Minimum building clearance detection method, device and server

Abstract

This invention provides a method, apparatus, and server for detecting minimum clearance, relating to the technical field of railway inspection and control. The method includes: acquiring three-dimensional point cloud data of a railway tunnel, wherein the three-dimensional point cloud data carries tunnel index information and tunnel feature information; extracting tunnel cross-section data at various intervals from the three-dimensional point cloud data using a pre-set distance threshold to establish a tunnel cross-section data set; generating cross-sectional distance feature images of each tunnel cross-section based on the tunnel index information and the tunnel cross-section data set; grouping the cross-sectional distance feature images using the tunnel feature information to obtain target feature image sets for each group, and determining a minimum clearance value set based on the target feature image sets. This invention can reduce the difficulty of screening minimum clearance values ​​for tunnels and improve operational efficiency.

Description

Technical Field

[0001] This invention relates to the technical field of railway inspection and control, and in particular to a method, device and server for detecting minimum building clearance. Background Technology

[0002] Using lasers to scan the tunnel under test yields point cloud data. Current technology suggests extracting tunnel cross-section data by cutting the point cloud data, dividing each cross-section into straight lines and left / right curves, and then selecting the minimum clearance value for each height. However, this method generates hundreds of thousands of tunnel cross-section data points for tunnels tens of kilometers long, resulting in a large workload, increasing the difficulty of clearance value selection, and reducing operational efficiency. Summary of the Invention

[0003] In view of this, the purpose of the present invention is to provide a minimum building clearance detection method, device and server, which can reduce the difficulty of screening the minimum clearance value of tunnels and improve the efficiency of operation.

[0004] In a first aspect, embodiments of the present invention provide a minimum building clearance detection method, the method comprising: acquiring three-dimensional point cloud data of a railway tunnel, wherein the three-dimensional point cloud data carries tunnel index information and tunnel feature information; extracting tunnel cross-section data at each interval distance from the three-dimensional point cloud data using a pre-set distance threshold to establish a tunnel cross-section data set; generating cross-sectional distance feature images of each tunnel cross-section based on the tunnel index information and the tunnel cross-section data set; grouping the cross-sectional distance feature images using the tunnel feature information to obtain a target feature image set for each group, and determining a minimum clearance value set based on the target feature image set.

[0005] In one embodiment, the tunnel indicator information includes lateral distance information and mileage information. The step of generating a cross-sectional distance feature image of each tunnel cross-section based on the tunnel indicator information and the tunnel cross-section data set includes: generating a first tunnel cross-section image based on the tunnel cross-section data set; adding distance measurement lines at corresponding height positions in the first tunnel cross-section image using pre-set measurement height information; annotating the distance measurement lines with distance values ​​for the left and right boundary distances using the lateral distance information to obtain a second tunnel cross-section image; and combining the mileage information with the second tunnel cross-section image to obtain a cross-sectional distance feature image of each tunnel cross-section.

[0006] In one embodiment, the step of adding distance measurement lines at corresponding height positions in the first tunnel cross-section image includes: when a high-attention device is detected in any height interval of the first tunnel cross-section image, increasing the attention of the height interval by increasing the distribution density of the distance measurement lines within the height interval.

[0007] In one embodiment, the tunnel feature information includes: height information. The step of grouping the cross-sectional distance feature images using the tunnel feature information to obtain a set of target feature images for each group includes: performing first-level grouping of the cross-sectional distance feature images according to the height information to obtain a first feature image set, wherein the first feature image set includes boundary distances at different heights of the same tunnel cross-section; and determining the target feature image set according to the first feature image set.

[0008] In one embodiment, the tunnel feature information further includes: steering information and turning radius information. The step of determining the target feature image set based on the first feature image set further includes: performing secondary grouping on the first feature image set based on the steering information and turning radius information to obtain a second feature image set, wherein the second feature image set includes different tunnel cross-sections with the same turning radius and the same steering, and the boundary distance at the same height; and determining the second feature image set as the target feature image set.

[0009] In one implementation, the step of determining a minimum limit value set based on a set of target feature images includes: determining the minimum boundary distance at each height in the same set of target feature images as the target limit value for height; integrating the target limit values ​​at the same height in the set of target feature images corresponding to different turning radii, and determining the minimum value as the minimum limit value.

