Laser scanning point category detection method, device and terminal equipment

Abstract

The present application is applicable to the field of computer vision technology, and provides a method, apparatus and terminal device for detecting the category of laser scanning points, including: obtaining a set of scanning points to be detected, wherein the set of scanning points to be detected includes scanning points obtained by each target beam of the laser radar detecting an object at a time point, and selecting scanning points corresponding to two adjacent target beams from the set of scanning points to be detected in turn according to the positional relationship between each target beam, as the current scanning point and the next scanning point, and then determining the ground reference point according to the height of the laser radar from the ground and the coordinate information of the current scanning point and the next scanning point in a preset three-dimensional coordinate system, and then determining the category to which the current scanning point and the next scanning point belong according to the positional relationship between the current scanning point and the next scanning point and the ground reference point, thereby improving the ground point detection result.

Description

Technical Field

[0001] The present application belongs to the field of computer vision technology, and in particular relates to a method, apparatus, terminal device, and computer-readable storage medium for detecting the category of laser scanning points. Background Art

[0002] In the semantic perception algorithm based on lidar, the ground point detection algorithm provides preprocessing for the subsequent drivable area and clustering algorithms. The ground point detection algorithm can simplify the processing flow of subsequent algorithms on point clouds and reduce the difficulty of problem handling.

[0003] In related technologies, some ground point detection methods utilize the characteristics of lidar scanning. For fixed-installation locations of the lidar, only certain beams will hit the ground. The angles of adjacent beams at the same angle are calculated to determine whether they are ground points. This can easily lead to inaccurate ground point detection results when the current beam and the next beam both hit the top plane of the same object at the same time, or when there is a slope on the top of the target. Summary of the Invention

[0004] The embodiments of the present application provide a target point category detection method, apparatus, terminal device and computer-readable storage medium, which can solve the problem of inaccurate ground point detection results when the current harness and the next harness are both hit on the top plane of the same object, or there is a slope on the top of the target.

[0005] In a first aspect, an embodiment of the present application provides a method for detecting a category of a laser scanning point, comprising:

[0006] Obtain a set of scanning points to be detected, wherein the set of scanning points to be detected includes scanning points obtained by each target beam of the laser radar when detecting an object at a time point; according to the positional relationship between each of the target beams, select scanning points corresponding to two adjacent target beams from the set of scanning points to be detected in turn as the current scanning point and the next scanning point; determine the ground reference point according to the height of the laser radar from the ground and the coordinate information of the current scanning point and the next scanning point in a preset three-dimensional coordinate system, wherein the preset three-dimensional coordinate system is determined according to the position of the laser radar; determine the categories to which the current scanning point and the next scanning point belong according to the positional relationship between the current scanning point and the next scanning point and the ground reference point, respectively.

[0007] In a second aspect, an embodiment of the present application provides a device for detecting a type of a laser scanning point, comprising:

[0008] A scanning point acquisition module is used to obtain a set of scanning points to be detected, wherein the set of scanning points to be detected includes scanning points obtained by each target beam of the laser radar when detecting an object at a time point; a scanning point selection module is used to select scanning points corresponding to two adjacent target beams from the set of scanning points to be detected in turn according to the positional relationship between each of the target beams, as the current scanning point and the next scanning point; a reference point determination module is used to determine the ground reference point according to the height of the laser radar from the ground and the coordinate information of the current scanning point and the next scanning point in a preset three-dimensional coordinate system, wherein the preset three-dimensional coordinate system is determined according to the position of the laser radar; a category analysis module is used to determine the category to which the current scanning point and the next scanning point belong according to the positional relationship between the current scanning point and the next scanning point and the ground reference point respectively.

[0009] In a third aspect, an embodiment of the present application provides a terminal 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 computer program, the method for detecting the category of the laser scanning points described in any one of the first aspects above is implemented.

[0010] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the laser scanning point category detection method described in any one of the first aspects above.

[0011] In a fifth aspect, an embodiment of the present application provides a computer program product. When the computer program product is run on a terminal device, the terminal device executes the laser scanning point category detection method described in any one of the first aspects above.

[0012] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here.

[0013] Compared with the prior art, the embodiments of the present application have the following advantages: by obtaining a set of scan points to be detected, wherein the set of scan points to be detected includes scan points obtained by each target beam of a laser radar detecting an object at a time point, and selecting scan points corresponding to two adjacent target beams from the set of scan points to be detected according to the positional relationship between each target beam, as the current scan point and the next scan point, and then determining a ground reference point according to the height of the laser radar from the ground and the coordinate information of the current scan point and the next scan point in a preset three-dimensional coordinate system, and then determining the category of the current scan point and the next scan point according to the positional relationship between the current scan point and the next scan point and the ground reference point. Thus, by determining the ground reference point according to the height of the laser radar from the ground and the coordinate information of the current scan point and the next scan point in the preset three-dimensional coordinate system, the ground reference point can be brought closer to the ground, and then, using the ground reference point as a reference, and determining the category of the current scan point and the next scan point according to the positional relationship between the current scan point and the next scan point and the ground reference point, the category of the current scan point and the next scan point can be more accurately determined, thereby improving the ground point detection result. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0015] Figure 1 1 is a flow chart of a method for detecting the type of laser scanning points provided in one embodiment of the present application;

[0016] Figure 2 This is a schematic diagram of a scene in which a partial beam of a laser radar according to an embodiment of the present application detects the ground;

[0017] Figure 3 is a flow chart of a method for detecting the type of laser scanning points provided in another embodiment of the present application;

[0018] Figure 4 This is a schematic diagram showing that the current scanning point and the next scanning point are ground points in one embodiment of the present application;

[0019] Figure 5 is a schematic diagram showing that the current scanning point and the next scanning point belong to convex points in one embodiment of the present application;

[0020] Figure 6 This is a schematic diagram showing that the current scanning point and the next scanning point are concave points in one embodiment of the present application;

[0021] Figure 7 This is a schematic diagram of an embodiment of the present application in which the current scanning point is a convex point and the next scanning point is a concave point;

[0022] Figure 8 This is a schematic diagram of an embodiment of the present application in which the current scanning point is a concave point and the next scanning point is a convex point;

[0023] Figure 9 This is a schematic diagram of an embodiment of the present application in which the current scanning point is a ground point and the next scanning point is a raised point;

[0024] Figure 10 This is a schematic diagram of an embodiment of the present application in which the current scanning point is a raised point and the next scanning point is a ground point;

[0025] Figure 11 is a schematic diagram of an embodiment of the present application in which the current scanning point and the next scanning point are convex points;

[0026] Figure 12 This is a schematic diagram of an embodiment of the present application in which the current scanning point is a ground point and the next scanning point is a depression point;

[0027] Figure 13 This is a schematic diagram of an embodiment of the present application in which the current scanning point is a sunken point and the next scanning point is a ground point;

[0028] Figure 14 is a schematic diagram of an embodiment of the present application in which the current scanning point and the next scanning point are recessed points;

[0029] Figure 15 is a structural diagram of a laser scanning point category detection device provided by another embodiment of the present application;

[0030] Figure 16 It is a structural diagram of the terminal device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0031] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.

[0032] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0033] It will also be understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0034] As used in this specification and the appended claims, the term "if" can be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0035] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0036] References to "one embodiment" or "some embodiments" in this specification mean that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in one or more embodiments of the present application. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more but not all embodiments," unless otherwise specifically emphasized. The terms "including," "comprising," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0037] It should be understood that the size of the serial numbers of each step in this embodiment does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of this application.

