Trolley positioning method, device and equipment based on laser radar and storage medium

Abstract

The invention provides a trolley positioning method and device based on a laser radar, equipment and a storage medium, and relates to the technical field of tunnel engineering. The method comprises the following steps: acquiring an attitude transformation matrix between a laser radar and a trolley, and a target center first coordinate of each target; obtaining point cloud data of the laser radar, and obtaining a target center second coordinate of each target according to the point cloud data; according to the target center first coordinate and the target center second coordinate of each target, a first conversion matrix between the radar coordinate system and the tunnel coordinate system is obtained through a singular value decomposition method, and according to the first conversion matrix and the attitude conversion matrix, a second conversion matrix between a trolley coordinate system where the trolley is located and the tunnel coordinate system is obtained; and positioning the trolley according to the second conversion matrix. According to the method, the positioning precision of the trolley in the tunnel is improved on the premise of high universality.

Description

Technical Field

[0001] The present application relates to the field of tunnel engineering technology, and in particular to a laser radar-based trolley positioning method, device, equipment and storage medium. Background Art

[0002] Tunnel construction is used to build passages connecting two places in mountains, underground and underwater. Tunnel construction is a complex and professional engineering activity, and accurate positioning of the construction trolley equipment in the tunnel is very important to ensure that the tunnel is constructed correctly according to the design requirements and avoid unnecessary resource consumption and construction costs. With the development of technologies such as wireless communication and sensors, the positioning problem in the tunnel is solved by algorithms or fusion calculations of multiple sensor data to obtain positioning results.

[0003] At present, the implementation methods of train positioning inside tunnels include pre-processing data based on optical fiber sensor networks, voiceprint fingerprint sensors, geomagnetic field sensors and other equipment, and inputting them into models to generate real-time monitoring data for tunnels; or performing simple positioning and deviation correction work based on laser radar to obtain positioning data. However, such methods rely on fusion calculations of multiple sensors, which is costly and prone to cumulative errors in the system, resulting in low accuracy; or using a single positioning algorithm based on point cloud feature matching, it is difficult to ensure the stability of positioning and there are problems with the range of adaptability.

[0004] How to improve the positioning accuracy of the trolley in the tunnel under the premise of high versatility is a problem that the present invention urgently needs to solve. Summary of the invention

[0005] The present application provides a laser radar-based trolley positioning method, device, equipment and storage medium to solve the problem of improving the trolley positioning accuracy in a tunnel under the premise of high versatility.

[0006] In a first aspect, the present application provides a trolley positioning method based on laser radar, the method comprising:

[0007] Obtain the attitude conversion matrix between the laser radar and the trolley, and the first coordinate of the target center of each target; wherein the attitude conversion matrix is ​​obtained by calibrating the attitude relationship between the laser radar and the trolley; the first coordinate of the center of each target is the coordinate of the corresponding target in the tunnel coordinate system measured by the total station;

[0008] Obtaining the point cloud data of the laser radar, and obtaining the second coordinate of the target center of each target according to the point cloud data; wherein the second coordinate of the center of each target is the coordinate of the corresponding target in the radar coordinate system;

[0009] According to the first coordinate of the target center and the second coordinate of the target center of each target, a first conversion matrix between the radar coordinate system and the tunnel coordinate system is obtained by a singular value decomposition method, and according to the first conversion matrix and the attitude conversion matrix, a second conversion matrix between the trolley coordinate system where the trolley is located and the tunnel coordinate system is obtained;

[0010] The trolley is positioned according to the second transformation matrix.

[0011] In a possible design, after acquiring the point cloud data of the laser radar, the method further includes:

[0012] Convert the point cloud data into text data; wherein the text data includes a plurality of three-dimensional points, a coordinate value of each three-dimensional point in a radar coordinate system, and a reflection intensity value of each three-dimensional point;

[0013] According to the point cloud data, the second coordinate of the target center of each target is obtained, including:

[0014] According to the coordinate value and reflection intensity value of each three-dimensional point, a plurality of target point sets are determined by three-dimensional point extraction; wherein each target point set includes a plurality of target points, and each target point is used to indicate a point on the target;

[0015] According to the coordinate value and reflection intensity value of each three-dimensional point, the second coordinate of the target center of each target is obtained.

[0016] In a possible design, multiple target point sets are determined by 3D point extraction according to the coordinate values ​​and reflection intensity values ​​of each 3D point, including:

[0017] According to the coordinate value and the reflection intensity value of each three-dimensional point, a plurality of three-dimensional points are filtered by a filtering method to obtain a plurality of first type points;

[0018] Clustering the multiple first type points through Euclidean clustering segmentation processing to obtain multiple first point sets;

[0019] Performing expansion processing and fitting processing on each first point set respectively to obtain a second point set corresponding to each first point set; wherein each second point set includes a plurality of second type points;

[0020] Through target matching, a plurality of target point sets are determined from the plurality of second point sets.

[0021] In a possible design, each coordinate value includes a depth value and a height value. Then, according to the coordinate value and the reflection intensity value of each three-dimensional point, a filtering method is used to filter the multiple three-dimensional points to obtain multiple first-type points, including:

[0022] According to the depth value and height value of each 3D point, a plurality of 3D points are directionally filtered by a straight-through filtering method to obtain a plurality of filter points; wherein the depth value of each filter point is within a depth threshold range; and the height value of each filter point is within a height threshold range;

[0023] According to the reflection intensity value of each filtering point, multiple filtering points are intensity filtered through point cloud reflection intensity filtering to obtain multiple first type points; wherein the reflection intensity value of each first type point is greater than the first reflection intensity threshold.

[0024] In one possible design, the target type point is any one of a plurality of first type points, and the first target point set is a first point set where the target type point is located;

[0025] For the target type points and the first target point set, each first point set is expanded and fitted respectively to obtain a second point set corresponding to each first point set, including:

[0026] Compare the target type point with multiple three-dimensional points of the text data to obtain multiple three-dimensional points corresponding to the target type point in the text data, establish an expansion range, and determine the expansion range as the expansion point of the first target point set, wherein the expansion range of the target type point refers to a spherical range with the target type point as the center and the distance threshold as the radius, and the expansion range is a spherical range established by the corresponding multiple three-dimensional points in the text data;

[0027] Eliminate duplicate points of the plurality of first-type points and the plurality of extended points of the first target point set to obtain a third point set corresponding to the first target point set;

[0028] By using a random sample consistency algorithm, a plane fitting is performed on the third point set corresponding to the first target point set to obtain a second point set corresponding to the first target point set.

