Point cloud ground detection method, medium, equipment and device

Abstract

The present invention discloses a method, medium, equipment, and device for ground point cloud detection. The method comprises: obtaining a ground point cloud region and dividing the ground point cloud region into grids to obtain multiple point cloud grids; and iteratively calculating the point cloud data corresponding to each point cloud grid using an information filtering algorithm to determine the state parameters corresponding to the point cloud grid. This method can effectively detect complex ground environments, thereby improving the accuracy of ground point cloud extraction.

Description

Technical Field

[0001] The present application relates to the field of vehicle intelligent driving technology, and in particular to a point cloud ground detection method, medium, equipment and device. Background Art

[0002] Ground detection technology is a preprocessing technology commonly used in autonomous driving technology. It is used to extract the road portion from the point cloud data of the lidar and provide a geometric expression of the plane to facilitate subsequent pedestrian 3D detection and reduce the difficulty of subsequent point cloud data processing.

[0003] In related technologies, when performing ground detection, if the ground is in an abnormal section (for example, an uneven section, or a sloping section of a bridge, etc.), the detection result will have a large deviation. Summary of the Invention

[0004] The present invention aims to solve at least one of the technical problems in the related art to a certain extent. To this end, one object of the present invention is to propose a point cloud ground detection method that can effectively detect complex ground environments and thereby improve the accuracy of ground point cloud extraction.

[0005] According to an embodiment of the present invention, the point cloud ground detection method includes: obtaining a ground point cloud area and gridding the ground point cloud area to obtain multiple point cloud grids; iteratively calculating the point cloud data corresponding to each of the point cloud grids through an information filtering algorithm to determine the state parameters corresponding to the point cloud grid.

[0006] According to the point cloud ground detection method of an embodiment of the present invention, first, a ground point cloud area is obtained, and the ground point cloud area is grid-divided to obtain a plurality of point cloud grids; then, the point cloud data corresponding to each of the point cloud grids is iteratively calculated through an information filtering algorithm to determine the state parameters corresponding to the point cloud grid; thereby achieving effective detection of complex ground environments and improving the accuracy of ground point cloud extraction.

[0007] In some embodiments, the point cloud data corresponding to each of the point cloud grids is iteratively calculated through an information filtering algorithm, including: determining whether the number of current iterative calculations is less than a preset iteration threshold; if not, outputting the state parameters corresponding to the point cloud grid; if yes, continuing to iteratively calculate the point cloud data corresponding to each of the point cloud grids.

[0008] In some embodiments, the point cloud data corresponding to each of the point cloud grids is iteratively calculated through an information filtering algorithm to determine the state parameters corresponding to the point cloud grid, including: iteratively calculating the point cloud data corresponding to each of the point cloud grids through an information filtering algorithm to obtain the point cloud information, surrounding grid information and previous frame grid information corresponding to the point cloud grid, wherein the point cloud information includes a point cloud information vector and a point cloud information matrix, the surrounding grid information includes a surrounding grid information vector and a surrounding grid information matrix, and the previous frame grid information includes a previous frame grid information vector and a previous frame grid information matrix; summing the point cloud information vector, the surrounding grid information vector and the previous frame grid information vector to obtain a first summation result; summing the point cloud information matrix, the surrounding grid information matrix and the previous frame grid information matrix to obtain a second summation result; and calculating the state parameters based on the first summation result and the second summation result.

[0009] In some embodiments, the state parameters include: a height value, an X-direction slope, and a Y-direction slope.

[0010] In some embodiments, the point cloud information vector and the point cloud information matrix are calculated using the following formula:

[0011]

[0012]

[0013]

[0014] H ij =[1,x i -nx,y i -ny]

[0015]

[0016] Among them, ξ lidar represents the point cloud information vector, α represents the weight of the point cloud information vector, P represents the number of point clouds in the point cloud grid, c j Represents the weight of the point under Gaussian distribution, z j Indicates the height of the point, represents the transpose of the transfer matrix of a point relative to the center of the grid, Indicates the height difference between the point and the predicted ground, H ij represents the transfer matrix of the point relative to the center of the grid, X i represents the information matrix used in each iteration, dz represents the height of the point from the predicted point, σ represents the variance of the set ground point, x i Indicates the x-coordinate of the point, x represents the x-coordinate of the grid center, yi represents the y-coordinate of the point, y represents the y-coordinate of the center of the grid, and n represents the slope of the point cloud grid. Represents the point cloud information matrix.

