CN110782465A - Ground segmentation method and device based on laser radar and storage medium - Google Patents
Ground segmentation method and device based on laser radar and storage medium Download PDFInfo
- Publication number
- CN110782465A CN110782465A CN201911404869.1A CN201911404869A CN110782465A CN 110782465 A CN110782465 A CN 110782465A CN 201911404869 A CN201911404869 A CN 201911404869A CN 110782465 A CN110782465 A CN 110782465A
- Authority
- CN
- China
- Prior art keywords
- ground
- point cloud
- value
- point
- laser radar
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- 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
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
- G01S7/4802—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Traffic Control Systems (AREA)
- Optical Radar Systems And Details Thereof (AREA)
Abstract
The embodiment of the application provides a ground segmentation method, a ground segmentation device and a storage medium based on a laser radar, wherein the method comprises the following steps: collecting point cloud data in a scanning area by a side-mounted laser radar; acquiring a marked point cloud meeting a marking condition from the point cloud data; calculating a ground height estimation value according to the marked point cloud; and judging whether the coordinate point in the point cloud data is a ground point or not according to the ground height estimation value. The embodiment of the application can accurately perform ground segmentation under the condition that the laser radar is installed laterally and has a certain installation inclination angle, so that the scanning blind area is reduced, and the accuracy and the stability of ground segmentation are improved.
Description
Technical Field
The application relates to an automatic driving technology, in particular to the technical field of radar data processing, and particularly relates to a ground segmentation method and device based on a laser radar and a storage medium.
Background
An automatic driving vehicle is also called an unmanned vehicle or a computer driving vehicle, and is an intelligent vehicle which can realize that the vehicle automatically travels along a road in an unmanned state. Generally, before an autonomous vehicle travels on an actual traffic road, a lot of tests are required to check the safety and stability of the autonomous vehicle. In the field of automatic driving, a laser radar is generally installed right above a vehicle roof, so as to acquire three-dimensional spatial information around a vehicle body. Because the automobile body shelters from and restriction such as laser beam exit angle, often can have the scanning blind area around the automobile body, consequently in on-vehicle multi-thread laser radar system, the automobile body side also can install laser radar usually and further reduce the blind area.
Most of the existing laser radar ground segmentation methods aim at the situation that a laser radar is installed on a car roof, and the segmentation accuracy is low under the condition that the installation position of the laser radar is obviously inclined.
Therefore, the prior art has defects and needs to be improved and developed.
Disclosure of Invention
The embodiment of the application provides a ground segmentation method, a ground segmentation device and a storage medium based on a laser radar, wherein the ground segmentation can be accurately carried out under the condition that the laser radar is installed on the side and has a certain installation inclination angle.
The embodiment of the application provides a ground segmentation method based on a laser radar, which comprises the following steps:
collecting point cloud data in a scanning area by a side-mounted laser radar;
acquiring a marked point cloud meeting a marking condition from the point cloud data;
calculating a ground height estimation value according to the marked point cloud;
and judging whether the coordinate point in the point cloud data is a ground point or not according to the ground height estimation value.
In the ground segmentation method based on the laser radar according to the embodiment of the present application, the determining whether a coordinate point in the point cloud data is a ground point according to the ground height estimation value includes:
judging whether the absolute value of the difference between the height value of each coordinate point in the point cloud data and the ground height estimated value is smaller than a second threshold value or not;
and determining the coordinate point of which the absolute value of the difference between the height value and the ground height estimated value in the point cloud data is smaller than a second threshold value as a ground point.
In the ground segmentation method based on the laser radar according to the embodiment of the present application, the determining whether a coordinate point in the point cloud data is a ground point according to the ground height estimation value includes:
calculating the orthographic projection distance of the laser beam of the side-mounted laser radar on the horizontal plane according to the ground height estimated value, the emergence angle of the laser beam of the side-mounted laser radar and the mounting position inclination angle;
judging whether the absolute value of the difference between the orthographic projection distance of each coordinate point in the point cloud data on the horizontal plane and the orthographic projection distance of the laser beam of the side-mounted laser radar on the horizontal plane is smaller than a third threshold value or not;
and determining a coordinate point, in the point cloud data, of which the absolute value of the difference between the orthographic projection distance of the horizontal plane and the orthographic projection distance of the laser beam of the side-mounted laser radar on the horizontal plane is smaller than a third threshold value, as a ground point.
In the ground segmentation method based on the laser radar according to the embodiment of the present application, the obtaining a marked point cloud satisfying a marking condition from the point cloud data includes:
judging whether the absolute value of the difference between the height value of each coordinate point in the point cloud data and the installation height value of the side-installed laser radar is smaller than a first threshold value or not;
and marking the coordinate point of which the absolute value of the difference between the height value in the point cloud data and the installation height value of the side-installed laser radar is smaller than a first threshold value to obtain the marked point cloud.
In the ground segmentation method based on the laser radar according to the embodiment of the present application, the calculating a ground height estimation value according to the marked point cloud includes:
and calculating the average value of the height values of all coordinate points in the marked point cloud to obtain the ground height estimation value.
In the ground segmentation method based on the laser radar in the embodiment of the application, before the collecting point cloud data in the scanning area by the side-mounted laser radar, the method further includes:
and calibrating the side-mounted laser radar.
The embodiment of the present application further provides a ground segmentation device based on laser radar, the device includes:
the acquisition unit is used for acquiring point cloud data in the scanning area through a side-mounted laser radar;
an acquisition unit configured to acquire a marker point cloud satisfying a marker condition from the point cloud data;
the calculating unit is used for calculating a ground height estimated value according to the marked point cloud;
and the judging unit is used for judging whether the coordinate point in the point cloud data is a ground point or not according to the ground height estimation value.
In the ground segmentation apparatus based on lidar according to an embodiment of the present application, the determining unit includes:
the first judgment subunit is used for judging whether the absolute value of the difference between the height value of each coordinate point in the point cloud data and the ground height estimation value is smaller than a second threshold value or not;
and the first determining subunit is used for determining the coordinate point of which the absolute value of the difference between the height value and the ground height estimated value in the point cloud data is smaller than a second threshold value as the ground point.
In the ground segmentation apparatus based on lidar according to an embodiment of the present application, the determining unit includes:
the calculating subunit is used for calculating the orthographic projection distance of the laser beam of the side-mounted laser radar on the horizontal plane according to the ground height estimated value, the emergence angle of the laser beam of the side-mounted laser radar and the mounting position inclination angle;
the second judgment subunit is used for judging whether the absolute value of the difference between the orthographic projection distance of each coordinate point in the point cloud data on the horizontal plane and the orthographic projection distance of the laser beam of the side-mounted laser radar on the horizontal plane is smaller than a third threshold value or not;
and the second determining subunit is used for determining a coordinate point, as a ground point, of the point cloud data, wherein the absolute value of the difference between the orthographic projection distance of the horizontal plane and the orthographic projection distance of the laser beam of the side-mounted laser radar on the horizontal plane is smaller than a third threshold value.
In the ground segmentation apparatus based on lidar according to an embodiment of the present application, the obtaining unit includes:
a third judging subunit, configured to judge whether an absolute value of a difference between a height value of each coordinate point in the point cloud data and an installation height value of the side-mounted laser radar is smaller than a first threshold;
and the marking subunit is used for marking the coordinate point of which the absolute value of the difference between the height value in the point cloud data and the installation height value of the side-installed laser radar is smaller than a first threshold value so as to obtain the marked point cloud.