[0029] In a possible design, the second target point set is any one of a plurality of second point sets;

[0030] For the second target point set, multiple target point sets are determined from the multiple second point sets through target matching, including:

[0031] Acquire a first length value and a first width value of the target, and the number of intensity points of the second target point set; wherein the number of intensity points of the second target point set refers to the number of second type points in the second target point set whose reflection intensity value is greater than the second reflection intensity threshold value;

[0032] Make a bounding box for the second target point set, and obtain a second length value and a second width value of the bounding box;

[0033] Whether the second target point set is a target point set is determined based on the numerical relationship between the first length value and the second length value, the numerical relationship between the first width value and the second width value, and the numerical relationship between the number of intensity points of the second target point set and the number threshold.

[0034] In one possible design, the target point set is any one of multiple target point sets.

[0035] For the target point set, the second coordinate of the target center of each target is obtained according to the coordinate value and reflection intensity value of each three-dimensional point, including:

[0036] Obtaining a point set feature vector of a target point set; wherein the point set feature vector of the target point set is obtained by a principal component analysis method;

[0037] According to the coordinate value and reflection intensity value of each target point of the target point set and the point set feature vector of the target point set, the second coordinate of the target center of the target corresponding to the target point set is obtained.

[0038] In a second aspect, the present application provides a trolley positioning device based on laser radar, comprising:

[0039] The acquisition module is used to obtain the attitude conversion matrix between the laser radar and the trolley, and the first coordinate of the target center of each target; wherein the attitude conversion matrix is ​​obtained by calibrating the attitude relationship between the laser radar and the trolley; the first coordinate of the center of each target is the coordinate of the corresponding target in the tunnel coordinate system measured by the total station;

[0040] The coordinate module is used to obtain the point cloud data of the laser radar, and obtain the second coordinate of the target center of each target according to the point cloud data; wherein the second coordinate of each target center is the coordinate of the corresponding target in the radar coordinate system;

[0041] A matrix module is used to obtain a first conversion matrix between the radar coordinate system and the tunnel coordinate system according to the first coordinate of the target center and the second coordinate of the target center of each target by a singular value decomposition method, and obtain a second conversion matrix between the trolley coordinate system where the trolley is located and the tunnel coordinate system according to the first conversion matrix and the attitude conversion matrix;

[0042] The positioning module is used to position the trolley according to the second conversion matrix.

[0043] In a third aspect, the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;

[0044] Memory stores computer-executable instructions;

[0045] The processor executes the computer execution instructions stored in the memory to implement a laser radar-based trolley positioning method according to the first aspect of the invention.

[0046] In a fourth aspect, the present application provides a computer-readable storage medium, in which computer execution instructions are stored. When the computer execution instructions are executed by a processor, they are used to implement a laser radar-based trolley positioning method according to the invention content of the first aspect.

[0047] In a fifth aspect, the present application provides a computer program product, including: a computer program, which, when executed by a processor, is used to implement a laser radar-based trolley positioning method according to the invention content of the first aspect.

[0048] The present application provides a laser radar-based trolley positioning method, device, equipment and storage medium, which obtain the attitude conversion matrix between the laser radar and the trolley, and the first coordinate of the target center of each target; wherein the attitude conversion matrix is ​​obtained by calibrating the attitude relationship between the laser radar and the trolley; the first coordinate of each target center is the coordinate of the corresponding target in the tunnel coordinate system measured by the total station; the point cloud data of the laser radar is obtained, and the second coordinate of the target center of each target is obtained according to the point cloud data; wherein the second coordinate of each target center is the coordinate of the corresponding target in the radar coordinate system; according to the first coordinate of the target center and the second coordinate of the target center of each target, the first conversion matrix between the radar coordinate system and the tunnel coordinate system is obtained by the singular value decomposition method, and according to the first conversion matrix and the attitude conversion matrix, the second conversion matrix between the trolley coordinate system where the trolley is located and the tunnel coordinate system is obtained; according to the second conversion matrix, the trolley is positioned. The following technical effects are achieved: data collection is achieved through laser radar, which reduces the cost of positioning and has wide adaptability; point cloud data calculation of the target and coordinate conversion are achieved through a variety of methods, which ensures the stability of positioning and improves the accuracy of positioning; the positioning problem of the trolley is solved through multiple matrices and target center coordinates, which reduces the possibility of errors and has strong versatility. It does not perform calculations based on the geometric feature information of the tunnel, which improves the accuracy of trolley positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0050] Figure 1A schematic diagram of the system architecture of a trolley positioning method based on laser radar provided in an embodiment of the present application;

[0051] Figure 2 Schematic diagram of the process of the trolley positioning method based on laser radar provided in the embodiment of the present application Figure 1 ;

[0052] Figure 3 Schematic diagram of the process of the trolley positioning method based on laser radar provided in the embodiment of the present application Figure 2 ;

[0053] Figure 4 A schematic diagram of a target for a trolley positioning method based on laser radar provided in an embodiment of the present application;

[0054] Figure 5 Schematic diagram of the process of the trolley positioning method based on laser radar provided in the embodiment of the present application Figure 3 ;

[0055] Figure 6 A schematic diagram of the structure of a trolley positioning device based on laser radar provided in an embodiment of the present application;

[0056] Figure 7 A schematic diagram of the structure of the electronic device hardware provided in an embodiment of the present application.

[0057] Reference numerals:

[0058] 100-trolley positioning system; 110-target center extraction module; 120-positioning calculation module;

[0059] 410-reflective plate; 420-target plate;

[0060] 600-trolley positioning device based on laser radar; 610-acquisition module; 620-coordinate module; 630-matrix module; 640-positioning module;

[0061] 700 - electronic device; 710 - processor; 720 - memory; 730 - communication component; 740 - bus. DETAILED DESCRIPTION

[0062] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0063] In the embodiments of the present application, words such as "first" and "second" are used to distinguish the same or similar items with basically the same functions and effects. Those skilled in the art will understand that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit the difference. It should be noted that in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "for example" in the present application should not be interpreted as being more preferred or more advantageous than other embodiments or design schemes. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way. In the embodiments of the present application, "at least one" refers to one or more, and "more" refers to two or more.