[0017] In some embodiments, the surrounding grid information vector and the surrounding grid information matrix are calculated using the following formula:

[0018]

[0019] β=0.8

[0020]

[0021]

[0022] Among them, ξ ground Represents the surrounding point cloud grid information vector, β represents the weight of the point cloud grid information vector, G represents the number of grids around the point cloud grid, represents the transpose of the transfer matrix of the surrounding grid relative to the central grid, ξ j represents the grid information vector, represents the surrounding grid information matrix, F ij Represents the transfer matrix of the surrounding grid relative to the central grid, nx i Indicates the center grid x coordinate, nx j Indicates the x coordinate of the surrounding grid, ny i Indicates the center grid y coordinate, ny j Indicates the y coordinate of the surrounding grid.

[0023] In some embodiments, the previous frame grid information vector and the previous frame grid information matrix are calculated using the following formula:

[0024]

[0025] γ=0.5

[0026]

[0027]

[0028] Among them, ξ last represents the grid information vector of the previous frame, γ represents the weight of the time information vector, represents the transpose of the time transfer matrix, represents the time information vector, Represents the grid information matrix of the previous frame, Q i represents the time transfer matrix.

[0029] In a second aspect, an embodiment of the present invention proposes a computer-readable storage medium on which a point cloud ground detection program is stored. When the point cloud ground detection program is executed by a processor, the point cloud ground detection method as described above is implemented.

[0030] According to the computer-readable storage medium of an embodiment of the present invention, by storing a point cloud ground detection program, the processor implements the point cloud ground detection method as described above when executing the point cloud ground detection program, thereby achieving effective detection of complex ground environments and improving the accuracy of ground point cloud extraction.

[0031] In a third aspect, an embodiment of the present invention proposes a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the point cloud ground detection method described above is implemented.

[0032] According to the computer device of an embodiment of the present invention, the point cloud ground detection program is stored in the memory, so that when the processor executes the point cloud ground detection program, it implements the point cloud ground detection method as described above, thereby achieving effective detection of complex ground environments and improving the accuracy of ground point cloud extraction.

[0033] In the fourth aspect, an embodiment of the present invention proposes a point cloud ground detection device, including: a grid division module, which is used to obtain a ground point cloud area and grid the ground point cloud area to obtain multiple point cloud grids; a calculation module, which is used to iteratively calculate the point cloud data corresponding to each point cloud grid through an information filtering algorithm to determine the state parameters corresponding to the point cloud grid.

[0034] According to the point cloud ground detection device of an embodiment of the present invention, a grid division module is set to obtain a ground point cloud area, and the ground point cloud area is grid-divided to obtain a plurality of point cloud grids; the calculation module is used to iteratively calculate the point cloud data corresponding to each of the point cloud grids through an information filtering algorithm to determine the state parameters corresponding to the point cloud grid; thereby achieving effective detection of complex ground environments and improving the accuracy of ground point cloud extraction.

[0035] Additional aspects and advantages of the present invention will be set forth in part in the description which follows and, in part, will be obvious from the description which follows, or may be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 is a schematic flow chart of a point cloud detection method according to an embodiment of the present invention;

[0037] Figure 2 2. It is a schematic diagram of a point cloud mesh iterative calculation process according to an embodiment of the present invention;

[0038] Figure 3 is a schematic diagram of ground detection results according to an embodiment of the present invention;

[0039] Figure 4 is a block diagram of a computer device according to an embodiment of the present invention;

[0040] Figure 5 4 is a block diagram of a point cloud detection device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0041] The following describes embodiments of the present invention in detail, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and are not to be construed as limiting the present invention.