[0038] In related technologies, some ground point detection methods utilize the characteristics of lidar scanning. For fixed-installation locations of the lidar, only certain beams will hit the ground. The angles of adjacent beams at the same angle are calculated to determine whether they are ground points. This can easily lead to inaccurate ground point detection results when the current beam and the next beam both hit the top plane of the same object at the same time, or when there is a slope on the top of the target.

[0039] The present application provides a method for detecting the category of a laser scanning point, which obtains a set of scanning points to be detected, wherein the set of scanning points to be detected includes scanning points obtained by each target beam of a laser radar detecting an object at a time point, and selects scanning points corresponding to two adjacent target beams from the set of scanning points to be detected according to the positional relationship between each target beam, as the current scanning point and the next scanning point. Then, a ground reference point is determined according to the height of the laser radar from the ground and the coordinate information of the current scanning point and the next scanning point in a preset three-dimensional coordinate system, and then the category of the current scanning point and the next scanning point is determined according to the positional relationship between the current scanning point and the next scanning point and the ground reference point. Thus, by determining the ground reference point according to the height of the laser radar from the ground and the coordinate information of the current scanning point and the next scanning point in the preset three-dimensional coordinate system, the ground reference point can be brought closer to the ground, and then, using the ground reference point as a reference, and determining the category of the current scanning point and the next scanning point according to the positional relationship between the current scanning point and the next scanning point and the ground reference point, the category of the current scanning point and the next scanning point can be more accurately determined, thereby improving the ground point detection result.

[0040] The laser scanning point category detection method provided in this application can be executed by a terminal device or a server. To illustrate the technical solution of this application, this method uses a terminal device as an example to illustrate the implementation process of the laser scanning point category detection method provided in this embodiment.

[0041] In one embodiment, referring to Figure 1 , provides a method for detecting the category of laser scanning points, as an example but not as a limitation, such as Figure 1 As shown, the laser scanning point category detection method may include the following steps:

[0042] Step 101 : obtaining a set of scanning points to be detected, wherein the set of scanning points to be detected includes scanning points obtained by each target beam of the laser radar detecting an object at a time point.

[0043] Among them, the laser radar can be a laser rotating ranging radar that simultaneously transmits and receives multiple laser beams. The laser radar can be 4-line, 8-line, 16-line, 32-line, 64-line, 128-line, etc.

[0044] The target beam can be any beam arranged vertically along the LiDAR that has a negative angle with the horizontal. With the LiDAR as the vertex of the angle and the horizontal as the starting point, counterclockwise rotation is positive and clockwise rotation is negative. The angle is the angle formed by rotating the beams clockwise around the horizontal line. The horizontal line can be a line parallel to the ground in the LiDAR's forward direction. Beams with negative angles with the horizontal line are most likely to detect the ground, so detection is limited to beams with negative angles with the horizontal line, improving detection efficiency.

[0045] Herein, a time point can be any time point when the laser radar is rotating to detect an object.

[0046] In this embodiment, the laser radar can be a multi-beam laser radar. In a laser radar scanning scene, refer to Figure 2 Schematic diagram of a scene in which part of the beam of the laser radar 10 detects the ground 30. Each beam of the laser radar 10 scans the ground at a point in time to obtain the three-dimensional coordinates of the ground reflection point. Each ground reflection point is distributed in the three-dimensional coordinate system in the form of a point according to the three-dimensional coordinates. The ground reflection point is the scanning point, and the set of scanning points is the set of scanning points to be detected.

[0047] It should be noted that the laser scanning point category detection method of the embodiment of the present application can be applied to any scenario using a laser radar for environmental perception, and the set of scanning points captured by the laser radar in any scenario at any time can be determined as the set of scanning points to be detected, so as to perform real-time analysis of the scanning points captured by the laser radar. For example, the laser scanning point category detection method of the embodiment of the present application can be applied in an autonomous driving algorithm to detect the category of scanning points captured by a laser radar installed in an autonomous driving vehicle.

[0048] Among them, the three-dimensional coordinate system can be a three-dimensional coordinate system constructed with the position of the laser radar 10 as the coordinate origin O, the positive direction of the Y axis as the forward direction of the laser radar detection, the positive direction of the X axis to the right of the forward direction of the laser radar detection, and the direction indicated by the thumb as the positive direction of the Z axis based on the right-hand rule.

[0049] Step 102 : According to the positional relationship between the target beams, scanning points corresponding to two adjacent target beams are selected from the set of scanning points to be detected as the current scanning point and the next scanning point.

[0050] The positional relationship between the target beams can be the arrangement relationship of the beams of the laser radar in the vertical direction, such as Figure 2As shown, the target beam of the laser radar 10 is the beam whose angle with the horizontal line 20 is a negative value among the beams arranged in the vertical direction of the laser radar 10, wherein the laser radar 10 is the vertex of the angle, the horizontal line 20 is the starting side, counterclockwise rotation is positive, and clockwise rotation is negative. The angle is the angle formed by the clockwise rotation of each beam with the horizontal line 20 as the starting side. For example, beam 1 is located above beam 2, beam 2 is located above beam 3, and beam 3 is located above beam 4. The angle between beam 1 and the horizontal line is smaller than that between beam 2, the angle between beam 2 and the horizontal line is smaller than that between beam 3, and the angle between beam 3 and the horizontal line is smaller than that between beam 4. When beam 1, beam 2, beam 3 and beam 4 are emitted onto the flat ground 30, the detection distance of beam 1 is farther than that of beam 2, the detection distance of beam 2 is farther than that of beam 3, and the detection distance of beam 3 is farther than that of beam 4.

[0051] The adjacent wiring harnesses may refer to wiring harnesses that are adjacent in positional relationship.

[0052] In one possible embodiment, Figure 2 As shown, wire harness 1 is adjacent to wire harness 2 , wire harness 2 is adjacent to wire harness 3 , and wire harness 3 is adjacent to wire harness 4 .

[0053] As a possible implementation method, the above step 102 may include: when the number of scanning points in the set of scanning points to be detected is even, according to the positional relationship between each target beam, select two adjacent scanning points corresponding to the target beams that are not selected from the set of scanning points to be detected in turn as the current scanning point and the next scanning point; when the number of scanning points in the set of scanning points to be detected is odd, according to the positional relationship between each target beam, select two adjacent scanning points corresponding to the target beams that are not selected from the set of scanning points to be detected in turn as the current scanning point and the next scanning point; when there is only one scanning point corresponding to the target beam that is not selected in the set of scanning points to be detected, select the target beam as the next scanning point, and select the scanning point corresponding to the target beam adjacent to the target beam as the current scanning point.

[0054] It should be understood that the selection of the current scanning point and the next scanning point should be based on the principle of non-repeated selection, and the scanning points corresponding to the unselected target beams should be selected first, which can reduce the number of calculations and improve the operation speed.

[0055] In one possible embodiment, Figure 2As shown, the set of scanning points to be detected includes scanning points corresponding to harness 1, harness 2, harness 3 and harness 4. The number of scanning points in the set of scanning points to be detected is an even number. When the order of selecting scanning points is from harness 1 to harness 4, the scanning points corresponding to the adjacent harness 1 and harness 2 are selected first, and the scanning point corresponding to harness 1 is used as the current scanning point, and the scanning point corresponding to harness 2 is the next scanning point. After determining the categories to which harness 1 and harness 2 belong, the adjacent harness 3 and harness 4 that have not been selected are selected, and the scanning point corresponding to harness 3 is used as the current scanning point, and the scanning point corresponding to harness 4 is the next scanning point.