[0064] It should be noted that the "at..." in the embodiment of the present application can be the instant when a certain situation occurs, or it can be a period of time after a certain situation occurs, and the embodiment of the present application does not specifically limit this. In addition, the trolley positioning method based on laser radar provided in the embodiment of the present application is only used as an example, and the trolley positioning method based on laser radar can also include more or less content.

[0065] In order to clearly describe the technical solutions of the embodiments of the present application, some terms and technologies involved in the embodiments of the present application are briefly introduced below:

[0066] Trolley: It is a large-scale mechanical equipment commonly used in tunnel construction. Its main function is to support the tunnel wall after tunnel excavation, ensure the safety and stability of the tunnel structure, and perform lining operations such as concrete pouring to form a solid tunnel inner wall.

[0067] Point cloud feature matching: Point cloud feature matching is a key step in point cloud processing, which is used to find corresponding points or regions in two or more point cloud data sets. This process usually includes two main stages: feature extraction and feature matching. Point cloud feature matching has a wide range of applications in 3D reconstruction, object recognition, robot navigation, map construction and other fields.

[0068] Face: Face is an important term in mining and tunneling, referring to the excavation working face or exposed rock surface. In underground engineering, the face is the front face where excavation or blasting operations are currently being carried out.

[0069] Attitude relationship calibration: Attitude relationship calibration is a key technology in the fields of multi-sensor fusion, robot navigation, augmented reality, virtual reality, etc. It involves determining the relative position and attitude relationship between two or more sensors or coordinate systems. Through calibration, it can ensure that the data between different sensors or devices can be correctly aligned and fused, thereby improving the overall performance and accuracy of the system. In this application, attitude relationship calibration can be performed between the lidar and the trolley.

[0070] Random Sample Consensus (RANSAC): is an iterative method for estimating mathematical model parameters from a set of data containing outliers. In point cloud processing, RANSAC is often used to fit planes. Even if there are a large number of noise points or outliers in the point cloud data, it can accurately find a suitable fitting plane.

[0071] Through filtering algorithm: Through filtering is a commonly used point cloud processing technology, which is used to filter out points within a specific range from point cloud data. This filtering method is particularly suitable for cropping or selecting point clouds along a certain axis (height direction, depth direction or other axis), thereby removing unnecessary points or retaining areas of interest.

[0072] Point cloud reflection intensity filtering: Point cloud reflection intensity filtering is a technology that screens and processes the reflection intensity of each point in the point cloud data. Reflection intensity is an important attribute in point cloud data, which reflects the reflection of the laser pulse emitted by the lidar on the target surface.

[0073] Euclidean cluster segmentation: Euclidean cluster segmentation is a common technique in point cloud processing that is used to segment point cloud data into different clusters, each cluster representing a separate object or region. This method uses the Euclidean distance between points to determine whether they belong to the same cluster. Euclidean cluster segmentation is particularly suitable for processing point cloud data without obvious features or textures, such as LiDAR data.

[0074] Bounding box: Bounding box is a commonly used concept in computer graphics, computer vision, 3D modeling and game development. It refers to a simple geometric body that is used to approximate the position and size of a more complex object or a group of objects. The main purpose of the bounding box is to simplify operations such as collision detection, frustum clipping, and fast rendering, thereby improving computational efficiency.

[0075] Principal Component Analysis (PCA) is a commonly used data dimensionality reduction technique, which is widely used in data science, machine learning, image processing and other fields. PCA transforms the original data into a new coordinate system through linear transformation, so that the new coordinate axis (called principal component) can maximize the variance of the data while maintaining the total variation information of the data. The purpose of this is to reduce the dimension of the data while retaining as much information as possible, thereby simplifying data analysis and processing.

[0076] Singular Value Decomposition (SVD) is a technique widely used in matrix analysis and linear algebra. It can decompose any real or complex matrix into the product of three matrices.

[0077] Tunnel operations play an extremely important role in modern infrastructure construction, involving transportation, water conservancy, energy and other fields. Accurate operations in tunnels are particularly important, and the positioning of working equipment trolleys in tunnels affects the progress and safety of tunnel operations.

[0078] With the development of wireless communication and sensor technologies, the positioning problem in tunnels is solved by algorithms or fusion calculations of multiple sensor data to obtain positioning results. Existing tunnel internal positioning implementation methods include:

[0079] First, the monitoring network layout is established through the set optical fiber sensor network, acoustic fingerprint sensor and geomagnetic field sensor, and the environmental monitoring data is collected through the initialized monitoring network and pre-processed;

[0080] Secondly, using the pre-trained first model, the environmental monitoring data is used as input and the train positioning information is output;

[0081] Finally, based on the current train positioning information and environmental monitoring data, the pre-trained second model is used to predict the train position and tunnel safety status to generate real-time tunnel monitoring data.

[0082] Alternatively, the positioning problem can be solved by using lidar through point cloud matching feature algorithm.

[0083] Although this method achieves the positioning effect, it also has some technical problems:

[0084] First, data is collected through multiple sensors and fused and calculated, which results in high costs and causes cumulative errors in the inertial navigation system, affecting positioning accuracy.

[0085] Secondly, using a simple point cloud matching feature algorithm cannot provide sufficient geometric feature information, making it difficult to ensure positioning stability and accuracy.

[0086] Taking the cost into consideration, this application also uses laser radar to realize the positioning of the trolley.

[0087] Therefore, how to improve the positioning accuracy of the trolley in the tunnel under the premise of high versatility is a problem that the present invention urgently needs to solve.

[0088] Based on this, the embodiments of the present application provide a laser radar-based trolley positioning method, device, equipment and storage medium, which can be used in the field of tunnel engineering technology, aiming to solve the above technical problems of the prior art.

[0089] Figure 1 A schematic diagram of the system architecture of the laser radar-based trolley positioning method provided in the embodiment of the present application. It should be noted that: Figure 1 What is shown is merely an example of a system architecture to which the embodiments of the present application can be applied, in order to help those skilled in the art understand the technical content of the present application, but it does not mean that the embodiments of the present application cannot be used in other devices, systems, environments or scenarios.

[0090] like Figure 1 As shown, the system architecture of the trolley positioning method based on laser radar includes: the trolley positioning system 100 includes: a target center extraction module 110 and a positioning calculation module 120.

[0091] The target center extraction module 110 processes the original point cloud data input by the laser radar, including the steps of filtering the point cloud, Euclidean clustering segmentation, point cloud expansion, plane fitting and target matching; it also includes: solving the feature vector of the target point cloud and solving the target center coordinate calculation.