In the ground segmentation device based on the laser radar in the embodiment of the application, the calculation unit is configured to calculate an average value of the height values of all coordinate points in the marked point cloud to obtain the ground height estimation value.
In the ground segmentation apparatus based on lidar according to an embodiment of the present application, the apparatus further includes:
and the calibration unit is used for calibrating the side-mounted laser radar.
The embodiment of the present application further provides a storage medium, where a computer program is stored, and when the computer program runs on a computer, the computer is enabled to execute the steps in the ground segmentation method based on laser radar.
According to the embodiment of the application, point cloud data in a scanning area are collected through a side-mounted laser radar; acquiring a marked point cloud meeting a marking condition from the point cloud data; calculating a ground height estimation value according to the marked point cloud; and judging whether the coordinate point in the point cloud data is a ground point or not according to the ground height estimation value. The embodiment of the application can accurately perform ground segmentation under the condition that the laser radar is installed laterally and has a certain installation inclination angle, so that the scanning blind area is reduced, and the accuracy and the stability of ground segmentation are improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings used in the description of the embodiments will be briefly introduced below. It is obvious that the drawings in the following description are only some embodiments of the application, and that for a person skilled in the art, other drawings can be derived from them without inventive effort.
Fig. 1 is a schematic flowchart of a ground segmentation method based on a lidar according to an embodiment of the present disclosure.
Fig. 2 is a top view of an installation manner of the laser radar according to the embodiment of the present application.
Fig. 3 is a front view of an installation manner of the laser radar according to the embodiment of the present application.
Fig. 4 is a top view of a coordinate system of a lidar according to an embodiment of the present disclosure.
Fig. 5 is a side view of a coordinate system of a lidar provided in an embodiment of the present application.
Fig. 6 is another schematic flowchart of a ground segmentation method based on lidar according to an embodiment of the present disclosure.
Fig. 7 is a schematic flowchart of a laser radar-based ground segmentation method according to an embodiment of the present application.
Fig. 8 is another front view of an installation manner of the laser radar according to the embodiment of the present application.
Fig. 9 is a schematic structural diagram of a ground partitioning device based on a lidar according to an embodiment of the present application.
Fig. 10 is another schematic structural diagram of a laser radar-based ground segmentation apparatus according to an embodiment of the present application.
Fig. 11 is a schematic structural diagram of a terminal device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. It is to be understood that the embodiments described are only a few embodiments of the present application and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without inventive step, are within the scope of the present application.
An automatic driving vehicle is also called an unmanned vehicle or a computer driving vehicle, and is an intelligent vehicle which can realize that the vehicle automatically travels along a road in an unmanned state. Generally, before an autonomous vehicle travels on an actual traffic road, a lot of tests are required to check the safety and stability of the autonomous vehicle. In the field of automatic driving, a laser radar is generally installed right above a vehicle roof, so as to acquire three-dimensional spatial information around a vehicle body. Because the automobile body shelters from and restriction such as laser beam exit angle, often can have the scanning blind area around the automobile body, consequently in on-vehicle multi-thread laser radar system, the automobile body side also can install laser radar usually and further reduce the blind area.
In the existing laser radar ground segmentation method, for example, a laser radar is equally divided according to a certain angle on a horizontal plane, a point cloud is organized in a ray form, whether each ray is a ground point is judged by evaluating a slope angle formed by two adjacent points on each ray, or a space is segmented into a plurality of sub-planes along the x direction, and plane fitting is performed on each sub-plane, so that the ground is segmented. Therefore, the embodiment of the application provides a ground segmentation method, a ground segmentation device and a storage medium based on a laser radar, and the ground segmentation can be accurately performed under the condition that the laser radar is installed laterally and has a certain installation inclination angle.
The embodiment of the application provides a ground segmentation method based on a laser radar, which can be applied to an automatic piloting vehicle, an unmanned robot, an unmanned airplane and the like.
Referring to fig. 1 to 5, fig. 1 is a schematic flowchart of a ground segmentation method based on a laser radar according to an embodiment of the present disclosure, and fig. 2 to 5 are views of an installation manner and a coordinate system of a laser radar according to an embodiment of the present disclosure. The ground segmentation method based on the laser radar is applied to an automatic driving vehicle, and the method can comprise the following steps:
Point cloud data is the most common and basic three-dimensional model used to represent three-dimensional images. The point cloud data can be directly measured, each point corresponds to a measuring point, each point in the point cloud data is not processed by other processing means, the maximum information content is contained, information required for constructing a three-dimensional image needs to be extracted from the point cloud data by other extracting means, and the process of extracting the information in the point cloud is the three-dimensional image processing.
The point cloud is a massive point set which expresses the target space distribution and the target surface characteristics under the same space reference system, and after the space coordinates of each sampling point on the surface of the object are obtained, the point set is obtained and is called as the point cloud (PointCloud).
The point cloud obtained by a three-dimensional scanner such as a laser radar includes rich information, such as three-dimensional coordinates (XYZ), laser reflection Intensity (Intensity), color information (RGB), classification values, time, and the like. Wherein the intensity information is related to the surface material, roughness, incident angle direction of the target, and the emission energy, laser wavelength, etc. of the instrument.
The method and the device for acquiring the point cloud data adopt the multi-line laser radar. The multi-line laser radar comprises a plurality of laser transmitters, each laser transmitter can measure a distance, the multi-line laser transmitters transmit laser through semiconductor laser transmitters, and echo optical signals are detected to obtain point cloud data.
As shown in fig. 2 and 3, a top view and a front view of one installation mode of the laser radar are provided, the laser radar is provided with a plurality of lines on the top and the left and right sides of the vehicle 1, for example, the laser radar 11 is arranged in the middle and is just above the roof of the vehicle, and the laser radars 12 are arranged on the left and right sides and have certain inclination angles.
As shown in fig. 3, the laser radar 11 being installed mainly scans most of the area near the vehicle body, for example, the area S1, and due to limitations such as vehicle body shielding and laser beam emission angles, there are often scanning blind areas around the vehicle body, so that it is necessary to install the laser radar 12 on the side to scan the area where the laser radar 11 being installed cannot scan or has low scanning accuracy, for example, the area S2, and the area S2 is the area near the vehicle body.
In some embodiments, before the acquiring point cloud data within the scanning area by the side-mounted lidar, calibrating the side-mounted lidar is further included. Specifically, the side-mounted laser radar 12 is calibrated to the coordinate system of the vehicle roof on which the laser radar 11 is being mounted, so that data scanned by the side-mounted laser radar 12 is mapped to the coordinate system on which the laser radar 11 is being mounted, and data collected by all the laser radars mounted on the vehicle are unified into the same coordinate system.
As shown in fig. 4 and 5, in the rectangular coordinate system (XYZ) established by the multiline lidar itself according to the embodiment of the present invention, the X axis is indicated as the heading direction, the Z axis is indicated as the direction pointing to the sky, and the Y axis is indicated as the left side of the heading direction.
For example, the installation height (height from the ground 2) of the side-mounted laser radar 12 is set to h, and after the calibration between the laser radars is completed, that is, after the side-mounted laser radar 12 is calibrated to the coordinate system of the vehicle roof on which the laser radar 11 is being installed, point cloud data in the scanning area S2 is collected by the side-mounted laser radar 12. Since an excessively large obstacle does not usually appear in the area close to the vehicle body, when point cloud data in the scanning area S2 is collected, the coordinates of the nearest k laser beams irradiated on the ground 2 may be counted. For example, k represents 1 to 3.
And 102, acquiring marked point clouds meeting marking conditions from the point cloud data.
