Roller coaster gauge measuring method and system based on three-dimensional point cloud data

Abstract

The invention discloses a roller coaster track gauge measurement method and system based on three-dimensional point cloud data, and relates to the technical field of roller coaster track gauge measurement, and the method comprises the steps: firstly obtaining the three-dimensional point cloud data of a space where a target roller coaster track is located, and extracting the three-dimensional point cloud data of the target roller coaster track from the three-dimensional point cloud data; based on the cross section features of the orbits, center track point cloud data of the two single-side orbits are extracted from the cross section features, the center track point cloud data of the two single-side orbits are matched with each other through a nearest neighbor search algorithm, a plurality of point cloud pairs are obtained, the distance between the two point clouds in each point cloud pair is calculated, and the distance between the two point clouds in each point cloud pair is calculated; therefore, the track gauge of any position of the target roller coaster track can be determined. According to the scheme, the three-dimensional point cloud data of the roller coaster track is obtained, the track gauge can be automatically measured and calculated through a designed algorithm, manual measurement is not needed, and calculation is accurate; moreover, the distance between the central points of the two rails can be measured, and the value of the rail gauge data is greatly improved.

Description

Technical Field

[0001] The present application relates to the technical field of roller coaster track gauge measurement, and in particular to a roller coaster track gauge measurement method and system based on three-dimensional point cloud data. Background Art

[0002] In recent years, with the substantial improvement of people's living standards, many amusement parks or theme parks have been built across the country. Among them, roller coasters attract a large number of tourists due to their strong stimulation to the senses. However, during the long-term high-speed operation of roller coasters, the roller coasters and tourist loads will impose periodic high loads on the tracks. This will cause fatigue damage and deformation of the tracks. From the time the roller coaster is installed and put into use until it is decommissioned, the tracks will generally not be removed or replaced. Once the deformation of the roller coaster track exceeds the allowable range or fatigue fracture occurs, it will cause the roller coaster to derail, resulting in serious casualties. For this reason, it is extremely necessary to conduct in-service inspections on the tracks of large-scale amusement facilities such as roller coasters.

[0003] Currently in the amusement facility inspection and testing industry, the measurement method of roller coaster track gauge has the following problems: the track gauge measured by the current measurement method refers to the distance between the inner sides of the two track edges, and the actual distance between the center points of the two tracks cannot be measured. As the track wears, the measurement results will be affected; the positioning point of the measurement starting position is not fixed, and the measurement results vary greatly; the track gauge measurement only selects the area that personnel can reach, and the unreachable part cannot be measured; the measurement method is manual. This type of measurement method has poor accuracy, low efficiency, and weak reference and comparative analysis value.

[0004] Therefore, how to improve and overcome the above-mentioned defects in the prior art and enhance the inspection and testing efficiency of large-scale amusement facilities is a technical problem that needs to be urgently solved in this field. Summary of the invention

[0005] The purpose of this application is to provide a roller coaster track gauge measurement method and system based on three-dimensional point cloud data, which can automatically and efficiently measure the actual track gauge between roller coaster tracks.

[0006] To achieve the above objectives, this application provides the following solutions:

[0007] In a first aspect, the present application provides a roller coaster track gauge measurement method based on three-dimensional point cloud data, comprising the following steps:

[0008] The three-dimensional point cloud data of the space where the target roller coaster track is located is obtained; the initial three-dimensional point cloud data includes the three-dimensional point cloud data of the target roller coaster track and the three-dimensional point cloud data of the surrounding environment of the target roller coaster track.

[0009] Based on the appearance features of the target roller coaster track, the three-dimensional point cloud data of the target roller coaster track is extracted from the three-dimensional point cloud data of the space where the target roller coaster track is located.

[0010] Based on the cross-sectional features of the track, the center track point cloud data of the two unilateral tracks of the target roller coaster track are extracted from the three-dimensional point cloud data of the target roller coaster track.

[0011] For the central track point cloud data of any single-sided track, a nearest neighbor search algorithm is used to match the central track point cloud data of another single-sided track to obtain several point cloud pairs.

[0012] For each point cloud pair, the distance between the two point clouds of the point cloud pair is calculated to determine the track gauge at any position of the target roller coaster track.

[0013] Optionally, obtaining three-dimensional point cloud data of the space where the target roller coaster track is located specifically includes: using a drone-mounted laser radar and a high-resolution laser scanning device to obtain the three-dimensional point cloud data of the space where the target roller coaster track is located in the form of visible light and / or laser dot marking.