[0056] In one possible embodiment, the set of scanning points to be detected includes scanning points corresponding to wire harness 1, wire harness 2, wire harness 3, wire harness 4 and wire harness 5. Wire harness 1 is located above wire harness 2, wire harness 2 is located above wire harness 3, wire harness 3 is located above wire harness 4, and wire harness 4 is located above wire harness 5. The number of scanning points in the set of scanning points to be detected is odd. When the order of selecting the scanning points is from the direction of wire harness 1 to wire harness 4, the scanning points corresponding to the adjacent wire harness 1 and wire harness 2 are selected first, and the scanning point corresponding to wire harness 1 is used as the current scanning point. Scan point, the scan point corresponding to harness 2 is the next scan point. After determining the categories of harness 1 and harness 2, select the adjacent and unselected harness 3 and harness 4, and use the scan point corresponding to harness 3 as the current scan point, and the scan point corresponding to harness 4 as the next scan point. After determining the categories of harness 3 and harness 4, only the scan point corresponding to harness 5 is not selected, then select the adjacent scan points corresponding to harness 4 and harness 5, and use the scan point corresponding to harness 4 as the current scan point, and the scan point corresponding to harness 5 as the next scan point.

[0057] Step 103, determine the ground reference point based on the height of the laser radar from the ground, the coordinate information of the current scanning point and the next scanning point in the preset three-dimensional coordinate system, wherein the preset three-dimensional coordinate system is determined according to the position of the laser radar.

[0058] The height of the laser radar from the ground may be the height of the fixed installation position of the laser radar from the ground during use. For example, if the laser radar is installed on a vehicle, the height of the laser radar from the ground may be the height of the installation position of the laser radar on the vehicle from the ground.

[0059] The preset three-dimensional coordinate system can be determined based on the position of the laser radar. For example, the three-dimensional coordinate system can be constructed with the position of the laser radar as the coordinate origin O, the positive direction of the Y axis as the forward direction detected by the laser radar, the positive direction of the X axis to the right of the forward direction detected by the laser radar, and the direction indicated by the thumb as the positive direction of the Z axis based on the right-hand rule.

[0060] The coordinate information of the current scanning point in the preset three-dimensional coordinate system may include the X-axis coordinate value, the Y-axis coordinate value, and the Z-axis coordinate value corresponding to the current scanning point in the preset three-dimensional coordinate system.

[0061] The coordinate information of the next scanning point in the preset three-dimensional coordinate system may include the X-axis coordinate value, the Y-axis coordinate value, and the Z-axis coordinate value corresponding to the current scanning point in the preset three-dimensional coordinate system.

[0062] The ground reference point may be a reference point used for scanning point category detection, and the ground reference point may be regarded as a point that is similar to a point on the ground.

[0063] As a possible implementation, step 103 may include:

[0064] According to the height of the laser radar from the ground, the coordinate information of the current scanning point and the next scanning point in the preset three-dimensional coordinate system, the symmetrical point of the next scanning point with respect to the current scanning point on the preset plane in the preset three-dimensional coordinate system is determined, and the symmetrical point is determined as the ground reference point.

[0065] The preset plane may be a plane with a Z value of -h in a preset three-dimensional coordinate system, where h is the height of the laser radar from the ground.

[0066] In an example, for the symmetrical point P2 about P1 on a preset plane, assuming that the height of the lidar from the ground is h, the current scanning point is P1 (x1, y1, z1), the next scanning point is P2 (x2, y2, z2), and the symmetrical point is G (x0, y0, z0), the coordinates of the symmetrical point can be calculated using the calculation formula for the symmetrical point. The calculation formula for the symmetrical point is:

[0067] x0=2*x1-x2

[0068] y0=2*y1-y2

[0069] z0=-h

[0070] Among them, x0 is the coordinate value of the symmetrical point in the preset three-dimensional coordinate system on the X axis, y0 is the coordinate value of the symmetrical point in the preset three-dimensional coordinate system on the Y axis, z0 is the coordinate value of the symmetrical point in the preset three-dimensional coordinate system on the Z axis, x1 is the coordinate value of the current scanning point in the preset three-dimensional coordinate system on the X axis, y1 is the coordinate value of the current scanning point in the preset three-dimensional coordinate system on the Y axis, z1 is the coordinate value of the current scanning point in the preset three-dimensional coordinate system on the Z axis, x2 is the coordinate value of the next scanning point in the preset three-dimensional coordinate system on the X axis, y2 is the coordinate value of the next scanning point in the preset three-dimensional coordinate system on the Y axis, z2 is the coordinate value of the next scanning point in the preset three-dimensional coordinate system on the Z axis, and h is the height of the lidar from the ground.

[0071] As the laser radar beam becomes higher and higher, the distance between the lines will become closer and closer. By selecting symmetrical points as ground reference points, it is more accurate than using projection points as references, and the amount of calculation can be kept very low.

[0072] Step 104 : Determine the categories to which the current scanning point and the next scanning point belong based on the positional relationships between the current scanning point and the next scanning point and the ground reference point, respectively.

[0073] The positional relationship may be a height relationship between the current scanning point and the next scanning point and a ground reference point, or an angle relationship between the current scanning point and the next scanning point and a ground reference point, etc.

[0074] The categories of the scanning points may include ground points, convex points, and concave points, etc., which are not limited in the present embodiment. In actual use, the categories of the identifiable scanning points may be determined according to actual needs and specific application scenarios.

[0075] The ground point may be a reflection point on the ground when the laser radar scans the line beam.

[0076] The raised point may be a reflection point that is not on the ground and is higher than the ground when the laser radar scans the line beam.

[0077] The concave point may be a reflection point where the beam scans a non-ground surface and is lower than the ground during laser radar scanning.

[0078] As one possible implementation, since a ground reference point can be a point close to the ground, the height coordinate value of the ground reference point (i.e., the Z-axis coordinate value of the ground reference point in a preset three-dimensional coordinate system) can represent the height coordinate value corresponding to the ground point. Therefore, the category of the current scan point can be determined based on the difference between the height coordinate value corresponding to the current scan point and the height coordinate value corresponding to the ground reference point; and the category of the next scan point can be determined based on the difference between the height coordinate value corresponding to the next scan point and the height coordinate value corresponding to the ground reference point.

[0079] It can be understood that a height difference threshold can be preset, and when the difference between the height coordinate value corresponding to the current scanning point and the height coordinate value corresponding to the ground reference point is less than or equal to the preset height difference threshold, it can be determined that the height of the current scanning point is very close to the ground, so that the category to which the current scanning point belongs can be determined as a ground point; similarly, when the difference between the height coordinate value corresponding to the next scanning point and the height coordinate value corresponding to the ground reference point is less than or equal to the preset height difference threshold, the category to which the next scanning point belongs can also be determined as a ground point.

[0080] Accordingly, when the difference between the height coordinate value corresponding to the current scanning point and the height coordinate value corresponding to the ground reference point is greater than a preset height difference threshold, and the height coordinate value corresponding to the current scanning point is greater than the height coordinate value corresponding to the ground reference point, it can be determined that the height of the current scanning point is greater than the ground, so that the category to which the current scanning point belongs can be determined as a raised point; similarly, when the difference between the height coordinate value corresponding to the next scanning point and the height coordinate value corresponding to the ground reference point is greater than a preset height difference threshold, and the height coordinate value corresponding to the next scanning point is greater than the height coordinate value corresponding to the ground reference point, the category to which the next scanning point belongs can also be determined as a raised point.

[0081] Accordingly, when the difference between the height coordinate value corresponding to the current scanning point and the height coordinate value corresponding to the ground reference point is greater than the preset height difference threshold, and the height coordinate value corresponding to the current scanning point is less than the height coordinate value corresponding to the ground reference point, it can be determined that the height of the current scanning point is lower than the ground, so that the category to which the current scanning point belongs can be determined as a sunken point; similarly, when the difference between the height coordinate value corresponding to the next scanning point and the height coordinate value corresponding to the ground reference point is greater than the preset height difference threshold, and the height coordinate value corresponding to the next scanning point is less than the height coordinate value corresponding to the ground reference point, the category to which the next scanning point belongs can also be determined as a sunken point.