[0010] In one implementation, the step of determining the minimum boundary distance at each height in the same set of target feature images as the target boundary value includes: using a pre-established correction model to correct the minimum boundary distance at each height in the set of target feature images to obtain the target boundary value.

[0011] Secondly, embodiments of the present invention also provide a minimum building clearance detection device, the device comprising: a point cloud data acquisition module for acquiring three-dimensional point cloud data of a railway tunnel, wherein the three-dimensional point cloud data carries tunnel index information and tunnel feature information; a cross-section data acquisition module for extracting tunnel cross-section data at various intervals from the three-dimensional point cloud data using a pre-set distance threshold to establish a tunnel cross-section data set; a feature image acquisition module for generating cross-sectional distance feature images of each tunnel cross-section based on the tunnel index information and the tunnel cross-section data set; and a minimum threshold value determination module for grouping the cross-sectional distance feature images using the tunnel feature information to obtain a target feature image set for each group, thereby determining a minimum clearance value set based on the target feature image set.

[0012] Thirdly, embodiments of the present invention also provide a server, including a processor and a memory, the memory storing computer-executable instructions executable by the processor, the processor executing the computer-executable instructions to implement any of the methods provided in the first aspect.

[0013] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing computer-executable instructions, which, when invoked and executed by a processor, cause the processor to implement any of the methods provided in the first aspect.

[0014] The embodiments of the present invention bring the following beneficial effects:

[0015] This invention provides a minimum building clearance detection method, device, and server. It acquires three-dimensional point cloud data of a railway tunnel, where the three-dimensional point cloud data carries tunnel indicator information and tunnel feature information. Using a pre-set distance threshold, tunnel cross-section data at various intervals are extracted from the three-dimensional point cloud data to establish a tunnel cross-section data set. Based on the tunnel indicator information and the tunnel cross-section data set, cross-sectional distance feature images of each tunnel cross-section are generated. The cross-sectional distance feature images are then grouped using the tunnel feature information to obtain target feature image sets for each group. A minimum clearance value set is determined based on the target feature image sets. This invention generates feature images from the tunnel cross-section data set and groups these feature images, reducing the difficulty of screening minimum clearance values ​​and improving operational efficiency.

[0016] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention are realized and obtained in accordance with the structures particularly pointed out in the description, claims and drawings.

[0017] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0018] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0019] Figure 1 A flowchart illustrating a minimum building clearance detection method provided in an embodiment of the present invention;

[0020] Figure 2 A flowchart illustrating another minimum building clearance detection method provided in an embodiment of the present invention;

[0021] Figure 3 This is a schematic diagram of the structure of a cross-sectional distance feature image provided in an embodiment of the present invention;

[0022] Figure 4 This is a flowchart illustrating a process for dividing folders based on indicator information, provided in an embodiment of the present invention.

[0023] Figure 5 This is a flowchart illustrating a process for dividing folders based on feature information, provided by an embodiment of the present invention.

[0024] Figure 6 This is a schematic diagram of the structure of a target feature image set provided in an embodiment of the present invention;

[0025] Figure 7 This is a schematic diagram of another target feature image set provided in an embodiment of the present invention;

[0026] Figure 8 This is a schematic diagram of a minimum building clearance detection device provided in an embodiment of the present invention;

[0027] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0029] Currently, the minimum clearance is calculated in the track surface coordinate system, from the center of the coordinate system at a certain height, as the horizontal distance from the left and right tunnel walls to the center of the track surface and the vertical distance from the top of the tunnel to the center of the track surface. There are many methods for minimum clearance detection, and point cloud-based tunnel detection methods are gradually being applied. Currently, this mainly involves cutting point cloud data. However, the length of a single minimum clearance detection operation can be tens of kilometers. When extracting point cloud data at 3cm intervals, hundreds of thousands of tunnel cross-sections are generated. Dividing these hundreds of thousands of tunnel cross-sections into individual tunnels, and then further dividing each individual tunnel into straight lines and left and right curves, and finally selecting the minimum clearance value for each height, is a labor-intensive process. The current operational efficiency is low and cannot meet daily work needs. Based on this, the minimum building clearance detection method provided by this invention, on the basis of existing massive point cloud, can automatically divide hundreds of thousands of cross sections into various tunnels and divide them according to straight lines and left and right curves through internal software processes, and extract the minimum clearance values ​​of each height, thereby improving operational efficiency and ensuring that the minimum clearance values ​​of multiple tunnels and multiple turning radii are obtained from the massive data collected at one time. It can ensure that 5 or more tunnels can be processed in 1 day, meeting the needs of daily work. By generating feature images from the tunnel cross section data set and grouping the feature images, the difficulty of screening the minimum clearance value of the tunnel can be reduced and operational efficiency can be improved.