The marked point cloud is a coordinate point set of the suspected ground points meeting the marking condition. And removing non-ground points from the point cloud data, and then marking the points meeting the marking conditions to obtain a marked point cloud which is used as basic data for next analysis.
In some embodiments, the obtaining a marker point cloud satisfying a marker condition from the point cloud data comprises:
judging whether the absolute value of the difference between the height value of each coordinate point in the point cloud data and the installation height value of the side-installed laser radar is smaller than a first threshold value or not;
and marking the coordinate point of which the absolute value of the difference between the height value in the point cloud data and the installation height value of the side-installed laser radar is smaller than a first threshold value to obtain the marked point cloud.
For example, it is determined whether the absolute value of the difference between the height value (Z value) of each coordinate point in the point cloud data and the installation height value h of the side-installed laser radar 12 is smaller than a first threshold;
and marking the coordinate point of which the absolute value of the difference between the height value Z in the point cloud data and the installation height value h of the side-installed laser radar 12 is smaller than a first threshold value to obtain the marked point cloud. For example, the first threshold may be set according to experimental data, for example, the first threshold is set to 0.2 m. The height value (Z value) of the coordinate point is the height of the scanning point of the lidar relative to the origin of the lidar coordinate system.
In order to simultaneously meet special conditions such as excessively narrow lane, large-area shielding on two sides and the like, when ground point statistics is carried out, the coordinate Z value of each point and the installation height h of the laser radar are compared, and if the difference value between the coordinate Z value of each point and the installation height h of the laser radar is too large, the point is judged to be a non-ground point, namely, the point does not participate in the statistics. If the difference value of the two points is within the first threshold range, marking can be carried out to obtain marking points of the suspected ground points, and after the coordinate Z values of all the points in the point cloud data are compared, all the obtained marking points form a marking point cloud.
And 103, calculating a ground height estimation value according to the marked point cloud.
Since no overlarge obstacle usually appears in the area close to the vehicle body, when the point cloud data in the scanning area S2 is collected, the coordinates of the latest k laser beams irradiated on the ground 2 are counted to obtain the estimated ground height. Specifically, after counting all the mark points satisfying the mark condition, calculating an average value of height values (Z values) of all coordinate points in the mark point cloud to obtain a ground height estimation value, where the ground height estimation value can be expressed by the following formula:
where h' represents the ground height estimate, n represents the number of points satisfying the labeling condition,
the coordinate Z value of each point is shown.
And 104, judging whether the coordinate point in the point cloud data is a ground point or not according to the ground height estimation value.
In some embodiments, the determining whether the coordinate point in the point cloud data is a ground point according to the ground height estimation value includes:
judging whether the absolute value of the difference between the height value of each coordinate point in the point cloud data and the ground height estimated value is smaller than a second threshold value or not;
and determining the coordinate point of which the absolute value of the difference between the height value and the ground height estimated value in the point cloud data is smaller than a second threshold value as a ground point.
Specifically, by comparing the coordinate Z values of all points in the point cloud data with the ground height estimation value, a point with a difference value smaller than a second threshold is determined as a ground point, and a point with a difference value larger than the second threshold is determined as a non-ground point.
In some embodiments, the determining whether the coordinate point in the point cloud data is a ground point according to the ground height estimation value includes:
calculating the orthographic projection distance of the laser beam of the side-mounted laser radar on the horizontal plane according to the ground height estimated value, the emergence angle of the laser beam of the side-mounted laser radar and the mounting position inclination angle;
judging whether the absolute value of the difference between the orthographic projection distance of each coordinate point in the point cloud data on the horizontal plane and the orthographic projection distance of the laser beam of the side-mounted laser radar on the horizontal plane is smaller than a third threshold value or not;
and determining a coordinate point, in the point cloud data, of which the absolute value of the difference between the orthographic projection distance of the horizontal plane and the orthographic projection distance of the laser beam of the side-mounted laser radar on the horizontal plane is smaller than a third threshold value, as a ground point.
Specifically, the orthogonal projection distances of all coordinate points in the point cloud data on the horizontal plane and the orthogonal projection distances of the laser beams of the side-mounted laser radar on the horizontal plane are compared, a point with the difference value smaller than a third threshold value is used as a ground point, and a point with the difference value larger than the third threshold value is determined as a non-ground point.
All the above optional technical solutions may be combined arbitrarily to form optional embodiments of the present application, and are not described herein again.
In particular implementation, the present application is not limited by the execution sequence of the described steps, and some steps may be performed in other sequences or simultaneously without conflict.
As can be seen from the above, in the ground segmentation method based on the laser radar provided in the embodiment of the present application, the point cloud data in the scanning area is collected by laterally installing the laser radar; acquiring a marked point cloud meeting a marking condition from the point cloud data; calculating a ground height estimation value according to the marked point cloud; and judging whether the coordinate point in the point cloud data is a ground point or not according to the ground height estimation value. The embodiment of the application can accurately perform ground segmentation under the condition that the laser radar is installed laterally and has a certain installation inclination angle, so that the scanning blind area is reduced, and the accuracy and the stability of ground segmentation are improved.
Referring to fig. 6, fig. 6 is another schematic flow chart of a ground segmentation method based on lidar according to an embodiment of the present disclosure. The ground segmentation method based on the laser radar can comprise the following steps:
Specifically, the side-mounted laser radar 12 is calibrated to the coordinate system of the vehicle roof on which the laser radar 11 is being mounted, so that data scanned by the side-mounted laser radar 12 is mapped to the coordinate system on which the laser radar 11 is being mounted, and data collected by all the laser radars mounted on the vehicle are unified into the same coordinate system.
As shown in fig. 4 and 5, in the rectangular coordinate system (XYZ) established by the multiline lidar itself according to the embodiment of the present invention, the X axis is indicated as the heading direction, the Z axis is indicated as the direction pointing to the sky, and the Y axis is indicated as the left side of the heading direction.
And step 202, collecting point cloud data in a scanning area through a side-mounted laser radar.
As shown in fig. 3, the laser radar 11 being installed mainly scans most of the area near the vehicle body, for example, the area S1, and due to limitations such as vehicle body shielding and laser beam emission angles, there are often scanning blind areas around the vehicle body, so that it is necessary to install the laser radar 12 on the side to scan the area where the laser radar 11 being installed cannot scan or has low scanning accuracy, for example, the area S2, and the area S2 is the area near the vehicle body.
For example, the installation height (height from the ground 2) of the side-mounted laser radar 12 is set to h, and after the calibration between the laser radars is completed, that is, after the side-mounted laser radar 12 is calibrated to the coordinate system of the vehicle roof on which the laser radar 11 is being installed, point cloud data in the scanning area S2 is collected by the side-mounted laser radar 12. Since an excessively large obstacle does not usually appear in the area close to the vehicle body, when point cloud data in the scanning area S2 is collected, the coordinates of the nearest k laser beams irradiated on the ground 2 may be counted. For example, k represents 1 to 3.
For example, it is determined whether the absolute value of the difference between the height value (Z value) of each coordinate point in the point cloud data and the installation height value h of the side-installed laser radar 12 is smaller than a first threshold value. If yes, go to step 204; if not, go to step 208.
And 204, marking the coordinate point of which the absolute value of the difference between the height value in the point cloud data and the installation height value of the side-installed laser radar is smaller than a first threshold value to obtain the marked point cloud.