[0014] Optionally, based on the appearance features of the target roller coaster track, the three-dimensional point cloud data of the target roller coaster track is extracted from the three-dimensional point cloud data of the space where the target roller coaster track is located, specifically including:

[0015] Based on the position, color intensity and normal direction of the target roller coaster track, initial three-dimensional point cloud data of the target roller coaster track is obtained by segmenting the three-dimensional point cloud data of the space where the target roller coaster track is located.

[0016] The initial three-dimensional point cloud data of the target roller coaster track is segmented and optimized to obtain the three-dimensional point cloud data of the target roller coaster track; the post-segmentation optimization operation includes removing noise points, filling holes and smoothing boundaries.

[0017] Optionally, based on the cross-sectional features of the track, the center track point cloud data of the two unilateral tracks of the target roller coaster track are extracted from the three-dimensional point cloud data of the target roller coaster track, including:

[0018] For the three-dimensional point cloud data of any single-side track of the target roller coaster track, the three-dimensional point cloud data of the single-side track is sliced ​​along the forward direction to obtain a plurality of slice data of the single-side track.

[0019] For any slice data, based on the cross-sectional features of the track, an area with a circular cross-section is searched in the slice data as the track cross-sectional area.

[0020] The center points of the track cross-section areas in all the slice data of the single-sided track are connected to obtain the center track point cloud data of the single-sided track.

[0021] Optionally, for the center track point cloud data of any one unilateral track, a nearest neighbor search algorithm is used to match the center track point cloud data of another unilateral track to obtain a plurality of point cloud pairs, specifically including:

[0022] Create a kd tree structure; the input of the kd tree structure is the center track point cloud data of any single-sided track.

[0023] For any point cloud on the central track point cloud data of a single-sided track, a kd tree structure is used to perform a nearest neighbor search in the central track point cloud data of another single-sided track, and the searched point cloud and point cloud are stored as a point cloud pair to obtain several point cloud pairs.

[0024] Optionally, for any point cloud pair, the distance between the two point clouds of the point cloud pair is calculated according to the following formula:

[0025]

[0026] Among them, d is the distance between the two point clouds of the point cloud pair, (x1, y1, z1) is the three-dimensional coordinate of one point cloud in the point cloud pair, and (x2, y2, z2) is the three-dimensional coordinate of the other point cloud in the point cloud pair.

[0027] Optionally, after calculating the distance between two point clouds of each point cloud pair, the method further includes:

[0028] The visualization module is used to visualize the distance between two point clouds of each point cloud.

[0029] Optionally, after calculating the distance between two point clouds of each point cloud pair, the method further includes:

[0030] According to the distance between two point clouds of each point cloud pair, the point cloud pair corresponding to the shortest distance value is determined.

[0031] The visualization module is used to visualize the distance between two point clouds of each point cloud pair, and the point cloud pair corresponding to the shortest distance value is highlighted.

[0032] In a second aspect, the present application provides a roller coaster track gauge measurement system based on three-dimensional point cloud data, comprising the following modules:

[0033] The three-dimensional point cloud data acquisition module is used to acquire the three-dimensional point cloud data of the space where the target roller coaster track is located; the initial three-dimensional point cloud data includes the three-dimensional point cloud data of the target roller coaster track and the three-dimensional point cloud data of the surrounding environment of the target roller coaster track.

[0034] The target track point cloud extraction module is used to extract the three-dimensional point cloud data of the target roller coaster track from the three-dimensional point cloud data of the space where the target roller coaster track is located based on the appearance features of the target roller coaster track.

[0035] The track center point cloud extraction module is used to extract the center track point cloud data of the two single-side tracks of the target roller coaster track from the three-dimensional point cloud data of the target roller coaster track based on the cross-sectional features of the track.

[0036] The point cloud nearest neighbor search module is used to match the central track point cloud data of any single-sided track with the central track point cloud data of another single-sided track using the nearest neighbor search algorithm to obtain several point cloud pairs.

[0037] The point cloud pair track gauge determination unit is used to calculate the distance between two point clouds of each point cloud pair to determine the track gauge of any position of the target roller coaster track.

[0038] Optionally, it also includes: a visual display module.

[0039] The visualization module is used to visualize the distance between two point clouds.