[0092] The positioning calculation module 120 realizes the conversion between the radar coordinate system and the tunnel coordinate system, and the conversion between the trolley coordinate system and the tunnel coordinate system through the SVD method, and obtains the positioning result of the trolley in the tunnel according to the conversion relationship.

[0093] Figure 2 Schematic diagram of the process of the trolley positioning method based on laser radar provided in the embodiment of the present application Figure 1 .like Figure 2 As shown, the method includes:

[0094] S201, obtaining the attitude conversion matrix between the laser radar and the platform, and the first coordinate of the target center of each target.

[0095] Among them, the attitude conversion matrix is ​​obtained by calibrating the attitude relationship between the laser radar and the trolley; the first coordinate of each target center is the coordinate of the corresponding target in the tunnel coordinate system measured by the total station.

[0096] Specifically, due to the position difference between the laser radar and the trolley, the attitude relationship between the laser radar and the trolley is calibrated to obtain the attitude conversion matrix between the laser radar and the trolley.

[0097] The total station measures the installed multiple targets to obtain the coordinates of the multiple targets in the tunnel coordinate system.

[0098] S202, obtaining point cloud data of the laser radar, and obtaining the second coordinate of the target center of each target based on the point cloud data.

[0099] Among them, the second coordinate of each target center is the coordinate of the corresponding target in the radar coordinate system.

[0100] Specifically, the point cloud data monitored by the laser radar is obtained, and the point cloud data is processed to obtain the second coordinate of the target center of each target, and the second coordinate of the target center of each target is the coordinate in the radar coordinate system.

[0101] S203. According to the first coordinate of the target center and the second coordinate of the target center of each target, a first transformation matrix between the radar coordinate system and the tunnel coordinate system is obtained by the singular value decomposition method, and according to the first transformation matrix and the attitude transformation matrix, a second transformation matrix between the trolley coordinate system where the trolley is located and the tunnel coordinate system is obtained.

[0102] Specifically, according to the first coordinate of the target center and the second coordinate of the target center of each target, the singular value decomposition method is used to solve the first transformation matrix from the radar coordinate system to the tunnel coordinate system; and according to the first transformation matrix and the attitude transformation matrix, the second transformation matrix from the trolley coordinate system where the trolley is located to the tunnel coordinate system is calculated.

[0103] S204: Position the trolley according to the second conversion matrix.

[0104] Specifically, the positioning result of the trolley in the speed-adjustable coordinate system is obtained according to the second transformation matrix and the origin of the trolley in the coordinate system.

[0105] The present application provides a laser radar-based trolley positioning method, device, equipment and storage medium, which obtain the attitude conversion matrix between the laser radar and the trolley, and the first coordinate of the target center of each target; wherein the attitude conversion matrix is ​​obtained by calibrating the attitude relationship between the laser radar and the trolley; the first coordinate of each target center is the coordinate of the corresponding target in the tunnel coordinate system measured by the total station; the point cloud data of the laser radar is obtained, and the second coordinate of the target center of each target is obtained according to the point cloud data; wherein the second coordinate of each target center is the coordinate of the corresponding target in the radar coordinate system; according to the first coordinate of the target center and the second coordinate of the target center of each target, the first conversion matrix between the radar coordinate system and the tunnel coordinate system is obtained by the singular value decomposition method, and according to the first conversion matrix and the attitude conversion matrix, the second conversion matrix between the trolley coordinate system where the trolley is located and the tunnel coordinate system is obtained; according to the second conversion matrix, the trolley is positioned. The following technical effects are achieved: data collection is achieved through laser radar, which reduces the cost of positioning and has wide adaptability; point cloud data calculation of the target and coordinate conversion are achieved through a variety of methods, which ensures the stability of positioning and improves the accuracy of positioning; the positioning problem of the trolley is solved through multiple matrices and target center coordinates, which reduces the possibility of errors and has strong versatility. It does not perform calculations based on the geometric feature information of the tunnel, which improves the accuracy of trolley positioning.

[0106] Figure 3 Schematic diagram of the process of the trolley positioning method based on laser radar provided in the embodiment of the present application Figure 2 In this embodiment Figure 2 Based on the embodiment, the steps of the trolley positioning method based on laser radar are described in detail, such as Figure 3 As shown, this embodiment provides a trolley positioning method based on laser radar, including:

[0107] S301, obtaining the attitude conversion matrix between the laser radar and the platform, and the first coordinate of the target center of each target.

[0108] Among them, the attitude conversion matrix is ​​obtained by calibrating the attitude relationship between the laser radar and the trolley; the first coordinate of each target center is the coordinate of the corresponding target in the tunnel coordinate system measured by the total station.

[0109] The principles of S301 and S201 are the same and will not be described in detail in this embodiment.

[0110] S302: Obtain point cloud data of the laser radar.

[0111] Specifically, the point cloud data monitored by the lidar is obtained.

[0112] S303: Convert the point cloud data into text data.

[0113] The text data includes a plurality of three-dimensional points, a coordinate value of each three-dimensional point in a radar coordinate system, and a reflection intensity value of each three-dimensional point.

[0114] Specifically, the point cloud data is converted into text data. The point cloud data includes the tunnel point cloud and target point cloud behind the trolley. Each point cloud data consists of the coordinate value and reflection intensity value in the radar coordinate system. The point cloud data is saved in the computer in text data format for processing by the trolley positioning system.

[0115] S304 , performing direction filtering on the multiple three-dimensional points by a straight-through filtering method according to the depth value and the height value of each three-dimensional point, to obtain multiple filtered points.

[0116] The depth value of each filter point is within the depth threshold range; the height value of each filter point is within the height threshold range.

[0117] Specifically, the second coordinate of the target center of each target is obtained according to the point cloud data. The second coordinate of each target center is the coordinate of the corresponding target in the radar coordinate system. According to the coordinate value and reflection intensity value of each three-dimensional point, multiple target point sets are determined by three-dimensional point extraction; each target point set includes multiple target points, and each target point is used to indicate a point on the target; according to the coordinate value and reflection intensity value of each three-dimensional point, multiple three-dimensional points are filtered by a filtering processing method to obtain multiple first type points; each coordinate value includes a depth value and a height value.

[0118] Through the straight-through filtering algorithm, multiple three-dimensional points are filtered in the depth direction and the height direction to obtain multiple filtered points.