[0042] The point cloud ground detection method according to an embodiment of the present invention will be described below with reference to the accompanying drawings.

[0043] See also Figure 1 , Figure 1 FIG. 1 is a flow chart of a point cloud ground detection method according to an embodiment of the present invention. Figure 1 As shown, the point cloud ground detection method includes the following steps:

[0044] S101: Acquire a ground point cloud and perform grid division on the ground point cloud to obtain a plurality of point cloud grids.

[0045] That is, after acquiring the three-dimensional point cloud, the ground point cloud region in the three-dimensional point cloud is extracted, and the ground point cloud region is meshed to obtain a plurality of point cloud meshes.

[0046] As an example, first, a region of interest is set, and the three-dimensional point cloud data outside the region of interest is removed according to the region of interest; then, the region of interest is divided according to a preset size (for example, 1m*1m) to obtain multiple point cloud grids; then, the sub-laser point cloud O corresponding to each grid is recorded separately.

[0047] S102 , performing iterative calculation on the ground point cloud corresponding to each point cloud grid using an information filtering algorithm to determine the state parameters corresponding to the point cloud grid.

[0048] In some embodiments, the point cloud data corresponding to each point cloud grid is iteratively calculated through an information filtering algorithm, including: determining whether the number of current iterative calculations is less than a preset iteration threshold; if not, outputting the state parameters corresponding to the point cloud grid; if yes, continuing to iteratively calculate the point cloud data corresponding to each point cloud grid.

[0049] That is to say, the number of iterations is preset. If the number of iterations reaches the preset number of iterations, the state parameters used to describe the point cloud mesh are directly output; if the number of iterations has not reached the preset number of iterations, the point cloud data corresponding to the point cloud mesh is continued to be iteratively calculated.

[0050] In some embodiments, the state parameters include: a height value, an X-direction slope, and a Y-direction slope.

[0051] In some embodiments, the point cloud data corresponding to each point cloud grid is iteratively calculated through an information filtering algorithm to determine the state parameters corresponding to the point cloud grid, including: iteratively calculating the point cloud data corresponding to each point cloud grid through an information filtering algorithm to obtain the point cloud information, surrounding grid information and previous frame grid information corresponding to the point cloud grid, wherein the point cloud information includes a point cloud information vector and a point cloud information matrix, the surrounding grid information includes a surrounding grid information vector and a surrounding grid information matrix, and the previous frame grid information includes a previous frame grid information vector and a previous frame grid information matrix; summing the point cloud information vector, the surrounding grid information vector and the previous frame grid information vector to obtain a first summation result; summing the point cloud information matrix, the surrounding grid information matrix and the previous frame grid information matrix to obtain a second summation result; and calculating the state parameters based on the first summation result and the second summation result.

[0052] In some embodiments, the point cloud information vector and the point cloud information matrix are calculated using the following formulas:

[0053]

[0054] d zj =z i -H ij X i

[0055]

[0056] H ij =[1,x i -nx,y i -ny]

[0057]

[0058] Among them, ξ lidar represents the point cloud information vector, α represents the weight of the point cloud information vector, P represents the number of point clouds in the point cloud grid, c j Represents the weight of the point under Gaussian distribution, z j Indicates the height of the point, represents the transpose of the transfer matrix of a point relative to the center of the grid, Indicates the height difference between the point and the predicted ground, Hij represents the transfer matrix of the point relative to the center of the grid, X i represents the information matrix used in each iteration, dz represents the height of the point from the predicted point, σ represents the variance of the set ground point, x i Indicates the x-coordinate of the point, x represents the x-coordinate of the grid center, y i represents the y-coordinate of the point, y represents the y-coordinate of the center of the grid, and n represents the slope of the point cloud grid. Represents the point cloud information matrix.