[0040] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0041] The present application provides a roller coaster track gauge measurement method and system based on three-dimensional point cloud data, the method includes: firstly obtaining the three-dimensional point cloud data of the space where the target roller coaster track is located, extracting the three-dimensional point cloud data of the target roller coaster track from it, then extracting the center track point cloud data of the two single-sided tracks based on the cross-sectional characteristics of the track, for the center track point cloud data of any single-sided track, using the nearest neighbor search algorithm to match in the center track point cloud data of the other single-sided track, obtaining a number of point cloud pairs, and finally calculating the distance between the two point clouds in each point cloud pair, that is, determining the track gauge at any position of the target roller coaster track. The above scheme of the present application obtains the three-dimensional point cloud data of the roller coaster track, can automatically generate a three-dimensional point cloud model, and the designed algorithm can automatically measure the track gauge. The whole process includes data collection and analysis process, each step can be realized digitally, the whole process can be completed automatically, no manual measurement is required, there is no human error, and the calculation is accurate; and the distance measurement between the center points of the two tracks can be realized, which greatly improves the value of the track gauge data. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0043] Figure 1 A flowchart of a roller coaster track gauge measurement method based on three-dimensional point cloud data provided in one embodiment of the present application.

[0044] Figure 2 This is a flowchart of step A3 in a roller coaster track gauge measurement method based on three-dimensional point cloud data provided in one embodiment of the present application.

[0045] Figure 3 A schematic diagram of the functional modules of a roller coaster track gauge measurement system based on three-dimensional point cloud data provided in one embodiment of the present application.

[0046] Figure 4 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0048] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0049] In an exemplary embodiment, Figure 1 As shown, a roller coaster track gauge measurement method based on three-dimensional point cloud data is provided, comprising the following steps:

[0050] A1. Acquire the three-dimensional point cloud data of the space where the target roller coaster track is located; the initial three-dimensional point cloud data includes the three-dimensional point cloud data of the target roller coaster track and the three-dimensional point cloud data of the surrounding environment of the target roller coaster track.

[0051] Specifically in this embodiment, the implementation method of step A1 can be: through the unmanned aerial vehicle loaded laser radar, using high-resolution laser scanning equipment to use visible light and / or laser dot form, to obtain the three-dimensional point cloud data of the space where the target roller coaster track is located. When the visible light + laser dot form is used for collection, the collection range is the point cloud data of the part of the target roller coaster track surface visible to the naked eye. Use the unmanned aerial vehicle loaded laser radar, use the high-resolution laser scanning equipment to obtain the point cloud data of the area where the roller coaster track is located, and obtain the accurate coordinate information of the photo through the GPS positioning system. Take the automatic flight mode, and autonomously complete the flight and shooting tasks according to the set route without manual operation, and obtain high-precision point cloud data within the range.

[0052] A2. Based on the appearance features of the target roller coaster track, the three-dimensional point cloud data of the target roller coaster track is extracted from the three-dimensional point cloud data of the space where the target roller coaster track is located. Specifically in this embodiment, step A2 includes the following steps:

[0053] A21. Based on the position, color intensity and normal direction of the target roller coaster track, initial three-dimensional point cloud data of the target roller coaster track is obtained by segmenting the three-dimensional point cloud data of the space where the target roller coaster track is located.

[0054] A22. Performing a post-segmentation optimization operation on the initial three-dimensional point cloud data of the target roller coaster track to obtain the three-dimensional point cloud data of the target roller coaster track; the post-segmentation optimization operation includes removing noise points, filling holes and smoothing boundaries.

[0055] In step A2, the drone collects point clouds of the entire area, including tracks and surrounding tree facilities, so the point cloud data needs to be segmented first to obtain pure track information. Before segmentation, extract the features of the point cloud, such as point location, color, intensity, normal direction, etc. These features help distinguish different objects. Segmentation algorithms can be geometry-based, attribute-based, clustering-based, or model-based. After segmentation, optimize the segmentation results to remove noise points, fill holes, smooth boundaries, etc., to improve the accuracy and quality of segmentation.

[0056] A3. Based on the cross-sectional features of the track, the center track point cloud data of the two unilateral tracks of the target roller coaster track are extracted from the three-dimensional point cloud data of the target roller coaster track. Figure 2 In the flowchart shown, step A3 specifically includes the following steps:

[0057] A31. For the three-dimensional point cloud data of any single-side track of the target roller coaster track, the three-dimensional point cloud data of the single-side track is sliced ​​along the forward direction to obtain a plurality of slice data of the single-side track.

