CN116883969A - Ground point cloud identification method and device, electronic equipment and storage medium - Google Patents
Ground point cloud identification method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN116883969A CN116883969A CN202310778252.6A CN202310778252A CN116883969A CN 116883969 A CN116883969 A CN 116883969A CN 202310778252 A CN202310778252 A CN 202310778252A CN 116883969 A CN116883969 A CN 116883969A
- Authority
- CN
- China
- Prior art keywords
- grid
- point cloud
- cloud data
- ground
- ground point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 64
- 238000001514 detection method Methods 0.000 claims abstract description 109
- 238000004590 computer program Methods 0.000 claims description 16
- 238000001914 filtration Methods 0.000 claims description 13
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 3
- 238000012545 processing Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 238000002372 labelling Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/89—Lidar systems specially adapted for specific applications for mapping or imaging
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
- G01S17/931—Lidar systems specially adapted for specific applications for anti-collision purposes of land vehicles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Electromagnetism (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Optical Radar Systems And Details Thereof (AREA)
Abstract
The invention discloses a ground point cloud identification method, a ground point cloud identification device, electronic equipment and a storage medium. The method comprises the following steps: acquiring point cloud data obtained by scanning an environment where a vehicle is located by a laser radar; converting the point cloud data into a first coordinate system and creating a first grid; under the first grid, performing ground point cloud detection on each grid in the first grid to obtain a first detection result; converting the point cloud data into a second coordinate system and creating a second grid; under the second grid, performing ground point cloud detection on each grid in the second grid to obtain a second detection result; and determining ground point cloud data in the point cloud data based on the first detection result and the second detection result. According to the invention, the ground point cloud detection is carried out on the point cloud data under the first coordinate system and the second coordinate system, so that the recognition accuracy of the ground point cloud data is improved.
Description
Technical Field
The present invention relates to the field of autopilot technologies, and in particular, to a method and apparatus for identifying a ground point cloud, an electronic device, and a storage medium.
Background
In the automatic driving embedded software development process, ground points are required to be filtered first and then detected or segmented to identify various obstacles, so that the total amount of point cloud processing can be reduced, and the time consumption and the burden of subsequent module processing can be reduced.
At present, two methods for identifying the ground point cloud generally exist, one is a ground point cloud identification method based on deep learning, the method is characterized in that the ground point cloud is marked, and then an ordered three-dimensional point cloud is used as input of a pre-trained ground detection model to obtain a ground detection result corresponding to a target ground; the other is a ground point cloud identification method based on a plurality of graphs, wherein the method is used for detecting the height difference of points on the same laser radar harness or the difference value between the plane angle value and the like based on plane detection, detecting the currently collected ground area of the laser point cloud, and separating ground points and non-ground points; however, the effectiveness of the first method depends on training data and labeling quality, the labeling accuracy can have a larger influence on the detection result, and the cost of the ground point cloud labeling and the time cost during labeling are higher; in addition, the accuracy of ground point cloud identification is low, either in method one or method two.
Disclosure of Invention
The invention provides a ground point cloud identification method, a ground point cloud identification device, electronic equipment and a storage medium, and aims to solve the technical problems.
According to an aspect of the present invention, there is provided a method for identifying a ground point cloud, including:
acquiring point cloud data obtained by scanning an environment where a vehicle is located by a laser radar;
converting the point cloud data into a first coordinate system and creating a first grid; under the first grid, performing ground point cloud detection on each grid in the first grid to obtain a first detection result; converting the point cloud data into a second coordinate system and creating a second grid; under the second grid, performing ground point cloud detection on each grid in the second grid to obtain a second detection result;
and determining ground point cloud data in the point cloud data based on the first detection result and the second detection result.
According to another aspect of the present invention, there is provided an identification apparatus for a ground point cloud, including:
the point cloud data acquisition module is used for acquiring point cloud data obtained by scanning the environment where the vehicle is located by the laser radar;
the ground point cloud detection module is used for converting the point cloud data into a first coordinate system and creating a first grid; under the first grid, performing ground point cloud detection on each grid in the first grid to obtain a first detection result; converting the point cloud data into a second coordinate system and creating a second grid; under the second grid, performing ground point cloud detection on each grid in the second grid to obtain a second detection result;
The ground point cloud data determining module is used for determining ground point cloud data in the point cloud data based on the first detection result and the second detection result.
