Method, device and electronic equipment for extracting roadway surface point cloud

Abstract

The present application provides a method, device, and electronic device for extracting a roadway surface point cloud. The method includes: dividing the original point cloud data according to the roadway surface curvature of the original point cloud data to obtain multiple long straight roadway point clouds; slicing each long straight roadway point cloud at equal intervals, using the mean of each point cloud slice as the point cloud center point of the point cloud slice, fitting the roadway centerline of the corresponding point cloud slice based on each point cloud center point and each target point; constructing a coordinate system for each point cloud slice based on the roadway center line, and projecting all point clouds of the point cloud slice onto a plane perpendicular to the roadway center line to obtain a projected point cloud; rasterizing all projected point clouds in the coordinate system of each point cloud slice to obtain multiple first grids; and extracting the projected point clouds in the first grids based on the point cloud density of the first grids. This shortens the extraction time, thereby resolving the problem of long time required for extracting roadway surface point clouds in existing solutions.

Description

Technical Field

[0001] The present application relates to the field of point cloud technology, and in particular to a method, device, computer-readable storage medium, and electronic device for extracting roadway surface point clouds. Background Art

[0002] The tunnel surface point cloud extraction technology combines 3D laser scanning technology with point cloud processing technology in computer graphics. By processing the collected point cloud data, the tunnel boundary information is extracted. When the existing scheme extracts the tunnel surface point cloud, it is necessary to evaluate each point in the point cloud, which greatly prolongs the extraction time, and thus makes the tunnel surface point cloud extraction time of the existing scheme longer. Summary of the Invention

[0003] The main purpose of this application is to provide a method, device, computer-readable storage medium and electronic device for extracting tunnel surface point clouds, so as to at least solve the problem that the time required for extracting tunnel surface point clouds in existing solutions is long.

[0004] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for extracting a tunnel surface point cloud is provided, the method comprising: obtaining original point cloud data, dividing the original point cloud data according to the tunnel surface curvature of the original point cloud data, and obtaining a plurality of long straight tunnel point clouds; performing equidistant slicing processing on each of the long straight tunnel point clouds to obtain a plurality of point cloud slices corresponding to the original point cloud data, and taking the mean of each of the point cloud slices as the point cloud center point of the point cloud slice, obtaining a plurality of target points, the target point being one of the points in the point cloud slice other than the point cloud center point, and performing a slicing process on the original point cloud data according to the curvature of the tunnel surface of the original point cloud data; performing equidistant slicing processing on each of the long straight tunnel point clouds to obtain a plurality of point cloud slices corresponding to the original point cloud data, and taking the mean of each of the point cloud slices as the point cloud center point of the point cloud slice, and obtaining a plurality of target points, the target point being one of the points in the point cloud slice other than the point cloud center point, and performing a slicing process on the original point cloud data according to the curvature of the tunnel surface of the original point cloud data; The target point is fitted with the lane center line of the corresponding point cloud slice; according to the lane center line, a coordinate system of each point cloud slice is constructed, and all point clouds of the point cloud slice are projected onto a plane perpendicular to the lane center line to obtain a projected point cloud; all the projected point clouds in the coordinate system of each point cloud slice are rasterized to obtain a plurality of first grids, each of which includes a plurality of first grids, and each of the first grids includes a plurality of projected point clouds; the point cloud density of each first grid is determined, and the projected point cloud in the first grid is extracted according to the point cloud density of the first grid.

[0005] Optionally, before dividing the point cloud original data according to the tunnel surface curvature of the point cloud original data to obtain multiple segments of long straight tunnel point clouds, the method also includes: determining a covariance matrix based on the point cloud original data; determining three eigenvalues ​​of the covariance matrix based on the covariance matrix, and determining the tunnel surface curvature based on the three eigenvalues; dividing the point cloud original data according to the tunnel surface curvature of the point cloud original data to obtain multiple segments of long straight tunnel point clouds, including: when the tunnel surface curvature is greater than or equal to a curvature threshold, dividing the point cloud original data according to the tunnel surface curvature to obtain multiple segments of the long straight tunnel point clouds.

[0006] Optionally, determining a covariance matrix based on the original point cloud data includes:

[0007] Determining the coordinates of a neighborhood point set of the original point cloud data according to the original point cloud data;

[0008] according to Determine the covariance matrix, where C is the covariance matrix, p k is the coordinate of the neighborhood point set of the original point cloud data, O i is the centroid of the neighborhood point set, and k is the number of the neighborhood points.

[0009] Optionally, determining the roadway surface curvature according to the three characteristic values ​​includes:

[0010] according to Determine the curvature of the roadway surface, where H is the curvature of the roadway surface, and λ0, λ1, and λ2 are the three eigenvalues ​​respectively.