[0058] A32. For any slice data, based on the cross-sectional features of the track, search for an area with a circular cross-section in the slice data as the track cross-sectional area.

[0059] A33. Connect the centers of the track cross-section areas in all the slice data of the single-sided track to obtain the center track point cloud data of the single-sided track.

[0060] In step A3, since the point cloud data of the track collected by the drone only includes the point cloud of the surfaces of two tracks. The point cloud data in the three-dimensional space needs to be cut into a series of two-dimensional "slices" or "cross sections" in a specific direction. Because the center point of the track is to be found, the direction of the slice is determined to be perpendicular to the axis of the track. Each slice is analyzed, and the vertical cross section of the circle is found according to the cylindrical shape of the track. The center of the circle is the center point of the single track. Then set the spacing between the slices, which depends on the required accuracy and the density of the point cloud. According to the preset slicing direction and spacing, extract the center point on each slice from the point cloud data.

[0061] Before further processing, you need to load the point cloud data of the center point trajectory of the two single-sided tracks, including position data (XYZ coordinates), color information (RGB), intensity information, reflectivity, normal vector, classification label, timestamp, accuracy information, and echo information. These data are usually stored in PCD file format. Use the pcl::io::loadPCDFile function provided by PCL to load these point cloud data into memory.

[0062] A4: For the center track point cloud data of any single-sided track, a nearest neighbor search algorithm is used to match the center track point cloud data of another single-sided track to obtain a plurality of point cloud pairs. In this embodiment, step A4 specifically includes the following steps:

[0063] A41. Create a kd tree structure; the input of the kd tree structure is the center track point cloud data of any single-sided track.

[0064] A42. For any point cloud on the central track point cloud data of a single-sided track, use the kd tree structure to perform a nearest neighbor search in the central track point cloud data of another single-sided track, store the searched point cloud and point cloud as a point cloud pair, and obtain several point cloud pairs.

[0065] In order to improve the efficiency of the nearest neighbor search, the kd tree (K-dimensional tree) data structure is usually used. The kd tree is a tree data structure that partitions the k-dimensional space (three-dimensional data XYZ), which can speed up the nearest neighbor search. In PCL, the pcl::KdTreeFLANN class is used to build the kd tree. The specific steps are to ensure that the header files related to the KD tree in the PCL library are included; create a point cloud object and fill it with data; create a pcl::KdTreeFLANN object and pass the point cloud data to it; the setInputCloud function of the pcl::KdTreeFLANN class automatically builds the KD tree.

[0066] Set the input point cloud of the kd tree to the point cloud of one of the tracks. For each point on the other track, use the kd tree to perform a nearest neighbor search. The pcl::KdTreeFLANN::nearestKSearch function accepts a query point and a search radius (an initial search radius can be set based on the known design values ​​of the roller coaster track, and then adjusted based on the search results. If many points are found to have no neighbors, increase the search radius; if many points are found to have multiple very close neighbors, reduce the search radius). Returns the index and distance of the point closest to the query point. In this process, record the index and distance of each pair of corresponding points.

[0067] A5. For each point cloud pair, calculate the distance between the two point clouds in the point cloud pair to determine the track gauge at any position of the target roller coaster track. Specifically, traverse all point cloud pairs, and for each point cloud pair, calculate the distance between the two point clouds in the point cloud pair according to the following formula:

[0068]

[0069] Among them, d is the distance between the two point clouds of the point cloud pair, (x1, y1, z1) is the three-dimensional coordinate of one point cloud in the point cloud pair, and (x2, y2, z2) is the three-dimensional coordinate of the other point cloud in the point cloud pair.

[0070] As an improved implementation, after calculating the distance between two point clouds in the point cloud pair in step A5, the method may further include the following steps:

[0071] A6. Use the visualization module to visualize the distance between two point clouds.

[0072] As another improved implementation, after calculating the distance between two point clouds in the point cloud pair in step A5, the following steps may also be included:

[0073] A6. According to the distance between two point clouds of each point cloud pair, determine the point cloud pair corresponding to the shortest distance value.

[0074] A7. Use the visualization module to visualize the distance between two point clouds and highlight the point cloud pair corresponding to the shortest distance value.