[0059] In some embodiments, the surrounding grid information vector and the surrounding grid information matrix are calculated using the following formulas:

[0060]

[0061] β=0.8

[0062]

[0063]

[0064] Among them, ξ ground Represents the surrounding point cloud grid information vector, β represents the weight of the point cloud grid information vector, G represents the number of grids around the point cloud grid, represents the transpose of the transfer matrix of the surrounding grid relative to the central grid, ξ j represents the grid information vector, represents the surrounding grid information matrix, F ij Represents the transfer matrix of the surrounding grid relative to the central grid, nx i Indicates the center grid x coordinate, nx j Indicates the x coordinate of the surrounding grid, ny i Indicates the center grid y coordinate, ny j Indicates the y coordinate of the surrounding grid.

[0065] In some embodiments, the previous frame grid information vector and the previous frame grid information matrix are calculated using the following formula:

[0066]

[0067] γ=0.5

[0068]

[0069]

[0070] Among them, ξ last represents the grid information vector of the previous frame, γ represents the weight of the time information vector, represents the transpose of the time transfer matrix, represents the time information vector, Represents the grid information matrix of the previous frame, Q i represents the time transfer matrix.

[0071] In some embodiments, for each sub-point cloud O corresponding to a point cloud grid, five corresponding parameters (h, dx, dy, nx, ny) are set; where h represents the height of the ground of the point cloud grid, dx represents the slope in the x-direction, dy represents the slope in the y-direction, and (nx, ny) represents the position of the center point of the point cloud grid relative to the coordinate origin. The ground parameters are affected by three state parameters (point cloud information, surrounding grid information, and previous frame grid information). Using the information filtering algorithm, after n iterations, we obtain:

[0072] The point cloud information vector is

[0073] Among them, d zj =z i -H ij X i

[0074]

[0075] H ij =[1,x i -nx,y i -ny], α=1

[0076] The point cloud information matrix is

[0077] The surrounding grid information vector is:

[0078] The surrounding grid information matrix is:

[0079] The first transfer matrix is:

[0080] The previous frame grid information vector (that is, the previous frame information vector of the current point cloud grid) is: γ = 0.5;

[0081] The grid information matrix of the previous frame is:

[0082] The second transfer matrix is:

[0083] Next, perform the summation:

[0084] The first summation result is: ξ=ξ lidar +ξ ground +ξ last

[0085]

[0086] [h new nx new ny new ]=∑ξ

[0087] As a specific embodiment of the present invention, Figure 2 As shown, for each point cloud mesh, the iterative calculation process includes the following steps:

[0088] S201, obtaining point cloud data of a point cloud grid.

[0089] S202, determine whether the current number of iterations is less than the preset number of iterations; if not, execute step S203; if yes, execute step S204.

[0090] S203: Output the state parameters corresponding to the point cloud mesh.

[0091] S204 , respectively calculating the point cloud information vector, the point cloud information matrix, the surrounding grid information vector, the surrounding grid information matrix, the previous frame grid information vector, and the previous frame grid information matrix.

[0092] S205 , performing a summation operation on the point cloud information vector, the surrounding grid information vector, and the previous frame grid information vector to obtain a first summation result.

[0093] S206 , performing a summation operation on the point cloud information matrix, the surrounding grid information matrix, and the previous frame grid information matrix to obtain a second summation result.

[0094] S207: Calculate a state parameter according to the first summation result and the second summation result.

[0095] To better illustrate, Figure 3 As shown, Figure 3 Schematic diagram of the final result obtained by the point cloud ground detection method proposed in an embodiment of the present invention.

[0096] To sum up, according to the point cloud ground detection method of an embodiment of the present invention, first, a ground point cloud area is obtained, and the ground point cloud area is grid-divided to obtain a plurality of point cloud grids; then, the point cloud data corresponding to each of the point cloud grids is iteratively calculated through an information filtering algorithm to determine the state parameters corresponding to the point cloud grid; thereby achieving effective detection of complex ground environments and improving the accuracy of ground point cloud extraction.

[0097] In order to implement the above embodiment, an embodiment of the present invention proposes a computer-readable storage medium, which stores a point cloud ground detection program. When the point cloud ground detection program is executed by a processor, the point cloud ground detection method as described above is implemented.