And marking the coordinate point of which the absolute value of the difference between the height value Z in the point cloud data and the installation height value h of the side-installed laser radar 12 is smaller than a first threshold value to obtain the marked point cloud. For example, the first threshold may be set according to experimental data, for example, the first threshold is set to 0.2 m. The height value (Z value) of the coordinate point is the height of the scanning point of the lidar relative to the origin of the lidar coordinate system.
If the difference value of the two points is within the first threshold range, marking can be carried out to obtain marking points of the suspected ground points, and after the coordinate Z values of all the points in the point cloud data are compared, all the obtained marking points form a marking point cloud.
Since no overlarge obstacle usually appears in the area close to the vehicle body, when the point cloud data in the scanning area S2 is collected, the coordinates of the latest k laser beams irradiated on the ground 2 are counted to obtain the estimated ground height. Specifically, after counting all the mark points satisfying the mark condition, calculating an average value of height values (Z values) of all coordinate points in the mark point cloud to obtain a ground height estimation value, where the ground height estimation value can be expressed by the following formula:
；
where h' represents the ground height estimate, n represents the number of points satisfying the labeling condition,
the coordinate Z value of each point is shown.
And step 207, determining the coordinate point of which the absolute value of the difference between the height value and the ground height estimated value in the point cloud data is smaller than a second threshold value as a ground point.
And step 208, determining the non-ground points.
And determining a coordinate point of which the absolute value of the difference between the height value in the point cloud data and the installation height value of the side-installed laser radar is greater than a first threshold value as a non-ground point.
And determining the coordinate point of which the absolute value of the difference between the height value and the ground height estimated value in the point cloud data is greater than a second threshold value as a non-ground point.
As can be seen from the above, in the ground segmentation method based on the laser radar provided in the embodiment of the present application, the point cloud data in the scanning area is collected by laterally installing the laser radar; acquiring a marked point cloud meeting a marking condition from the point cloud data; calculating a ground height estimation value according to the marked point cloud; judging whether the absolute value of the difference between the height value of each coordinate point in the point cloud data and the ground height estimated value is smaller than a second threshold value or not; and determining the coordinate point of which the absolute value of the difference between the height value and the ground height estimated value in the point cloud data is smaller than a second threshold value as a ground point. The embodiment of the application can accurately perform ground segmentation under the condition that the laser radar is installed laterally and has a certain installation inclination angle, so that the scanning blind area is reduced, and the accuracy and the stability of ground segmentation are improved.
Referring to fig. 7 and 8, fig. 7 is a schematic flowchart illustrating a ground segmentation method based on a lidar according to an embodiment of the present disclosure, and fig. 8 is another front view illustrating an installation manner of the lidar according to an embodiment of the present disclosure. The ground segmentation method based on the laser radar can comprise the following steps:
and 301, calibrating the laser radar arranged on the opposite side.
Specifically, the side-mounted laser radar 12 is calibrated to the coordinate system of the vehicle roof on which the laser radar 11 is being mounted, so that data scanned by the side-mounted laser radar 12 is mapped to the coordinate system on which the laser radar 11 is being mounted, and data collected by all the laser radars mounted on the vehicle are unified into the same coordinate system.
As shown in fig. 4 and 5, in the rectangular coordinate system (XYZ) established by the multiline lidar itself according to the embodiment of the present invention, the X axis is indicated as the heading direction, the Z axis is indicated as the direction pointing to the sky, and the Y axis is indicated as the left side of the heading direction.
And 302, collecting point cloud data in the scanning area through a side-mounted laser radar.
As shown in fig. 3, the laser radar 11 being installed mainly scans most of the area near the vehicle body, for example, the area S1, and due to limitations such as vehicle body shielding and laser beam emission angles, there are often scanning blind areas around the vehicle body, so that it is necessary to install the laser radar 12 on the side to scan the area where the laser radar 11 being installed cannot scan or has low scanning accuracy, for example, the area S2, and the area S2 is the area near the vehicle body.
For example, the installation height (height from the ground 2) of the side-mounted laser radar 12 is set to h, and after the calibration between the laser radars is completed, that is, after the side-mounted laser radar 12 is calibrated to the coordinate system of the vehicle roof on which the laser radar 11 is being installed, point cloud data in the scanning area S2 is collected by the side-mounted laser radar 12. Since an excessively large obstacle does not usually appear in the area close to the vehicle body, when point cloud data in the scanning area S2 is collected, the coordinates of the nearest k laser beams irradiated on the ground 2 may be counted. For example, k represents 1 to 3.
For example, it is determined whether the absolute value of the difference between the height value (Z value) of each coordinate point in the point cloud data and the installation height value h of the side-installed laser radar 12 is smaller than a first threshold value. If yes, go to step 304; if not, go to step 309.
And marking the coordinate point of which the absolute value of the difference between the height value Z in the point cloud data and the installation height value h of the side-installed laser radar 12 is smaller than a first threshold value to obtain the marked point cloud. For example, the first threshold may be set according to experimental data, for example, the first threshold is set to 0.2 m. The height value (Z value) of the coordinate point is the height of the scanning point of the lidar relative to the origin of the lidar coordinate system.
If the difference value of the two points is within the first threshold range, marking can be carried out to obtain marking points of the suspected ground points, and after the coordinate Z values of all the points in the point cloud data are compared, all the obtained marking points form a marking point cloud.
And 305, calculating the average value of the height values of all coordinate points in the marked point cloud to obtain a ground height estimated value.
Since no overlarge obstacle usually appears in the area close to the vehicle body, when the point cloud data in the scanning area S2 is collected, the coordinates of the latest k laser beams irradiated on the ground 2 are counted to obtain the estimated ground height. Specifically, after counting all the mark points satisfying the mark condition, calculating an average value of height values (Z values) of all coordinate points in the mark point cloud to obtain a ground height estimation value, where the ground height estimation value can be expressed by the following formula one:
；
where h' represents the ground height estimate, n represents the number of points satisfying the labeling condition,
the coordinate Z value of each point is shown.
And step 306, calculating the orthographic projection distance of the laser beam of the side-mounted laser radar on the horizontal plane according to the ground height estimated value, the emergence angle of the laser beam of the side-mounted laser radar and the mounting position inclination angle.
For example, as shown in fig. 8, a rectangular coordinate system (XYZ) is a coordinate system of the side-mounted laser radar after calibration between the laser radars is completed. The coordinate system (X 'Y' Z ') is a coordinate system before the calibration of the laser radars with side-mounted laser radars is not completed, i.e. the coordinate system of the radar 12 with side-mounted laser radars, wherein the X' axis is indicated as the direction of the vehicle head, the Z 'axis is indicated as the direction pointing above the laser radars with side-mounted laser radars, the Y' axis is indicated as the left side of the advancing direction of the vehicle head, and the Y 'axis is perpendicular to the Z' axis.
On the premise that the actual installation position and angle of the side-mounted laser radar 12 are known, since the exit angle of each beam of the laser radar is an intrinsic parameter, the projection radius r of each laser beam on the horizontal ground and the projection radius r' of each laser beam on the scanned object can be used as judgment conditions. The projection radius r of the laser beam on the horizontal ground can be expressed by the formula two:
wherein r represents the projection radius of the laser beam A on the horizontal ground point a, h' represents the estimated ground height value, the angle theta represents the exit angle of the laser beam A of the side-mounted laser radar 12, and the angle α represents the mounting position inclination angle of the side-mounted laser radar 12.