According to another aspect of the present invention, there is provided an electronic apparatus including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of identifying a ground point cloud according to any one of the embodiments of the present invention.
According to another aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to implement the method for identifying a ground point cloud according to any embodiment of the present invention when executed.
According to the technical scheme, point cloud data obtained by scanning the environment where the vehicle is located through the laser radar are obtained; converting the point cloud data into a first coordinate system and creating a first grid; under the first grid, performing ground point cloud detection on each grid in the first grid to obtain a first detection result; converting the point cloud data into a second coordinate system and creating a second grid; under the second grid, performing ground point cloud detection on each grid in the second grid to obtain a second detection result; and determining the ground point cloud data in the point cloud data based on the first detection result and the second detection result. And the ground point cloud detection is carried out on the point cloud data under the first coordinate system and the second coordinate system, so that the identification accuracy of the ground point cloud data is improved.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a method for identifying a ground point cloud according to an embodiment of the present invention;
FIG. 2 is a schematic view of a first grid according to a first embodiment of the present invention;
FIG. 3 is a schematic view of a second grid provided in accordance with a first embodiment of the present invention;
FIG. 4 is a flow chart of radial detection in a polar coordinate system according to an embodiment of the present invention;
FIG. 5 is a flow chart of lateral detection in a polar coordinate system according to an embodiment of the present invention;
FIG. 6 is a flow chart of detection based on a third determination condition in a Cartesian coordinate system according to a first embodiment of the present invention;
FIG. 7 is a flow chart of detection based on a fourth determination condition in a Cartesian coordinate system according to a first embodiment of the present invention;
fig. 8 is a schematic structural diagram of a ground point cloud identification device according to a second embodiment of the present invention;
fig. 9 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
Fig. 1 is a flowchart of a method for identifying a ground point cloud according to an embodiment of the present invention, where the method may be implemented by a device for identifying a ground point cloud, and the device for identifying a ground point cloud may be implemented in hardware and/or software, and the device for identifying a ground point cloud may be configured in a vehicle-mounted terminal. As shown in fig. 1, the method includes:
s110, acquiring point cloud data obtained by scanning the environment where the vehicle is located by the laser radar.
In the running process of the automatic driving vehicle, the laser radar scans the point cloud data of the environment where the vehicle is located, and the non-ground point cloud is used as a potential obstacle to avoid, so that the ground point cloud data and the non-ground point cloud data in the environment point cloud data need to be accurately identified, and the ground point cloud data in the point cloud data are filtered.
In some embodiments, optionally, after the acquiring the point cloud data obtained by scanning the environment of the vehicle with the lidar, the method further includes: acquiring a preset area range; and filtering the point cloud data based on the preset area range, and removing the point cloud data outside the preset area range.
The preset area range refers to an interest area of the ground point cloud data, specifically, the preset area range includes ranges of the point cloud data on all coordinate axes under a space coordinate system, namely ranges on an X axis, a Y axis and a Z axis, and if the point cloud data meets the ranges on the X axis, the Y axis and the Z axis, the point cloud data is in the preset area range; it is understood that the above-mentioned spatial coordinate system uses the center of the vehicle as the origin of coordinates, and the preset area range is set by those skilled in the art according to experience and requirements, which is not limited herein. In this embodiment, the point cloud data may be filtered according to the preset area range, so as to reject the point cloud data outside the preset area range; the point cloud data is filtered before the ground point cloud data is identified, so that the processing amount of the point cloud data can be reduced, and the resource loss is reduced.
S120, converting the point cloud data into a first coordinate system, and creating a first grid; under the first grid, performing ground point cloud detection on each grid in the first grid to obtain a first detection result; converting the point cloud data into a second coordinate system and creating a second grid; and under the second grid, performing ground point cloud detection on each grid in the second grid to obtain a second detection result.
The first coordinate system is a polar coordinate system, the center of the vehicle is taken as a pole of the polar coordinate system, and the polar coordinate system is divided into a plurality of sector areas according to the angular resolution under the polar coordinate system; dividing a polar coordinate system into a plurality of annular areas according to the distance resolution, and intersecting the sector areas with the annular areas to obtain a plurality of sectors so as to obtain a first grid; fig. 2 is a schematic view of a first grid according to an embodiment of the present invention, where, as shown in fig. 2, the first grid is formed by intersecting a sector area and an annular area, and each sector in the first grid is a grid in the first grid. It should be noted that the size of the first grid is set by those skilled in the art according to experience and requirements, and is not limited herein, and it is understood that the size of the first grid is related to the preset area range.