[0098] According to the computer-readable storage medium of an embodiment of the present invention, by storing a point cloud ground detection program, the processor implements the point cloud ground detection method as described above when executing the point cloud ground detection program, thereby achieving effective detection of complex ground environments and improving the accuracy of ground point cloud extraction.

[0099] In order to implement the above embodiment, the embodiment of the present invention provides a computer device, such as Figure 4 As shown, the computer device 400 includes a memory 401, a processor 402, and a computer program stored in the memory 401 and executable on the processor 402. When the processor 402 executes the program, the above-mentioned point cloud ground detection method is implemented.

[0100] According to the computer device of an embodiment of the present invention, the point cloud ground detection program is stored in the memory, so that when the processor executes the point cloud ground detection program, it implements the point cloud ground detection method as described above, thereby achieving effective detection of complex ground environments and improving the accuracy of ground point cloud extraction.

[0101] In order to implement the above embodiment, the present invention proposes a point cloud ground detection device, such as Figure 5 As shown, the point cloud ground detection device includes: a grid division module 10 and a calculation module 20.

[0102] The grid division module 10 is used to obtain a ground point cloud area and perform grid division on the ground point cloud area to obtain a plurality of point cloud grids;

[0103] The calculation module 20 is used to perform iterative calculations on the point cloud data corresponding to each point cloud grid through an information filtering algorithm to determine the state parameters corresponding to the point cloud grid.

[0104] In some embodiments, the calculation module 20 is also used to determine whether the number of current iterative calculations is less than a preset iteration threshold; if not, output the state parameters corresponding to the point cloud grid; if yes, continue to iterate the point cloud data corresponding to each point cloud grid.

[0105] In some embodiments, the calculation module 20 is also used to iteratively calculate the point cloud data corresponding to each of the point cloud grids through an information filtering algorithm to obtain the point cloud information, surrounding grid information and previous frame grid information corresponding to the point cloud grid, wherein the point cloud information includes a point cloud information vector and a point cloud information matrix, the surrounding grid information includes a surrounding grid information vector and a surrounding grid information matrix, and the previous frame grid information includes a previous frame grid information vector and a previous frame grid information matrix; performing a summation operation on the point cloud information vector, the surrounding grid information vector and the previous frame grid information vector to obtain a first summation result; performing a summation operation on the point cloud information matrix, the surrounding grid information matrix and the previous frame grid information matrix to obtain a second summation result; and calculating the state parameter based on the first summation result and the second summation result.

[0106] In some embodiments, the state parameters include: a height value, an X-direction slope, and a Y-direction slope.

[0107] In some embodiments, the point cloud information vector and the point cloud information matrix are calculated using the following formula:

[0108]

[0109]

[0110]

[0111] H ij =[1,x i -nx,y i -ny]

[0112]

[0113] Among them, ξ lidar represents the point cloud information vector, α represents the weight of the point cloud information vector, P represents the number of point clouds in the point cloud grid, c j Represents the weight of the point under Gaussian distribution, z j Indicates the height of the point, represents the transpose of the transfer matrix of a point relative to the center of the grid, Indicates the height difference between the point and the predicted ground, H ij represents the transfer matrix of the point relative to the center of the grid, X i represents the information matrix used in each iteration, dz represents the height of the point from the predicted point, σ represents the variance of the set ground point, x i Indicates the x-coordinate of the point, x represents the x-coordinate of the grid center, y i represents the y-coordinate of the point, y represents the y-coordinate of the center of the grid, and n represents the slope of the point cloud grid. Represents the point cloud information matrix.

[0114] In some embodiments, the surrounding grid information vector and the surrounding grid information matrix are calculated using the following formula:

[0115]

[0116] β=0.8

[0117]

[0118]

[0119] Among them, ξ ground Represents the surrounding point cloud grid information vector, β represents the weight of the point cloud grid information vector, G represents the number of grids around the point cloud grid, represents the transpose of the transfer matrix of the surrounding grid relative to the central grid, ξ j represents the grid information vector, represents the surrounding grid information matrix, F ij Represents the transfer matrix of the surrounding grid relative to the central grid, nx i Indicates the center grid x coordinate, nx j Indicates the x coordinate of the surrounding grid, ny i Indicates the center grid y coordinate, ny j Indicates the y coordinate of the surrounding grid.