Further, the projection radius r' of the laser beam irradiated on the scanned object can be expressed by the following formula three:
where r 'represents the projection radius of the laser beam a on the scanned object 3, and x' and y 'are the x' value and y 'value of the coordinate point a' of the laser beam on the scanned object 3, respectively. The projection radius r 'is the orthogonal projection distance of the scanning coordinate point a' of the laser beam scanning of the side-mounted laser radar on the scanned object 3 on the horizontal plane.
The scanned object may be a flat ground, a convex or concave ground, an obstacle on the ground, or the like.
As shown in fig. 8, where r represents a projection radius of the laser beam a on the horizontal ground point a, the projection radius r is a forward projection distance of the exit scanning line a of the side-mounted laser radar 12 on the horizontal plane, the forward projection distance r of the laser beam a of the side-mounted laser radar 12 on the horizontal plane is calculated by using the ground height estimated value h ', the exit angle θ of the laser beam a of the side-mounted laser radar 12 and the mounting position inclination angle α, r ' represents a projection radius of the laser beam a on the scanned object 3, x ' and y ' are an x ' value and a y ' value of a coordinate point a ' of the laser beam a on the scanned object 3, respectively, the projection radius r ' is a forward projection distance of the scanning point a ' of the exit scanning line a of the laser radar 12 on the scanned object 13 on the horizontal plane, the projection radius r ' is a projection radius r ' on the scanned object and an absolute projection radius r ' of the laser beam on the horizontal plane, and if the absolute projection radius r ' is smaller than a third projection radius r, the third projection step is performed, for example, if the absolute projection radius r ' is smaller than the third projection distance r ' is set, and the third projection radius r, and the third projection distance is performed.
And 308, determining a coordinate point, in the point cloud data, of which the absolute value of the difference between the orthographic projection distance of the horizontal plane and the orthographic projection distance of the laser beam of the side-mounted laser radar is smaller than a third threshold value, as a ground point.
And determining a coordinate point of which the absolute value of the difference between the height value in the point cloud data and the installation height value of the side-installed laser radar is greater than a first threshold value as a non-ground point.
And determining a coordinate point, in the point cloud data, of which the absolute value of the difference between the orthographic projection distance of the horizontal plane and the orthographic projection distance of the laser beam of the side-mounted laser radar is greater than a third threshold value, as a non-ground point.
For example, as shown in fig. 8, a coordinate point a 'in the point cloud data, at which the absolute value of the difference between the forward projection distance r' on the horizontal plane and the forward projection distance r on the horizontal plane of the laser beam of the side-mounted laser radar is greater than a third threshold value, is determined as a non-ground point.
As can be seen from the above, in the ground segmentation method based on the laser radar provided in the embodiment of the present application, the point cloud data in the scanning area is collected by laterally installing the laser radar; acquiring a marked point cloud meeting a marking condition from the point cloud data; calculating a ground height estimation value according to the marked point cloud; calculating the orthographic projection distance of the laser beam of the side-mounted laser radar on the horizontal plane according to the ground height estimated value, the emergence angle of the laser beam of the side-mounted laser radar and the mounting position inclination angle; judging whether the absolute value of the difference between the orthographic projection distance of each coordinate point in the point cloud data on the horizontal plane and the orthographic projection distance of the laser beam of the side-mounted laser radar on the horizontal plane is smaller than a third threshold value or not; and determining a coordinate point, in the point cloud data, of which the absolute value of the difference between the orthographic projection distance of the horizontal plane and the orthographic projection distance of the laser beam of the side-mounted laser radar on the horizontal plane is smaller than a third threshold value, as a ground point. The embodiment of the application can accurately perform ground segmentation under the condition that the laser radar is installed laterally and has a certain installation inclination angle, so that the scanning blind area is reduced, and the accuracy and the stability of ground segmentation are improved.
The embodiment of the application also provides a ground segmentation device based on the laser radar, and the ground segmentation device based on the laser radar can be integrated in an automatic driving vehicle and can also be integrated in a laser radar system.
Referring to fig. 9, fig. 9 is a schematic structural diagram of a ground partitioning device based on lidar according to an embodiment of the present disclosure. The lidar based ground segmentation apparatus 40 may include:
and the acquisition unit 42 is used for acquiring point cloud data in the scanning area through the side-mounted laser radar.
An obtaining unit 43, configured to obtain a marked point cloud satisfying a marking condition from the point cloud data.
And the calculating unit 44 is used for calculating a ground height estimated value according to the marked point cloud.
And the judging unit 45 is used for judging whether the coordinate point in the point cloud data is a ground point or not according to the ground height estimation value.
Referring to fig. 10, fig. 10 is a schematic structural diagram of another lidar-based ground segmentation apparatus according to an embodiment of the present disclosure. The lidar based ground segmentation apparatus 40 may include:
and the calibration unit 41 is used for calibrating the side-mounted laser radar.
And the acquisition unit 42 is used for acquiring point cloud data in the scanning area through the side-mounted laser radar.
An obtaining unit 43, configured to obtain a marked point cloud satisfying a marking condition from the point cloud data.
And the calculating unit 44 is used for calculating a ground height estimated value according to the marked point cloud.
And the judging unit 45 is used for judging whether the coordinate point in the point cloud data is a ground point or not according to the ground height estimation value.
In some embodiments, the determining unit 45 includes:
a first determining subunit 451, configured to determine whether an absolute value of a difference between a height value of each coordinate point in the point cloud data and the ground height estimated value is smaller than a second threshold;
a first determining subunit 452, configured to determine, as a ground point, a coordinate point in the point cloud data where an absolute value of a difference between the height value and the ground height estimated value is smaller than a second threshold.
In some embodiments, the determining unit 45 further includes:
a calculation sub-unit 453, configured to calculate a forward projection distance of the laser beam of the side-mounted lidar on a horizontal plane according to the ground height estimated value, the exit angle of the laser beam of the side-mounted lidar, and the mounting position inclination angle;
a second determining subunit 454, configured to determine whether an absolute value of a difference between a forward projection distance of each coordinate point in the point cloud data on the horizontal plane and a forward projection distance of the laser beam of the side-mounted laser radar on the horizontal plane is smaller than a third threshold;
a second determining subunit 455, configured to determine, as a ground point, a coordinate point in the point cloud data where an absolute value of a difference between the orthographic projection distance of the horizontal plane and the orthographic projection distance of the laser beam of the side-mounted lidar is smaller than a third threshold.
In some embodiments, the obtaining unit 43 includes:
a third determining subunit 431, configured to determine whether an absolute value of a difference between a height value of each coordinate point in the point cloud data and an installation height value of the side-mounted lidar is smaller than a first threshold;
a marking subunit 432, configured to mark a coordinate point in the point cloud data where an absolute value of a difference between a height value and an installation height value of the side-mounted lidar is smaller than a first threshold, so as to obtain the marked point cloud.
In some embodiments, the calculating unit 44 is configured to calculate an average of all coordinate point height values in the marked point cloud to obtain the ground height estimation value.
In specific implementation, the modules may be implemented as independent entities, or may be combined arbitrarily and implemented as one or several entities.
As can be seen from the above, in the ground partitioning device 40 based on the laser radar provided in the embodiment of the present application, the side-mounted laser radar is calibrated by the calibration unit 41; the acquisition unit 42 acquires point cloud data within the scanning area using a side-mounted lidar. The acquisition unit 43 acquires a marker point cloud satisfying a marker condition from the point cloud data. The calculation unit 44 calculates a ground height estimate from the marker point cloud. Whether the coordinate point in the point cloud data is the ground point is judged by the judging unit 45 according to the ground height estimated value. The embodiment of the application can accurately perform ground segmentation under the condition that the laser radar is installed laterally and has a certain installation inclination angle, so that the scanning blind area is reduced, and the accuracy and the stability of ground segmentation are improved.