[0082] The present application provides a method for detecting the category of a laser scanning point, which obtains a set of scanning points to be detected, wherein the set of scanning points to be detected includes scanning points obtained by each target beam of a laser radar detecting an object at a time point, and selects scanning points corresponding to two adjacent target beams from the set of scanning points to be detected according to the positional relationship between each target beam, as the current scanning point and the next scanning point. Then, a ground reference point is determined according to the height of the laser radar from the ground and the coordinate information of the current scanning point and the next scanning point in a preset three-dimensional coordinate system, and then the category of the current scanning point and the next scanning point is determined according to the positional relationship between the current scanning point and the next scanning point and the ground reference point. Thus, by determining the ground reference point according to the height of the laser radar from the ground and the coordinate information of the current scanning point and the next scanning point in the preset three-dimensional coordinate system, the ground reference point can be brought closer to the ground, and then, using the ground reference point as a reference, and determining the category of the current scanning point and the next scanning point according to the positional relationship between the current scanning point and the next scanning point and the ground reference point, the category of the current scanning point and the next scanning point can be more accurately determined, thereby improving the ground point detection result.

[0083] In one embodiment, referring to Figure 3 , which is a flow chart of another method for detecting the category of laser scanning points provided in an embodiment of the present application, including:

[0084] Step 301 : Acquire a set of scanning points to be detected, wherein the set of scanning points to be detected includes scanning points obtained by each target beam of the laser radar detecting an object at a time point.

[0085] Step 302 : Based on the positional relationship between the target beams, two adjacent scanning points corresponding to the target beams are selected from the set of scanning points to be detected as the current scanning point and the next scanning point.

[0086] Step 303, determine the ground reference point based on the height of the laser radar from the ground, the coordinate information of the current scanning point and the next scanning point in the preset three-dimensional coordinate system, wherein the preset three-dimensional coordinate system is determined based on the position of the laser radar.

[0087] The specific implementation process and principle of the above steps 301 to 303 can be referred to the detailed description of the above embodiment and will not be repeated here.

[0088] Step 304 : Generate a first vector based on the coordinate information of the current scanning point and the ground reference point in the preset three-dimensional coordinate system.

[0089] The first vector may be a vector between the current scanning point and the ground reference point.

[0090] In this embodiment, assuming that the current scanning point is P1, the next scanning point is P2, and the ground reference point is G, the first vector is expressed as

[0091] Step 305 : Generate a second vector based on the coordinate information of the current scanning point and the next scanning point in the preset three-dimensional coordinate system.

[0092] The second vector may be a vector between the current scanning point and the next scanning point.

[0093] In this embodiment, assuming that the current scanning point is P1, the next scanning point is P2, and the ground reference point is G, the second vector is expressed as

[0094] Step 306: Determine the categories to which the current scanning point and the next scanning point belong based on the angle between the first vector and the second vector.

[0095] In one possible embodiment, the categories to which the current scanning point and the next scanning point belong can be determined by the angle range to which the angle between the first vector and the second vector belongs. That is, in one possible implementation of the embodiment of the present application, the above step 306 may include:

[0096] Based on the angle between the first vector and the second vector, determine whether the angle between the first vector and the second vector belongs to the first preset angle range; when the angle between the first vector and the second vector belongs to the first preset angle range, generate a third vector based on the coordinate information of the ground reference point and the next scanning point in the preset three-dimensional coordinate system; based on the angle between the third vector and the preset plane, determine the categories to which the current scanning point and the next scanning point belong; when the angle between the first vector and the second vector does not belong to the first preset angle range, determine the average heights corresponding to the ground reference point, the current scanning point and the next scanning point based on the coordinate information of the ground reference point, the current scanning point and the next scanning point in the preset three-dimensional coordinate system; determine the categories to which the current scanning point and the next scanning point belong based on the average heights and the coordinate information of the current scanning point and the next scanning point in the preset three-dimensional coordinate system.

[0097] The first preset angle range may be an angle range for determining whether the current scanning point, the next scanning point, and the ground reference point are approximately fitted into a straight line.

[0098] The first preset angle range may be a range of [180°-θ, 180°+θ], where θ is an angle threshold for determining whether the angle is close to a straight line.

[0099] It should be understood that since the ground is not completely horizontal, even if the next scanning point and the ground reference point are both reflection points of the beam on the ground, the angle between the first vector and the second vector is not necessarily 180°. For this reason, an angle θ is usually set as an angle threshold for judging whether it is close to a straight line. If the angle between the first vector and the second vector is within the angle threshold, it can be regarded as the current scanning point, the next scanning point and the ground reference point are fitted into a straight line, which can improve the accuracy of the category detection of the scanning point.

[0100] The angle threshold can be set according to the actual detection situation, such as 10°, 12° or 15°, etc.

[0101] It should be understood that the angle between the first vector and the second vector is within a first preset angle range, indicating that the current scanning point, the next scanning point, and the ground reference point fit approximately into a straight line.

[0102] The third vector may be a vector between the ground reference point and the next scanning point.

[0103] In this embodiment, assuming that the current scanning point is P1, the next scanning point is P2, and the ground reference point is G, the third vector is expressed as

[0104] In one possible embodiment, when the angle between the first vector and the second vector falls within a first preset angle range, the current scan point, the next scan point, and the ground reference point fit closely to a straight line. The categories of the current and next scan points can be determined based on the angle between the ground reference point and the next scan point's vectors and a preset plane. That is, in one possible implementation of this embodiment of the present application, determining the categories of the current and next scan points based on the angle between the third vector and the preset plane may include:

[0105] When the angle between the third vector and the preset plane is within a second preset angle range, it is determined that the categories to which the current scanning point and the next scanning point belong are ground points.

[0106] When the angle between the third vector and the preset plane is not within the second preset angle range and the angle between the third vector and the preset plane is a positive number, it is determined that the category to which the current scanning point and the next scanning point belong is a raised point, where the raised point refers to a scanning point that is higher than the ground.

[0107] When the angle between the third vector and the preset plane is not within the second preset angle range and the angle between the third vector and the preset plane is negative, it is determined that the category to which the current scanning point and the next scanning point belong is a sunken point, where a sunken point refers to a scanning point below the ground.

[0108] The second preset angle range may be used to determine whether the current scanning point and the next scanning point are approximately on a preset plane.

[0109] The second preset angle range may be set according to actual detection conditions, and the second preset angle range may be set to [-10°, 10°] or [-15°, 15°], etc.

[0110] It should be understood that the angle between the third vector and the preset plane can be the angle of the acute angle formed by the third vector and the preset plane when the vertex of the angle is at the ground reference point, the projection of the third vector on the preset plane is the starting edge, counterclockwise rotation is positive, and clockwise rotation is negative.

[0111] It should be understood that when the current scanning point, the next scanning point and the ground reference point are fitted into an approximately straight line, the angle between the vectors of the ground reference point and the next scanning point and the preset plane can be used to determine whether the current scanning point and the next scanning point are approximately on the preset plane.

[0112] It should be understood that the current scanning point and the next scanning point are approximately on the preset plane, which means that the current scanning point and the next scanning point are ground points.

[0113] As an example, Figure 4The current scanning point and the next scanning point are schematic diagrams of ground points. The current scanning point is P1, the next scanning point is P2, the ground reference point is G, and the first vector With the second vector The angle between them is approximately 180°, and the third vector The angle with the preset plane is approximately 0°, and the current scanning point and the next scanning point are both ground points.