[0011] Optionally, according to each of the point cloud center points and each of the target points, the tunnel center line of the corresponding point cloud slice is fitted, including: a connecting step: connecting the point cloud center point and the target point to obtain an initial center line, and obtaining multiple distance values, and determining a distance average based on all the distance values, wherein the distance value is used to characterize the distance between one of the points in the point cloud slice other than the point cloud center point and the target point and the initial center line; a judging step: repeatedly obtaining the target point and the connecting step, and taking the initial center line corresponding to the minimum value of the distance average as the tunnel center line.

[0012] Optionally, determining the point cloud density of each of the first grids includes:

[0013] according to Determine the point cloud density of the first grid, where ρ is the point cloud density, L x , L y , L zare the lengths of the first grid in each direction respectively, and N is the total number of point clouds of the original point cloud data.

[0014] Optionally, the projected point cloud in the first grid is extracted according to the point cloud density of the first grid, including: when the point cloud density of the first grid is greater than or equal to a density threshold, the projected point cloud in the first grid is extracted; when the point cloud density of the first grid is less than the density threshold, all the projected point clouds in the coordinate system of each point cloud slice are rasterized again with a grid size smaller than the first grid to obtain multiple second grids, each second grid includes multiple second grids, and each second grid includes multiple projected point clouds; the point cloud density of each second grid is determined again, and all the projected point clouds in the second grid are extracted according to the point cloud density of the second grid.

[0015] According to another aspect of the present application, a device for extracting a tunnel surface point cloud is provided, which includes an acquisition unit, a first processing unit, a second processing unit, a third processing unit and a determination unit; the acquisition unit is used to acquire original point cloud data, divide the original point cloud data according to the tunnel surface curvature of the original point cloud data, and obtain multiple segments of long straight tunnel point clouds; the first processing unit is used to perform equidistant slicing processing on each of the long straight tunnel point clouds to obtain multiple point cloud slices corresponding to the original point cloud data, and use the mean value of each of the point cloud slices as the point cloud center point of the point cloud slice to obtain multiple target points, wherein the target point is one of the points in the point cloud slice other than the point cloud center point, and the target point is obtained according to each of the point cloud slices. The cloud center point and each target point are fitted with the lane center line of the corresponding point cloud slice; the second processing unit is used to construct the coordinate system of each point cloud slice according to the lane center line, and project all the point clouds of the point cloud slice to a plane perpendicular to the lane center line to obtain a projected point cloud; the third processing unit is used to perform rasterization processing on all the projected point clouds in the coordinate system of each point cloud slice to obtain multiple first grids, each of the first grids includes multiple first grids, and each of the first grids includes multiple projected point clouds; the determination unit is used to determine the point cloud density of each first grid, and extract the projected point cloud in the first grid according to the point cloud density of the first grid.

[0016] According to another aspect of the present application, a computer-readable storage medium is provided, which includes a stored program, wherein when the program is run, the device where the computer-readable storage medium is located is controlled to execute any one of the methods for extracting a roadway surface point cloud.

[0017] According to another aspect of the present application, an electronic device is provided, which includes one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for executing any one of the methods for extracting a roadway surface point cloud.

[0018] By applying the technical solution of the present application, the point cloud is first sliced ​​into multiple point cloud slices, the center line of the tunnel is obtained for each point cloud slice, and a coordinate system is constructed. The point cloud density of each grid is calculated through rasterization processing, so that the subsequent extraction of the point cloud is more in line with the actual situation, thereby shortening the extraction time, thereby solving the problem of long time for extracting tunnel surface point clouds in existing solutions. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings that constitute part of this application are used to provide a further understanding of this application. The illustrative embodiments of this application and their descriptions are used to explain this application and do not constitute an improper limitation on this application. In the drawings:

[0020] Figure 1 A hardware structure block diagram of a mobile terminal for executing a method for extracting a roadway surface point cloud provided in an embodiment of the present application is shown;

[0021] Figure 2 A schematic diagram of a process for extracting a roadway surface point cloud according to an embodiment of the present application is shown;

[0022] Figure 3 A schematic diagram of the process of establishing the centerline of the roadway is shown;

[0023] Figure 4 shows a schematic diagram of point cloud projection;

[0024] Figure 5 A schematic diagram of the process of extracting another method of roadway surface point cloud is shown;

[0025] Figure 6 A structural block diagram of a tunnel surface point cloud extraction device provided according to an embodiment of the present application is shown.

[0026] The above drawings include the following reference numerals:

[0027] 1. Point cloud model of a long straight roadway; 2. Point cloud slice; 3. Point cloud center point; 4. Roadway centerline; 5. 2D projection grid; 6. 2D point cloud projection. DETAILED DESCRIPTION

[0028] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0029] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0030] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0031] As introduced in the background technology, the tunnel surface point cloud extraction technology combines three-dimensional laser scanning technology and point cloud processing technology in computer graphics. By processing the collected point cloud data, the tunnel boundary information is extracted. When the existing scheme extracts the tunnel surface point cloud, it is necessary to judge each point in the point cloud, which greatly prolongs the extraction time, and thus makes the tunnel surface point cloud extraction time longer in the existing scheme. In order to solve the problem of the long time of tunnel surface point cloud extraction in the existing scheme, the embodiments of the present application provide a tunnel surface point cloud extraction method, device, computer-readable storage medium and electronic device.