In this embodiment, under the first grid, ground point cloud detection is performed on each grid in the first grid to obtain a first detection result, where the first detection result includes whether each grid in the first grid is a ground grid, and if so, the grid is marked as the ground grid.
The second coordinate system is a Cartesian coordinate system, and a second grid is established according to the preset Cartesian grid size under the Cartesian coordinate system; fig. 3 is a schematic view of a second grid according to an embodiment of the present invention, and as shown in fig. 3, the second grid is composed of a grid with a side length of 0.5 m. It should be noted that, the dimensions of the second grid and the grids in the second grid are set by those skilled in the art according to experience and requirements, and are not limited herein; it will be appreciated that the size of the second grid is related to the predetermined area range.
In this embodiment, under the second grid, performing ground point cloud detection on each grid in the second grid to obtain a second detection result, where the second detection result includes whether each grid in the second grid is a ground grid, and if so, marking the grid as the ground grid.
In some embodiments, optionally, after the first grid or the second grid is created, the point cloud data may be filtered twice, and point cloud data that is not in the first grid or the second grid may be removed.
On the basis of the above embodiment, optionally, after creating the first grid or the second grid, the method further includes: and filling the grids in the first grid or the second grid with water to obtain the highest point and the lowest point in each grid.
In this embodiment, the first grid or the second grid is filled with water to obtain the highest point and the lowest point in each grid of the first grid or the second grid, so that the elevation of the lowest point and the elevation of the highest point in the grid can be determined according to the point cloud data of the highest point and the point cloud data of the lowest point in the grid.
On the basis of the foregoing embodiment, optionally, under the first grid, performing ground point cloud detection on each grid in the first grid to obtain a first detection result, where the step of obtaining the first detection result includes: radially traversing a mesh in the first grid; for any grid, judging whether the grid meets a first judging condition of ground point clouds or not based on point cloud data of the highest point and the lowest point in the grid, and if the grid meets the first judging condition, marking the grid as a ground grid; and/or traversing a grid of the first grid laterally; for any grid, determining a first height difference based on point cloud data of the lowest points of the grid and adjacent grids, judging whether the grid meets a second judging condition of ground point clouds based on the first height difference, and marking the grid as a ground grid if the grid meets the second judging condition.
The radial traversing method of the grids in the first grids comprises the steps of firstly traversing the grids in a single sector area radially, and then traversing the grids in each sector area in turn along the anticlockwise direction until traversing the true first grids; as shown in fig. 2, the radial traversal of the mesh in the first grid is to traverse the mesh in the fan area Col0 from the pole outwardly along the radius of the fan area and then traverse the mesh in the fan area Col 1-fan area Col365 in the counterclockwise direction.
In this embodiment, the first grid is traversed based on the radial traversal method, and for any grid, whether the current grid meets the first judgment condition is judged based on the point cloud data of the highest point and the lowest point in the current grid, and if the current grid meets the first judgment condition, the current grid is marked as the ground grid. The first determination condition is a condition for determining whether the grid in the first grid is a ground grid when the first grid is traversed radially, specifically, the first determination condition includes a height difference threshold, an angle threshold, a first seed point condition and an adjacent growth relationship, the angle threshold is set by a person skilled in the art, the angle threshold is not limited herein, and the angle threshold can be read from a configuration file.
Illustratively, the first seed point condition is as follows:
polar_grid_lowest[index]<(0.3+(max_h_threshold-0.2)*
seed_radius*0.003)
wherein, pole_grid_low [ index ] represents the lowest point elevation of the current grid, max_h_threshold represents the height difference threshold, and seed_radius is the distance between the lowest point and the pole of the current grid.