[0114] It should be understood that the current scanning point and the next scanning point are not located on the preset plane, which means that the current scanning point and the next scanning point are not ground points.

[0115] It should be understood that the current scanning point and the next scanning point are not on the preset plane, and the angle between the third vector and the preset plane is a positive number, indicating that the current scanning point and the next scanning point are higher than the scanning point on the ground, which is a convex point.

[0116] The scanning point above the ground may be a scanning point whose height coordinate in a preset three-dimensional coordinate system is greater than the height coordinate of the scanning point on the ground.

[0117] The height coordinate may be a coordinate value corresponding to a dimension representing height in a coordinate system.

[0118] As an example, Figure 5 The current scanning point and the next scanning point shown are schematic diagrams of convex points. The current scanning point is P1, the next scanning point is P2, the ground reference point is G, and the first vector With the second vector The angle between them is approximately 180°, and the third vector The angle between the third vector and the preset plane is not within the second preset angle range, and the angle between the third vector and the preset plane is a positive number. The current scanning point and the next scanning point are both convex points.

[0119] It should be understood that the current scanning point and the next scanning point are not on the preset plane, and the angle between the third vector and the preset plane is negative, indicating that the current scanning point and the next scanning point are lower than the scanning point on the ground, which is a concave point.

[0120] The scanning point below the ground may be a scanning point whose height coordinate in a preset three-dimensional coordinate system is smaller than the height coordinate of the scanning point on the ground.

[0121] As an example, Figure 6 The current scanning point and the next scanning point shown are schematic diagrams of depression points. The current scanning point is P1, the next scanning point is P2, the ground reference point is G, and the first vector With the second vector The angle between them is approximately 180°, and the third vector The angle between the third vector and the preset plane is not within the second preset angle range, and the angle between the third vector and the preset plane is negative, and the current scanning point and the next scanning point are both concave points.

[0122] In one possible embodiment, when the angle between the first vector and the second vector does not fall within the first preset angle range, since the current scanning point P1, the next scanning point P2, and the ground reference point G are not approximately in a straight line, the categories of the current scanning point P1 and the next scanning point P2 are different, and the categories are any two combinations of one scanning point being a ground point, one scanning point being a convex point, and one scanning point being a concave point. The categories to which the current scanning point and the next scanning point belong can be determined by the height range to which the height mean belongs. The height mean can be the average of the Z coordinate values ​​of the ground reference point, the current scanning point, and the next scanning point. That is, in a possible implementation of the embodiment of the present application, determining the categories to which the current scanning point and the next scanning point belong based on the height mean, the coordinate information of the current scanning point and the next scanning point in the preset three-dimensional coordinate system, can include:

[0123] When the height mean falls within the preset height range, the categories to which the current scanning point and the next scanning point belong are determined based on their corresponding height coordinate values, where the height coordinate value refers to the coordinate value corresponding to the height dimension in the preset three-dimensional coordinate system.

[0124] When the average height does not fall within the preset height range, the categories to which the current scanning point and the next scanning point belong are determined based on the relationship between the average height and the height coordinate value of the ground reference point.

[0125] The preset height range can be used to determine whether the average height is near the height of a ground reference point. The preset height range can be used to determine whether one of the two scanning points is below the ground and the other is above the ground.

[0126] Furthermore, if the average height value falls within a preset height range, and one of the two scanning points, the current scanning point P1 and the next scanning point P2, is located below the ground and the other is located above the ground, the categories to which the current scanning point and the next scanning point belong can be determined based on the relationship between the height coordinate value corresponding to the current scanning point and the average height value. That is, in one possible implementation of the embodiment of the present application, determining the categories to which the current scanning point and the next scanning point belong based on the height coordinate values ​​corresponding to the current scanning point and the next scanning point includes:

[0127] When the height coordinate value corresponding to the current scanning point is greater than the mean height, the category to which the current scanning point belongs is determined to be a convex point, and the category to which the next scanning point belongs is a concave point; when the height coordinate value corresponding to the current scanning point is less than the mean height, the category to which the current scanning point belongs is determined to be a concave point, and the category to which the next scanning point belongs is a convex point.

[0128] As an example, Figure 7-Figure 8 The current scanning point and the next scanning point are shown as a schematic diagram, one of which is a convex point and the other is a concave point. The current scanning point is P1, the next scanning point is P2, the ground reference point is G, and the first vector With the second vector The angle between them does not fall within the first preset angle range, and the height average falls within the preset height range. The scanning point with a height coordinate value greater than the height average is a convex point, and the scanning point with a height coordinate value less than the height average is a concave point.

[0129] Furthermore, if the average height does not fall within the preset height range, the categories to which the current and next scanning points belong can be determined based on the relationship between the average height and the height coordinate values ​​corresponding to the ground reference point, as well as the relationship between the height coordinate values ​​corresponding to the current and next scanning points and the average height. That is, in one possible implementation of the embodiment of the present application, determining the categories to which the current and next scanning points belong based on the relationship between the average height and the height coordinate values ​​of the ground reference point includes:

[0130] When the height mean is greater than the height coordinate value corresponding to the ground reference point, and the height coordinate values ​​corresponding to the current scanning point and the next scanning point are both greater than the height mean, the category to which the current scanning point and the next scanning point belong is determined to be a convex point.

[0131] When the height mean is greater than the height coordinate value corresponding to the ground reference point, and the height coordinate value corresponding to the current scanning point is greater than the height mean, and the height coordinate value corresponding to the next scanning point is less than the height mean, it is determined that the category to which the current scanning point belongs is a raised point, and the category to which the next scanning point belongs is a ground point.

[0132] When the height mean is greater than the height coordinate value corresponding to the ground reference point, the height coordinate value corresponding to the current scanning point is less than the height mean, and the height coordinate value corresponding to the next scanning point is greater than the height mean, the category to which the current scanning point belongs is determined to be a ground point, and the category to which the next scanning point belongs is determined to be a raised point.

[0133] As an example, Figures 9-11 The current scanning point and the next scanning point are schematic diagrams in which one or both are convex points. The current scanning point is P1, the next scanning point is P2, the ground reference point is G, and the first vector With the second vector The angle between them does not fall within the first preset angle range, and the average height does not fall within the preset height range. When the average height is greater than the height coordinate value corresponding to the ground reference point, the height coordinate values ​​corresponding to the current scanning point P1 and the next scanning point P2 are both greater than the average height. The category to which the current scanning point P1 and the next scanning point P2 belong is a convex point, such as Figure 11 As shown in the figure, the height coordinate value corresponding to the current scanning point P1 is greater than the height mean, and the height coordinate value corresponding to the next scanning point P2 is less than the height mean. The category to which the current scanning point P1 belongs is a convex point, and the category to which the next scanning point P2 belongs is a ground point. Figure 10 As shown in the figure, the height coordinate value corresponding to the current scan point P1 is less than the height mean, and the height coordinate value corresponding to the next scan point P2 is greater than the height mean. The category to which the current scan point P1 belongs is a ground point, and the category to which the next scan point P2 belongs is a convex point, as shown in the figure. Figure 9 shown.

[0134] When the height mean is less than the height coordinate value corresponding to the ground reference point, and the height coordinate values ​​corresponding to the current scanning point and the next scanning point are both less than the height mean, it is determined that the category to which the current scanning point and the next scanning point belong is a sunken point.

[0135] When the height mean is less than the height coordinate value corresponding to the ground reference point, and the height coordinate value corresponding to the current scanning point is greater than the height mean, and the height coordinate value corresponding to the next scanning point is less than the height mean, it is determined that the category to which the current scanning point belongs is a ground point, and the category to which the next scanning point belongs is a depression point.