[0030] based on Figure 1 The diagram shows a flowchart of a minimum building clearance detection method, which mainly includes the following steps S102 to S108:

[0031] Step S102: Obtain three-dimensional point cloud data of the railway tunnel. The three-dimensional point cloud data carries tunnel indicator information and tunnel feature information. The tunnel indicator information includes: tunnel name information, lateral distance information and mileage information. The tunnel feature information includes: height information, turning information and turning radius information. The turning information includes: left turn, right turn and straight. In one embodiment, the point cloud information of the railway tunnel can be obtained by scanning the tunnel with a laser.

[0032] Step S104: Using a pre-set distance threshold, extract tunnel cross-section data at each interval distance from the three-dimensional point cloud data to establish a tunnel cross-section data set. In one embodiment, select point cloud data of tunnel segments with the same tunnel name, turning direction, and turning radius, divide the tunnel segments into multiple tunnel cross-section data according to the distance threshold, and establish a tunnel cross-section data set.

[0033] Step S106: Based on the tunnel index information and the tunnel cross-section data set, generate cross-sectional distance feature images for each tunnel cross-section. The tunnel cross-section data includes the location of the tunnel cross-section (i.e., mileage) and distance lines at various heights within the same tunnel cross-section. In one embodiment, the cross-sectional distance feature images include distance lines at various heights. The distance lines are used to characterize the distance between the centerline and the left and right boundaries of the track at any height in the track surface coordinate system.

[0034] Step S108: The cross-sectional distance feature images are grouped using tunnel feature information to obtain a set of target feature images for each group. A set of minimum limit values ​​is determined based on the set of target feature images. The set of target feature images includes multiple groups. Within the same group, there are limit values ​​for different turning radii of the same tunnel and the same direction at the same height relative to the horizontal boundary of the tunnel. In one embodiment, the cross-sectional distance feature images are grouped using height information, turning information, and turning radius information to obtain a set of target feature images. The limit values ​​for different turning radii of the same tunnel and the same direction at the same height relative to the horizontal boundary of the tunnel are sorted from smallest to largest within the same group. Multiple images within the same group are integrated. Target feature images in the same group can be displayed simultaneously. The minimum limit value of different turning radii of the same tunnel and the same direction at the same height is obtained by analysis using manual or limit value screening models. This limit value is determined as the minimum limit value. The minimum limit values ​​of different turning radii of the same tunnel and the same direction at different heights are used to establish a set of minimum limit values ​​for the corresponding tunnel and tunnel turning.

[0035] The minimum building clearance detection method provided in this embodiment of the invention generates feature images from tunnel cross-section data sets and groups the feature images, which can reduce the difficulty of screening the minimum clearance value of tunnels and improve work efficiency.

[0036] This invention also provides an implementation method for establishing a target feature image set, as detailed in (1) to (3) below:

[0037] (1) Based on the tunnel cross-section data set, a first tunnel cross-section image is generated. Using pre-set measurement height information, distance measurement lines are added at corresponding height positions in the first tunnel cross-section image. The distance measurement lines are annotated with distance values ​​for the left and right boundaries using lateral distance information to obtain a second tunnel cross-section image. The mileage information is combined with the second tunnel cross-section image to obtain the cross-sectional distance feature image of each tunnel cross-section. The first tunnel cross-section image includes the position of the tunnel cross-section and distance lines at various heights within the same tunnel cross-section. The second tunnel cross-section image includes the clearance values ​​of different turning radii of the same tunnel and the same turn at the same height. In one embodiment, the cross-sectional distance feature image includes distance lines at various heights. The distance lines are used to characterize the distance between the centerline and the left and right boundaries of the track at any height in the track surface coordinate system.