The adjacent growth relationship is as follows:
alternatively, |current_z_diff| < max_h_threshold
Wherein current_angle represents the angle between the line between the lowest point in the current grid and the lowest point in the previous grid and the horizontal plane, pre_angle represents the previous angle, seed_radius represents the distance between the lowest point and the pole of the current grid, max_angle_threshold represents the angle threshold, current_z_diff represents the height difference between the lowest point in the current grid and the lowest point in the previous grid, and max_h_threshold represents the height difference threshold. It will be appreciated that, when traversing the initial mesh, the lowest point of the previous mesh is 0,
it should be noted that, the above determination conditions are all empirical formulas, and the setting is adjusted by those skilled in the art according to experience and actual conditions.
Fig. 4 is a flowchart of radial detection in a polar coordinate system according to an embodiment of the present invention, and as shown in fig. 4, the radial detection process is as follows:
1) Traversing grids in the first grid based on the radial traversing method;
2) Judging whether point cloud data exist in the current grid or not for any grid, if the point cloud data exist in the current grid, calculating the height difference between the lowest point and the highest point of the current grid based on the point cloud data of the lowest point and the highest point in the current grid to serve as the grid height difference; otherwise, filtering the current grid;
3) Judging whether the grid height difference is larger than a height difference threshold value, and if so, filtering the current grid; otherwise, taking the lowest point in the current grid as the current point, calculating the distance and the height difference between the current point and the previous point (namely the lowest point in the previous grid) and the current angle of the included angle between the connecting line of the two points and the horizontal plane, and calculating the distance between the current point and the pole;
4) Judging whether the current point meets a first seed point condition according to the distance between the current point and the previous point, the elevation of the current point and the elevation difference threshold value, if the first seed condition is met, marking the current point as a seed point, marking the current grid as a ground grid, setting the current point as the previous point, and setting the current angle value as the previous angle;
5) If the first seed condition is not met, judging whether the current angle, the previous angle and the height difference between the current point and the previous point meet the adjacent growth relation, and if so, marking the current grid as a ground grid; if the adjacent growth relation is not met, 2 seed points are searched for in a forward direction from the current sector area, and if any seed point is not found, the elevation of the previous point is set to be 0; if only 1 seed point is found, setting the elevation of the found seed point as the elevation of the previous point; if 2 seed points are found, calculating the height of the current grid according to the height difference and the horizontal distance of the 2 seed points, and assigning the height value to the previous point; it should be noted that the purpose of this is to determine the height value of the previous seed point as precisely as possible, and to maintain the continuity of the ground growth.
The transverse traversing method of the grids in the first grid comprises the steps of traversing the grids in the annular area firstly, and then traversing the grids in each annular area from the poles outwards in sequence until traversing the whole first grid; as shown in fig. 2, the method for traversing the grids in the first grid is to traverse the grids in the circular area Row1 with the poles as the centers, and then sequentially traverse the grids in the annular areas Row2-Row … from the poles outwards until traversing the whole first grid.
In this embodiment, traversing the grids in the first grid based on the above-mentioned transverse traversing method, for any grid, determining the lowest point elevation of the current grid and the lowest point elevation of the adjacent grid based on the point cloud data of the lowest points in the current grid and the adjacent grid, and determining whether the current grid meets the second determination condition based on the first elevation difference, and if the current grid meets the second determination condition, marking the current grid as a ground grid. The second determination condition is a condition for determining whether the grid in the first grid is a ground grid when traversing the first grid transversely, and the first height difference is a height difference between the lowest point of the current grid and the lowest point of the adjacent grid, and it should be noted that, under the first grid, the adjacent grid refers to the adjacent grid in the same annular area as the current grid, that is, the adjacent grid is a left grid and a right grid of the current grid in the annular area.
Fig. 5 is a flowchart of lateral detection in a polar coordinate system according to an embodiment of the present invention, and as shown in fig. 5, the lateral detection process is as follows:
1) Traversing grids in the first grid based on the transverse traversing method;
2) Judging whether point cloud data exist in the current grid or whether the current grid is marked as a ground grid, and if the point cloud data exist in the current grid or the current grid is marked as the ground grid, calculating the height difference between the lowest point and the highest point of the current grid based on the point cloud data of the lowest point and the highest point in the current grid to serve as grid height difference; otherwise, filtering the current grid;
3) Judging whether the grid height difference is larger than a height difference threshold value, and if so, filtering the current grid; otherwise, searching left and right grids of the current grid, and if seed points exist in the left and right grids, acquiring the lowest point elevation of the left and right grids; otherwise, setting the lowest point elevation of the left grid and the right grid as a maximum value;
4) Respectively calculating the height difference between the current grid and the left and right grids based on the lowest point heights of the current grid and the left and right grids, judging whether at least one first height difference is smaller than a height difference threshold value, and marking the current grid as a ground grid if at least one first height difference is smaller than the height difference threshold value; otherwise, filtering the current grid;
5) Traversing the current annular region again in the opposite direction of traversing the current annular region, and identifying the ground grids in the current annular region of the first grid based on the steps 2-4.