[0136] When the height mean is less than the height coordinate value corresponding to the ground reference point, and the height coordinate value corresponding to the current scanning point is less than the height mean, and the height coordinate value corresponding to the next scanning point is greater than the height mean, it is determined that the category to which the current scanning point belongs is a depression point, and the category to which the next scanning point belongs is a ground point.

[0137] As an example, Figure 12-14 The current scanning point and the next scanning point are either or both of them are sunken points. The current scanning point is P1, the next scanning point is P2, the ground reference point is G, and the first vector With the second vector The angle between them does not fall within the first preset angle range, and the average height does not fall within the preset height range. When the average height is less than the height coordinate value corresponding to the ground reference point, the height coordinate values ​​corresponding to the current scanning point P1 and the next scanning point P2 are both less than the average height. The current scanning point P1 and the next scanning point P2 belong to the category of concave points, such as Figure 14As shown in the figure, the height coordinate value corresponding to the current scanning point P1 is greater than the height mean, and the height coordinate value corresponding to the next scanning point P2 is less than the height mean. The category to which the current scanning point P1 belongs is a ground point, and the category to which the next scanning point P2 belongs is a sunken point. Figure 12 As shown in the figure, the height coordinate value corresponding to the current scanning point P1 is less than the height mean, and the height coordinate value corresponding to the next scanning point P2 is greater than the height mean. The category to which the current scanning point P1 belongs is a sunken point, and the category to which the next scanning point P2 belongs is a ground point. Figure 13 shown.

[0138] The present application provides a category detection method for laser scanning points, by obtaining a set of scanning points to be detected, wherein the set of scanning points to be detected includes scanning points obtained by each target beam of the laser radar when detecting an object at a time point, and then according to the positional relationship between each target beam, the scanning points corresponding to two adjacent target beams are selected from the set of scanning points to be detected in turn as the current scanning point and the next scanning point, so as to determine the symmetrical point of the next scanning point about the preset plane of the current scanning point in the preset three-dimensional coordinate system according to the height of the laser radar from the ground and the coordinate information of the current scanning point and the next scanning point in the preset three-dimensional coordinate system, and determine the symmetrical point as the ground reference point, and then determine the category to which the current scanning point and the next scanning point belong according to the positional relationship between the current scanning point and the next scanning point and the ground reference point respectively. Therefore, by determining the ground reference point based on the height of the laser radar from the ground and the coordinate information of the current scan point and the next scan point in the preset three-dimensional coordinate system, the ground reference point can be brought closer to the ground. Then, using the ground reference point as a reference, the categories of the current scan point and the next scan point can be determined based on their positional relationship with the ground reference point. This allows for more accurate judgment of the types of the current scan point and the next scan point, further improving the ground point detection results. Further analysis of angles and relative distances can be used to more accurately distinguish ground points from non-ground points, as well as to determine whether they are convex points or concave points. At the same time, the introduction of hyperparameters can be reduced, making the difficulty of the detection algorithm lower.

[0139] It should be understood that although Figure 1 as well as Figure 3 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. In addition, Figure 1 as well as Figure 3At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The order of execution of these steps or stages is not necessarily one by one, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

[0140] In one embodiment, Figure 15 As shown, a device for detecting the category of a laser scanning point is provided. The device can be a software module or a hardware module, or a combination of the two to form a part of a computer device. The device specifically includes:

[0141] The scanning point acquisition module 610 is used to acquire a set of scanning points to be detected, wherein the set of scanning points to be detected includes scanning points obtained by each target beam of the laser radar detecting an object at a time point.

[0142] The scanning point selection module 620 is used to select scanning points corresponding to two adjacent target beams from the set of scanning points to be detected according to the positional relationship between the target beams as the current scanning point and the next scanning point.

[0143] The reference point determination module 630 is used to determine the ground reference point based on the height of the laser radar from the ground, the coordinate information of the current scanning point and the next scanning point in the preset three-dimensional coordinate system, wherein the preset three-dimensional coordinate system is determined based on the position of the laser radar.

[0144] The category analysis module 640 is configured to determine the categories to which the current scanning point and the next scanning point belong based on the positional relationships between the current scanning point and the next scanning point and the ground reference point, respectively.

[0145] In one embodiment, the scanning point selection module 620 is also used to: when the number of scanning points in the set of scanning points to be detected is an even number, select two adjacent scanning points corresponding to the unselected target beams from the set of scanning points to be detected in turn according to the positional relationship between the target beams, as the current scanning point and the next scanning point; when the number of scanning points in the set of scanning points to be detected is an odd number, select two adjacent scanning points corresponding to the two unselected target beams from the set of scanning points to be detected in turn according to the positional relationship between the target beams, as the current scanning point and the next scanning point; when there is only one scanning point corresponding to the unselected target beam left in the set of scanning points to be detected, the scanning point corresponding to the target beam is used as the next scanning point, and the scanning point corresponding to the target beam adjacent to the target beam is selected as the current scanning point.

[0146] In one embodiment, the reference point determination module 630 is also used to: determine the symmetrical point of the next scanning point about the current scanning point on the preset plane in the preset three-dimensional coordinate system based on the height of the laser radar from the ground, the coordinate information of the current scanning point and the next scanning point in the preset three-dimensional coordinate system; and determine the symmetrical point as the ground reference point.

[0147] In one embodiment, the category analysis module 640 is also used to: generate a first vector based on the coordinate information of the current scanning point and the ground reference point in the preset three-dimensional coordinate system; generate a second vector based on the coordinate information of the current scanning point and the next scanning point in the preset three-dimensional coordinate system; and determine the category to which the current scanning point and the next scanning point belong based on the angle between the first vector and the second vector.

[0148] In one embodiment, the category analysis module 640 is further used to: determine whether the angle between the first vector and the second vector belongs to a first preset angle range based on the angle between the first vector and the second vector; if the angle between the first vector and the second vector belongs to the first preset angle range, generate a third vector based on the coordinate information of the ground reference point and the next scanning point in the preset three-dimensional coordinate system; determine the categories to which the current scanning point and the next scanning point belong based on the angle between the third vector and the preset plane; if the angle between the first vector and the second vector does not belong to the first preset angle range, determine the average heights corresponding to the ground reference point, the current scanning point and the next scanning point based on the coordinate information of the ground reference point, the current scanning point and the next scanning point in the preset three-dimensional coordinate system; determine the categories to which the current scanning point and the next scanning point belong based on the average heights and the coordinate information of the current scanning point and the next scanning point in the preset three-dimensional coordinate system.

[0149] In one embodiment, the category analysis module 640 is further used to: when the angle between the third vector and the preset plane is within the second preset angle range, determine that the category to which the current scanning point and the next scanning point belong is a ground point; when the angle between the third vector and the preset plane is not within the second preset angle range, and the angle between the third vector and the preset plane is a positive number, determine that the category to which the current scanning point and the next scanning point belong is a convex point, wherein a convex point refers to a scanning point above the ground; when the angle between the third vector and the preset plane is not within the second preset angle range, and the angle between the third vector and the preset plane is a negative number, determine that the category to which the current scanning point and the next scanning point belong is a concave point, wherein a concave point refers to a scanning point below the ground.

[0150] In one embodiment, the category analysis module 640 is also used to: when the mean height falls within a preset height range, determine the categories to which the current scanning point and the next scanning point belong based on the height coordinate values ​​corresponding to the current scanning point and the next scanning point, wherein the height coordinate value refers to the coordinate value corresponding to the height dimension in the preset three-dimensional coordinate system; when the mean height does not fall within the preset height range, determine the categories to which the current scanning point and the next scanning point belong based on the relationship between the mean height and the height coordinate value of the ground reference point.