[0032] The technical solutions in the embodiments of the present invention will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present invention.

[0033] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for extracting a tunnel surface point cloud according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1Only one is shown) a processor 102 (the processor 102 may include but is not limited to a microprocessor MCU or a programmable logic device FPGA and other processing devices) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It will be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown.

[0034] The memory 104 can be used to store computer programs, such as application software programs and modules, such as the computer program corresponding to the method for extracting a roadway surface point cloud in the embodiments of the present invention. The processor 102 executes the computer programs stored in the memory 104 to execute various functional applications and data processing, thereby implementing the aforementioned method. The memory 104 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory remote from the processor 102, which can be connected to the mobile terminal via a network. Examples of such networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof. The transmission device 106 is used to receive or transmit data via a network. Specific examples of such networks may include a wireless network provided by the mobile terminal's telecommunications provider. In one example, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0035] In this embodiment, a method for extracting a roadway surface point cloud running on a mobile terminal, a computer terminal or a similar computing device is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0036] Figure 2 It is a flow chart of a method for extracting a tunnel surface point cloud provided in accordance with an embodiment of the present application.

[0037] like Figure 2 As shown, the method includes the following steps:

[0038] Step S201, obtaining original point cloud data, dividing the original point cloud data according to the curvature of the roadway surface, and obtaining multiple segments of long straight roadway point clouds;

[0039] In one embodiment of the present application, before dividing the original point cloud data according to the curvature of the roadway surface to obtain multiple segments of long straight roadway point clouds, the method further includes:

[0040] According to the above point cloud original data, the covariance matrix is ​​determined;

[0041] In one embodiment of the present application, determining the covariance matrix based on the above-mentioned original point cloud data includes:

[0042] According to the original point cloud data, the coordinates of the neighborhood point set of the original point cloud data are determined;

[0043] according to Determine the covariance matrix, where C is the above covariance matrix, p k is the coordinate of the neighborhood point set of the original point cloud data, O i is the centroid of the above neighborhood point set, and k is the number of the above neighborhood points;

[0044] Specifically, the coordinates of the neighborhood point set of the point cloud original data are first determined based on the point cloud original data, and then the covariance matrix is ​​determined based on the coordinates of the neighborhood point set of the point cloud original data, the center of gravity of the neighborhood point set and the number of neighborhood points, so that the point cloud original data is reasonably divided.

[0045] Determining three eigenvalues ​​of the covariance matrix according to the covariance matrix, and determining the curvature of the roadway surface according to the three eigenvalues;

[0046] In one embodiment of the present application, determining the curvature of the roadway surface according to the three characteristic values ​​includes:

[0047] according to Determine the curvature of the above-mentioned roadway surface, where H is the curvature of the above-mentioned roadway surface, λ0, λ1, and λ2 are the three eigenvalues ​​obtained by solving the above-mentioned covariance matrix, and λ0 is the minimum value of the three eigenvalues. The size of the eigenvalue determines the degree of stretching of the original point cloud data on the corresponding eigenvector, that is, the main deformation degree.

[0048] Specifically, the three eigenvalues ​​of the covariance matrix are first obtained, and then the curvature of the roadway surface is obtained according to the three eigenvalues.

[0049] The above-mentioned point cloud original data is divided according to the tunnel surface curvature of the above-mentioned point cloud original data to obtain multiple segments of long straight tunnel point clouds, including: when the above-mentioned tunnel surface curvature is greater than or equal to the curvature threshold, the above-mentioned point cloud original data is divided according to the above-mentioned tunnel surface curvature to obtain multiple segments of the above-mentioned long straight tunnel point clouds.

[0050] Specifically, when the curvature of the tunnel surface is less than the curvature threshold, no slicing is performed. When the curvature of the tunnel surface is greater than or equal to the curvature threshold, the original point cloud data is divided according to the curvature of the tunnel surface to obtain multiple segments of the long straight tunnel point cloud, thereby achieving the purpose of reasonable division of the original point cloud data.

[0051] Step S202: performing equidistant slicing processing on each of the long straight roadway point clouds to obtain a plurality of point cloud slices corresponding to the original point cloud data, and taking the mean of each of the point cloud slices as the point cloud center point of the point cloud slice, obtaining a plurality of target points, wherein the target point is one of the points in the point cloud slice other than the point cloud center point, and fitting the roadway center line of the corresponding point cloud slice based on each of the point cloud center points and each of the target points;

[0052] Specifically, the benefits of equally spaced slicing processing are: equally spaced slicing can convert point cloud data into a regular sequence form, thereby improving the efficiency of data processing and better analyzing the data in subsequent processing. A point is randomly found from the points other than the center point of the point cloud in the above point cloud slice, and the point is used as the target point. The target point and the center point of the point cloud are then connected to obtain the center line of the tunnel.