[0075] Specifically, when performing visualization, the PCL visualization module is used. The PCL visualization module provides the pcl::visualization::PCLVisualizer class to create a 3D visualization window. The specific steps are to ensure that the header file of the PCL visualization module is included; create a pcl::visualization::PCLVisualizer object and create a visualization window; use the addPointCloud method to add the point cloud to the visualizer; set a suitable viewpoint to better view the point cloud; call the spin method to start the visualization loop. Display the two tracks in different colors and draw a green line between them to indicate the shortest distance.

[0076] Based on the same inventive concept, the embodiment of the present application also provides a roller coaster track gauge measurement system based on three-dimensional point cloud data for implementing the roller coaster track gauge measurement method based on three-dimensional point cloud data involved above. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more embodiments of the roller coaster track gauge measurement system based on three-dimensional point cloud data provided below can refer to the limitations of the roller coaster track gauge measurement method based on three-dimensional point cloud data above, and will not be repeated here.

[0077] In an exemplary embodiment, Figure 3 As shown, a roller coaster track gauge measurement system based on three-dimensional point cloud data is provided, including the following modules:

[0078] The three-dimensional point cloud data acquisition module is used to acquire the three-dimensional point cloud data of the space where the target roller coaster track is located; the initial three-dimensional point cloud data includes the three-dimensional point cloud data of the target roller coaster track and the three-dimensional point cloud data of the surrounding environment of the target roller coaster track.

[0079] The target track point cloud extraction module is used to extract the three-dimensional point cloud data of the target roller coaster track from the three-dimensional point cloud data of the space where the target roller coaster track is located based on the appearance features of the target roller coaster track.

[0080] The track center point cloud extraction module is used to extract the center track point cloud data of the two single-side tracks of the target roller coaster track from the three-dimensional point cloud data of the target roller coaster track based on the cross-sectional features of the track.

[0081] The point cloud nearest neighbor search module is used to match the center track point cloud data of any single-sided track with the center track point cloud data of another single-sided track using the nearest neighbor search algorithm to obtain several point cloud pairs.

[0082] The point cloud pair track gauge determination unit is used to calculate the distance between two point clouds of each point cloud pair to determine the track gauge of any position of the target roller coaster track.

[0083] As an improved implementation method, the system also includes: a visualization display module, which is used to visualize the distance between two point clouds of each point cloud pair.

[0084] certainly, Figure 3 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different functions. Figure 3 One or at least two components of the system shown.

[0085] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a roller coaster track gauge measurement method based on three-dimensional point cloud data is implemented.

[0086] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0087] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0088] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0089] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0090] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0091] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0092] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0093] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0094] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A roller coaster track gauge measurement method based on three-dimensional point cloud data, It is characterized in that include: Acquire three-dimensional point cloud data of the space where the target roller coaster track is located; The initial three-dimensional point cloud data includes the three-dimensional point cloud data of the target roller coaster track and the three-dimensional point cloud data of the surrounding environment of the target roller coaster track; Based on the appearance features of the target roller coaster track, extracting the three-dimensional point cloud data of the target roller coaster track from the three-dimensional point cloud data of the space where the target roller coaster track is located; Based on the cross-sectional features of the track, the center track point cloud data of the two unilateral tracks of the target roller coaster track are extracted from the three-dimensional point cloud data of the target roller coaster track; For the center track point cloud data of any one of the single-sided tracks, a nearest neighbor search algorithm is used to match the center track point cloud data of another single-sided track to obtain a plurality of point cloud pairs; For each point cloud pair, the distance between two point clouds of the point cloud pair is calculated to determine the track gauge at any position of the target roller coaster track.

2. The roller coaster track gauge measurement method based on three-dimensional point cloud data according to claim 1, It is characterized in that Acquiring the three-dimensional point cloud data of the space where the target roller coaster track is located, specifically includes: using a laser radar loaded on an unmanned aerial vehicle, using a high-resolution laser scanning device, and using visible light and / or laser dot marking to obtain the three-dimensional point cloud data of the space where the target roller coaster track is located.