[0119] S305 , performing intensity filtering on multiple filter points through point cloud reflection intensity filtering according to the reflection intensity value of each filter point, to obtain multiple first type points.

[0120] The reflection intensity value of each first type point is greater than the first reflection intensity threshold.

[0121] Specifically, according to the reflection intensity value corresponding to each filter point, the point cloud reflection intensity filtering algorithm is used to filter out the three-dimensional points whose reflection intensity is less than the first reflection intensity threshold, and retain the three-dimensional points whose reflection intensity is greater than the first reflection intensity threshold, to obtain multiple first type points.

[0122] S306 , clustering the plurality of first type points through Euclidean clustering segmentation processing to obtain a plurality of first point sets.

[0123] Specifically, the three-dimensional points whose Euclidean distance is less than a threshold are clustered by using the Euclidean clustering segmentation processing method to obtain multiple first point sets.

[0124] S307, comparing the target type point with multiple three-dimensional points of the text data to obtain multiple three-dimensional points corresponding to the target type point in the text data, establishing an expansion range, and determining the expansion range as the expansion points of the first target point set.

[0125] The extended range of the target type point refers to a spherical range with the target type point as the center and the distance threshold as the radius, and the extended range is a spherical range established by corresponding multiple three-dimensional points in the text data.

[0126] Specifically, each first point set is expanded and fitted respectively to obtain a second point set corresponding to each first point set; wherein each second point set includes multiple second type points; the target type point is any one of the multiple first type points, and the first target point set is the first point set where the target type point is located.

[0127] A sphere with a distance threshold as the radius is established with the target type point as the sphere center, and the three-dimensional points of the point cloud data within the distance threshold are added to the first point set of the corresponding points to obtain multiple first target point sets.

[0128] S308 , removing duplicate points from the plurality of first type points and the plurality of extended points of the first target point set to obtain a third point set corresponding to the first target point set.

[0129] Specifically, multiple first-type points and multiple extended points of the first target point set are repeatedly eliminated, points with overlapping positions are eliminated, and only one point is retained to obtain a third point set corresponding to the first target click.

[0130] S309 , performing plane fitting on the third point set corresponding to the first target point set by using a random sample consistency algorithm to obtain a second point set corresponding to the first target point set.

[0131] Specifically, the RANSAC plane fitting method is used to perform plane fitting on the third click corresponding to the first target point set to obtain the second point set corresponding to the first target click.

[0132] S310, obtaining a first length value and a first width value of the target, and the number of intensity points of the second target point set.

[0133] The second target point set is any one of the plurality of second point sets. The number of intensity points of the second target point set refers to the number of second type points in the second target point set whose reflection intensity value is greater than the second reflection intensity threshold.

[0134] Specifically, multiple target point sets are determined from multiple second point sets through target matching, the length and width of the target are obtained, the target length is the first length value, and the target width is the first width value, and the number of second type points whose reflection intensity values ​​are greater than the second reflection intensity threshold is determined.

[0135] S311 , construct a bounding box for the second target point set, and obtain a second length value and a second width value of the bounding box.

[0136] Specifically, a bounding box is drawn for the second target click, and a solution is performed to obtain the length and width of the bounding box, and a second length value and a second width value of the bounding box are set.

[0137] S312. Determine whether the second target point set is a target point set based on the numerical relationship between the first length value and the second length value, the numerical relationship between the first width value and the second width value, and the numerical relationship between the number of intensity points of the second target point set and the number threshold.

[0138] Specifically, based on the numerical relationship between the first length value and the second length value, the numerical relationship between the first width value and the second width value, and the numerical relationship between the number of intensity points clicked by the second target and the number threshold, a judgment is made to obtain the target point set in the second target point set.

[0139] S313, obtaining the point set feature vector of the target point set.

[0140] The point set feature vector of the target point set is obtained by principal component analysis; the target point set is any one of the multiple target point sets.

[0141] Specifically, the second coordinate of the target center of each target is obtained according to the coordinate value and reflection intensity value of each three-dimensional point. The target click set is solved by the principal component analysis PCA method to obtain the point set feature vector.

[0142] S314, obtaining the second coordinate of the target center of the target corresponding to the target point set according to the coordinate value and reflection intensity value of each target point of the target point set and the point set feature vector of the target point set.

[0143] Specifically, the second coordinate of the target center corresponding to the target point set is obtained by calculating the coordinate value, reflection intensity value, target point coordinate average value, number of target point sets and point set feature vector corresponding to each target point set.

[0144] S315. According to the first coordinate of the target center and the second coordinate of the target center of each target, the first transformation matrix between the radar coordinate system and the tunnel coordinate system is obtained by the singular value decomposition method, and according to the first transformation matrix and the attitude transformation matrix, the second transformation matrix between the trolley coordinate system where the trolley is located and the tunnel coordinate system is obtained.

[0145] S316. Position the trolley according to the second conversion matrix.

[0146] The principles of S315 and S316 are similar to those of S203 and S204, and will not be further described in this embodiment.

[0147] For ease of understanding, a specific embodiment is introduced here:

[0148] Figure 4 A schematic diagram of a target for a trolley positioning method based on a laser radar provided in an embodiment of the present application. As shown in the figure, outside the reflector 410 is a target plate 420, and the center of the target in the present application is the reflector 410. This embodiment assumes that three targets are arranged. Figure 5 Schematic diagram of the process of the trolley positioning method based on laser radar provided in the embodiment of the present application Figure 3 .

[0149] S501, obtain the attitude conversion matrix between the laser radar and the platform , and the first coordinate of the target center measured by the total station .

[0150] S502: Acquire the point cloud data of the laser radar, and obtain the target point cloud of each target based on the point cloud data.

[0151] Through straight-through filtering, the original point cloud is filtered in the depth direction and height direction, retaining the depth direction With height direction Point cloud within the range, obtain filtered point cloud data .

[0152] Through point cloud reflection intensity filtering, point clouds with reflection intensity less than the intensity threshold θ are filtered out, and point clouds with reflection intensity greater than Point cloud, get the filtered point cloud data .