[0053] In one embodiment of the present application, step S202, i.e., fitting the corresponding lane center line of the above-mentioned point cloud slice according to each of the above-mentioned point cloud center points and each of the above-mentioned target points, includes: a connecting step: connecting the above-mentioned point cloud center point and the above-mentioned target point to obtain an initial center line, and obtaining multiple distance values, and determining the distance average value based on all the distance values, the above-mentioned distance value is used to characterize the distance between one of the points other than the above-mentioned point cloud center point and the above-mentioned target point in the above-mentioned point cloud slice and the above-mentioned initial center line; a judgment step: repeatedly obtaining the above-mentioned target point and the above-mentioned connecting step, and taking the above-mentioned initial center line corresponding to the minimum value of the above-mentioned distance average value as the above-mentioned lane center line.

[0054] Specifically, all points in the above point cloud slice except the center point of the above point cloud should be used as target points once, and then a point in the above point cloud slice except the center point of the above point cloud can be obtained that is most suitable as the target point. Using this point as the target point can ensure the accuracy of subsequent point cloud extraction.

[0055] Step S203: constructing a coordinate system for each of the point cloud slices according to the lane centerline, and projecting all point clouds of the point cloud slices onto a plane perpendicular to the lane centerline to obtain a projected point cloud;

[0056] Step S204: performing rasterization processing on all the projected point clouds in the coordinate system of each of the point cloud slices to obtain a plurality of first grids, each of the first grids including a plurality of first grids, each of which includes a plurality of the projected point clouds;

[0057] Specifically, the process of constructing the coordinate system is as follows: take a point on the center line as the origin, the Y axis is the direction of the lane center line, and the Z axis points directly above the lane, and establish the right-hand coordinate system. After the coordinates are established, the coordinate points are converted according to the new coordinate axis to carry out the next projection calculation, such as Figure 3 and Figure 4 As shown, the long straight tunnel point cloud model 1, point cloud slice 2, point cloud center point 3, tunnel center line 4, two-dimensional projection grid 5, and two-dimensional point cloud projection 6 are displayed. Figure 3 The process of establishing the lane centerline based on the center point of the uniform slice is shown. Figure 4 The point cloud 2D projection process is shown;

[0058] Step S205 , determining the point cloud density of each of the first grids, and extracting the projected point cloud in the first grid according to the point cloud density of the first grid.

[0059] In one embodiment of the present application, step S205, i.e., determining the point cloud density of each of the first grids, includes:

[0060] according to Determine the point cloud density of the first grid, where ρ is the point cloud density, L x , L y , L z are the lengths of the first grid in each direction, and N is the total number of point clouds in the original point cloud data.

[0061] Specifically, using L x =ceil(X max -X min ), L y =ceil(Y max -Y min ), L z =ceil(Z max -Z min ), to obtain L x , L y , L z , ceil is rounded up, X max and X minare the maximum and minimum values ​​of the first grid in the X-axis direction, Y max 、Y min , Z max and Z min Similarly, I will not elaborate on it here.

[0062] In one embodiment of the present application, step S205, i.e., extracting the projected point cloud in the first grid according to the point cloud density of the first grid, includes:

[0063] When the point cloud density of the first grid is greater than or equal to a density threshold, extracting the projected point cloud in the first grid;

[0064] When the point cloud density of the first grid is less than the density threshold, all the projected point clouds in the coordinate system of each of the point cloud slices are rasterized again with a grid size smaller than the first grid to obtain a plurality of second grids, each of the second grids including a plurality of second grids, and each of the second grids including a plurality of the projected point clouds;

[0065] The point cloud density of each of the second grids is determined again, and all of the projected point clouds in the second grids are extracted according to the point cloud density of the second grids.

[0066] Specifically, when the point cloud density of the first grid is greater than or equal to the density threshold, the projected point cloud in the first grid is extracted; when the point cloud density of the first grid is less than the density threshold, a grid smaller in size than the first grid is required to rasterize all the projected point clouds in the coordinate system of the point cloud slice, thereby improving the accuracy of point cloud extraction.

[0067] Through the above embodiment, by first slicing the point cloud into multiple point cloud slices, then obtaining the center line of the tunnel for each point cloud slice, and constructing a coordinate system, the point cloud density of each grid can be calculated through rasterization processing, so that the subsequent extraction of the point cloud is more in line with the actual situation, thereby shortening the extraction time, thereby solving the problem of the long time required to extract the tunnel surface point cloud in the existing solution.

[0068] In order to enable those skilled in the art to more clearly understand the technical solution of the present application, the implementation process of the method for extracting the tunnel surface point cloud of the present application will be described in detail below with reference to specific embodiments.

[0069] This embodiment relates to a specific method for extracting roadway surface point clouds, such as Figure 5 As shown, the following steps are included:

[0070] Step S1: Scan the tunnel with a 3D laser scanner to obtain original point cloud data. The original point cloud data should be mainly straight features without large bends.