3. The roller coaster track gauge measurement method based on three-dimensional point cloud data according to claim 1, It is characterized in that Based on the appearance features of the target roller coaster track, extracting the three-dimensional point cloud data of the target roller coaster track from the three-dimensional point cloud data of the space where the target roller coaster track is located specifically includes: Based on the position, color intensity and normal direction of the target roller coaster track, segmenting the initial three-dimensional point cloud data of the target roller coaster track from the three-dimensional point cloud data of the space where the target roller coaster track is located; The initial three-dimensional point cloud data of the target roller coaster track is subjected to a post-segmentation optimization operation to obtain the three-dimensional point cloud data of the target roller coaster track; the post-segmentation optimization operation includes removing noise points, filling holes and smoothing boundaries.

4. The roller coaster track gauge measurement method based on three-dimensional point cloud data according to claim 1, It is characterized in that Based on the cross-sectional features of the track, the center track point cloud data of the two unilateral tracks of the target roller coaster track are extracted from the three-dimensional point cloud data of the target roller coaster track, including: For the three-dimensional point cloud data of any single-side track of the target roller coaster track, the three-dimensional point cloud data of the single-side track is sliced ​​along the forward direction to obtain a plurality of slice data of the single-side track; For any slice data, based on the cross-sectional features of the track, a region with a circular cross-section is searched in the slice data as the track cross-sectional region; The center points of the track cross-section areas in all the slice data of the single-sided track are connected to obtain the center track point cloud data of the single-sided track.

5. The roller coaster track gauge measurement method based on three-dimensional point cloud data according to claim 1, It is characterized in that For the center track point cloud data of any one of the single-sided tracks, a nearest neighbor search algorithm is used to match the center track point cloud data of another single-sided track to obtain a number of point cloud pairs, specifically including: Create a kd tree structure; the input of the kd tree structure is the center track point cloud data of any one of the single-sided tracks; For any point cloud on the central track point cloud data of the single-sided track, the kd tree structure is used to perform a nearest neighbor search in the central track point cloud data of another single-sided track, and the searched point cloud and the point cloud are stored as a point cloud pair to obtain a plurality of point cloud pairs.

6. The roller coaster track gauge measurement method based on three-dimensional point cloud data according to claim 1, It is characterized in that For any point cloud pair, the distance between the two point clouds of the point cloud pair is calculated according to the following formula: Where d is the distance between the two point clouds, (x 1 ,y 1 ,z 1 ) is the three-dimensional coordinate of a point cloud in the point cloud pair, (x 2 ,y 2 ,z 2 ) is the three-dimensional coordinate of another point cloud in the point cloud pair.

7. The roller coaster track gauge measurement method based on three-dimensional point cloud data according to claim 1, It is characterized in that After calculating the distance between two point clouds of each point cloud pair, the method further includes: The visualization module is used to visualize the distance between two point clouds of each point cloud.

8. The roller coaster track gauge measurement method based on three-dimensional point cloud data according to claim 1, It is characterized in that After calculating the distance between two point clouds of each point cloud pair, the method further includes: According to the distance between two point clouds of each point cloud pair, the point cloud pair corresponding to the shortest distance value is determined; The visualization module is used to visualize the distance between two point clouds of each point cloud pair, and the point cloud pair corresponding to the shortest distance value is highlighted.

9. A roller coaster track gauge measurement system based on three-dimensional point cloud data, It is characterized in that include: A three-dimensional point cloud data acquisition module, used to acquire three-dimensional point cloud data of the space where the target roller coaster track is located; The initial three-dimensional point cloud data includes the three-dimensional point cloud data of the target roller coaster track and the three-dimensional point cloud data of the surrounding environment of the target roller coaster track; A target track point cloud extraction module, used for extracting the three-dimensional point cloud data of the target roller coaster track from the three-dimensional point cloud data of the space where the target roller coaster track is located based on the appearance features of the target roller coaster track; A track center point cloud extraction module is used to extract the center track point cloud data of the two single-side tracks of the target roller coaster track from the three-dimensional point cloud data of the target roller coaster track based on the cross-sectional features of the track; A point cloud nearest neighbor search module is used to match the center track point cloud data of any one of the single-sided tracks with the center track point cloud data of another single-sided track using a nearest neighbor search algorithm to obtain a plurality of point cloud pairs; The point cloud pair track gauge determination unit is used to calculate the distance between two point clouds of each point cloud pair to determine the track gauge of any position of the target roller coaster track.

10. The roller coaster track gauge measurement system based on three-dimensional point cloud data according to claim 9, It is characterized in that Also includes: Visual display module; The visualization display module is used to visualize the distance between two point clouds of each point cloud pair.

Images