[0120] In some embodiments, the previous frame grid information vector and the previous frame grid information matrix are calculated using the following formula:

[0121]

[0122] γ=0.5

[0123]

[0124]

[0125] Among them, ξ last represents the grid information vector of the previous frame, γ represents the weight of the time information vector, represents the transpose of the time transfer matrix, represents the time information vector, Represents the grid information matrix of the previous frame, Q i represents the time transfer matrix.

[0126] It should be noted that the above description of the point cloud ground detection method is also applicable to the point cloud ground detection device and will not be repeated here.

[0127] In summary, according to the point cloud ground detection device of an embodiment of the present invention, a grid division module is set to obtain a ground point cloud area, and the ground point cloud area is grid-divided to obtain multiple point cloud grids; the calculation module is used to iteratively calculate the point cloud data corresponding to each of the point cloud grids through an information filtering algorithm to determine the state parameters corresponding to the point cloud grid; thereby achieving effective detection of complex ground environments and improving the accuracy of ground point cloud extraction.

[0128] It should be noted that the logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device), or in conjunction with such instruction execution system, apparatus, or device. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transmit a program for use by an instruction execution system, apparatus, or device, or in conjunction with such instruction execution system, apparatus, or device. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection portion having one or more wires (electronic device), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and portable compact disc read-only memory (CDROM). Furthermore, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing it in another suitable manner if necessary, and then storing it in a computer memory.

[0129] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0130] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that a specific feature, structure, material, or characteristic described in conjunction with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0131] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like to indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0132] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "plurality" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0133] In the present invention, unless otherwise specified or limited, the terms "installed," "connected," "connect," "fixed," etc. should be understood in a broad sense. For example, they can refer to fixed connection, detachable connection, or integration; mechanical connection, electrical connection; direct connection, or indirect connection through an intermediate medium; internal communication between two components, or interaction between two components, unless otherwise specified. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0134] In the present invention, unless otherwise expressly specified or limited, when a first feature is "above" or "below" a second feature, it may mean that the first and second features are in direct contact, or that the first and second features are in indirect contact through an intermediary. Furthermore, when a first feature is "above," "above," or "above" a second feature, it may mean that the first feature is directly above or diagonally above the second feature, or simply means that the first feature is at a higher level than the second feature. When a first feature is "below," "below," or "below" a second feature, it may mean that the first feature is directly below or diagonally below the second feature, or simply means that the first feature is at a lower level than the second feature.

[0135] Although the embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and are not to be construed as limitations on the present invention. A person skilled in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A point cloud ground detection method, characterized in that: include: Acquire a ground point cloud area, and perform grid division on the ground point cloud area to obtain a plurality of point cloud grids; Performing iterative calculations on the point cloud data corresponding to each point cloud grid using an information filtering algorithm to determine the state parameters corresponding to the point cloud grid; Performing iterative calculations on the point cloud data corresponding to each point cloud grid using an information filtering algorithm to determine the state parameters corresponding to the point cloud grid, including: Iteratively calculating the point cloud data corresponding to each point cloud grid through an information filtering algorithm to obtain point cloud information, surrounding grid information, and previous frame grid information corresponding to the point cloud grid, wherein the point cloud information includes a point cloud information vector and a point cloud information matrix, the surrounding grid information includes a surrounding grid information vector and a surrounding grid information matrix, and the previous frame grid information includes a previous frame grid information vector and a previous frame grid information matrix; Performing a summation operation on the point cloud information vector, the surrounding grid information vector, and the previous frame grid information vector to obtain a first summation result; Performing a summation operation on the point cloud information matrix, the surrounding grid information matrix, and the previous frame grid information matrix to obtain a second summation result; The state parameter is calculated according to the first summation result and the second summation result.