[0071] Step S2: Considering the situation of small curvature, the roadway point cloud can be divided by the roadway surface curvature difference to obtain multiple long straight roadway point clouds;

[0072] Step S3: Slice the obtained long straight roadway point cloud at equal intervals along the roadway extension direction to obtain point cloud slices corresponding to the original point cloud data;

[0073] Step S4: taking the mean of the point cloud slice as the center point of the point cloud slice, and fitting the lane centerline according to the center point of the point cloud slice and the target point, where the target point is one of the points in the point cloud slice other than the center point of the point cloud;

[0074] Step S5: Establish a coordinate system with the fitted lane centerline as the Y axis, and project the lane point cloud data onto a plane perpendicular to the lane centerline;

[0075] Step S6: Rasterize the grids along the coordinate axes, denoted as X1, X2, ..., Xi-1, Xi, Xi+1, ..., Xn, and search for the number of points in the grids in the same row from the center grid toward both ends, and calculate the density of the points in the grids in the same row;

[0076] Step S7: Set a density threshold. When the point density in the grid Xi is less than the density threshold, determine whether the point cloud in the grid is a roadway surface point cloud. If so, mark the point cloud in the grid. Otherwise, perform subdivision processing and enter step S8.

[0077] Step S8: Select a smaller grid than that in step S6, and repeat steps S6 to S7 for the point cloud in the adjacent grid Xi-1 close to the center direction of the non-roadway surface point cloud grid to obtain a more refined marked point cloud;

[0078] Step S9: retain all marked point clouds and complete the roadway surface point cloud extraction.

[0079] The specific method for judging the surface point cloud is as follows:

[0080] First, starting from any point p1 with coordinates (x1, y1) in the grid point set Р, take any point p2 with coordinates (x2, y2) in the neighborhood point set R with a radius of 2α, and calculate the coordinates (x0, y0) of the circle center po determined by points p1 and p2.

[0081]

[0082] in,

[0083]

[0084] O is the intermediate calculation value, and the distance from other points in the neighborhood to the center of the circle p is calculated. o If d is greater than α, it means there is no other point in the circle, then the point is a surface point cloud, otherwise it is a non-surface point cloud.

[0085] It realizes the point cloud extraction of complete, comprehensive and continuous surface data of the tunnel without the need for other processes. It can be used as a preprocessing step for tunnel point cloud analysis, retains the point cloud required for tunnel deformation monitoring, improves processing speed and efficiency, and effectively solves the problems of small measurement range and long time consumption of traditional tunnel surrounding rock deformation monitoring, and quickly realizes comprehensive monitoring of tunnel deformation.

[0086] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0087] The embodiment of the present application also provides a device for extracting a point cloud of a roadway surface. It should be noted that the device for extracting a point cloud of a roadway surface in the embodiment of the present application can be used to execute the method for extracting a point cloud of a roadway surface provided in the embodiment of the present application. The device is used to implement the above-mentioned embodiments and preferred implementations, and those that have been explained will not be repeated here. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and conceivable.

[0088] The following introduces the device for extracting the tunnel surface point cloud provided in the embodiment of the present application.

[0089] Figure 6 This is a structural block diagram of a device for extracting a roadway surface point cloud according to an embodiment of the present application. Figure 6As shown, the device includes an acquisition unit 61, a first processing unit 62, a second processing unit 63, a third processing unit 64 and a determination unit 65; the acquisition unit 61 is used to acquire original point cloud data, and divide the original point cloud data according to the curvature of the roadway surface of the original point cloud data to obtain multiple segments of long straight roadway point clouds; the first processing unit 62 is used to perform equidistant slicing processing on each of the above-mentioned long straight roadway point clouds to obtain multiple point cloud slices corresponding to the original point cloud data, and use the average value of each of the above-mentioned point cloud slices as the point cloud center point of the above-mentioned point cloud slice to obtain multiple target points, and the above-mentioned target point is one of the points in the above-mentioned point cloud slice other than the above-mentioned point cloud center point, and according to the above-mentioned point cloud center point and the above-mentioned point cloud center point, the target point is obtained. The target point is fitted with the lane center line of the corresponding point cloud slice; the second processing unit 63 is used to construct the coordinate system of each of the above point cloud slices according to the lane center line, and project all the point clouds of the above point cloud slices to a plane perpendicular to the lane center line to obtain a projected point cloud; the third processing unit 64 is used to perform rasterization processing on all the above projected point clouds in the coordinate system of each of the above point cloud slices to obtain a plurality of first grids, each of the above first grids respectively includes a plurality of first grids, and each of the above first grids includes a plurality of the above projected point clouds; the determination unit 65 is used to determine the point cloud density of each of the above first grids, and extract the above projected point clouds in the above first grids according to the point cloud density of the above first grids.

[0090] In the above-mentioned device, the point cloud is first sliced ​​into multiple point cloud slices, and then the center line of the tunnel is obtained for each point cloud slice, and a coordinate system is constructed. The point cloud density of each grid is calculated through rasterization processing, so that the subsequent extraction of the point cloud is more in line with the actual situation, thereby shortening the extraction time, thereby solving the problem of the long time required to extract the tunnel surface point cloud in the existing scheme.

[0091] In one embodiment of the present application, the device also includes a fourth processing unit and a fifth processing unit. Before dividing the above-mentioned point cloud original data according to the tunnel surface curvature of the above-mentioned point cloud original data to obtain multiple segments of long straight tunnel point clouds, the fourth processing unit is used to determine the covariance matrix based on the above-mentioned point cloud original data; the fifth processing unit is used to determine the three eigenvalues ​​of the above-mentioned covariance matrix based on the above-mentioned covariance matrix, and determine the above-mentioned tunnel surface curvature based on the above-mentioned three eigenvalues; the acquisition unit includes a first processing module, and the first processing module is used to divide the above-mentioned point cloud original data according to the above-mentioned tunnel surface curvature when the above-mentioned tunnel surface curvature is greater than or equal to the curvature threshold to obtain multiple segments of the above-mentioned long straight tunnel point cloud.

[0092] In one embodiment of the present application, the fourth processing unit includes a second processing module and a first determining module, wherein the second processing module is configured to determine the coordinates of a neighborhood point set of the original point cloud data based on the original point cloud data;

[0093] The first determining module is used to Determine the covariance matrix, where C is the above covariance matrix, p k is the coordinate of the neighborhood point set of the original point cloud data, O i is the centroid of the above neighborhood point set, and k is the number of the above neighborhood points.

[0094] In one embodiment of the present application, the fifth processing unit includes a second determining module,

[0095] The second determining module is used to Determine the curvature of the roadway surface, where H is the curvature of the roadway surface, and λ0, λ1, and λ2 are the three characteristic values.

[0096] In one embodiment of the present application, the first processing unit includes a third processing module and a fourth processing module, and the third processing module is used to execute the connection step: connecting the above-mentioned point cloud center point and the above-mentioned target point to obtain an initial center line, and obtaining multiple distance values, and determining the distance average based on all the distance values, and the above-mentioned distance value is used to characterize the distance between one of the points other than the above-mentioned point cloud center point and the above-mentioned target point in the above-mentioned point cloud slice and the above-mentioned initial center line; the fourth processing module is used to execute the judgment step: repeatedly obtaining the above-mentioned target point and the above-mentioned connection step, and taking the above-mentioned initial center line corresponding to the minimum value of the above-mentioned distance average as the above-mentioned lane center line.

[0097] In one embodiment of the present application, the determining unit includes a third determining module,

[0098] The third determining module is used to Determine the point cloud density of the first grid, where ρ is the point cloud density, L x , L y , L z are the lengths of the first grid in each direction, and N is the total number of point clouds in the original point cloud data.

[0099] In one embodiment of the present application, the determination unit includes a fifth processing module, a sixth processing module and a fourth determination module. The fifth processing module is used to extract the above-mentioned projected point cloud in the above-mentioned first grid when the above-mentioned point cloud density of the above-mentioned first grid is greater than or equal to the density threshold; the sixth processing module is used to rasterize all the above-mentioned projected point clouds in the coordinate system of each of the above-mentioned point cloud slices again with a grid size smaller than the above-mentioned first grid when the above-mentioned point cloud density of the above-mentioned first grid is less than the above-mentioned density threshold, so as to obtain multiple second grids, each of the above-mentioned second grids respectively including multiple second grids, and each of the above-mentioned second grids including multiple above-mentioned projected point clouds; the fourth determination module is used to determine the point cloud density of each of the above-mentioned second grids again, and extract all the above-mentioned projected point clouds in the above-mentioned second grids according to the above-mentioned point cloud density of the above-mentioned second grids.

[0100] The device for extracting a roadway surface point cloud includes a processor and a memory. The acquisition unit, first processing unit, second processing unit, third processing unit, and determination unit are all stored as program units in the memory. The processor executes the program units stored in the memory to implement the corresponding functions. All of the modules are located in the same processor; alternatively, the modules can be located in different processors in any combination.

[0101] The processor contains a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and by adjusting the kernel parameters, the problem of long time required to extract the roadway surface point cloud in the existing solution can be solved.

[0102] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0103] An embodiment of the present invention provides a computer-readable storage medium, which includes a stored program. When the program is run, the device where the computer-readable storage medium is located is controlled to execute the method for extracting the tunnel surface point cloud.

[0104] An embodiment of the present invention provides a processor, which is used to run a program, wherein the program executes the method for extracting the tunnel surface point cloud when running.

[0105] An embodiment of the present invention provides a device, which includes a processor, a memory, and a program stored in the memory and capable of running on the processor. When the processor executes the program, at least the following steps are implemented: obtaining original point cloud data, dividing the original point cloud data according to the curvature of the roadway surface of the original point cloud data to obtain multiple segments of long straight roadway point clouds; performing equal-interval slicing processing on each of the above-mentioned long straight roadway point clouds to obtain multiple point cloud slices corresponding to the original point cloud data, and taking the average of each of the above-mentioned point cloud slices as the point cloud center point of the above-mentioned point cloud slice, obtaining multiple target points, the above-mentioned target point being one of the points in the above-mentioned point cloud slice other than the above-mentioned point cloud center point, according to Each of the above point cloud center points and each of the above target points is fitted with the corresponding lane centerline of the above point cloud slice; based on the above lane centerline, a coordinate system of each of the above point cloud slices is constructed, and all of the point clouds of the above point cloud slices are projected onto a plane perpendicular to the above lane centerline to obtain a projected point cloud; all of the above projected point clouds in the coordinate system of each of the above point cloud slices are rasterized to obtain multiple first grids, each of the above first grids includes multiple first grids, and each of the above first grids includes multiple projected point clouds; the point cloud density of each of the above first grids is determined, and the above projected point clouds in the above first grids are extracted based on the above point cloud density of the above first grids. The device in this article can be a server, PC, PAD, mobile phone, etc.

[0106] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program initialized with at least the following method steps: obtaining original point cloud data, dividing the original point cloud data according to the curvature of the roadway surface of the original point cloud data to obtain multiple long straight roadway point clouds; performing equal-interval slicing processing on each of the above-mentioned long straight roadway point clouds to obtain multiple point cloud slices corresponding to the original point cloud data, and taking the average of each of the above-mentioned point cloud slices as the point cloud center point of the above-mentioned point cloud slice, obtaining multiple target points, the above-mentioned target point being one of the points in the above-mentioned point cloud slice other than the above-mentioned point cloud center point, and according to the average of each of the above-mentioned point cloud slices The method comprises the following steps: fitting the center line of the lane of the point cloud slice corresponding to the point and each of the target points; constructing the coordinate system of each of the point cloud slices according to the lane center line, and projecting all the point clouds of the point cloud slices to a plane perpendicular to the lane center line to obtain a projected point cloud; performing rasterization processing on all the projected point clouds in the coordinate system of each of the point cloud slices to obtain a plurality of first grids, each of the first grids respectively including a plurality of first grids, and each of the first grids including a plurality of projected point clouds; determining the point cloud density of each of the first grids, and extracting the projected point clouds in the first grids according to the point cloud density of the first grids.

[0107] The present application also provides an electronic device, which includes one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include a method for executing any of the above-mentioned methods for extracting a roadway surface point cloud. By first slicing the point cloud into multiple point cloud slices, then obtaining the roadway centerline for each point cloud slice, and constructing a coordinate system, the point cloud density of each grid is calculated through rasterization processing, so that the subsequent extraction of the point cloud is more in line with the actual situation, thereby shortening the extraction time, thereby solving the problem of the long time required to extract the roadway surface point cloud in the existing solution.

[0108] Obviously, those skilled in the art will appreciate that the various modules or steps of the present invention described above can be implemented using a general-purpose computing device, can be centralized on a single computing device, or can be distributed across a network of multiple computing devices. They can be implemented using program code executable by the computing device, and thus, can be stored in a storage device and executed by the computing device. In some cases, the steps shown or described herein can be performed in a different order than that shown, or can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0109] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0110] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0111] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0112] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0113] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0114] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0115] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0116] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0117] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

[0118] 1) The method for extracting the tunnel surface point cloud of the present application first slices the point cloud into multiple point cloud slices, then obtains the tunnel centerline for each point cloud slice, and constructs a coordinate system. The point cloud density of each grid is calculated through rasterization processing, so that the subsequent extraction of the point cloud is more in line with the actual situation, thereby shortening the extraction time, thereby solving the problem of the long time required for extracting the tunnel surface point cloud in the existing scheme.

[0119] 2) The device for extracting the tunnel surface point cloud of the present application first slices the point cloud into multiple point cloud slices, then obtains the tunnel center line for each point cloud slice, and constructs a coordinate system. The point cloud density of each grid is calculated through rasterization processing, so that the subsequent extraction of the point cloud is more in line with the actual situation, thereby shortening the extraction time, thereby solving the problem of the long time required for extracting the tunnel surface point cloud in the existing scheme.

[0120] The above description is merely a preferred embodiment of the present application and is not intended to limit the present application. Various modifications and variations are possible for those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present application shall be included within the scope of protection of the present application.