On the basis of the foregoing embodiment, optionally, under the second grid, performing ground point cloud detection on each grid in the second grid to obtain a second detection result, where the step of obtaining the second detection result includes: traversing grids in the second grid, judging whether any grid meets a third judging condition of ground point cloud based on point cloud data of the highest point and the lowest point in the grids, and marking the grid as a ground grid if the grid meets the third judging condition; and/or traversing grids in the second grid, for any grid, determining a second height difference based on point cloud data of the lowest points of the grid and adjacent grids, judging whether the grid meets a fourth judging condition of ground point clouds based on the second height, and marking the grid as a ground grid if the grid meets the fourth judging condition.
The third determination condition is a condition for determining whether the grid in the first grid is a ground grid when traversing the second grid, specifically, the third determination condition includes a height difference threshold and a second seed point condition, the height difference threshold is set by a person skilled in the art, and the height difference threshold is not limited herein and can be read from a configuration file.
Illustratively, the second seed condition is as follows:
grid_lowest_h[index]<
(0.3+(max_h_threshold-0.3)*seed_radius*0.02)
wherein grid_low_h [ index ] is the lowest point elevation in the current grid, and max_h_threshold represents the elevation difference threshold; seed_radius represents the distance of the lowest point in the current grid from the origin of coordinates.
It should be noted that the above determination conditions are empirical formulas, and the setting is adjusted by those skilled in the art according to experience and actual conditions.
In this embodiment, the grids in the second grid are traversed, and for any grid, whether the current grid meets the third judgment condition is judged based on the point cloud data of the highest point and the lowest point in the current grid, and if the third judgment condition is met, the current grid is marked as the ground grid.
Fig. 6 is a flowchart of detection based on a third determination condition in the cartesian coordinate system according to the first embodiment of the invention, and as shown in fig. 6, the detection based on the third determination condition is as follows:
1) Traversing a grid in the second grid;
2) Judging whether point cloud data exist in the current grid or not for any grid, if the point cloud data exist in the current grid, calculating the height difference between the lowest point and the highest point of the current grid based on the point cloud data of the lowest point and the highest point in the current grid to serve as the grid height difference; otherwise, filtering the current grid;
3) Judging whether the grid height difference is larger than a height difference threshold value, and if so, filtering the current grid; otherwise, the lowest point in the current grid is used as the current point;
4) Judging whether the current point meets the second seed point condition, if so, marking the current grid as a ground grid; otherwise, the current grid is filtered.
Wherein the fourth determination condition is another determination condition for determining whether or not the mesh in the first mesh is a ground mesh when traversing the second mesh. In this embodiment, the grids in the second grid are traversed, for any grid, the lowest point elevation of the current grid and the lowest point elevation of the adjacent grid are determined based on the point cloud data of the lowest points in the current grid and the adjacent grid, whether the current grid meets the fourth judgment condition is judged based on the second elevation difference of the lowest point elevation of the current grid and the lowest point elevation Cheng Queding of the adjacent grid, and if the current grid meets the fourth judgment condition, the current grid is marked as the ground grid. The second height difference is the height difference of the lowest point of the current grid and the adjacent grid. In the second grid, the adjacent grids refer to adjacent grids sharing one edge with the current grid, that is, the adjacent grids are four grids of the second grid, that is, the upper, lower, left and right grids adjacent to the current grid, referring to fig. 3.