[0153] right Perform Euclidean clustering to cluster point clouds with Euclidean distance less than d into one category, and finally obtain Point cloud clustering:

[0154]

[0155] First, set the expansion threshold radius , traverse all points in the current cluster and compare them with the original point cloud, taking this point as the center of the sphere, and the distance from this point is less than the radius All original point clouds are added to the current cluster , complete the expansion; then Remove duplicate points and remove points that overlap each other, leaving only one point. The expanded point cloud clusters are used as candidate point cloud clusters for the target point cloud:

[0156]

[0157] Cluster each expanded candidate target point cloud separately Perform RANSAC plane fitting to obtain the plane model of each expanded cluster, retain the inner points of each expanded cluster point cloud RANSAC fitting, and finally obtain n point cloud classes after RANSAC plane fitting:

[0158]

[0159] First of all Make a bounding box and find out the length and width of the bounding box; at the same time, set the number of high-intensity point cloud matching threshold points to , set the high reflection intensity matching threshold to , find Medium and high reflection intensity is greater than the intensity matching threshold The number of point clouds .

[0160]

[0161] in, for The length and width of the bounding box, Lr and Wr are the actual size of the target, that is Figure 5 The actual size of the target plate 420, and are the range thresholds for length and width respectively.

[0162] Through the above algorithm process, 3 target point clouds are finally extracted , respectively , , .

[0163] S503, calculating the center point coordinates of each target point cloud to obtain the second coordinates of the center of the target point cloud of each target.

[0164] For the three target point clouds respectively Calculate the center point coordinates:

[0165] Through PCA principal component analysis, the target point cloud Solve for the point cloud feature vector V.

[0166]

[0167] The target point cloud center coordinates are calculated using the target center calculation formula. The formula is as follows:

[0168]

[0169] in, is the center coordinate of the target point cloud; is the average coordinate value of the target point cloud; n is the total number of target point clouds; : No. The reflection intensity value of the point cloud; : No. Point cloud coordinates.

[0170] S404, according to the first coordinate of the target center and the second coordinate of the target point cloud center, solve the conversion relationship between the radar coordinate system and the tunnel coordinate system, and calculate the conversion matrix from the trolley coordinate system to the tunnel coordinate system.

[0171] based on and Coordinates, the transformation relationship between the radar coordinate system and the tunnel coordinate system is solved by the SVD method, and the transformation matrix from the lidar coordinate system to the tunnel coordinate system is obtained .

[0172] The transformation matrix from the trolley coordinate system to the tunnel coordinate system is calculated using the following formula.

[0173]

[0174] S505. According to the transformation matrix, the positioning result of the trolley in the tunnel is calculated.

[0175] According to the following calculation formula, the positioning result of the trolley in the tunnel is calculated. The calculation formula is as follows

[0176]

[0177] in, is the origin of the trolley coordinate system, This is the positioning result of the trolley in the tunnel.

[0178] The present application provides a laser radar-based trolley positioning method, device, equipment and storage medium, which obtain the attitude conversion matrix between the laser radar and the trolley, and the first coordinate of the target center of each target; wherein the attitude conversion matrix is ​​obtained by calibrating the attitude relationship between the laser radar and the trolley; the first coordinate of each target center is the coordinate of the corresponding target in the tunnel coordinate system measured by the total station; the point cloud data of the laser radar is obtained, and the second coordinate of the target center of each target is obtained according to the point cloud data; wherein the second coordinate of each target center is the coordinate of the corresponding target in the radar coordinate system; according to the first coordinate of the target center and the second coordinate of the target center of each target, the first conversion matrix between the radar coordinate system and the tunnel coordinate system is obtained by the singular value decomposition method, and according to the first conversion matrix and the attitude conversion matrix, the second conversion matrix between the trolley coordinate system where the trolley is located and the tunnel coordinate system is obtained; according to the second conversion matrix, the trolley is positioned. The following technical effects have been achieved: data collection is achieved through laser radar, which reduces the cost of positioning and has wide adaptability; point cloud data calculation and coordinate conversion of the target are achieved through a variety of methods, which ensures the stability of positioning and improves the accuracy of positioning; the positioning problem of the trolley is solved through multiple matrices and target center coordinates, which reduces the possibility of errors, and has strong versatility. It does not calculate based on the geometric feature information of the tunnel, which improves the accuracy of trolley positioning. The center coordinates of the target point cloud in the tunnel point cloud can be automatically extracted, which has the advantages of automation, high precision and strong stability. The positioning conversion relationship is solved by combining the target center coordinates automatically extracted by the laser radar and the target center coordinates measured by the total station, and the positioning accuracy is high.

[0179] The embodiment of the present invention can divide the electronic device or the main control device into functional modules according to the above method example. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present invention is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0180] Figure 6 This is a schematic diagram of the structure of the trolley positioning device based on laser radar provided in the embodiment of the present application. Figure 6 As shown, the laser radar-based trolley positioning device 600 includes an acquisition module 610 , a coordinate module 620 , a matrix module 630 and a positioning module 640 .

[0181] The acquisition module 610 is used to obtain the attitude conversion matrix between the laser radar and the vehicle, and the first coordinate of the target center of each target; wherein the attitude conversion matrix is ​​obtained by calibrating the attitude relationship between the laser radar and the vehicle; the first coordinate of the center of each target is the coordinate of the corresponding target in the tunnel coordinate system measured by the total station;

[0182] The coordinate module 620 is used to obtain the point cloud data of the laser radar, and obtain the second coordinate of the target center of each target according to the point cloud data; wherein the second coordinate of each target center is the coordinate of the corresponding target in the radar coordinate system;

[0183] The matrix module 630 is used to obtain a first conversion matrix between the radar coordinate system and the tunnel coordinate system according to the first coordinate of the target center and the second coordinate of the target center of each target by a singular value decomposition method, and obtain a second conversion matrix between the trolley coordinate system where the trolley is located and the tunnel coordinate system according to the first conversion matrix and the attitude conversion matrix;

[0184] The positioning module 640 is used to position the trolley according to the second conversion matrix.

[0185] In a possible design, the laser radar-based trolley positioning device 600 further includes:

[0186] A conversion module, used to convert the point cloud data into text data; wherein the text data includes a plurality of three-dimensional points, a coordinate value of each three-dimensional point in a radar coordinate system, and a reflection intensity value of each three-dimensional point;

[0187] The coordinate module 620 includes:

[0188] A three-dimensional point extraction module, used to determine a plurality of target point sets by three-dimensional point extraction according to the coordinate value and reflection intensity value of each three-dimensional point; wherein each target point set includes a plurality of target points, and each target point is used to indicate a point on the target;

[0189] The target second module is used to obtain the second coordinate of the target center of each target according to the coordinate value and reflection intensity value of each three-dimensional point.