Claims

1. A method for extracting point clouds from roadway surfaces, characterized in that: include: Acquiring original point cloud data, dividing the original point cloud data according to the curvature of the roadway surface of the original point cloud data to obtain multiple segments of long straight roadway point clouds; Performing equidistant slicing processing on each of the long straight roadway point clouds to obtain a plurality of point cloud slices corresponding to the original point cloud data, and taking the mean of each of the point cloud slices as the point cloud center point of the point cloud slice, obtaining a plurality of target points, each of the target points being one of the points in the point cloud slice other than the point cloud center point, and fitting the roadway center line of the corresponding point cloud slice based on each of the point cloud center points and each of the target points; Constructing a coordinate system of each point cloud slice according to the lane centerline, and projecting all point clouds of the point cloud slice onto a plane perpendicular to the lane centerline to obtain a projected point cloud; performing rasterization processing on all the projected point clouds in the coordinate system of each point cloud slice to obtain a plurality of first grids, each of the first grids comprising a plurality of first grids, each of which comprises a plurality of the projected point clouds; The point cloud density of each of the first grids is determined, and the projected point cloud in the first grid is extracted according to the point cloud density of the first grid.

2. The method according to claim 1, characterized in that Before dividing the original point cloud data according to the curvature of the roadway surface of the original point cloud data to obtain a plurality of long straight roadway point clouds, the method further includes: Determine a covariance matrix based on the original point cloud data; Determining three eigenvalues ​​of the covariance matrix according to the covariance matrix, and determining the curvature of the roadway surface according to the three eigenvalues; The original point cloud data is divided according to the curvature of the roadway surface of the original point cloud data to obtain multiple segments of long straight roadway point clouds, including: When the curvature of the roadway surface is greater than or equal to a curvature threshold, the original point cloud data is divided according to the curvature of the roadway surface to obtain multiple segments of the long straight roadway point cloud.

3. The method according to claim 2, characterized in that Determine the covariance matrix based on the original point cloud data, including: Determining the coordinates of a neighborhood point set of the original point cloud data according to the original point cloud data; according to Determine the covariance matrix, where C is the covariance matrix, p k is the coordinate of the neighborhood point set of the original point cloud data, O i is the centroid of the neighborhood point set, and k is the number of the neighborhood points.

4. The method according to claim 2, characterized in that Determining the curvature of the roadway surface according to the three characteristic values ​​includes: according to Determine the curvature of the roadway surface, where H is the curvature of the roadway surface, and λ0, λ1, and λ2 are the three eigenvalues ​​respectively.

5. The method according to claim 1, wherein Fitting the lane center line of the corresponding point cloud slice according to each point cloud center point and each target point includes: a connecting step: connecting the point cloud center point and the target point to obtain an initial center line, and obtaining a plurality of distance values, and determining a distance average value based on all the distance values, wherein the distance value is used to represent the distance between one of the points other than the point cloud center point and the target point in the point cloud slice and the initial center line; Determination step: Repeat the steps of obtaining the target point and the connecting line, and use the initial center line corresponding to the minimum value of the average distance as the center line of the lane.

6. The method according to claim 1, wherein Determining the point cloud density of each of the first grids includes: according to Determine the point cloud density of the first grid, where ρ is the point cloud density, L x , L y , L z are the lengths of the first grid in each direction respectively, and N is the total number of point clouds of the original point cloud data.

7. The method according to any one of claims 1 to 6, characterized in that Extracting the projected point cloud in the first grid according to the point cloud density of the first grid includes: When the point cloud density of the first grid is greater than or equal to a density threshold, extracting the projected point cloud in the first grid; When the point cloud density of the first grid is less than the density threshold, rasterizing all the projected point clouds in the coordinate system of each point cloud slice again with a grid size smaller than the first grid to obtain a plurality of second grids, each of the second grids including a plurality of second grids, and each of the second grids including a plurality of projected point clouds; The point cloud density of each second grid is determined again, and all the projected point clouds in the second grid are extracted according to the point cloud density of the second grid.

8. A device for extracting point clouds from a roadway surface, characterized in that: include: an acquisition unit, configured to acquire original point cloud data, and divide the original point cloud data according to the curvature of the roadway surface of the original point cloud data to obtain a plurality of long straight roadway point clouds; a first processing unit configured to perform equidistant slicing processing on each of the long straight roadway point clouds to obtain a plurality of point cloud slices corresponding to the original point cloud data, and to use the mean of each of the point cloud slices as the point cloud center point of the point cloud slice, to obtain a plurality of target points, each of the target points being one of the points in the point cloud slice other than the point cloud center point, and to fit the roadway center line of the corresponding point cloud slice based on each of the point cloud center points and each of the target points; a second processing unit, configured to construct a coordinate system of each of the point cloud slices according to the lane centerline, and project all point clouds of the point cloud slices onto a plane perpendicular to the lane centerline to obtain a projected point cloud; a third processing unit, configured to perform rasterization processing on all the projected point clouds in the coordinate system of each point cloud slice to obtain a plurality of first grids, each of the first grids comprising a plurality of first grids, each of which comprises a plurality of the projected point clouds; A determination unit is configured to determine a point cloud density of each of the first grids, and extract the projected point cloud in the first grid according to the point cloud density of the first grid.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the method for extracting the roadway surface point cloud according to any one of claims 1 to 7.

10. An electronic device, characterized in that: include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for executing the roadway surface point cloud extraction method according to any one of claims 1 to 7.

Images