an external storage device of a computer device, such as a plug-in hard disk equipped on the computer device, a smart memory card (Smart Media Card, referred to as SMC), a secure digital (Secure Digital, referred to as SD) card, a flash card, etc. Of course, the computer-readable storage medium can also include both the internal storage unit of the computer device and its external storage device. In this embodiment, the computer-readable storage medium is generally used to store an operating system and various application software installed on the computer device. In addition, the computer-readable storage medium can also be used to temporarily store various types of data that have been output or are to be output.

[0067] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and structure diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in an alternative implementation, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the structure diagram and / or the flow chart, and the combination of boxes in the structure diagram and / or the flow chart, can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0068] In addition, the functional modules or units in the various embodiments of the present invention may be integrated together to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

[0069] If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a smart phone, a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium can be a non-volatile storage medium or a volatile storage medium. For example, the storage medium can be: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a disk or an optical disk, and other media that can store program codes.

[0070] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A method for denoising underground tunnel laser point cloud, characterized in that: The method comprises: Use mobile 3D laser scanning technology to obtain laser point cloud data and positioning trajectory data of the tunnel; According to the positioning trajectory data, the laser point cloud data is divided along the direction of the lane to form multiple sections of profile laser point cloud data; Dividing each section of the profile laser point cloud data on a two-dimensional plane according to the positioning trajectory data to form a plurality of local target point cloud ranges; All laser points within the range of each local target point cloud are traversed, the Euclidean distance between each laser point and the positioning trajectory data is calculated, and noise points are eliminated according to the Euclidean distance.

2. The underground tunnel laser point cloud denoising method according to claim 1, characterized in that: The laser point cloud data are discrete laser points, the positioning trajectory data are time-sequential positioning trajectory points, and the positioning trajectory points are distributed along the direction of the lane.

3. The underground tunnel laser point cloud denoising method according to claim 2, characterized in that: The laser point cloud data is divided along the direction of the lane according to the positioning trajectory data to form multiple sections of profile laser point cloud data, including: Starting from the starting or ending side of the positioning trajectory point, all laser point cloud data within a preset number of the positioning trajectory points are sequentially intercepted along the direction of the lane to form multi-segment profile laser point cloud data.

4. The underground tunnel laser point cloud denoising method according to claim 2, characterized in that: The laser point cloud data of each section is divided on a two-dimensional plane according to the positioning trajectory data to form a plurality of local target point cloud ranges, including: In each section of the cross-sectional laser point cloud data, projecting each section of the cross-sectional laser point cloud data according to the positioning trajectory data according to a two-dimensional plane; Taking the positioning trajectory data as endpoints, the projected sections of the profile laser point cloud data are divided into equal angles on a two-dimensional plane to form a plurality of local target point cloud ranges.

5. The underground tunnel laser point cloud denoising method according to claim 4 is characterized in that: In each section of the cross-sectional laser point cloud data, projecting each section of the cross-sectional laser point cloud data according to the positioning trajectory data according to a two-dimensional plane includes: Determine a normal vector according to the positioning trajectory data, and construct a projection plane according to the positioning trajectory data and the normal vector; The laser point cloud data of each section of the cross-section are projected onto the projection plane, and the point cloud coordinates of each laser point are determined according to the distance from each laser point in the laser point cloud data of each section of the cross-section to the projection plane.

6. The underground tunnel laser point cloud denoising method according to claim 5, characterized in that: The positioning trajectory data is used as an endpoint, and each segment of the projected profile laser point cloud data is divided into equal angles on a two-dimensional plane to form a plurality of local target point cloud ranges, including: Taking the positioning trajectory data as the endpoint, dividing each segment of the projected cross-section laser point cloud data into a fan-shaped segment at every preset angle, and cutting it into a plurality of local target point cloud ranges; The polar coordinates of each laser point in the local target point cloud range are calculated.

7. The underground tunnel laser point cloud denoising method according to claim 2, characterized in that: The traversing all laser points within the range of each local target point cloud, calculating the Euclidean distance between each laser point and the positioning trajectory data, and eliminating noise points according to the Euclidean distance, includes: Calculating the Euclidean distance between each laser point within the local target point cloud and the positioning trajectory data, and calculating the average and standard deviation of the Euclidean distances of all laser points; The absolute value of the difference between the Euclidean distance of each laser point and the average value is calculated, and the laser points whose absolute value is greater than a preset multiple of the standard deviation are determined as the noise points, and the noise points are removed.

8. A laser point cloud denoising device for underground tunnels, characterized in that: The device comprises: An acquisition module, used to acquire laser point cloud data and positioning trajectory data of the lane by using mobile 3D laser scanning technology; The first segmentation module is used to segment the laser point cloud data along the direction of the lane according to the positioning trajectory data to form multiple sections of profile laser point cloud data; A second segmentation module is used to segment each section of the profile laser point cloud data on a two-dimensional plane according to the positioning trajectory data to form a plurality of local target point cloud ranges; The elimination module is used to traverse all laser points within the range of each local target point cloud, calculate the Euclidean distance between each laser point and the positioning trajectory data, and eliminate noise points according to the Euclidean distance.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the underground tunnel laser point cloud denoising method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the underground tunnel laser point cloud denoising method described in any one of claims 1 to 7 are implemented.

Images