[0151] In one embodiment, the category analysis module 640 is also used to: when the height coordinate value corresponding to the current scanning point is greater than the height mean, determine that the category to which the current scanning point belongs is a convex point, and the category to which the next scanning point belongs is a concave point; when the height coordinate value corresponding to the current scanning point is less than the height mean, determine that the category to which the current scanning point belongs is a concave point, and the category to which the next scanning point belongs is a convex point.

[0152] In one embodiment, the category analysis module 640 is further used to: when the height mean is greater than the height coordinate value corresponding to the ground reference point, and the height coordinate values ​​corresponding to the current scanning point and the next scanning point are both greater than the height mean, determine that the category to which the current scanning point and the next scanning point belong is a convex point; when the height mean is greater than the height coordinate value corresponding to the ground reference point, and the height coordinate value corresponding to the current scanning point is greater than the height mean, and the height coordinate value corresponding to the next scanning point is less than the height mean, determine that the category to which the current scanning point belongs is a convex point, and the category to which the next scanning point belongs is a ground point; when the height mean is greater than the height coordinate value corresponding to the ground reference point, and the height coordinate value corresponding to the current scanning point is less than the height mean, and the height coordinate value corresponding to the next scanning point is greater than the height mean, determine that the category to which the current scanning point belongs is a ground point, and the category to which the next scanning point belongs is a convex point. The category to which it belongs is a convex point; when the average height is less than the height coordinate value corresponding to the ground reference point, and the height coordinate values ​​corresponding to the current scanning point and the next scanning point are both less than the average height, the category to which the current scanning point and the next scanning point belong is determined to be a concave point; when the average height is less than the height coordinate value corresponding to the ground reference point, and the height coordinate value corresponding to the current scanning point is greater than the average height, and the height coordinate value corresponding to the next scanning point is less than the average height, the category to which the current scanning point belongs is determined to be a ground point, and the category to which the next scanning point belongs is a concave point; when the average height is less than the height coordinate value corresponding to the ground reference point, and the height coordinate value corresponding to the current scanning point is less than the average height, and the height coordinate value corresponding to the next scanning point is greater than the average height, the category to which the current scanning point belongs is determined to be a concave point, and the category to which the next scanning point belongs is a ground point.

[0153] The present application provides a category detection device for laser scanning points, which obtains a set of scanning points to be detected, wherein the set of scanning points to be detected includes scanning points obtained by each target beam of the laser radar when detecting an object at a time point, and then selects two adjacent scanning points corresponding to the target beams from the set of scanning points to be detected in turn according to the positional relationship between the target beams, as the current scanning point and the next scanning point, so as to determine the symmetrical point of the next scanning point about the preset plane of the current scanning point in the preset three-dimensional coordinate system according to the height of the laser radar from the ground and the coordinate information of the current scanning point and the next scanning point in the preset three-dimensional coordinate system, and determine the symmetrical point as the ground reference point, and then determine the category to which the current scanning point and the next scanning point belong according to the positional relationship between the current scanning point and the next scanning point and the ground reference point respectively. Therefore, by determining the ground reference point based on the height of the laser radar from the ground and the coordinate information of the current scan point and the next scan point in the preset three-dimensional coordinate system, the ground reference point can be brought closer to the ground. Then, using the ground reference point as a reference, the categories of the current scan point and the next scan point can be determined based on their positional relationship with the ground reference point. This allows for more accurate judgment of the types of the current scan point and the next scan point, further improving the ground point detection results. Further analysis of angles and relative distances can be used to more accurately distinguish ground points from non-ground points, as well as to determine whether they are convex points or concave points. At the same time, the introduction of hyperparameters can be reduced, making the difficulty of the detection algorithm lower.

[0154] The specific definitions of the laser scanning point classification detection device can be found in the definitions of the laser scanning point classification detection method described above and will not be repeated here. Each module in the aforementioned laser scanning point classification detection device can be implemented in whole or in part through software, hardware, or a combination thereof. Each of these modules can be embedded in or independent of a processor in a computer device in hardware form, or stored in a computer device memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0155] Figure 16 This is a schematic diagram of the structure of a terminal device provided in one embodiment of the present application. Figure 16 As shown, the terminal device 700 of this embodiment includes: at least one processor 710 ( Figure 16 Only one is shown in the figure) a processor, a memory 720, and a computer program 721 stored in the memory 720 and executable on at least one processor 710. When the processor 710 executes the computer program 721, the steps in the above-mentioned embodiment of the method for detecting the category of the laser scanning point are implemented.

[0156] The terminal device 700 can be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal device may include, but is not limited to, a processor 710 and a memory 720. Those skilled in the art will understand that Figure 16 This is merely an example of the terminal device 700 and does not constitute a limitation on the terminal device 700 . The terminal device 700 may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal device 700 may also include input and output devices, network access devices, etc.

[0157] The processor 710 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor may be a microprocessor or any conventional processor.

[0158] In some embodiments, the memory 720 may be an internal storage unit of the terminal device 700, such as a hard disk or memory of the terminal device 700. In other embodiments, the memory 720 may also be an external storage device of the terminal device 700, such as a plug-in hard disk equipped on the terminal device 700, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Furthermore, the memory 720 may also include both an internal storage unit of the terminal device 700 and an external storage device. The memory 720 is used to store an operating system, application programs, a boot loader, data, and other programs, such as program code of a computer program. The memory 720 may also be used to temporarily store data that has been output or is about to be output.

[0159] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0160] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0161] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0162] In the embodiments provided in this application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are merely illustrative. For example, the division of the modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0163] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0164] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0165] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, it can implement the steps of the above-mentioned various method embodiments. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0166] The present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed through a computer program product. When the computer program product is run on a terminal device, the terminal device can implement the steps in the above-mentioned method embodiments when executing.

[0167] The above embodiments are intended only to illustrate the technical solutions of the present application and are not intended to limit them. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they may still modify the technical solutions described in the above embodiments or replace some of the technical features therein with equivalents; and such modifications or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present application and should be included within the scope of protection of the present application.

Claims

1. A method for detecting the category of a laser scanning point, characterized in that: include: Acquire a set of scan points to be detected, wherein the set of scan points to be detected includes scan points obtained by each target beam of the laser radar detecting an object at a time point; According to the positional relationship between the target line beams, scanning points corresponding to two adjacent target line beams are selected from the set of scanning points to be detected as the current scanning point and the next scanning point; Determine, based on the height of the laser radar from the ground and the coordinate information of the current scanning point and the next scanning point in a preset three-dimensional coordinate system, a symmetrical point of the next scanning point about the current scanning point on a preset plane in the preset three-dimensional coordinate system, and determine the symmetrical point as a ground reference point, wherein the preset three-dimensional coordinate system is determined based on the position of the laser radar; When the current scanning point, the next scanning point, and the ground reference point are fitted to approximately form a straight line, generating a third vector based on coordinate information of the ground reference point and the next scanning point in the preset three-dimensional coordinate system, and determining the categories to which the current scanning point and the next scanning point belong based on an angle between the third vector and the preset plane; In the case that the current scanning point, the next scanning point and the ground reference point are not fitted into an approximately straight line, the average heights corresponding to the ground reference point, the current scanning point and the next scanning point are determined based on the coordinate information of the ground reference point, the current scanning point and the next scanning point in the preset three-dimensional coordinate system, and the categories to which the current scanning point and the next scanning point belong are determined based on the average heights and the coordinate information of the current scanning point and the next scanning point in the preset three-dimensional coordinate system.