The embodiment of the application further provides a terminal device, which comprises a processor and a memory, wherein a computer program is stored in the memory, and the processor is used for executing the ground segmentation method based on the laser radar by calling the computer program stored in the memory. The terminal device may be an autonomous vehicle, an unmanned robot, an unmanned airplane, or the like.
Referring to fig. 11, fig. 11 is a schematic structural diagram of a terminal device according to an embodiment of the present disclosure, where the terminal device may be used to implement the ground segmentation method based on lidar according to the foregoing embodiment. The terminal equipment can be equipment such as an automatic piloting vehicle, an unmanned robot, an unmanned airplane and the like.
As shown in fig. 11, the terminal device 1200 may include an RF (Radio Frequency) circuit 110, a memory 120 including one or more computer-readable storage media (only one shown in the figure), an input unit 130, a display unit 140, a sensor 150, an audio circuit 160, a transmission module 170, a processor 180 including one or more processing cores (only one shown in the figure), and a battery 190. Those skilled in the art will appreciate that the terminal device 1200 configuration shown in fig. 11 does not constitute a limitation of terminal device 1200, and may include more or fewer components than shown, or some components in combination, or a different arrangement of components. Wherein:
the RF circuit 110 is used for receiving and transmitting electromagnetic waves, and performs interconversion between the electromagnetic waves and electrical signals, so as to communicate with a communication network or other devices. The RF circuitry 110 may include various existing circuit elements for performing these functions, such as an antenna, a radio frequency transceiver, a digital signal processor, an encryption/decryption chip, a Subscriber Identity Module (SIM) card, memory, and so forth. The RF circuitry 110 may communicate with various networks such as the internet, an intranet, a wireless network, or with other devices over a wireless network.
The memory 120 may be configured to store software programs and modules, such as program instructions/modules corresponding to the laser radar-based ground segmentation method in the foregoing embodiment, and the processor 180 may execute various functional applications and data processing by operating the software programs and modules stored in the memory 120, so that the ground segmentation may be accurately performed under the condition that the laser radar is installed at a side and has a certain installation inclination, so as to reduce a scanning blind area and improve accuracy and stability of the ground segmentation. Memory 120 may include high speed random access memory and may also include non-volatile memory, such as one or more magnetic storage systems, flash memory, or other non-volatile solid-state memory. In some examples, the memory 120 may further include memory located remotely from the processor 180, which may be connected to the terminal device 1200 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input unit 130 may be used to receive input numeric or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control. For example, the input unit 130 may be an in-vehicle touch panel of an autonomous vehicle, a physical key, or the like.
The display unit 140 may be used to display information input by or provided to a user and various graphic user interfaces of the terminal apparatus 1200, which may be configured by graphics, text, icons, video, and any combination thereof.
Terminal device 1200 can also include at least one sensor 150, such as a multiline lidar, a light sensor, a motion sensor, and other sensors. For example, a multiline lidar is used to collect point cloud data.
The audio circuit 160 includes a speaker 161 and a microphone 162, and the audio circuit 160 may provide an audio interface between a user and the terminal device 1200.
The terminal device 1200 may help the user send and receive e-mails, browse web pages, access streaming media, etc. through the transmission module 170 (e.g., Wi-Fi module, bluetooth module), which provides the user with wireless broadband internet access. Although fig. 11 shows the transmission module 170, it is understood that it does not belong to the essential constitution of the terminal device 1200, and may be omitted entirely as needed within the scope not changing the essence of the invention.
The processor 180 is a control center of the terminal apparatus 1200, connects various parts of the entire terminal apparatus using various interfaces and lines, and performs various functions of the terminal apparatus 1200 and processes data by running or executing software programs and/or modules stored in the memory 120 and calling data stored in the memory 120, thereby performing overall monitoring of the automatic driving apparatus. Optionally, processor 180 may include one or more processing cores.
Terminal device 1200 also includes a battery 190 that powers the various components, and battery 190 may also include one or more dc or ac batteries, recharging systems, battery failure detection circuits, battery converters or inverters, battery status indicators, or any other component.
Although not shown, the terminal device 1200 may further include a camera (e.g., a front camera, a rear camera), a bluetooth module, a power module, and the like, which are not described in detail herein. Specifically, in this embodiment, the terminal apparatus 1200 includes the memory 120, and one or more programs, wherein the one or more programs are stored in the memory 120, and the one or more programs configured to be executed by the one or more processors 180 include instructions for:
collecting point cloud data in a scanning area by a side-mounted laser radar; acquiring a marked point cloud meeting a marking condition from the point cloud data; calculating a ground height estimation value according to the marked point cloud; and judging whether the coordinate point in the point cloud data is a ground point or not according to the ground height estimation value.
In some embodiments, the processor 180 is configured to determine whether the coordinate point in the point cloud data is a ground point according to the ground height estimation value, including:
judging whether the absolute value of the difference between the height value of each coordinate point in the point cloud data and the ground height estimated value is smaller than a second threshold value or not; and determining the coordinate point of which the absolute value of the difference between the height value and the ground height estimated value in the point cloud data is smaller than a second threshold value as a ground point.
In some embodiments, the processor 180 is configured to determine whether the coordinate point in the point cloud data is a ground point according to the ground height estimation value, including:
calculating the orthographic projection distance of the laser beam of the side-mounted laser radar on the horizontal plane according to the ground height estimated value, the emergence angle of the laser beam of the side-mounted laser radar and the mounting position inclination angle;
judging whether the absolute value of the difference between the orthographic projection distance of each coordinate point in the point cloud data on the horizontal plane and the orthographic projection distance of the laser beam of the side-mounted laser radar on the horizontal plane is smaller than a third threshold value or not;
and determining a coordinate point, in the point cloud data, of which the absolute value of the difference between the orthographic projection distance of the horizontal plane and the orthographic projection distance of the laser beam of the side-mounted laser radar on the horizontal plane is smaller than a third threshold value, as a ground point.
In some embodiments, the processor 180 is configured to obtain a marked point cloud satisfying a marking condition from the point cloud data, and includes:
judging whether the absolute value of the difference between the height value of each coordinate point in the point cloud data and the installation height value of the side-installed laser radar is smaller than a first threshold value or not;
and marking the coordinate point of which the absolute value of the difference between the height value in the point cloud data and the installation height value of the side-installed laser radar is smaller than a first threshold value to obtain the marked point cloud.
In some embodiments, the processor 180 is configured to calculate a ground height estimate from the marker point cloud, comprising: and calculating the average value of the height values of all coordinate points in the marked point cloud to obtain the ground height estimation value.
In some embodiments, the processor 180 is configured to, prior to the acquisition of the point cloud data within the scanning area by the side-mounted lidar, further configured to: and calibrating the side-mounted laser radar.
As can be seen from the above, an embodiment of the present application provides a terminal device 1200, where the terminal device 1200 executes the following steps: collecting point cloud data in a scanning area by a side-mounted laser radar; acquiring a marked point cloud meeting a marking condition from the point cloud data; calculating a ground height estimation value according to the marked point cloud; and judging whether the coordinate point in the point cloud data is a ground point or not according to the ground height estimation value. The embodiment of the application can accurately perform ground segmentation under the condition that the laser radar is installed laterally and has a certain installation inclination angle, so that the scanning blind area is reduced, and the accuracy and the stability of ground segmentation are improved.
An embodiment of the present application further provides a storage medium, where a computer program is stored in the storage medium, and when the computer program runs on a computer, the computer executes the ground segmentation method based on lidar according to any of the embodiments.
It should be noted that, for the ground segmentation method based on lidar described in the present application, it can be understood by those skilled in the art that all or part of the process for implementing the ground segmentation method based on lidar described in the present application may be implemented by controlling related hardware through a computer program, where the computer program may be stored in a computer readable storage medium, such as a memory of a mobile terminal, and executed by at least one processor in the mobile terminal, and during the execution, the process may include the process of the embodiment of the ground segmentation method based on lidar described in the present application. The storage medium may be a magnetic disk, an optical disk, a Read Only Memory (ROM), a Random Access Memory (RAM), or the like.
For the ground partitioning device based on the lidar according to the embodiment of the present application, each functional module may be integrated in one processing chip, or each module may exist alone physically, or two or more modules may be integrated in one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium, such as a read-only memory, a magnetic or optical disk, or the like.
In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiment of the present application, the ground segmentation apparatus based on the lidar and the ground segmentation method based on the lidar in the above embodiments belong to the same concept, and any one of the methods provided in the embodiment of the ground segmentation method based on the lidar may be operated on the ground segmentation apparatus based on the lidar.
The ground segmentation method, device and storage medium based on the lidar provided by the embodiments of the present application are described in detail above. The principle and the implementation of the present application are explained herein by applying specific examples, and the above description of the embodiments is only used to help understand the method and the core idea of the present application; meanwhile, for those skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.
Claims (10)
1. A ground segmentation method based on laser radar, characterized in that the method comprises:
collecting point cloud data in a scanning area by a side-mounted laser radar;
acquiring a marked point cloud meeting a marking condition from the point cloud data;
calculating a ground height estimation value according to the marked point cloud;
and judging whether the coordinate point in the point cloud data is a ground point or not according to the ground height estimation value.
2. The lidar-based ground segmentation method of claim 1, wherein the determining whether the coordinate point in the point cloud data is a ground point according to the ground height estimate comprises:
judging whether the absolute value of the difference between the height value of each coordinate point in the point cloud data and the ground height estimated value is smaller than a second threshold value or not;
and determining the coordinate point of which the absolute value of the difference between the height value and the ground height estimated value in the point cloud data is smaller than a second threshold value as a ground point.
3. The lidar-based ground segmentation method of claim 1, wherein the determining whether the coordinate point in the point cloud data is a ground point according to the ground height estimate comprises:
calculating the orthographic projection distance of the laser beam of the side-mounted laser radar on the horizontal plane according to the ground height estimated value, the emergence angle of the laser beam of the side-mounted laser radar and the mounting position inclination angle;
judging whether the absolute value of the difference between the orthographic projection distance of each coordinate point in the point cloud data on the horizontal plane and the orthographic projection distance of the laser beam of the side-mounted laser radar on the horizontal plane is smaller than a third threshold value or not;
and determining a coordinate point, in the point cloud data, of which the absolute value of the difference between the orthographic projection distance of the horizontal plane and the orthographic projection distance of the laser beam of the side-mounted laser radar on the horizontal plane is smaller than a third threshold value, as a ground point.
4. The lidar-based ground segmentation method of any one of claims 1 to 3, wherein the obtaining of the marker point cloud satisfying a marker condition from the point cloud data comprises:
judging whether the absolute value of the difference between the height value of each coordinate point in the point cloud data and the installation height value of the side-installed laser radar is smaller than a first threshold value or not;
and marking the coordinate point of which the absolute value of the difference between the height value in the point cloud data and the installation height value of the side-installed laser radar is smaller than a first threshold value to obtain the marked point cloud.
5. The lidar-based ground segmentation method of claim 1, wherein the calculating a ground height estimate from the marker point cloud comprises:
and calculating the average value of the height values of all coordinate points in the marked point cloud to obtain the ground height estimation value.
6. The lidar-based ground segmentation method of claim 1, wherein prior to the acquisition of the point cloud data within the scan area by the side-mounted lidar, further comprising:
and calibrating the side-mounted laser radar.
7. A lidar-based ground segmentation apparatus, the apparatus comprising:
the acquisition unit is used for acquiring point cloud data in the scanning area through a side-mounted laser radar;
an acquisition unit configured to acquire a marker point cloud satisfying a marker condition from the point cloud data;
the calculating unit is used for calculating a ground height estimated value according to the marked point cloud;
and the judging unit is used for judging whether the coordinate point in the point cloud data is a ground point or not according to the ground height estimation value.
8. The lidar-based ground segmentation apparatus of claim 7, wherein the determination unit comprises:
the first judgment subunit is used for judging whether the absolute value of the difference between the height value of each coordinate point in the point cloud data and the ground height estimation value is smaller than a second threshold value or not;
and the first determining subunit is used for determining the coordinate point of which the absolute value of the difference between the height value and the ground height estimated value in the point cloud data is smaller than a second threshold value as the ground point.
9. The lidar-based ground segmentation apparatus of claim 7, wherein the determination unit comprises:
the calculating subunit is used for calculating the orthographic projection distance of the laser beam of the side-mounted laser radar on the horizontal plane according to the ground height estimated value, the emergence angle of the laser beam of the side-mounted laser radar and the mounting position inclination angle;
the second judgment subunit is used for judging whether the absolute value of the difference between the orthographic projection distance of each coordinate point in the point cloud data on the horizontal plane and the orthographic projection distance of the laser beam of the side-mounted laser radar on the horizontal plane is smaller than a third threshold value or not;
and the second determining subunit is used for determining a coordinate point, as a ground point, of the point cloud data, wherein the absolute value of the difference between the orthographic projection distance of the horizontal plane and the orthographic projection distance of the laser beam of the side-mounted laser radar on the horizontal plane is smaller than a third threshold value.
10. A storage medium having stored thereon a computer program which, when run on a computer, causes the computer to perform the steps of the lidar-based ground segmentation method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911404869.1A CN110782465B (en) | 2019-12-30 | 2019-12-30 | Ground segmentation method and device based on laser radar and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911404869.1A CN110782465B (en) | 2019-12-30 | 2019-12-30 | Ground segmentation method and device based on laser radar and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110782465A true CN110782465A (en) | 2020-02-11 |
| CN110782465B CN110782465B (en) | 2020-03-27 |
Family
ID=69394807
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911404869.1A Active CN110782465B (en) | 2019-12-30 | 2019-12-30 | Ground segmentation method and device based on laser radar and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110782465B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111427026A (en) * | 2020-02-21 | 2020-07-17 | 深圳市镭神智能系统有限公司 | Laser radar calibration method and device, storage medium and self-moving equipment |
| CN111435163A (en) * | 2020-03-18 | 2020-07-21 | 深圳市镭神智能系统有限公司 | Ground point cloud data filtering method and device, detection system and storage medium |
| CN111624622A (en) * | 2020-04-24 | 2020-09-04 | 库卡机器人(广东)有限公司 | Obstacle detection method and device |
| CN114002687A (en) * | 2020-07-14 | 2022-02-01 | 北醒（北京）光子科技有限公司 | Detection method based on laser radar |
| CN114002688A (en) * | 2020-07-14 | 2022-02-01 | 北醒（北京）光子科技有限公司 | Detection system based on laser radar |
| WO2022062519A1 (en) * | 2020-09-22 | 2022-03-31 | 上海钛米机器人股份有限公司 | Ground detection method and apparatus, device, and storage medium |
| CN114359863A (en) * | 2021-12-23 | 2022-04-15 | 深圳优地科技有限公司 | Laser radar data processing method and device and computer readable storage medium |
| CN115079128A (en) * | 2022-08-23 | 2022-09-20 | 深圳市欢创科技有限公司 | Method and device for distortion removal of laser radar point cloud data and robot |
| CN115164882A (en) * | 2022-07-13 | 2022-10-11 | 深圳市优必选科技股份有限公司 | Laser distortion removing method, device and system and readable storage medium |
| WO2022146827A3 (en) * | 2020-12-29 | 2022-10-20 | Qualcomm Incorporated | Global motion estimation using road and ground object labels for geometry-based point cloud compression |
| US11949909B2 (en) | 2020-12-29 | 2024-04-02 | Qualcomm Incorporated | Global motion estimation using road and ground object labels for geometry-based point cloud compression |
| CN115164882B (en) * | 2022-07-13 | 2024-10-22 | 深圳市优必选科技股份有限公司 | Laser distortion removal method, device and system and readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100207936A1 (en) * | 2009-02-13 | 2010-08-19 | Harris Corporation | Fusion of a 2d electro-optical image and 3d point cloud data for scene interpretation and registration performance assessment |
| CN103675814A (en) * | 2013-09-25 | 2014-03-26 | 中国科学院电子学研究所 | A circumference-SAR-based method for determining the height of a ground level of a building |
| CN104298998A (en) * | 2014-09-28 | 2015-01-21 | 北京理工大学 | 3D point cloud data processing method |
| CN105404898A (en) * | 2015-11-26 | 2016-03-16 | 福州华鹰重工机械有限公司 | Loose-type point cloud data segmentation method and device |
| CN108596860A (en) * | 2018-05-10 | 2018-09-28 | 芜湖航飞科技股份有限公司 | A kind of ground point cloud dividing method based on three-dimensional laser radar |
-
2019
- 2019-12-30 CN CN201911404869.1A patent/CN110782465B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100207936A1 (en) * | 2009-02-13 | 2010-08-19 | Harris Corporation | Fusion of a 2d electro-optical image and 3d point cloud data for scene interpretation and registration performance assessment |
| CN103675814A (en) * | 2013-09-25 | 2014-03-26 | 中国科学院电子学研究所 | A circumference-SAR-based method for determining the height of a ground level of a building |
| CN104298998A (en) * | 2014-09-28 | 2015-01-21 | 北京理工大学 | 3D point cloud data processing method |
| CN105404898A (en) * | 2015-11-26 | 2016-03-16 | 福州华鹰重工机械有限公司 | Loose-type point cloud data segmentation method and device |
| CN108596860A (en) * | 2018-05-10 | 2018-09-28 | 芜湖航飞科技股份有限公司 | A kind of ground point cloud dividing method based on three-dimensional laser radar |
Non-Patent Citations (1)
| Title |
|---|
| 李犇: "点云数据滤波处理及特征提取研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111427026A (en) * | 2020-02-21 | 2020-07-17 | 深圳市镭神智能系统有限公司 | Laser radar calibration method and device, storage medium and self-moving equipment |
| CN111435163A (en) * | 2020-03-18 | 2020-07-21 | 深圳市镭神智能系统有限公司 | Ground point cloud data filtering method and device, detection system and storage medium |
| CN111624622A (en) * | 2020-04-24 | 2020-09-04 | 库卡机器人(广东)有限公司 | Obstacle detection method and device |
| CN114002687A (en) * | 2020-07-14 | 2022-02-01 | 北醒（北京）光子科技有限公司 | Detection method based on laser radar |
| CN114002688A (en) * | 2020-07-14 | 2022-02-01 | 北醒（北京）光子科技有限公司 | Detection system based on laser radar |
| WO2022062519A1 (en) * | 2020-09-22 | 2022-03-31 | 上海钛米机器人股份有限公司 | Ground detection method and apparatus, device, and storage medium |
| WO2022146827A3 (en) * | 2020-12-29 | 2022-10-20 | Qualcomm Incorporated | Global motion estimation using road and ground object labels for geometry-based point cloud compression |
| US11949909B2 (en) | 2020-12-29 | 2024-04-02 | Qualcomm Incorporated | Global motion estimation using road and ground object labels for geometry-based point cloud compression |
| CN114359863A (en) * | 2021-12-23 | 2022-04-15 | 深圳优地科技有限公司 | Laser radar data processing method and device and computer readable storage medium |
| CN115164882A (en) * | 2022-07-13 | 2022-10-11 | 深圳市优必选科技股份有限公司 | Laser distortion removing method, device and system and readable storage medium |
| CN115164882B (en) * | 2022-07-13 | 2024-10-22 | 深圳市优必选科技股份有限公司 | Laser distortion removal method, device and system and readable storage medium |
| CN115079128A (en) * | 2022-08-23 | 2022-09-20 | 深圳市欢创科技有限公司 | Method and device for distortion removal of laser radar point cloud data and robot |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110782465B (en) | 2020-03-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110782465B (en) | Ground segmentation method and device based on laser radar and storage medium | |
| US20200348408A1 (en) | Vehicle Positioning Method and Vehicle Positioning Apparatus | |
| CN111052132B (en) | Verification module system and method for motion-based lane detection using multiple sensors | |
| US20190219688A1 (en) | Environment perception method and base station | |
| JP2021516401A (en) | Data fusion method and related equipment | |
| EP3792660B1 (en) | Method, apparatus and system for measuring distance | |
| US10551494B2 (en) | Road information detection apparatus and road information detection method | |
| CN114637023A (en) | System and method for laser depth map sampling | |
| WO2021207954A1 (en) | Target identification method and device | |
| CN110516621B (en) | Method and device for detecting barrier-free driving area, vehicle and storage medium | |
| CN111435163A (en) | Ground point cloud data filtering method and device, detection system and storage medium | |
| CN112666535A (en) | Environment sensing method and system based on multi-radar data fusion | |
| WO2022198637A1 (en) | Point cloud noise filtering method and system, and movable platform | |
| CN111913177A (en) | Method and device for detecting target object and storage medium | |
| KR102060286B1 (en) | Radar object detection threshold value determination method using image information and radar object information generation device using the same | |
| CN114442073A (en) | Laser radar calibration method and device, vehicle and storage medium | |
| US11054245B2 (en) | Image processing apparatus, device control system, imaging apparatus, image processing method, and recording medium | |
| CN113734176A (en) | Environment sensing system and method for intelligent driving vehicle, vehicle and storage medium | |
| CN111332306A (en) | Traffic road perception auxiliary driving early warning device based on machine vision | |
| CN115755026A (en) | Vehicle guiding method and vehicle | |
| CN113611008B (en) | Vehicle driving scene acquisition method, device, equipment and medium | |
| CN111332305A (en) | Active early warning type traffic road perception auxiliary driving early warning system | |
| CN115902839A (en) | Port laser radar calibration method and device, storage medium and electronic equipment | |
| TWI843116B (en) | Moving object detection method, device, electronic device and storage medium | |
| EP4279954A1 (en) | Dual sensing method of object and computing apparatus for object sensing |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20200211 Assignee: Tianyi Transportation Technology Co.,Ltd. Assignor: CIIC Technology Co.,Ltd.|Zhongzhixing (Shanghai) Transportation Technology Co.,Ltd. Contract record no.: X2022980001515 Denomination of invention: A ground segmentation method, device and storage medium based on lidar Granted publication date: 20200327 License type: Common License Record date: 20220214 |