[0038] In one implementation, when a high-attention device is detected in any height range of the first tunnel cross-section image, the attention of the height range is increased by increasing the distribution density of distance measurement lines within the height range. In practical applications, if there are many power lines at any height of any mileage in a railway tunnel, the distribution density of distance measurement lines is increased at that location to increase the attention and obtain a more accurate clearance value for that location.

[0039] (2) The cross-sectional distance feature images are grouped into first-level groups according to the height information to obtain a first feature image set. The first feature image set includes the boundary distances at different heights of the same tunnel cross-section. In one embodiment, point cloud data of tunnel segments with the same tunnel name, turning direction and turning radius are selected. The tunnel segments are divided into multiple tunnel cross-section data according to the distance threshold to establish a tunnel cross-section data set. The folder storing the tunnel cross-section data is grouped and the files are named according to the tunnel name, turning direction and turning radius. The distance feature images of each tunnel cross-section of the tunnel segment with the same tunnel name, turning direction and turning radius are stored in the folder to obtain the first feature image set.

[0040] (3) Determine a target feature image set based on the first feature image set. Perform secondary grouping on the first feature image set based on steering information and turning radius information to obtain a second feature image set. The second feature image set includes different tunnel cross-sections with the same turning radius and steering direction, and their boundary distances at the same height. The second feature image set is then determined as the target feature image set. The target feature image set includes multiple groups, with each group containing the boundary values ​​of different turning radii with the same tunnel and steering direction at the same height, representing the distance from the horizontal boundary of the tunnel. In one embodiment, height information, steering information, and turning radius information are used to analyze the cross-sections. Distance feature images are grouped to obtain a set of target feature images. Within the same group, the clearance values ​​of different turning radii of the same tunnel and the same turn at the same height are sorted from smallest to largest. Multiple images from the same group are integrated, and target feature images of the same group can be displayed simultaneously. The minimum clearance value of different turning radii of the same tunnel and the same turn at the same height is obtained by analysis using manual or clearance value screening models. This clearance value is determined as the minimum clearance value. Using the minimum clearance values ​​of different turning radii of the same tunnel and the same turn at different heights, a set of minimum clearance values ​​for the corresponding tunnel and tunnel turn is established.

[0041] Regarding the aforementioned step S108, this embodiment of the invention also provides an implementation method for determining the minimum boundary value based on a set of target feature images. The minimum boundary distance at each height in the same set of target feature images is determined as the target boundary value for height. The target boundary values ​​at the same height in the set of target feature images corresponding to different turning radii are integrated, and the minimum value is determined as the minimum boundary value. In one implementation method, a pre-established correction model is used to correct the minimum boundary distance at each height in the set of target feature images to obtain the target boundary value.

[0042] To facilitate understanding of the minimum building clearance detection method provided in the above embodiments, this invention provides an application example of the minimum building clearance detection method, see [link to example]. Figure 2 The flowchart shown is another method for detecting minimum building clearance. This method mainly includes the following steps S202 to S210:

[0043] Step S202: Create a tunnel table using the 3D point cloud data of the railway tunnel. Referring to the tunnel representation diagram shown in Table 1, use the 3D point cloud data of the railway tunnel to divide the starting and ending mileages of each tunnel, and divide the left and right curve segments and straight segments of each tunnel. Finally, further divide according to the turning radius to obtain the starting and ending positions of tunnels with the same tunnel name, the same turning radius, and the same direction in the tunnel table, and extract the cross-section of this tunnel segment.

[0044] Step S204: Based on the indicator information, the tunnel table is grouped into primary groups to determine the start and end positions of each tunnel, and cross-sectional distance feature images of each group of tunnels are created using 3D point cloud data. (See also...) Figure 3 The diagram shows a structural schematic of a cross-sectional distance feature image. Cross-sections of tunnels with the same name, turning radius, and direction are extracted at equal intervals of 3cm and exported as CAD format. The CAD file marks the distance from each height to the tunnel cross-section and names them with mileage.