Fig. 7 is a flowchart of detection based on a fourth determination condition in the cartesian coordinate system according to the first embodiment of the invention, and as shown in fig. 7, the detection based on the fourth determination condition is as follows:
1) Traversing a grid in the second grid;
2) Judging whether point cloud data exist in the current grid or not for any grid, if the point cloud data exist in the current grid, calculating the height difference between the lowest point and the highest point of the current grid based on the point cloud data of the lowest point and the highest point in the current grid to serve as the grid height difference; otherwise, filtering the current grid;
3) Judging whether the grid height difference is larger than a height difference threshold value, and if so, filtering the current grid; otherwise, the lowest point in the current grid is the current point;
4) Acquiring four adjacent grids adjacent to the current grid and the lowest point elevation of each adjacent grid, and respectively determining a second elevation difference based on the highest point elevation and the current point elevation of each adjacent grid; if the adjacent mesh does not have point cloud data or has no lowest point, the lowest point elevation of the adjacent mesh is set to a maximum value.
5) Judging whether at least one second height difference is smaller than a height difference threshold value, and if at least one second height difference is smaller than the height difference threshold value, marking the current grid as a ground grid.
It should be noted that, in this embodiment, two detection modes are provided under the first coordinate system and the second coordinate system, one of the two detection modes may be used as a main detection mode, and the other detection mode may be used as a leak detection mode, so as to improve the accuracy of detection.
S130, determining the ground point cloud data in the point cloud data based on the first detection result and the second detection result.
Specifically, traversing the point cloud data, and for any point cloud data, if the grid of the first grid and/or the grid of the second grid where the point cloud data is located is a ground grid, determining that the point cloud data is ground point cloud data.
In this embodiment, all the point cloud data are traversed, for any point cloud data, whether the first grid mesh in which the point cloud data are located is determined as a ground grid mesh, and whether the second grid mesh in which the point cloud data are located is determined as a ground grid mesh, and if the first grid mesh and/or the second grid mesh in which the point cloud data are located are/is the ground grid mesh, the point cloud data are ground point cloud data until all the ground point cloud data are identified.
According to the technical scheme, point cloud data obtained by scanning the environment where the vehicle is located through the laser radar are obtained; converting the point cloud data into a first coordinate system and creating a first grid; under the first grid, performing ground point cloud detection on each grid in the first grid to obtain a first detection result; converting the point cloud data into a second coordinate system and creating a second grid; under the second grid, performing ground point cloud detection on each grid in the second grid to obtain a second detection result; and determining the ground point cloud data in the point cloud data based on the first detection result and the second detection result. And the ground point cloud detection is carried out on the point cloud data under the first coordinate system and the second coordinate system, so that the identification accuracy of the ground point cloud data is improved.
Example two
Fig. 8 is a schematic structural diagram of a ground point cloud identification device according to a second embodiment of the present invention. As shown in fig. 8, the apparatus includes:
the point cloud data acquisition module 810 is configured to acquire point cloud data obtained by scanning an environment where a vehicle is located by a laser radar;
the ground point cloud detection module 820 is configured to convert the point cloud data into a first coordinate system and create a first grid; under the first grid, performing ground point cloud detection on each grid in the first grid to obtain a first detection result; converting the point cloud data into a second coordinate system and creating a second grid; under the second grid, performing ground point cloud detection on each grid in the second grid to obtain a second detection result;
the ground point cloud data determining module 830 is configured to determine ground point cloud data in the point cloud data based on the first detection result and the second detection result.
On the basis of the above embodiment, optionally, the apparatus further includes a point cloud data filtering module, configured to obtain a preset area range; and filtering the point cloud data based on the preset area range, and removing the point cloud data outside the preset area range.
On the basis of the above embodiment, optionally, the apparatus further includes a water-flooding filling module, configured to perform water-flooding filling on the grids in the first grid or the second grid, to obtain a highest point and a lowest point in each of the grids.
Optionally, on the basis of the above embodiment, the ground point cloud detection module 820 includes a first ground detection unit for traversing the grids in the first grid radially; for any grid, judging whether the grid meets a first judging condition of ground point clouds or not based on point cloud data of the highest point and the lowest point in the grid, and if the grid meets the first judging condition, marking the grid as a ground grid; and/or traversing a grid of the first grid laterally; for any grid, determining a first height difference based on point cloud data of the lowest points of the grid and adjacent grids, judging whether the grid meets a second judging condition of ground point clouds based on the first height difference, and marking the grid as a ground grid if the grid meets the second judging condition.