[0190] In a possible design, the 3D point extraction module includes:

[0191] A filtering processing module, used to filter the multiple three-dimensional points through a filtering processing method according to the coordinate value and reflection intensity value of each three-dimensional point, so as to obtain multiple first type points;

[0192] A clustering segmentation module, used for clustering the plurality of first type points through Euclidean clustering segmentation processing to obtain a plurality of first point sets;

[0193] An expansion and fitting module, used to perform expansion processing and fitting processing on each first point set respectively, to obtain a second point set corresponding to each first point set; wherein each second point set includes a plurality of second type points;

[0194] The target point set module is used to determine multiple target point sets from multiple second point sets through target matching.

[0195] In a possible design, each coordinate value includes a depth value and a height value, and the filtering processing module includes:

[0196] A through-filter module is used to perform directional filtering on multiple three-dimensional points according to the depth value and height value of each three-dimensional point through a through-filter method to obtain multiple filter points; wherein the depth value of each filter point is within a depth threshold range; and the height value of each filter point is within a height threshold range;

[0197] The reflection filtering module is used to perform intensity filtering on multiple filter points according to the reflection intensity value of each filter point through point cloud reflection intensity filtering to obtain multiple first type points; wherein the reflection intensity value of each first type point is greater than the first reflection intensity threshold.

[0198] In one possible design, the target type point is any one of a plurality of first type points, and the first target point set is a first point set where the target type point is located;

[0199] Expanded fitting modules, including:

[0200] An expansion module is used to compare the target type point with multiple three-dimensional points of the text data, obtain multiple three-dimensional points corresponding to the target type point in the text data, establish an expansion range, and determine the expansion range as the expansion point of the first target point set, wherein the expansion range of the target type point refers to a spherical range with the target type point as the center and the distance threshold as the radius, and the expansion range is a spherical range established by the corresponding multiple three-dimensional points in the text data;

[0201] A removal module, used for removing duplicate points from a plurality of first type points and a plurality of extended points of the first target point set to obtain a third point set corresponding to the first target point set;

[0202] The fitting module is used to perform plane fitting on the third point set corresponding to the first target point set through a random sample consistency algorithm to obtain a second point set corresponding to the first target point set.

[0203] In a possible design, the second target point set is any one of a plurality of second point sets;

[0204] For the second target point set, the target point set module includes:

[0205] A data acquisition module is used to acquire a first length value and a first width value of the target, and the number of intensity points of the second target point set; wherein the number of intensity points of the second target point set refers to the number of second type points in the second target point set whose reflection intensity value is greater than the second reflection intensity threshold value;

[0206] A bounding box module, used to construct a bounding box for the second target point set to obtain a second length value and a second width value of the bounding box;

[0207] The judgment module is used to judge whether the second target point set is a target point set according to the numerical relationship between the first length value and the second length value, the numerical relationship between the first width value and the second width value, and the numerical relationship between the number of intensity points of the second target point set and the number threshold.

[0208] In one possible design, the target point set is any one of multiple target point sets.

[0209] For the target point set, the second target module includes:

[0210] A feature vector module is used to obtain a point set feature vector of a target point set; wherein the point set feature vector of the target point set is obtained by a principal component analysis method;

[0211] The coordinate calculation module is used to obtain the second coordinate of the target center of the target corresponding to the target point set according to the coordinate value and reflection intensity value of each target point in the target point set and the point set feature vector of the target point set.

[0212] The present embodiment provides a trolley positioning device based on laser radar, which can execute the trolley positioning method based on laser radar of the above-mentioned embodiment. Its implementation principle and technical effect are similar, and will not be described in detail in the present embodiment.

[0213] In the specific implementation of the aforementioned trolley positioning method based on laser radar, each module can be implemented as a processor, and the processor can execute computer execution instructions stored in the memory, so that the processor executes the aforementioned trolley positioning method based on laser radar.

[0214] Figure 7 This is a schematic diagram of the structure of the electronic device hardware provided in the embodiment of the present application. Figure 7 As shown, the electronic device 700 includes: at least one processor 710 and a memory 720. The electronic device 700 also includes a communication component 730. The processor 710, the memory 720 and the communication component 730 are connected via a bus 740.

[0215] In the specific implementation process, at least one processor 710 executes the computer execution instructions stored in the memory 720, so that at least one processor 710 executes a laser radar-based trolley positioning method as executed by the electronic device side above.

[0216] The specific implementation process of the processor 710 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0217] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0218] The memory may include a high-speed RAM memory, and may also include a non-volatile storage NVM, such as at least one disk storage.

[0219] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of this application is not limited to only one bus or one type of bus.

[0220] The above-mentioned functions implemented by the electronic device and the main control device introduce the scheme provided by the embodiment of the present invention. It can be understood that in order to implement the above-mentioned functions, the electronic device or the main control device includes a hardware structure and / or software module corresponding to the execution of each function. In combination with the units and algorithm steps of each example described in the embodiment disclosed in the embodiment of the present invention, the embodiment of the present invention can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the technical solution of the embodiment of the present invention.

[0221] The present application also provides a computer-readable storage medium, in which computer execution instructions are stored. When the computer execution instructions are executed by a processor, they are used to implement the above-mentioned laser radar-based trolley positioning method.

[0222] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof.

[0223] Such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0224] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as ASIC). Of course, the processor and the readable storage medium can also exist as discrete components in an electronic device or a main control device.

[0225] The present application also provides a computer program product, which includes: a computer program, which is stored in a readable storage medium. At least one processor of an electronic device can read the computer program from the readable storage medium. When the computer program is executed by the processor, it is used to implement the above-mentioned laser radar-based trolley positioning method.