[0045] Step S206: Perform secondary grouping of the tunnel table based on feature information to determine target feature data. (See also...) Figure 4 The diagram shows a flowchart of a process for dividing folders based on indicator information. Figure 5 The diagram shows a flowchart of a process for dividing folders based on feature information. The tunnel table is sent to the image generation model to filter each DXF (i.e., CAD file). Each tunnel is set as the main folder, and each tunnel is divided into straight segments, left curve segments, and right curve segments. Different turning radii need to be saved to multiple subordinate folders.

[0046] Step S208: Generate a target feature image set based on the target feature data. (See also...) Figure 6 The diagram shows a structure of a target feature image set. Each DXF is converted into an image, and all DXFs are read, sorted from smallest to largest according to a certain height limit value, and a fixed number of DXFs are selected (e.g., 16 DXFs per image). The fixed number of DXFs are then converted into the corresponding images.

[0047] Step S210: Determine the minimum bounding value set based on the target feature image set. (See also...) Figure 7 The diagram shows another structural schematic of the target feature image set. The left side displays the limit values ​​for each height, and the right side displays the loaded image information. It is divided according to the rail surface height (e.g., filtering the limit value by the left rail plane height of 0.0m; only one limit value needs to be filtered. Double-clicking each section position will display a checkmark in the software, indicating the minimum limit value at that height). There are multiple turning radii for the same turn in the same tunnel. Each turning radius includes a batch of height limit values. The target limit value is obtained by correcting the height limit value using a correction formula. The minimum value of the target limit value for different turning radii at the same height is determined as the minimum limit value for the same turn in the same tunnel at this height, and the final result is output to the user terminal.

[0048] In summary, this invention can generate feature images from tunnel cross-section data sets and group these feature images, thereby reducing the difficulty of selecting minimum clearance values ​​for tunnels and improving operational efficiency.

[0049] Regarding the minimum building clearance detection method provided in the foregoing embodiments, this invention provides a minimum building clearance detection device, see [link to relevant documentation]. Figure 8 The diagram shows a structural schematic of a minimum building clearance detection device, which includes the following components:

[0050] The point cloud data acquisition module 802 acquires three-dimensional point cloud data of the railway tunnel, wherein the three-dimensional point cloud data carries tunnel index information and tunnel feature information.

[0051] The cross-section data acquisition module 804 uses a pre-set distance threshold to extract tunnel cross-section data at each interval from the three-dimensional point cloud data and establishes a tunnel cross-section data set.

[0052] The feature image acquisition module 806 generates cross-sectional distance feature images for each tunnel section based on tunnel index information and tunnel cross-section data set.

[0053] The minimum critical value determination module 808 uses tunnel feature information to group the cross-sectional distance feature images to obtain a set of target feature images for each group, and then determines the minimum limit value set based on the set of target feature images.

[0054] The data processing device provided in this application generates feature images from a set of tunnel cross-section data and groups the feature images, which can reduce the difficulty of screening the minimum clearance value of the tunnel and improve work efficiency.

[0055] In one embodiment, the tunnel indicator information includes lateral distance information and mileage information. During the step of generating cross-sectional distance feature images of each tunnel cross-section based on the tunnel indicator information and the tunnel cross-section data set, the feature image acquisition module 806 is further configured to: generate a first tunnel cross-section image based on the tunnel cross-section data set; add distance measurement lines at corresponding height positions in the first tunnel cross-section image using pre-set measurement height information; annotate the distance measurement lines with distance values ​​for the left and right boundary distances using the lateral distance information to obtain a second tunnel cross-section image; and combine the mileage information with the second tunnel cross-section image to obtain cross-sectional distance feature images of each tunnel cross-section.

[0056] In one embodiment, when adding distance measurement lines at corresponding height positions in the first tunnel cross-section image, the feature image acquisition module 806 is further configured to: when a high-attention device is detected in any height interval of the first tunnel cross-section image, increase the attention of the height interval by increasing the distribution density of the distance measurement lines within the height interval.

[0057] In one embodiment, the tunnel feature information includes height information. When performing the step of grouping the cross-sectional distance feature images using the tunnel feature information to obtain a set of target feature images for each group, the minimum threshold determination module 808 is further configured to: perform first-level grouping of the cross-sectional distance feature images according to the height information to obtain a first feature image set, wherein the first feature image set includes boundary distances at different heights of the same tunnel cross-section; and determine the target feature image set according to the first feature image set.

[0058] In one embodiment, the tunnel feature information further includes: steering information and turning radius information. When performing the step of determining the target feature image set based on the first feature image set, the minimum threshold determination module 808 is further configured to: perform secondary grouping on the first feature image set based on the steering information and turning radius information to obtain a second feature image set, wherein the second feature image set includes different tunnel cross-sections with the same turning radius and the same steering, and the boundary distance at the same height; and determine the second feature image set as the target feature image set.

[0059] In one embodiment, when performing the step of determining the minimum limit value set based on the target feature image set, the minimum critical value determination module 808 is further configured to: determine the minimum boundary distance at each height in the same target feature image set as the target limit value of the height; integrate the target limit values ​​of the same height in the target feature image sets corresponding to different turning radii, and determine the minimum value as the minimum limit value.

[0060] In one embodiment, when performing the step of determining the minimum boundary distance at each height in the same set of target feature images as the target limit value, the minimum critical value determination module 808 is further configured to: use a pre-established correction model to correct the minimum boundary distance at each height in the set of target feature images to obtain the target limit value.

[0061] The device provided in this embodiment of the invention has the same implementation principle and technical effect as the aforementioned method embodiment. For the sake of brevity, any parts not mentioned in the device embodiment can be referred to the corresponding content in the aforementioned method embodiment.

[0062] This invention provides an electronic device, specifically, the electronic device includes a processor and a storage device; the storage device stores a computer program, and the computer program, when run by the processor, executes the method described in any of the above embodiments.

[0063] Figure 9This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. The electronic device 100 includes: a processor 90, a memory 91, a bus 92, and a communication interface 93. The processor 90, the communication interface 93, and the memory 91 are connected through the bus 92. The processor 90 is used to execute executable modules, such as computer programs, stored in the memory 91.

[0064] The memory 91 may include high-speed random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one communication interface 93 (which can be wired or wireless), such as the Internet, wide area network, local area network, metropolitan area network, etc.

[0065] Bus 92 can be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 9 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0066] The memory 91 is used to store programs. After receiving an execution instruction, the processor 90 executes the programs. The method executed by the device for defining the flow process disclosed in any of the foregoing embodiments of the present invention can be applied to the processor 90 or implemented by the processor 90.

[0067] The processor 90 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of the processor 90 or by instructions in software form. The processor 90 may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules may reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 91. Processor 90 reads the information in memory 91 and, in conjunction with its hardware, completes the steps of the above method.

[0068] The computer program product of the readable storage medium provided in the embodiments of the present invention includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the methods described in the foregoing method embodiments. For specific implementation, please refer to the foregoing method embodiments, which will not be repeated here.

[0069] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0070] Finally, it should be noted that the above-described embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit it. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for detecting minimum building clearance, characterized in that, The method includes: Acquire three-dimensional point cloud data of a railway tunnel, wherein the three-dimensional point cloud data carries tunnel index information and tunnel feature information; Using a pre-set distance threshold, tunnel cross-section data at each interval distance is extracted from the three-dimensional point cloud data to establish a tunnel cross-section data set; Based on the tunnel index information and the tunnel cross-section data set, a cross-sectional distance feature image of each tunnel cross-section is generated; The cross-sectional distance feature image is grouped using the tunnel feature information to obtain a set of target feature images for each group, and a set of minimum limit values ​​is determined based on the set of target feature images. The tunnel indicator information includes lateral distance information and mileage information. The step of generating cross-sectional distance feature images of each tunnel cross-section based on the tunnel indicator information and the tunnel cross-section data set includes: generating a first tunnel cross-section image based on the tunnel cross-section data set; adding distance measurement lines at corresponding height positions in the first tunnel cross-section image using pre-set measurement height information; annotating the distance measurement lines with distance values ​​for the left and right boundaries using the lateral distance information to obtain a second tunnel cross-section image; combining the mileage information with the second tunnel cross-section image to obtain the cross-sectional distance feature images of each tunnel cross-section. The first tunnel cross-section image includes the position of the tunnel cross-section and distance lines at various heights within the same tunnel cross-section; the second tunnel cross-section image includes the clearance values ​​at the same height for different turning radii of the same tunnel and the same direction; the cross-sectional distance feature images include distance lines at various heights, which are used to characterize the distance between the centerline and the left and right boundaries of the track at any height in the track surface coordinate system. The step of adding distance measurement lines at corresponding height positions in the first tunnel cross-section image includes: when a high-attention device is detected in any height interval of the first tunnel cross-section image, increasing the attention of the height interval by increasing the distribution density of the distance measurement lines in the height interval.

2. The method according to claim 1, characterized in that, The tunnel feature information includes height information. The step of grouping the cross-sectional distance feature image using the tunnel feature information to obtain a set of target feature images for each group includes: The cross-sectional distance feature images are grouped into a first-level group based on the height information to obtain a first feature image set, wherein the first feature image set includes the boundary distances at different heights of the same tunnel cross-section; The target feature image set is determined based on the first feature image set.

3. The method according to claim 2, characterized in that, The tunnel feature information further includes: turning information and turning radius information. The step of determining the target feature image set based on the first feature image set further includes: The first feature image set is grouped into two levels based on the steering information and the turning radius information to obtain a second feature image set. The second feature image set includes different tunnel cross-sections with the same turning radius and the same steering, and the boundary distance at the same height. The second set of feature images is determined as the target set of feature images.

4. The method according to claim 1, characterized in that, The step of determining the minimum bounding value set based on the target feature image set includes: The minimum boundary distance at each height in the same set of target feature images is determined as the target limit value at that height; The target boundary values ​​at the same height are integrated from the target feature image sets corresponding to different turning radii, and the minimum value is determined as the minimum boundary value.

5. The method according to claim 4, characterized in that, The step of determining the minimum boundary distance at each height in the same set of target feature images as the target boundary value at that height includes: The minimum boundary distance at each height in the target feature image set is corrected using a pre-established correction model to obtain the target boundary value.

6. A minimum building clearance detection device, characterized in that, The device includes: The point cloud data acquisition module acquires three-dimensional point cloud data of the railway tunnel, wherein the three-dimensional point cloud data carries tunnel index information and tunnel feature information. The cross-section data acquisition module uses a pre-set distance threshold to extract tunnel cross-section data at each interval from the three-dimensional point cloud data, and establishes a tunnel cross-section data set. The feature image acquisition module generates cross-sectional distance feature images for each tunnel cross-section based on the tunnel index information and the tunnel cross-section data set. The minimum critical value determination module uses the tunnel feature information to group the cross-sectional distance feature image to obtain a set of target feature images for each group, and determines the minimum limit value set based on the set of target feature images. The tunnel indicator information includes lateral distance information and mileage information. The step of generating cross-sectional distance feature images of each tunnel cross-section based on the tunnel indicator information and the tunnel cross-section data set includes: generating a first tunnel cross-section image based on the tunnel cross-section data set; adding distance measurement lines at corresponding height positions in the first tunnel cross-section image using pre-set measurement height information; annotating the distance measurement lines with distance values ​​for the left and right boundaries using the lateral distance information to obtain a second tunnel cross-section image; combining the mileage information with the second tunnel cross-section image to obtain the cross-sectional distance feature images of each tunnel cross-section. The first tunnel cross-section image includes the position of the tunnel cross-section and distance lines at various heights within the same tunnel cross-section; the second tunnel cross-section image includes the clearance values ​​at the same height for different turning radii of the same tunnel and the same direction; the cross-sectional distance feature images include distance lines at various heights, which are used to characterize the distance between the centerline and the left and right boundaries of the track at any height in the track surface coordinate system. The step of adding distance measurement lines at corresponding height positions in the first tunnel cross-section image includes: when a high-attention device is detected in any height interval of the first tunnel cross-section image, increasing the attention of the height interval by increasing the distribution density of the distance measurement lines in the height interval.

7. A server, characterized in that, The method includes a processor and a memory, the memory storing computer-executable instructions executable by the processor, the processor executing the computer-executable instructions to implement the method of any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions that, when invoked and executed by a processor, cause the processor to perform the method described in any one of claims 1 to 5.

Images