On the basis of the above embodiment, optionally, the ground point cloud detection module 820 includes a second ground detection unit, configured to traverse a mesh in the second grid, determine, for any mesh, whether the mesh meets a third determination condition of the ground point cloud based on point cloud data of a highest point and a lowest point in the mesh, and if the mesh meets the third determination condition, mark the mesh as a ground mesh; and/or traversing grids in the second grid, for any grid, determining a second height difference based on point cloud data of the lowest points of the grid and adjacent grids, judging whether the grid meets a fourth judging condition of ground point clouds based on the second height, and marking the grid as a ground grid if the grid meets the fourth judging condition.
On the basis of the above embodiment, optionally, the first determination condition includes a height difference threshold, an angle threshold, a first seed point condition, and an adjacent growth relationship; the third decision condition includes a difference of elevation threshold value and a second seed point condition.
On the basis of the foregoing embodiment, optionally, the ground point cloud data determining module 830 is specifically configured to traverse the point cloud data, and for any point cloud data, if the mesh of the first grid and/or the mesh of the second grid where the point cloud data is located is the ground mesh, the point cloud data is the ground point cloud data.
The identification device for the ground point cloud provided by the embodiment of the invention can execute the identification method for the ground point cloud provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Example III
Fig. 9 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 9, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.
Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as the identification method of the ground point cloud.
In some embodiments, the method of identifying a ground point cloud may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the above-described ground point cloud identification method may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the method of identifying the ground point cloud in any other suitable way (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
The computer program for implementing the ground point cloud identification method of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
Example IV
The fourth embodiment of the present invention also provides a computer readable storage medium, where computer instructions are stored, where the computer instructions are configured to cause a processor to execute a method for identifying a ground point cloud, where the method includes:
acquiring point cloud data obtained by scanning an environment where a vehicle is located by a laser radar;
converting the point cloud data into a first coordinate system and creating a first grid; under the first grid, performing ground point cloud detection on each grid in the first grid to obtain a first detection result; converting the point cloud data into a second coordinate system and creating a second grid; under the second grid, performing ground point cloud detection on each grid in the second grid to obtain a second detection result;
and determining the ground point cloud data in the point cloud data based on the first detection result and the second detection result.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method for identifying a ground point cloud, comprising:
acquiring point cloud data obtained by scanning an environment where a vehicle is located by a laser radar;
converting the point cloud data into a first coordinate system and creating a first grid; under the first grid, performing ground point cloud detection on each grid in the first grid to obtain a first detection result; converting the point cloud data into a second coordinate system and creating a second grid; under the second grid, performing ground point cloud detection on each grid in the second grid to obtain a second detection result;
and determining ground point cloud data in the point cloud data based on the first detection result and the second detection result.
2. The method of claim 1, wherein after the acquiring the point cloud data obtained by the lidar scanning the environment in which the vehicle is located, the method further comprises:
acquiring a preset area range;
and filtering the point cloud data based on the preset area range, and removing the point cloud data outside the preset area range.
3. The method of claim 1, wherein after creating the first grid or the second grid, the method further comprises:
And filling the grids in the first grid or the second grid with water to obtain the highest point and the lowest point in each grid.
4. The method of claim 3, wherein performing ground point cloud detection on each grid of the first grid under the first grid to obtain a first detection result comprises:
radially traversing a mesh in the first grid; for any grid, judging whether the grid meets a first judging condition of ground point clouds or not based on point cloud data of the highest point and the lowest point in the grid, and if the grid meets the first judging condition, marking the grid as a ground grid; and/or the number of the groups of groups,
traversing the grids in the first grid transversely; for any grid, determining a first height difference based on point cloud data of the lowest points of the grid and adjacent grids, judging whether the grid meets a second judging condition of ground point clouds based on the first height difference, and marking the grid as a ground grid if the grid meets the second judging condition.
5. The method of claim 3, wherein performing ground point cloud detection on each grid in the second grid under the second grid to obtain a second detection result comprises:
Traversing grids in the second grid, judging whether any grid meets a third judging condition of ground point cloud based on point cloud data of the highest point and the lowest point in the grids, and marking the grid as a ground grid if the grid meets the third judging condition; and/or the number of the groups of groups,
traversing grids in the second grid, determining a second height difference for any grid based on point cloud data of the lowest points of the grid and adjacent grids, judging whether the grid meets a fourth judging condition of ground point clouds based on the second height, and marking the grid as a ground grid if the grid meets the fourth judging condition.