[0226] Those skilled in the art can understand that all or part of the steps of the above method embodiments can be completed by hardware related to program instructions. The above program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above method embodiments are executed; and the above storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0227] So far, the technical solution of the present application has been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present application is obviously not limited to these specific embodiments, and the above embodiments are only used to illustrate the technical solution of the present application rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A trolley positioning method based on laser radar, characterized in that: The method is used for positioning a trolley in a tunnel, the trolley is equipped with a laser radar, and a plurality of targets are arranged in the tunnel, and the method comprises: Obtaining the attitude conversion matrix between the laser radar and the trolley, and the first coordinate of the target center of each target; wherein the attitude conversion matrix is ​​obtained by calibrating the attitude relationship between the laser radar and the trolley; the first coordinate of each target center is the coordinate of the corresponding target in the tunnel coordinate system measured by the total station; Acquire the point cloud data of the laser radar, and obtain the second coordinate of the target center of each target according to the point cloud data; wherein the second coordinate of each target center is the coordinate of the corresponding target in the radar coordinate system; According to the first coordinates of the target center and the second coordinates of the target center of each target, a first conversion matrix between the radar coordinate system and the tunnel coordinate system is obtained by a singular value decomposition method, and according to the first conversion matrix and the attitude conversion matrix, a second conversion matrix between the trolley coordinate system where the trolley is located and the tunnel coordinate system is obtained; The trolley is positioned according to the second transformation matrix.

2. The method according to claim 1, characterized in that After acquiring the point cloud data of the laser radar, the method further includes: Converting the point cloud data into text data; wherein the text data includes a plurality of three-dimensional points, a coordinate value of each of the three-dimensional points in the radar coordinate system, and a reflection intensity value of each of the three-dimensional points; The step of obtaining the second coordinate of the target center of each target according to the point cloud data includes: According to the coordinate value and reflection intensity value of each of the three-dimensional points, a plurality of target point sets are determined by three-dimensional point extraction; wherein each of the target point sets includes a plurality of target points, and each of the target points is used to indicate a point on the target; According to the coordinate value and reflection intensity value of each of the three-dimensional points, the second coordinate of the target center of each of the targets is obtained.

3. The method according to claim 2, characterized in that The method of determining a plurality of target point sets by extracting three-dimensional points according to the coordinate values ​​and reflection intensity values ​​of each of the three-dimensional points includes: According to the coordinate value and the reflection intensity value of each of the three-dimensional points, filtering the multiple three-dimensional points by a filtering processing method to obtain multiple first type points; Clustering the first-type points through Euclidean clustering segmentation to obtain a plurality of first point sets; Performing expansion processing and fitting processing on each of the first point sets respectively to obtain a second point set corresponding to each of the first point sets; wherein each of the second point sets includes a plurality of second type points; Through target matching, a plurality of target point sets are determined from a plurality of the second point sets.

4. The method according to claim 3, characterized in that: Each of the coordinate values ​​includes a depth value and a height value, and the filtering process is performed on the plurality of three-dimensional points according to the coordinate value and the reflection intensity value of each of the three-dimensional points through a filtering process to obtain a plurality of first type points, including: According to the depth value and height value of each of the three-dimensional points, the plurality of three-dimensional points are directionally filtered by a straight-through filtering method to obtain a plurality of filter points; wherein the depth value of each of the filter points is within a depth threshold range; and the height value of each of the filter points is within a height threshold range; According to the reflection intensity value of each of the filtering points, the multiple filtering points are intensity filtered through point cloud reflection intensity filtering to obtain the multiple first type points; wherein the reflection intensity value of each of the first type points is greater than the first reflection intensity threshold.

5. The method according to claim 3, characterized in that: The target type point is any one of the plurality of first type points, and the first target point set is the first point set where the target type point is located; For the target type points and the first target point sets, respectively performing expansion processing and fitting processing on each of the first point sets to obtain a second point set corresponding to each of the first point sets includes: Compare the target type point with a plurality of three-dimensional points of the text data to obtain a plurality of the three-dimensional points corresponding to the target type point in the text data, establish an expansion range, and determine the expansion range as the expansion point of the first target point set, wherein the expansion range of the target type point refers to a spherical range with the target type point as the center and a distance threshold as the radius, and the expansion range is a spherical range established by the plurality of the three-dimensional points corresponding to the text data; Eliminate duplicate points of the plurality of the first type points and the plurality of the extended points of the first target point set to obtain a third point set corresponding to the first target point set; A plane fitting is performed on the third point set corresponding to the first target point set by using a random sample consistency algorithm to obtain a second point set corresponding to the first target point set.

6. The method according to claim 3, characterized in that The second target point set is any one of the plurality of second point sets; For the second target point set, determining a plurality of target point sets from a plurality of the second point sets through target matching includes: Acquire a first length value and a first width value of the target, and the number of intensity points of the second target point set; wherein the number of intensity points of the second target point set refers to the number of second type points in the second target point set whose reflection intensity value is greater than a second reflection intensity threshold value; Make a bounding box for the second target point set to obtain a second length value and a second width value of the bounding box; Whether the second target point set is the target point set is determined based on the numerical relationship between the first length value and the second length value, the numerical relationship between the first width value and the second width value, and the numerical relationship between the number of intensity points of the second target point set and the number threshold.

7. The method according to claim 2, characterized in that The target point set is any one of the multiple target point sets. For the target point set, obtaining the second coordinate of the target center of each target according to the coordinate value and reflection intensity value of each three-dimensional point includes: Obtaining a point set feature vector of the target point set; wherein the point set feature vector of the target point set is obtained by principal component analysis; According to the coordinate value and reflection intensity value of each target point of the target point set and the point set feature vector of the target point set, the second coordinate of the target center of the target corresponding to the target point set is obtained.

8. A trolley positioning device based on laser radar, characterized in that: include: An acquisition module is used to acquire the attitude conversion matrix between the laser radar and the trolley, and the first coordinate of the target center of each target; wherein the attitude conversion matrix is ​​obtained by calibrating the attitude relationship between the laser radar and the trolley; the first coordinate of each target center is the coordinate of the corresponding target in the tunnel coordinate system measured by the total station; A coordinate module, used to obtain the point cloud data of the laser radar, and obtain the second coordinate of the target center of each target according to the point cloud data; wherein the second coordinate of each target center is the coordinate of the corresponding target in the radar coordinate system; A matrix module, used for obtaining a first conversion matrix between the radar coordinate system and the tunnel coordinate system according to the first coordinate of the target center and the second coordinate of the target center of each target by a singular value decomposition method, and obtaining a second conversion matrix between the trolley coordinate system where the trolley is located and the tunnel coordinate system according to the first conversion matrix and the attitude conversion matrix; A positioning module is used to position the trolley according to the second conversion matrix.

9. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; When the processor executes the computer-executable instructions stored in the memory, it is used to implement a laser radar-based trolley positioning method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement a laser radar-based trolley positioning method as described in any one of claims 1 to 7.

Images