2. The point cloud ground detection method according to claim 1, characterized in that: The point cloud data corresponding to each point cloud grid is iteratively calculated using an information filtering algorithm, including: Determine whether the current number of iterative calculations is less than a preset iteration threshold; If not, output the state parameters corresponding to the point cloud mesh; If yes, continue to iteratively calculate the point cloud data corresponding to each point cloud grid.

3. The point cloud ground detection method according to claim 1, characterized in that: The state parameters include: height value, X-direction slope and Y-direction slope.

4. The point cloud ground detection method according to claim 1, characterized in that: The point cloud information vector and the point cloud information matrix are calculated using the following formula: in, Represents the point cloud information vector, Represents the weight of the point cloud information vector, represents the number of point clouds in the point cloud grid, represents the weight of the point under Gaussian distribution, Indicates the height of the point, represents the transpose of the transfer matrix of a point relative to the center of the grid, Indicates the height difference between the point and the predicted ground, represents the transfer matrix of the point relative to the center of the grid, represents the information matrix used in each iteration, Indicates the height of the point from the predicted point. Represents the variance of the set ground points, Represents the x-coordinate of the point, x represents the x-coordinate of the grid center, Indicates the y-coordinate of the point, represents the y coordinate of the center of the grid, represents the slope of the point cloud mesh, Represents the point cloud information matrix.

5. The point cloud ground detection method according to claim 1, characterized in that: The surrounding grid information vector and the surrounding grid information matrix are calculated using the following formula: in, Represents the surrounding point cloud grid information vector, represents the weight of the point cloud mesh information vector, Indicates the number of surrounding grids of the point cloud grid, represents the transpose of the transfer matrix of the surrounding grid relative to the central grid, represents the grid information vector, represents the surrounding grid information matrix, represents the transfer matrix of the surrounding grid relative to the central grid, represents the center grid x coordinate, represents the x-coordinate of the surrounding grid, represents the center grid y coordinate, Indicates the y coordinate of the surrounding grid.

6. The point cloud ground detection method according to claim 1, characterized in that: The previous frame grid information vector and the previous frame grid information matrix are calculated using the following formula: in, Represents the grid information vector of the previous frame, represents the weight of the time information vector, represents the transpose of the time transfer matrix, represents the time information vector, Represents the grid information matrix of the previous frame, represents the time transfer matrix.

7. A computer-readable storage medium, characterized in that A point cloud ground detection program is stored thereon, and when the point cloud ground detection program is executed by a processor, the point cloud ground detection method according to any one of claims 1 to 6 is implemented.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the point cloud ground detection method according to any one of claims 1 to 6 is implemented.

9. A point cloud ground detection device, characterized in that: include: A grid division module, the grid division module is used to obtain a ground point cloud area and perform grid division on the ground point cloud area to obtain a plurality of point cloud grids; A calculation module, configured to perform iterative calculations on the point cloud data corresponding to each point cloud grid using an information filtering algorithm to determine a state parameter corresponding to the point cloud grid; Performing iterative calculations on the point cloud data corresponding to each point cloud grid using an information filtering algorithm to determine the state parameters corresponding to the point cloud grid, including: Iteratively calculating the point cloud data corresponding to each point cloud grid through an information filtering algorithm to obtain point cloud information, surrounding grid information, and previous frame grid information corresponding to the point cloud grid, wherein the point cloud information includes a point cloud information vector and a point cloud information matrix, the surrounding grid information includes a surrounding grid information vector and a surrounding grid information matrix, and the previous frame grid information includes a previous frame grid information vector and a previous frame grid information matrix; Performing a summation operation on the point cloud information vector, the surrounding grid information vector, and the previous frame grid information vector to obtain a first summation result; Performing a summation operation on the point cloud information matrix, the surrounding grid information matrix, and the previous frame grid information matrix to obtain a second summation result; The state parameter is calculated according to the first summation result and the second summation result.

Images