2. The method according to claim 1, wherein The step of selecting scanning points corresponding to two adjacent target beams from the set of scanning points to be detected as the current scanning point and the next scanning point according to the positional relationship between the target beams includes: When the number of scanning points in the set of scanning points to be detected is even, selecting scanning points corresponding to two adjacent unselected target beams from the set of scanning points to be detected in sequence according to the positional relationship between the target beams as the current scanning point and the next scanning point; When the number of scanning points in the set of scanning points to be detected is odd, based on the positional relationship between the target beams, two adjacent scanning points corresponding to two unselected target beams are selected from the set of scanning points to be detected in turn as the current scanning point and the next scanning point. When there is only one scanning point corresponding to an unselected target beam left in the set of scanning points to be detected, the scanning point corresponding to the target beam is selected as the next scanning point, and the scanning point corresponding to the target beam adjacent to the target beam is selected as the current scanning point.

3. The method according to claim 1, wherein Before generating a third vector based on coordinate information of the ground reference point and the next scanning point in the preset three-dimensional coordinate system when the current scanning point, the next scanning point, and the ground reference point are fitted to approximately form a straight line, and determining the categories to which the current scanning point and the next scanning point belong based on an angle between the third vector and the preset plane, the method includes: Generate a first vector according to coordinate information of the current scanning point and the ground reference point in the preset three-dimensional coordinate system; generating a second vector according to coordinate information of the current scanning point and the next scanning point in the preset three-dimensional coordinate system; According to the angle between the first vector and the second vector, it is determined whether the current scanning point, the next scanning point, and the ground reference point fit approximately into a straight line.

4. The method according to claim 3, wherein The determining, based on the angle between the first vector and the second vector, whether the current scanning point, the next scanning point, and the ground reference point fit approximately into a straight line includes: determining, based on the angle between the first vector and the second vector, whether the angle between the first vector and the second vector falls within a first preset angle range; When the angle between the first vector and the second vector falls within the first preset angle range, determining that the current scanning point, the next scanning point, and the ground reference point are fitted to approximately form a straight line; When the angle between the first vector and the second vector does not fall within the first preset angle range, it is determined that the current scanning point, the next scanning point, and the ground reference point do not fit approximately into a straight line.

5. The method according to any one of claims 1 to 4, characterized in that The determining, based on the angle between the third vector and the preset plane, the categories to which the current scanning point and the next scanning point belong, includes: When the angle between the third vector and the preset plane is within a second preset angle range, determining that the categories to which the current scanning point and the next scanning point belong are ground points; If the angle between the third vector and the preset plane is not within the second preset angle range and the angle between the third vector and the preset plane is a positive number, determining that the current scanning point and the next scanning point belong to a category of convex points, wherein the convex point refers to a scanning point that is higher than the ground; When the angle between the third vector and the preset plane is not within the second preset angle range and the angle between the third vector and the preset plane is negative, it is determined that the category to which the current scanning point and the next scanning point belong is a sunken point, wherein the sunken point refers to a scanning point below the ground.

6. The method according to any one of claims 1 to 4, characterized in that The determining, based on the height mean, coordinate information of the current scanning point and the next scanning point in the preset three-dimensional coordinate system, the categories to which the current scanning point and the next scanning point belong includes: When the height mean falls within a preset height range, determining the categories to which the current scanning point and the next scanning point belong based on height coordinate values ​​corresponding to the current scanning point and the next scanning point, wherein the height coordinate values ​​refer to coordinate values ​​corresponding to the height dimension in the preset three-dimensional coordinate system; When the average height does not fall within the preset height range, the categories to which the current scanning point and the next scanning point belong are determined according to a relationship between the average height and the height coordinate value of the ground reference point.

7. The method according to claim 6, wherein The determining, based on the height coordinate values ​​corresponding to the current scanning point and the next scanning point, the categories to which the current scanning point and the next scanning point belong, includes: When the height coordinate value corresponding to the current scanning point is greater than the height mean, determining that the category to which the current scanning point belongs is a convex point, and the category to which the next scanning point belongs is a concave point; When the height coordinate value corresponding to the current scanning point is less than the height mean, it is determined that the category to which the current scanning point belongs is a concave point, and the category to which the next scanning point belongs is a convex point.

8. The method according to claim 6, wherein The determining, based on the relationship between the height mean value and the height coordinate value of the ground reference point, the categories to which the current scanning point and the next scanning point belong, includes: When the height average is greater than the height coordinate value corresponding to the ground reference point, and the height coordinate values ​​corresponding to the current scanning point and the next scanning point are both greater than the height average, determining that the categories to which the current scanning point and the next scanning point belong are convex points; When the height mean is greater than the height coordinate value corresponding to the ground reference point, and the height coordinate value corresponding to the current scanning point is greater than the height mean, and the height coordinate value corresponding to the next scanning point is less than the height mean, determining that the category to which the current scanning point belongs is a convex point, and the category to which the next scanning point belongs is a ground point; When the height mean is greater than the height coordinate value corresponding to the ground reference point, the height coordinate value corresponding to the current scan point is less than the height mean, and the height coordinate value corresponding to the next scan is greater than the height mean, determining that the category to which the current scan point belongs is a ground point, and the category to which the next scan point belongs is a convex point; When the height mean is smaller than the height coordinate value corresponding to the ground reference point, and the height coordinate values ​​corresponding to the current scanning point and the next scanning point are both smaller than the height mean, determining that the categories to which the current scanning point and the next scanning point belong are sunken points; When the height mean is smaller than the height coordinate value corresponding to the ground reference point, and the height coordinate value corresponding to the current scanning point is larger than the height mean, and the height coordinate value corresponding to the next scanning point is smaller than the height mean, determining that the category to which the current scanning point belongs is a ground point, and the category to which the next scanning point belongs is a sunken point; When the height mean is smaller than the height coordinate value corresponding to the ground reference point, and the height coordinate value corresponding to the current scanning point is smaller than the height mean, and the height coordinate value corresponding to the next scanning point is larger than the height mean, it is determined that the category to which the current scanning point belongs is a depression point, and the category to which the next scanning point belongs is a ground point.

9. A laser scanning point category detection device, characterized in that: include: A scanning point acquisition module is used to acquire a set of scanning points to be detected, wherein the set of scanning points to be detected includes scanning points obtained by each target beam of the laser radar detecting an object at a time point; A scanning point selection module is used to select scanning points corresponding to two adjacent target beams from the set of scanning points to be detected according to the positional relationship between the target beams, as the current scanning point and the next scanning point; a reference point determination module, configured to determine, based on the height of the laser radar from the ground and the coordinate information of the current scanning point and the next scanning point in a preset three-dimensional coordinate system, a symmetrical point of the next scanning point with respect to the current scanning point on a preset plane in the preset three-dimensional coordinate system, and determine the symmetrical point as a ground reference point, wherein the preset three-dimensional coordinate system is determined based on the position of the laser radar; a first category analysis module, configured to generate a third vector based on coordinate information of the ground reference point and the next scanning point in the preset three-dimensional coordinate system, when the current scanning point, the next scanning point, and the ground reference point are fitted to approximately form a straight line, and determine the category to which the current scanning point and the next scanning point belong based on an angle between the third vector and the preset plane; The second category analysis module is used to determine the corresponding average heights of the ground reference point, the current scanning point and the next scanning point according to the coordinate information of the ground reference point, the current scanning point and the next scanning point in the preset three-dimensional coordinate system when the current scanning point, the next scanning point and the ground reference point are not fitted into an approximately straight line, and determine the categories to which the current scanning point and the next scanning point belong according to the average heights and the coordinate information of the current scanning point and the next scanning point in the preset three-dimensional coordinate system.

10. A terminal 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 computer program, the method according to any one of claims 1 to 8 is implemented.

11. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images