6. The method of any of claims 1-5, wherein the determining ground point cloud data in the point cloud data based on the first and second detection results comprises:
traversing the point cloud data, and for any point cloud data, if the grid of the first grid and/or the grid of the second grid where the point cloud data is located is a ground grid, determining that the point cloud data is ground point cloud data.
7. The method of claim 4 or 5, wherein the first decision condition comprises a height difference threshold, an angle threshold, a first seed point condition, and a neighbor growing relationship; the third decision condition includes a difference of elevation threshold value and a second seed point condition.
8. A ground point cloud identification device, comprising:
the point cloud data acquisition module is used for acquiring point cloud data obtained by scanning the environment where the vehicle is located by the laser radar;
the ground point cloud detection module is used for converting the point cloud data into a first coordinate system and creating a first grid; under the first grid, performing ground point cloud detection on each grid in the first grid to obtain a first detection result; converting the point cloud data into a second coordinate system and creating a second grid; under the second grid, performing ground point cloud detection on each grid in the second grid to obtain a second detection result;
the ground point cloud data determining module is used for determining ground point cloud data in the point cloud data based on the first detection result and the second detection result.
9. An electronic device, the electronic device comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of identifying a ground point cloud of any one of claims 1-7.
10. A computer readable storage medium, characterized in that the computer readable storage medium stores computer instructions for causing a processor to implement the method of identifying a ground point cloud according to any of claims 1-7 when executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310778252.6A CN116883969A (en) | 2023-06-28 | 2023-06-28 | Ground point cloud identification method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310778252.6A CN116883969A (en) | 2023-06-28 | 2023-06-28 | Ground point cloud identification method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116883969A true CN116883969A (en) | 2023-10-13 |
Family
ID=88261298
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310778252.6A Pending CN116883969A (en) | 2023-06-28 | 2023-06-28 | Ground point cloud identification method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116883969A (en) |
-
2023
- 2023-06-28 CN CN202310778252.6A patent/CN116883969A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111582054B (en) | Point cloud data processing method and device and obstacle detection method and device | |
| CN116520353B (en) | Ground detection method, device, storage medium and equipment based on laser point cloud | |
| CN113971723B (en) | Method, device, equipment and storage medium for constructing three-dimensional map in high-precision map | |
| CN114882198A (en) | Target determination method, device, equipment and medium | |
| CN110927743A (en) | Intelligent vehicle positioning method based on multi-line laser point cloud polarization representation | |
| CN114332487A (en) | Image-based accumulated water early warning method, device, equipment, storage medium and product | |
| CN116091709B (en) | Three-dimensional reconstruction method and device for building, electronic equipment and storage medium | |
| CN111783648A (en) | Method and device for extracting guardrail in road point cloud | |
| CN116681932A (en) | Object identification method and device, electronic equipment and storage medium | |
| CN113920273B (en) | Image processing method, device, electronic equipment and storage medium | |
| CN116883969A (en) | Ground point cloud identification method and device, electronic equipment and storage medium | |
| CN112884026B (en) | Image identification-assisted power transmission line laser LiDAR point cloud classification method | |
| CN116434181A (en) | Ground point detection method, device, electronic equipment and medium | |
| CN114694138B (en) | Road surface detection method, device and equipment applied to intelligent driving | |
| CN117392000B (en) | Noise removing method and device, electronic equipment and storage medium | |
| CN114155508B (en) | Road change detection method, device, equipment and storage medium | |
| CN117953451A (en) | Road boundary detection method, device, equipment and medium | |
| CN116934779A (en) | Laser point cloud segmentation method and device, electronic equipment and storage medium | |
| CN117853707A (en) | Three-dimensional target detection and model training method, device, equipment and vehicle | |
| CN117419736A (en) | Target area determining method and device, electronic equipment and storage medium | |
| CN118262313A (en) | Road area detection method and device and electronic equipment | |
| CN116795131A (en) | Unmanned aerial vehicle inspection method and device for power distribution line based on radar | |
| CN116642503A (en) | Likelihood map updating method, device, equipment and storage medium | |
| CN118212469A (en) | Point cloud-based power line classification post-processing method and device, equipment and medium | |
| CN118154795A (en) | Ground generation method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |