CN114646932A - Radar external parameter calibration method and device based on external radar and computer equipment - Google Patents
Radar external parameter calibration method and device based on external radar and computer equipment Download PDFInfo
- Publication number
- CN114646932A CN114646932A CN202210559879.8A CN202210559879A CN114646932A CN 114646932 A CN114646932 A CN 114646932A CN 202210559879 A CN202210559879 A CN 202210559879A CN 114646932 A CN114646932 A CN 114646932A
- Authority
- CN
- China
- Prior art keywords
- radar
- point cloud
- cloud data
- point
- registered
- 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
- 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
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/40—Means for monitoring or calibrating
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Optical Radar Systems And Details Thereof (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The application relates to a radar external parameter calibration method, a radar external parameter calibration device, computer equipment, a storage medium and a computer program product based on an external radar. The method comprises the following steps: the method comprises the steps of obtaining radar point cloud data of an external radar and to-be-calibrated point cloud data of a to-be-calibrated radar, wherein the external radar and the to-be-calibrated radar have a field-of-view overlapping area, and the to-be-calibrated radar comprises a first radar and a second radar; performing point cloud registration on the radar point cloud data and the point cloud data to be registered of the first radar to obtain a transformation relation between the external radar and the first radar; based on the transformation relation, projecting the radar point cloud data to a coordinate system where the first radar is located to obtain fusion point cloud data; and carrying out point cloud registration on the fused point cloud data and the to-be-registered point cloud data of the second radar to obtain a radar external reference calibration result. By adopting the method, the radar external parameter calibration can be realized.
Description
Technical Field
The application relates to the technical field of intelligent driving, in particular to a radar external parameter calibration method and device based on an external radar and computer equipment.
Background
The radar external reference calibration refers to external reference calibration of a radar installed on a vehicle, and is a very important link in the field of intelligent driving, positioning and sensing in the field of intelligent driving need to depend on accurate external reference, and the external reference calibration refers to relative position relation between the radars, including translation and rotation.
In the conventional technology, the radar external reference calibration mode is that one of the radars on the vehicle is selected as a main radar, and then calibration is performed through the overlapped area of the main radar and the other radars. However, for the solid-state laser radar, because the field of view is relatively small, the solid-state laser radar may not have a field of view overlapping region with other radars, and is difficult to calibrate based on field of view overlapping, and the calibration of the radars without field of view overlapping cannot be realized according to the conventional method.
Disclosure of Invention
In view of the foregoing, it is desirable to provide an extrinsic radar calibration method, an extrinsic radar calibration apparatus, a computer device, a computer readable storage medium, and a computer program product, which are capable of implementing an extrinsic radar calibration.
In a first aspect, the application provides a radar external reference calibration method based on an external radar. The method comprises the following steps:
the method comprises the steps of obtaining radar point cloud data of an external radar and to-be-calibrated point cloud data of a to-be-calibrated radar, wherein the external radar and the to-be-calibrated radar have a field-of-view overlapping area, and the to-be-calibrated radar comprises a first radar and a second radar;
performing point cloud registration on the radar point cloud data and the cloud data of the point to be registered of the first radar to obtain a transformation relation between the external radar and the first radar;
based on the transformation relation, projecting the radar point cloud data to a coordinate system where the first radar is located to obtain fused point cloud data;
and carrying out point cloud registration on the fused point cloud data and the to-be-registered point cloud data of the second radar to obtain a radar external reference calibration result.
In one embodiment, the point cloud registration of the radar point cloud data and the point cloud data to be registered of the first radar, and obtaining the transformation relation between the external radar and the first radar comprises:
traversing the radar point cloud data and the cloud data of the point to be registered of the first radar, and determining a point cloud overlapping area between the radar point cloud data and the cloud data of the point to be registered of the first radar;
and carrying out point cloud registration on the point cloud data in the point cloud overlapping area to obtain a transformation relation between the external radar and the first radar.
In one embodiment, the point cloud registration of the point cloud data in the point cloud overlapping area to obtain the transformation relation between the external radar and the first radar comprises:
based on the obtained initial transformation parameters, transforming point cloud data to be registered of the first radar in the point cloud overlapping area to obtain transformed point cloud data;
comparing the transformed point cloud data with the radar point cloud data in the point cloud overlapping area to obtain a point cloud distance error;
and carrying out iterative optimization on the initial transformation parameters based on the point cloud distance error to obtain a transformation relation between the external radar and the first radar.
In one embodiment, the iterative optimization of the initial transformation parameter based on the point cloud distance error to obtain the transformation relation between the extrinsic radar and the first radar includes:
optimizing initial transformation parameters;
based on the optimized initial transformation parameters, transforming point cloud data to be registered of the first radar in the point cloud overlapping area to obtain secondary transformation point cloud data;
comparing the secondary transformation point cloud data with the radar point cloud data in the point cloud overlapping area to obtain a new point cloud distance error;
and continuously performing iterative optimization on the optimized initial transformation parameters based on the new point cloud distance error until the latest point cloud distance error meets the iterative optimization stop condition, so as to obtain the transformation relation between the external radar and the first radar.
In one embodiment, the point cloud registration of the fusion point cloud data and the cloud data of the point to be registered of the second radar to obtain the radar external reference calibration result comprises:
traversing the fusion point cloud data and the to-be-registered point cloud data of the second radar, and determining a target overlapping area between the fusion point cloud data and the to-be-registered point cloud data of the second radar;
and performing point cloud registration on point cloud data in the target overlapping area based on the acquired radar conversion initial value between the first radar and the second radar to obtain a radar external reference calibration result.
In one embodiment, the radar point cloud data comprises at least two frames of radar point clouds, the point cloud data to be registered of the radar to be calibrated comprises at least two frames of point clouds to be registered of a first radar and a second radar, the at least two frames of radar point clouds are respectively matched with the at least two frames of point clouds to be registered in a time dimension, and the fused point cloud data comprises at least two frames of fused point clouds matched with the at least two frames of radar point clouds frame by frame;
performing point cloud registration on the fused point cloud data and the to-be-registered point cloud data of the second radar to obtain a radar external reference calibration result, wherein the step of performing point cloud registration on the fused point cloud data and the to-be-registered point cloud data of the second radar comprises the following steps:
respectively carrying out point cloud registration on the at least two frames of fused point clouds and a single frame of point cloud to be registered matched in the point cloud data to be registered of the second radar to obtain single frame external reference calibration results matched with the at least two frames of fused point clouds;
and obtaining a radar external reference calibration result based on the single-frame external reference calibration result.
In a second aspect, the application further provides a radar external reference calibration device based on the external radar. The device comprises:
the system comprises an acquisition module, a calibration module and a calibration module, wherein the acquisition module is used for acquiring radar point cloud data of an external radar and to-be-calibrated point cloud data of a radar to be calibrated, the external radar and the radar to be calibrated have a field-of-view overlapping area, and the radar to be calibrated comprises a first radar and a second radar;
the first registration module is used for carrying out point cloud registration on the radar point cloud data and the to-be-registered point cloud data of the first radar to obtain a transformation relation between the external radar and the first radar;
the projection module is used for projecting the radar point cloud data to a coordinate system where the first radar is located based on the transformation relation to obtain fused point cloud data;
and the second registration module is used for carrying out point cloud registration on the fused point cloud data and the to-be-registered point cloud data of the second radar to obtain a radar external reference calibration result.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor implementing the following steps when executing the computer program:
the method comprises the steps of obtaining radar point cloud data of an external radar and to-be-calibrated point cloud data of a to-be-calibrated radar, wherein the external radar and the to-be-calibrated radar have a field-of-view overlapping area, and the to-be-calibrated radar comprises a first radar and a second radar;
performing point cloud registration on the radar point cloud data and the cloud data of the point to be registered of the first radar to obtain a transformation relation between the external radar and the first radar;
based on the transformation relation, projecting the radar point cloud data to a coordinate system where the first radar is located to obtain fused point cloud data;
and carrying out point cloud registration on the fused point cloud data and the to-be-registered point cloud data of the second radar to obtain a radar external reference calibration result.
In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:
the method comprises the steps of obtaining radar point cloud data of an external radar and to-be-calibrated point cloud data of a to-be-calibrated radar, wherein the external radar and the to-be-calibrated radar have a field-of-view overlapping area, and the to-be-calibrated radar comprises a first radar and a second radar;
performing point cloud registration on the radar point cloud data and the cloud data of the point to be registered of the first radar to obtain a transformation relation between the external radar and the first radar;
based on the transformation relation, projecting the radar point cloud data to a coordinate system where the first radar is located to obtain fused point cloud data;
and carrying out point cloud registration on the fused point cloud data and the to-be-registered point cloud data of the second radar to obtain a radar external reference calibration result.
In a fifth aspect, the present application further provides a computer program product. The computer program product comprising a computer program which when executed by a processor performs the steps of:
the method comprises the steps of obtaining radar point cloud data of an external radar and to-be-calibrated point cloud data of a to-be-calibrated radar, wherein the external radar and the to-be-calibrated radar have a field-of-view overlapping area, and the to-be-calibrated radar comprises a first radar and a second radar;
performing point cloud registration on the radar point cloud data and the cloud data of the point to be registered of the first radar to obtain a transformation relation between the external radar and the first radar;
based on the transformation relation, projecting the radar point cloud data to a coordinate system where the first radar is located to obtain fused point cloud data;
and carrying out point cloud registration on the fused point cloud data and the to-be-registered point cloud data of the second radar to obtain a radar external reference calibration result.
According to the radar external reference calibration method, device, computer equipment, storage medium and computer program product based on the external radar, by acquiring radar point cloud data of the external radar and to-be-registered point cloud data of the to-be-registered radar, point cloud registration can be performed based on radar point cloud data in an overlapping area with to-be-registered point cloud data of a first radar, so that a transformation relation between the external radar and the first radar is obtained, the radar point cloud data can be projected to a coordinate system where the first radar is located based on the transformation relation, fusion point cloud data in an overlapping area with to-be-registered point cloud data of a second radar and corresponding to the coordinate system where the first radar is located is obtained, and therefore a radar external reference calibration result can be obtained by performing point cloud registration on the fusion point cloud data and to-be-registered point cloud data of the second radar, and the whole process can be realized based on the external radar in an overlapping area with a view field of the to-registered radar in the to-be calibrated radar, so that no view field is present on the vehicle And overlapping point cloud areas appear in the radars to be calibrated in the overlapping areas, so that radar external reference calibration is realized.
Drawings
FIG. 1 is an application environment diagram of an extrinsic radar calibration method based on an extrinsic radar in an embodiment;
FIG. 2 is a schematic flow chart illustrating a radar external reference calibration method based on an external radar in one embodiment;
FIG. 3 is a diagram of an application environment of a radar external reference calibration method based on an external radar in another embodiment;
FIG. 4 is a diagram of an application environment of a radar external reference calibration method based on an external radar in still another embodiment;
FIG. 5 is a schematic diagram of point cloud data to be registered in one embodiment;
FIG. 6 is a schematic flowchart illustrating a radar external reference calibration method based on an external radar in another embodiment;
FIG. 7 is a diagram of an application environment of a radar external reference calibration method based on an external radar in another embodiment;
FIG. 8 is a schematic illustration of an overlapping region of point clouds in one embodiment;
FIG. 9 is a block diagram of an embodiment of an external radar-based radar external reference calibration device;
FIG. 10 is a diagram showing an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The radar external reference calibration method based on the external radar provided by the embodiment of the application can be applied to the application environment shown in fig. 1. The external radar 102 is placed at a certain height above the vehicle 104 equipped with the radar to be calibrated, the certain height can be set by itself as required, the radar to be calibrated comprises a first radar 106 and a second radar 108, and no overlapping area exists between the fields of view of the first radar 106 and the second radar 108. When radar external reference calibration is performed, the server 110 obtains radar point cloud data of the external radar 102 and cloud data of a point to be registered of a radar to be calibrated (including the first radar 106 and the second radar 108), the external radar and the radar to be calibrated have a field of view overlapping region, point cloud registration is performed on the radar point cloud data and the cloud data of the point to be registered of the first radar 106 to obtain a transformation relation between the external radar 102 and the first radar 106, the radar point cloud data is projected to a coordinate system where the first radar 106 is located based on the transformation relation to obtain fusion point cloud data, point cloud registration is performed on the fusion point cloud data and the cloud data of the point to be registered of the second radar 108 to obtain a radar external reference calibration result. The external radar 102 may be, but is not limited to, various laser radars, the vehicle 104 may be, but is not limited to, various autonomous vehicles, and the server 110 may be implemented by an independent server or a server cluster composed of a plurality of servers, and may also be a node on a block chain.
In one embodiment, as shown in fig. 2, an extrinsic radar calibration method based on an extrinsic radar is provided, which is described by taking the method as an example applied to the server 110 in fig. 1, and includes the following steps:
The external radar and the radar to be calibrated have a field-of-view overlapping region, namely, the radar is not assembled on the vehicle provided with the radar to be calibrated. For example, as shown in fig. 1, the external radar may be a radar placed at a certain height above the vehicle equipped with the radar to be calibrated, and the certain height may be set as required. For another example, as shown in fig. 3, the external radar may be a radar mounted on a target vehicle, and the target vehicle is located on a side of the vehicle mounted with the radar to be calibrated. For example, in order to ensure that there is a field-of-view overlapping region with the radar in the radar to be calibrated, the external radar may be a 360-degree laser radar.
The radar to be calibrated refers to a radar which needs to calibrate external parameters on a vehicle. For example, the radar to be calibrated may specifically refer to a solid-state laser radar on a vehicle, which needs to calibrate external parameters. The cloud data of the point to be calibrated of the radar to be calibrated refers to the point cloud data acquired by the radar to be calibrated. For example, the cloud data of the point to be registered of the radar to be calibrated may specifically refer to at least one frame of point cloud to be registered acquired by the radar to be calibrated. It should be noted that the radar to be calibrated generally includes at least two radars, namely a first radar and a second radar, and there is no overlapping area of fields of view between the first radar and the second radar. For example, as shown in fig. 4, the first radar and the second radar may specifically be a forward laser radar and a backward laser radar which are mounted on the vehicle and have no overlapping area of the fields of view, and the cloud data of the point to be registered of the corresponding radar to be calibrated may be as shown in fig. 5, where a first area 502 is the cloud data of the point to be registered of the first radar, and a second area 504 is the cloud data of the point to be registered of the second radar, and as can be seen from fig. 5, the cloud data of the point to be registered of the first radar and the second radar have no overlapping area.
Specifically, when radar external reference calibration is carried out on a radar to be calibrated on any vehicle, the server can acquire radar point cloud data of the external radar and cloud data of a point to be calibrated of the radar to be calibrated, wherein the external radar can be a radar which is located in a view field overlapping region with the radar in the radar to be calibrated and is located on other vehicles adjacent to any vehicle, and the radar to be calibrated comprises a first radar and a second radar.
And 204, carrying out point cloud registration on the radar point cloud data and the to-be-registered point cloud data of the first radar to obtain a transformation relation between the external radar and the first radar.
The point cloud registration is to input two point clouds and output a transformation, so that the coincidence degree of the two point clouds is as high as possible. The transformation may or may not be rigid, if only rigid transformations are considered, i.e. the transformation comprises only rotations, translations. Point cloud registration can be generally divided into two steps, coarse registration and fine registration. Coarse registration refers to relatively coarse registration under the condition that transformation between two point clouds is completely unknown, the purpose is mainly to provide a relatively good initial transformation value for fine registration, and the fine registration criterion is to give an initial transformation and further optimize to obtain more accurate transformation. The transformation relation between the external radar and the first radar is a transformation relation which enables the coincidence degree of the radar point cloud data and the cloud data of the point to be registered of the first radar to be as high as possible, namely the transformation relation obtained based on point cloud registration.
Specifically, when point cloud registration is performed, the server needs to determine a point cloud overlapping area between the radar point cloud data and the point cloud data to be registered of the first radar, and perform point cloud registration on the point cloud data in the point cloud overlapping area to obtain a transformation relation between the external radar and the first radar.
And step 206, projecting the radar point cloud data to a coordinate system where the first radar is located based on the transformation relation to obtain fused point cloud data.
The fusion point cloud data is obtained by projecting radar point cloud data to a coordinate system where the first radar is located based on a transformation relation, and the fusion point cloud data comprises the projected radar point cloud data and the to-be-registered point cloud data of the first radar.
Specifically, the server projects points in the radar point cloud data to a coordinate system where the first radar is located respectively based on the transformation relation, and fused point cloud data is obtained.
And 208, performing point cloud registration on the fusion point cloud data and the to-be-registered point cloud data of the second radar to obtain a radar external reference calibration result.
Specifically, the external radar is an external radar which has a view field overlapping region with the first radar and the second radar, and an overlapping region can exist between fusion point cloud data obtained by projecting radar point cloud data of the external radar and to-be-registered point cloud data of the second radar, so that the server can perform point cloud registration on the fusion point cloud data and to-be-registered point cloud data of the second radar to obtain a radar external reference calibration result. When point cloud registration is performed on the fused point cloud data and the cloud data of the point to be registered of the second radar, the server also needs to determine a target overlapping area between the fused point cloud data and the cloud data of the point to be registered of the second radar, and then performs point cloud registration on the cloud data of the point in the target overlapping area based on a radar conversion initial value between the first radar and the second radar, so as to obtain a radar external reference calibration result. The radar transformation initial value refers to initial radar external parameters obtained based on the relative position relation between the first radar and the second radar, and comprises a rotation matrix and a translation matrix.
The radar external reference calibration method based on the external radar can perform point cloud registration based on the radar point cloud data with the overlapped area with the point cloud data to be registered of the first radar to obtain the transformation relation between the external radar and the first radar, further project the radar point cloud data to the coordinate system of the first radar based on the transformation relation to obtain the fusion point cloud data which has the overlapped area with the point cloud data to be registered of the second radar and corresponds to the coordinate system of the first radar, thereby performing point cloud registration to obtain the radar external reference calibration result by performing point cloud registration to the fusion point cloud data and the point cloud data to be registered of the second radar, and the whole process can enable the radar to be calibrated to appear the overlapped area without the visual field overlapped area on the vehicle based on the external radar with the visual field overlapped area with the radar in the radar to be calibrated, and realizing radar external parameter calibration.
In one embodiment, the point cloud registration of the radar point cloud data and the point cloud data to be registered of the first radar is performed, and the obtaining of the transformation relation between the external radar and the first radar comprises:
traversing the radar point cloud data and the cloud data of the point to be registered of the first radar, and determining a point cloud overlapping area between the radar point cloud data and the cloud data of the point to be registered of the first radar;
and carrying out point cloud registration on the point cloud data in the point cloud overlapping area to obtain a transformation relation between the external radar and the first radar.
Specifically, the server traverses the radar point cloud data and the cloud data of the first radar point to be registered, calculates the point distance between the point in the radar point cloud data and the point in the cloud data of the first radar point to be registered, determines a target point with the point distance smaller than a preset distance threshold value, and takes a point cloud area including all the target points as a point cloud overlapping area between the radar point cloud data and the cloud data of the first radar point to be registered. After the point cloud overlapping area is obtained, the server performs point cloud registration on the point cloud data in the point cloud overlapping area through an iterative closest point algorithm or a normal distribution transformation algorithm to obtain a transformation relation between the external radar and the first radar.
The iterative closest point algorithm is mainly used for point cloud registration in a three-dimensional space, and is not only suitable for plane scenes, but also suitable for scenes such as curves and curved surfaces. When the point cloud registration result does not meet the requirement of ideal precision, the error is reduced in continuous iteration through the iteration nearest point algorithm, so that the ideal precision value is realized. The initial coarse match provides a better initial position for the subsequent fine match, while the effect of the iterative closest point algorithm is to further narrow the error to approach the ideal precision value indefinitely. The core of the iterative closest point algorithm lies in that the iterative closest point algorithm is continuously iterated, rotation and translation are carried out through registration between points, the measurement standard is based on a least square method, and the distance between a point and a point is required to be within a certain threshold range. The point cloud registration by the iterative closest point algorithm may be as follows: and based on the obtained initial transformation parameters, transforming point cloud data to be registered of the first radar in the point cloud overlapping area to obtain a transformed point cloud number, and performing point cloud registration by comparing the transformed point cloud data with the radar point cloud data in the point cloud overlapping area to obtain a transformation relation between the external radar and the first radar. The initial transformation parameters refer to initial transformation external parameters obtained based on a relative position relation between the external radar and the first radar, and comprise a rotation matrix and a translation matrix.
The normal distribution transformation algorithm is substantially used for determining the optimal matching by calculating the attitude transformation between the point cloud and the point cloud, compared with the iterative closest point algorithm, the registration effect of the normal distribution transformation algorithm is similar to that of the iterative closest point algorithm, and the improvement is substantially equal to the rasterization of the iterative closest point algorithm. The general process of the normal distribution transformation algorithm is as follows: under the condition that two point clouds, namely a source point cloud P and a target point cloud Q, are known, a space where the source point cloud P is located is divided into grids of one unit and one unit (namely, the projection of a three-dimensional space on a two-dimensional space), normal distribution parameters of the unit grids are calculated according to the distribution condition of points in the divided unit grids, the points in the target point cloud Q are transformed according to a transfer matrix, the number of the target point clouds in the divided grid of the space where the source point cloud P is located is counted, the corresponding probability distribution is calculated according to the distribution condition of the points, and finally the optimal values of all the points are solved, namely the rigid body transformation between the target point cloud and the source point cloud is solved. In this embodiment, the source point cloud may specifically be cloud data of a point to be registered of the first radar in the point cloud overlapping area, and the target point cloud may specifically be radar point cloud data in the point cloud overlapping area.
In this embodiment, a point cloud overlapping region between the radar point cloud data and the first radar point cloud data to be registered can be determined by traversing the radar point cloud data and the first radar point cloud data to be registered, and then point cloud registration can be performed on the point cloud data in the point cloud overlapping region, so that accurate registration is achieved, and a transformation relationship between the external radar and the first radar is obtained.
In one embodiment, the point cloud registration of the point cloud data in the point cloud overlapping region to obtain the transformation relation between the external radar and the first radar comprises:
based on the obtained initial transformation parameters, transforming point cloud data to be registered of the first radar in the point cloud overlapping area to obtain transformed point cloud data;
comparing the transformed point cloud data with the radar point cloud data in the point cloud overlapping area to obtain a point cloud distance error;
and carrying out iterative optimization on the initial transformation parameters based on the point cloud distance error to obtain a transformation relation between the external radar and the first radar.
The initial transformation parameters refer to initial transformation external parameters between the external radar and the first radar, which are obtained based on the relative position relation between the external radar and the first radar. The point cloud distance error is the sum of the distance errors of each point in the cloud data of the point to be registered of the first radar in the point cloud overlapping area and the nearest neighbor point in the radar point cloud data in the point cloud overlapping area. The nearest neighbor point is a point which is closest to a point in the radar point cloud data in the point cloud overlapping area and the point in the cloud data of the point to be registered of the first radar in the point cloud overlapping area, and can be obtained by calculating and transforming the distance between each point in the point cloud data and each point in the radar point cloud data in the point cloud overlapping area, and each point in the transformed point cloud data corresponds to each point in the cloud data of the point to be registered of the first radar in the point cloud overlapping area one by one.
It should be noted that the distance may specifically be an euclidean distance, a mahalanobis distance, a point-to-plane distance, and the like, and this embodiment is not limited in this respect. Where euclidean distance refers to the true distance between two points in an m-dimensional space, or the natural length of a vector (i.e., the distance of the point from the origin). The euclidean distance in two and three dimensions is the actual distance between two points. Mahalanobis distance can be defined as the degree of difference between two random variables that obey the same distribution and whose covariance matrix is Σ. The distance from the point to the plane refers to the distance from the point in the transformed point cloud data to the plane where the radar point cloud data is located in the point cloud overlapping area. For example, when the distance is a euclidean distance, the distance error may be obtained by transforming the spatial coordinates of each point in the point cloud data and the spatial coordinates of its nearest neighbor. When the distance is a mahalanobis distance, the distance error can be calculated by a covariance matrix.
Specifically, the server transforms point cloud data to be registered of a first radar in a point cloud overlapping area based on the obtained initial transformation parameters to obtain transformed point cloud data, compares the transformed point cloud data with the radar point cloud data in the point cloud overlapping area to find out the nearest neighbor of each point in the radar point cloud data in the point cloud overlapping area of the point cloud data to be registered of the first radar in the point cloud overlapping area, calculates the distance error between each point and the nearest neighbor of each point in the point cloud data to be registered of the first radar in the point cloud overlapping area based on the transformed point cloud data corresponding to the point cloud data to be registered of the first radar in the point cloud overlapping area, obtains the point cloud distance error based on the distance errors corresponding to all points, iteratively optimizes the initial transformation parameters by an optimization algorithm based on the point cloud distance errors until the iteration meets the preset iteration stop condition, and stopping iteration, and finally obtaining the optimized transformation parameters, namely the transformation relation between the external radar and the first radar.
The preset iteration stop condition may be set as required, for example, the preset iteration stop condition may specifically be that the point cloud distance error is smaller than a preset error threshold. For another example, the preset iteration stop condition may specifically be that the iteration number reaches a preset iteration number threshold.
In the embodiment, the point cloud data to be registered of the first radar in the point cloud overlapping area is transformed based on the initial transformation parameters to obtain the transformed point cloud data, and then the transformed point cloud data and the radar point cloud data in the point cloud overlapping area are compared to determine the registration condition between the transformed point cloud data and the radar point cloud data in the point cloud overlapping area to obtain the point cloud distance error, so that the initial transformation parameters can be iteratively optimized based on the point cloud distance error, the initial transformation parameters are continuously optimized to realize the registration of the transformed point cloud data and the radar point cloud data in the point cloud overlapping area, and the transformation relation between the external radar and the first radar is obtained.
In one embodiment, the iterative optimization of the initial transformation parameters based on the point cloud distance error to obtain the transformation relation between the outlaid radar and the first radar comprises:
optimizing initial transformation parameters;
based on the optimized initial transformation parameters, transforming point cloud data to be registered of the first radar in the point cloud overlapping area to obtain secondary transformation point cloud data;
comparing the secondary transformation point cloud data with the radar point cloud data in the point cloud overlapping area to obtain a new point cloud distance error;
and continuously performing iterative optimization on the optimized initial transformation parameters based on the new point cloud distance error until the latest point cloud distance error meets the iterative optimization stop condition, so as to obtain the transformation relation between the external radar and the first radar.
Specifically, the server optimizes an initial transformation parameter by using an optimization algorithm, transforms cloud data of a point to be registered of a first radar in a point cloud overlapping region based on the optimized initial transformation parameter to obtain secondary transformation point cloud data, compares the secondary transformation point cloud data with the radar point cloud data in the point cloud overlapping region to find out a nearest neighbor point of each point in the radar point cloud data in the point cloud overlapping region in the cloud data of the point to be registered of the first radar in the point cloud overlapping region, calculates a distance error between each point and the nearest neighbor point in the cloud data of the point to be registered of the first radar in the point cloud overlapping region based on the secondary transformation point cloud data corresponding to the cloud data of the point to be registered of the first radar in the point cloud overlapping region, obtains a new point cloud distance error based on the distance errors corresponding to all points, and if the new point cloud distance error does not satisfy an iterative optimization stop condition, and continuously carrying out iterative optimization on the optimized initial transformation parameters based on the new point cloud distance error.
Specifically, during each optimization, the server transforms point cloud data to be registered of the first radar in the point cloud overlapping area based on the optimized initial transformation parameters to obtain transformed point cloud data matched with the current optimization, compares the transformed point cloud data matched with the current optimization with the radar point cloud data in the point cloud overlapping area to obtain a point cloud distance error matched with the current optimization, and obtains a transformation relation between the external radar and the first radar until the point cloud distance error matched with the current optimization meets an iterative optimization stop condition, namely the latest point cloud distance error meets the iterative optimization stop condition.
In this embodiment, the registration of the transformed point cloud data and the radar point cloud data in the point cloud overlapping region is realized by continuously optimizing the initial transformation parameters, so as to obtain the transformation relationship between the external radar and the first radar.
In one embodiment, the point cloud registration of the fusion point cloud data and the cloud data of the point to be registered of the second radar to obtain the radar external reference calibration result comprises:
traversing the fusion point cloud data and the to-be-registered point cloud data of the second radar, and determining a target overlapping area between the fusion point cloud data and the to-be-registered point cloud data of the second radar;
and performing point cloud registration on point cloud data in the target overlapping area based on the acquired radar conversion initial value between the first radar and the second radar to obtain a radar external reference calibration result.
The radar transformation initial value refers to initial radar external parameters obtained based on the relative position relation between the first radar and the second radar, and comprises a rotation matrix and a translation matrix. The target overlapping area is a point cloud overlapping area between the fused point cloud data and the to-be-registered point cloud data of the second radar.
Specifically, the server traverses the fusion point cloud data and the to-be-registered point cloud data of the second radar, determines the distance between each point in the fusion point cloud data and each point in the to-be-registered point cloud data of the second radar, determines a target overlapping area between the fusion point cloud data and the to-be-registered point cloud data of the second radar based on the distance, performs point cloud registration on the fusion point cloud data in the target overlapping area and the to-be-registered point cloud data of the second radar based on the acquired radar transformation initial value between the first radar and the second radar to obtain a transformation relation between the fusion point cloud data in the target overlapping area and the to-be-registered point cloud data of the second radar, and takes the transformation relation as a radar external reference calibration result. The method for point cloud registration of the fusion point cloud data in the target overlapping area and the to-be-registered point cloud data of the second radar is the same as the method for point cloud registration of the radar point cloud data in the point cloud overlapping area and the to-be-registered point cloud data of the first radar, and the method is not repeated here.
In this embodiment, a target overlapping area between the fusion point cloud data and the cloud data of the point to be registered of the second radar can be determined by traversing the fusion point cloud data and the cloud data of the point to be registered of the second radar, and then point cloud data in the target overlapping area can be subjected to point cloud registration by obtaining a radar transformation initial value between the first radar and the second radar, so that accurate registration is realized, and a radar external reference calibration result is obtained.
In one embodiment, the radar point cloud data comprises at least two frames of radar point clouds, the point cloud data to be registered of the radar to be calibrated comprises at least two frames of point clouds to be registered of a first radar and a second radar, the at least two frames of radar point clouds are respectively matched with the at least two frames of point clouds to be registered in a time dimension, and the fused point cloud data comprises at least two frames of fused point clouds matched with the at least two frames of radar point clouds frame by frame;
performing point cloud registration on the fused point cloud data and the to-be-registered point cloud data of the second radar to obtain a radar external reference calibration result, wherein the step of performing point cloud registration on the fused point cloud data and the to-be-registered point cloud data of the second radar comprises the following steps:
respectively carrying out point cloud registration on the at least two frames of fused point clouds and a single frame of point cloud to be registered matched in the point cloud data to be registered of the second radar to obtain single frame external reference calibration results matched with the at least two frames of fused point clouds;
and obtaining a radar external reference calibration result based on the single-frame external reference calibration result.
Here, matching in the time dimension means corresponding to the same time.
Specifically, when radar external reference calibration is carried out, in order to improve calibration accuracy, a server acquires multi-frame data for calibration, the acquired radar point cloud data comprises at least two frames of radar point clouds, point cloud data to be registered of a radar to be calibrated comprises at least two frames of point clouds to be registered of a first radar and a second radar, the at least two frames of radar point clouds are respectively matched with the at least two frames of point clouds to be registered in a time dimension, the server respectively carries out point cloud registration on one frame of radar point cloud and one frame of point cloud to be registered which are matched with the same time dimension when carrying out point cloud registration on the radar point cloud data and the point cloud data to be registered of the first radar, the obtained conversion relation between the external radar and the first radar is matched with the at least two frames of radars frame by frame, and the radar data are projected to a coordinate system where the first radar is located on the basis of the corresponding conversion relation, the obtained fusion point cloud data also comprises at least two frames of fusion point clouds matched with at least two frames of radar point clouds frame by frame.
Specifically, after at least two frames of fused point clouds matched with at least two frames of radar point clouds frame by frame are obtained, the server respectively carries out point cloud registration on single frames of point clouds to be registered matched in the at least two frames of fused point clouds and point cloud data to be registered of a second radar to obtain single frame external reference calibration results matched with the at least two frames of fused point clouds, and then averages the single frame external reference calibration results to obtain radar external reference calibration results.
In the embodiment, the calibration precision can be improved by performing radar external reference calibration by using at least two frames of radar point clouds and at least two frames of point clouds to be registered matched with the at least two frames of radar point clouds in the time dimension.
In an embodiment, as shown in fig. 6, a flowchart is used to describe the radar external reference calibration method based on an external radar of the present application, where the radar external reference calibration method based on an external radar specifically includes the following steps:
and 622, performing point cloud registration on point cloud data in the target overlapping area based on the acquired radar conversion initial value between the first radar and the second radar to obtain a radar external reference calibration result.
In one embodiment, as shown in fig. 7, the radar external reference calibration method of the present application may be applied to indoor calibration, wherein the radar to be calibrated includes a forward laser radar (first radar) and a backward laser radar (second radar) assembled on a vehicle, the external radar is placed at a certain height above the vehicle assembled with the radar to be calibrated, and the certain height may be set as required for the global laser radar having a field-of-view overlapping region with the forward laser radar and the backward laser radar.
Specifically, the server acquires radar point cloud data of an external radar and point cloud data to be registered of a radar to be calibrated, traverses the radar point cloud data and the point cloud data to be registered of a first radar, determines a point cloud overlapping area between the radar point cloud data and the point cloud data to be registered of the first radar, transforms the point cloud data to be registered of the first radar in the point cloud overlapping area based on the acquired initial transformation parameters to obtain transformed point cloud data, compares the transformed point cloud data with the radar point cloud data in the point cloud overlapping area to obtain a point cloud distance error, optimizes the initial transformation parameters, transforms the point cloud data to be registered of the first radar in the point cloud overlapping area based on the optimized initial transformation parameters to obtain secondary transformation data, compares the secondary transformation point cloud data with the radar point cloud data in the point cloud overlapping area to obtain a new point cloud distance error, and continuously performing iterative optimization on the optimized initial transformation parameters based on the new point cloud distance error until the latest point cloud distance error meets the iterative optimization stop condition to obtain a transformation relation between the external radar and the first radar, projecting radar point cloud data to a coordinate system where the first radar is located based on the transformation relation to obtain fusion point cloud data, traversing the fusion point cloud data and the to-be-registered point cloud data of the second radar, determining a target overlapping area between the fusion point cloud data and the to-be-registered point cloud data of the second radar, and performing point cloud registration on the point cloud data in the target overlapping area based on the obtained radar transformation initial value between the first radar and the second radar to obtain a radar external reference calibration result.
It should be noted that, as shown in fig. 8, the external radar is a global laser radar having a view field overlapping region with the forward laser radar and the backward laser radar, and then there must be a point cloud overlapping region between the radar point cloud data and the forward laser radar point cloud and the backward laser radar point cloud respectively, so that the vehicle itself has no view field overlapping region and the backward laser radar has an overlapping point cloud region based on the external radar, and radar external reference calibration is realized.
Further, as shown in fig. 7, in the indoor calibration, the vehicle may be placed on a turntable, the turntable may rotate, and as the vehicle is slowly rotated by using the turntable, at least two frames of data may be obtained for calibration, and the calibration accuracy may be improved by performing calibration using at least two frames of data.
It should be understood that, although the steps in the flowcharts related to the embodiments as described above are sequentially displayed as indicated by arrows, the steps are not necessarily performed sequentially as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in the flowcharts related to the embodiments described above may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the execution order of the steps or stages is not necessarily sequential, but may be rotated or alternated with other steps or at least a part of the steps or stages in other steps.
Based on the same inventive concept, the embodiment of the application also provides an external radar-based radar external reference calibration device for realizing the external radar-based radar external reference calibration method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the method, so that specific limitations in one or more embodiments of the external radar-based radar external reference calibration device provided below can be referred to the limitations on the external radar-based radar external reference calibration method in the foregoing, and details are not repeated herein.
In one embodiment, as shown in fig. 9, there is provided an external radar-based radar external reference calibration apparatus, including: an acquisition module 902, a first registration module 904, a projection module 906, and a second registration module 908, wherein:
an obtaining module 902, configured to obtain radar point cloud data of an external radar and cloud data of a point to be calibrated of a radar to be calibrated, where the external radar and the radar to be calibrated have a field-of-view overlapping region, and the radar to be calibrated includes a first radar and a second radar;
a first registration module 904, configured to perform point cloud registration on the radar point cloud data and the cloud data of the point to be registered of the first radar to obtain a transformation relationship between the external radar and the first radar;
a projection module 906, configured to project the radar point cloud data to a coordinate system where the first radar is located based on the transformation relation, so as to obtain fused point cloud data;
and a second registration module 908, configured to perform point cloud registration on the fusion point cloud data and the to-be-registered point cloud data of the second radar to obtain a radar external reference calibration result.
The radar external reference calibration device based on the external radar can perform point cloud registration based on the radar point cloud data which has an overlapping area with the point cloud data to be registered of the first radar to obtain a transformation relation between the external radar and the first radar, further project the radar point cloud data to a coordinate system where the first radar is located based on the transformation relation to obtain fusion point cloud data which has an overlapping area with the point cloud data to be registered of the second radar and corresponds to the coordinate system where the first radar is located, thereby performing point cloud registration on the fusion point cloud data and the point cloud data to be registered of the second radar to obtain a radar external reference calibration result, and the whole process can enable the radar to be calibrated to have an overlapping area without a visual field overlapping area on a vehicle based on the external radar which has a visual field overlapping area with the radar in the radar to be calibrated, and realizing radar external parameter calibration.
In one embodiment, the first registration module is further configured to traverse the radar point cloud data and the cloud data of the point to be registered of the first radar, determine a point cloud overlapping region between the radar point cloud data and the cloud data of the point to be registered of the first radar, and perform point cloud registration on the point cloud data in the point cloud overlapping region to obtain a transformation relationship between the external radar and the first radar.
In an embodiment, the first registration module is further configured to transform point cloud data to be registered of the first radar in the point cloud overlapping area based on the obtained initial transformation parameter to obtain transformed point cloud data, compare the transformed point cloud data with the radar point cloud data in the point cloud overlapping area to obtain a point cloud distance error, and perform iterative optimization on the initial transformation parameter based on the point cloud distance error to obtain a transformation relation between the external radar and the first radar.
In one embodiment, the first registration module is further configured to optimize an initial transformation parameter, transform point cloud data to be registered of the first radar in the point cloud overlapping area based on the optimized initial transformation parameter to obtain quadratic transformation point cloud data, compare the quadratic transformation point cloud data with the radar point cloud data in the point cloud overlapping area to obtain a new point cloud distance error, and continue iterative optimization on the optimized initial transformation parameter based on the new point cloud distance error until the latest point cloud distance error meets an iterative optimization stop condition, so as to obtain a transformation relationship between the external radar and the first radar.
In an embodiment, the second registration module is further configured to traverse the fused point cloud data and the cloud data of the point to be registered of the second radar, determine a target overlapping area between the fused point cloud data and the cloud data of the point to be registered of the second radar, and perform point cloud registration on the point cloud data in the target overlapping area based on an obtained radar transformation initial value between the first radar and the second radar, so as to obtain a radar external reference calibration result.
In one embodiment, the radar point cloud data includes at least two frames of radar point clouds, the to-be-registered point cloud data of the to-be-calibrated radar includes at least two frames of to-be-registered point clouds of a first radar and a second radar, the at least two frames of radar point clouds are respectively matched with the at least two frames of to-be-registered point clouds in a time dimension, the fused point cloud data includes at least two frames of fused point clouds matched with the at least two frames of radar point clouds frame by frame, the second registration module is further configured to respectively perform point cloud registration on the at least two frames of fused point clouds and a single frame of to-be-registered point cloud matched with the to-be-registered point cloud data of the second radar, so as to obtain a single frame of external reference calibration result matched with each of the at least two frames of fused point clouds, and obtain a radar external reference calibration result based on the single frame of external reference calibration result.
All modules in the radar external parameter calibration device based on the external radar can be completely or partially realized through software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 10. The computer device includes a processor, a memory, an Input/Output interface (I/O for short), and a communication interface. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer equipment is used for storing data such as radar point cloud data, point cloud data to be registered and the like. The input/output interface of the computer device is used for exchanging information between the processor and an external device. The communication interface of the computer device is used for connecting and communicating with an external terminal through a network. The computer program is executed by a processor to realize a radar external reference calibration method based on an external radar.
It will be appreciated by those skilled in the art that the configuration shown in fig. 10 is a block diagram of only a portion of the configuration associated with the present application, and is not intended to limit the computing device to which the present application may be applied, and that a particular computing device may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In an embodiment, a computer device is further provided, which includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above method embodiments when executing the computer program.
In an embodiment, a computer-readable storage medium is provided, in which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.
In one embodiment, a computer program product or computer program is provided that includes computer instructions stored in a computer-readable storage medium. The computer instructions are read by a processor of a computer device from a computer-readable storage medium, and the computer instructions are executed by the processor to cause the computer device to perform the steps in the above-mentioned method embodiments.
It should be noted that the data (including but not limited to data for analysis, stored data, displayed data, etc.) referred to in the present application are data authorized by the user or fully authorized by each party, and the collection, use and processing of the related data need to comply with relevant laws and regulations and standards of relevant countries and regions.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high-density embedded nonvolatile Memory, resistive Random Access Memory (ReRAM), Magnetic Random Access Memory (MRAM), Ferroelectric Random Access Memory (FRAM), Phase Change Memory (PCM), graphene Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others. The databases involved in the embodiments provided herein may include at least one of relational and non-relational databases. The non-relational database may include, but is not limited to, a block chain based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing based data processing logic devices, etc., without limitation.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.
Claims (10)
1. A radar external reference calibration method based on an external radar is characterized by comprising the following steps:
the method comprises the steps of obtaining radar point cloud data of an external radar and to-be-calibrated point cloud data of a to-be-calibrated radar, wherein the external radar and the to-be-calibrated radar have a field-of-view overlapping area, and the to-be-calibrated radar comprises a first radar and a second radar;
performing point cloud registration on the radar point cloud data and the cloud data of the point to be registered of the first radar to obtain a transformation relation between the external radar and the first radar;
based on the transformation relation, projecting the radar point cloud data to a coordinate system where the first radar is located to obtain fused point cloud data;
and carrying out point cloud registration on the fusion point cloud data and the to-be-registered point cloud data of the second radar to obtain a radar external reference calibration result.
2. The method of claim 1, wherein the point cloud registration of the radar point cloud data and the point cloud data to be registered of the first radar, and obtaining the transformation relationship between the outlay radar and the first radar comprises:
traversing the radar point cloud data and the cloud data of the point to be registered of the first radar, and determining a point cloud overlapping area between the radar point cloud data and the cloud data of the point to be registered of the first radar;
and carrying out point cloud registration on the point cloud data in the point cloud overlapping area to obtain a transformation relation between the external radar and the first radar.
3. The method of claim 2, wherein the point cloud registration of the point cloud data in the point cloud overlapping region to obtain the transformation relationship between the outlay radar and the first radar comprises:
converting the cloud data of the point to be registered of the first radar in the point cloud overlapping area based on the obtained initial conversion parameters to obtain converted point cloud data;
comparing the converted point cloud data with the radar point cloud data in the point cloud overlapping area to obtain a point cloud distance error;
and performing iterative optimization on the initial transformation parameters based on the point cloud distance error to obtain a transformation relation between the external radar and the first radar.
4. The method of claim 3, wherein iteratively optimizing the initial transformation parameters based on the point cloud range error to obtain a transformation relationship between the outlying radar and the first radar comprises:
optimizing the initial transformation parameters;
based on the optimized initial transformation parameters, transforming the cloud data of the point to be registered of the first radar in the point cloud overlapping area to obtain secondary transformation point cloud data;
comparing the secondary transformation point cloud data with the radar point cloud data in the point cloud overlapping area to obtain a new point cloud distance error;
and continuously performing iterative optimization on the optimized initial transformation parameters based on the new point cloud distance error until the latest point cloud distance error meets an iterative optimization stop condition, so as to obtain a transformation relation between the external radar and the first radar.
5. The method according to claim 1, wherein the point cloud registration of the fused point cloud data and the cloud data of the point to be registered of the second radar to obtain a radar external reference calibration result comprises:
traversing the fused point cloud data and the cloud data of the point to be registered of the second radar, and determining a target overlapping area between the fused point cloud data and the cloud data of the point to be registered of the second radar;
and performing point cloud registration on point cloud data in the target overlapping area based on the acquired radar conversion initial value between the first radar and the second radar to obtain a radar external reference calibration result.
6. The method according to claim 1, wherein the radar point cloud data comprises at least two frames of radar point clouds, the to-be-registered point cloud data of the to-be-calibrated radar comprises at least two frames of to-be-registered point clouds of the first radar and the second radar, the at least two frames of radar point clouds are respectively matched with the at least two frames of to-be-registered point clouds in a time dimension, and the fused point cloud data comprises at least two frames of fused point clouds matched with the at least two frames of radar point clouds frame by frame;
performing point cloud registration on the fusion point cloud data and the cloud data of the point to be registered of the second radar to obtain a radar external reference calibration result, wherein the step of performing point cloud registration on the fusion point cloud data and the cloud data of the point to be registered of the second radar comprises the following steps:
respectively carrying out point cloud registration on the at least two frames of fusion point clouds and the single frame of point cloud to be registered matched in the point cloud data to be registered of the second radar to obtain single frame external reference calibration results matched with the at least two frames of fusion point clouds;
and obtaining a radar external reference calibration result based on the single-frame external reference calibration result.
7. The utility model provides a radar external reference calibration device based on external radar which characterized in that, the device includes:
the system comprises an acquisition module, a calibration module and a calibration module, wherein the acquisition module is used for acquiring radar point cloud data of an external radar and to-be-calibrated point cloud data of a radar to be calibrated, the external radar and the radar to be calibrated have a field-of-view overlapping area, and the radar to be calibrated comprises a first radar and a second radar;
the first registration module is used for carrying out point cloud registration on the radar point cloud data and the cloud data of the point to be registered of the first radar to obtain a transformation relation between the external radar and the first radar;
the projection module is used for projecting the radar point cloud data to a coordinate system where the first radar is located based on the transformation relation to obtain fusion point cloud data;
and the second registration module is used for carrying out point cloud registration on the fusion point cloud data and the point cloud data to be registered of the second radar to obtain a radar external reference calibration result.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 6.
9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program realizes the steps of the method of any one of claims 1 to 6 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210559879.8A CN114646932B (en) | 2022-05-23 | 2022-05-23 | Radar external parameter calibration method and device based on external radar and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210559879.8A CN114646932B (en) | 2022-05-23 | 2022-05-23 | Radar external parameter calibration method and device based on external radar and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114646932A true CN114646932A (en) | 2022-06-21 |
| CN114646932B CN114646932B (en) | 2022-10-21 |
Family
ID=81996943
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210559879.8A Active CN114646932B (en) | 2022-05-23 | 2022-05-23 | Radar external parameter calibration method and device based on external radar and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114646932B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115236644A (en) * | 2022-07-26 | 2022-10-25 | 广州文远知行科技有限公司 | Laser radar external parameter calibration method, device, equipment and storage medium |
| CN116299367A (en) * | 2023-05-18 | 2023-06-23 | 中国测绘科学研究院 | Multi-laser space calibration method |
| CN116740197A (en) * | 2023-08-11 | 2023-09-12 | 之江实验室 | External parameter calibration method and device, storage medium and electronic equipment |
| CN117689536A (en) * | 2024-02-01 | 2024-03-12 | 浙江华是科技股份有限公司 | Laser radar splicing registration method, system, device and computer storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110741282A (en) * | 2019-08-21 | 2020-01-31 | 深圳市速腾聚创科技有限公司 | External parameter calibration method and device, computing equipment and computer storage medium |
| CN111771140A (en) * | 2019-01-30 | 2020-10-13 | 深圳市大疆创新科技有限公司 | Detection device external parameter calibration method, data processing device and detection system |
| CN112462350A (en) * | 2020-12-10 | 2021-03-09 | 苏州一径科技有限公司 | Radar calibration method and device, electronic equipment and storage medium |
| US20210103040A1 (en) * | 2019-10-02 | 2021-04-08 | Korea University Research And Business Foundation | EXTRINSIC CALIBRATION METHOD OF MULTIPLE 3D LiDAR SENSORS FOR AUTONOMOUS NAVIGATION SYSTEM |
| WO2021156026A1 (en) * | 2020-02-03 | 2021-08-12 | Continental Automotive Gmbh | Method for calibrating the extrinsic characteristics of a lidar |
| CN113625288A (en) * | 2021-06-15 | 2021-11-09 | 中国科学院自动化研究所 | Camera and laser radar pose calibration method and device based on point cloud registration |
| CN113640756A (en) * | 2021-08-11 | 2021-11-12 | 北京航迹科技有限公司 | Data calibration method, system, device, computer program and storage medium |
| CN113866747A (en) * | 2021-10-13 | 2021-12-31 | 上海师范大学 | Calibration method and device for multiple laser radars |
| CN114119682A (en) * | 2021-11-22 | 2022-03-01 | 武汉中海庭数据技术有限公司 | Laser point cloud and image registration method and registration system |
| CN114152935A (en) * | 2021-11-19 | 2022-03-08 | 苏州一径科技有限公司 | Method, device and equipment for evaluating radar external parameter calibration precision |
-
2022
- 2022-05-23 CN CN202210559879.8A patent/CN114646932B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111771140A (en) * | 2019-01-30 | 2020-10-13 | 深圳市大疆创新科技有限公司 | Detection device external parameter calibration method, data processing device and detection system |
| CN110741282A (en) * | 2019-08-21 | 2020-01-31 | 深圳市速腾聚创科技有限公司 | External parameter calibration method and device, computing equipment and computer storage medium |
| US20210103040A1 (en) * | 2019-10-02 | 2021-04-08 | Korea University Research And Business Foundation | EXTRINSIC CALIBRATION METHOD OF MULTIPLE 3D LiDAR SENSORS FOR AUTONOMOUS NAVIGATION SYSTEM |
| WO2021156026A1 (en) * | 2020-02-03 | 2021-08-12 | Continental Automotive Gmbh | Method for calibrating the extrinsic characteristics of a lidar |
| CN112462350A (en) * | 2020-12-10 | 2021-03-09 | 苏州一径科技有限公司 | Radar calibration method and device, electronic equipment and storage medium |
| CN113625288A (en) * | 2021-06-15 | 2021-11-09 | 中国科学院自动化研究所 | Camera and laser radar pose calibration method and device based on point cloud registration |
| CN113640756A (en) * | 2021-08-11 | 2021-11-12 | 北京航迹科技有限公司 | Data calibration method, system, device, computer program and storage medium |
| CN113866747A (en) * | 2021-10-13 | 2021-12-31 | 上海师范大学 | Calibration method and device for multiple laser radars |
| CN114152935A (en) * | 2021-11-19 | 2022-03-08 | 苏州一径科技有限公司 | Method, device and equipment for evaluating radar external parameter calibration precision |
| CN114119682A (en) * | 2021-11-22 | 2022-03-01 | 武汉中海庭数据技术有限公司 | Laser point cloud and image registration method and registration system |
Non-Patent Citations (4)
| Title |
|---|
| CHAO GAO等: "On-line Calibration of Multiple LIDARs on a Mobile Vehicle Platform", 《2010 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION》 * |
| JIANHAO JIAO等: "A Novel Dual-Lidar Calibration Algorithm Using Planar Surfaces", 《2019 IEEE INTELLIGENT VEHICLES SYMPOSIUM》 * |
| MENGWEN HE等: "Pairwise LIDAR Calibration Using Multi-Type 3D Geometric Features in Natural Scene", 《2013 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS)》 * |
| 尹露: "分布式激光雷达与视觉信息融合关键技术研究", 《中国优秀博硕士学位论文全文数据库(博士)工程科技Ⅱ辑(月刊)》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115236644A (en) * | 2022-07-26 | 2022-10-25 | 广州文远知行科技有限公司 | Laser radar external parameter calibration method, device, equipment and storage medium |
| CN116299367A (en) * | 2023-05-18 | 2023-06-23 | 中国测绘科学研究院 | Multi-laser space calibration method |
| CN116299367B (en) * | 2023-05-18 | 2024-01-26 | 中国测绘科学研究院 | Multi-laser space calibration method |
| CN116740197A (en) * | 2023-08-11 | 2023-09-12 | 之江实验室 | External parameter calibration method and device, storage medium and electronic equipment |
| CN116740197B (en) * | 2023-08-11 | 2023-11-21 | 之江实验室 | External parameter calibration method and device, storage medium and electronic equipment |
| CN117689536A (en) * | 2024-02-01 | 2024-03-12 | 浙江华是科技股份有限公司 | Laser radar splicing registration method, system, device and computer storage medium |
| CN117689536B (en) * | 2024-02-01 | 2024-05-10 | 浙江华是科技股份有限公司 | Laser radar splicing registration method, system, device and computer storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114646932B (en) | 2022-10-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114646932B (en) | Radar external parameter calibration method and device based on external radar and computer equipment | |
| CN109545072B (en) | Map construction pose calculation method, map construction pose calculation device, map construction pose storage medium and map construction pose calculation system | |
| CN109584357B (en) | Three-dimensional modeling method, device and system based on multiple contour lines and storage medium | |
| US10613546B2 (en) | Stochastic map-aware stereo vision sensor model | |
| EP3745310A1 (en) | Method for calibrating a multi-sensor system using an artificial neural network | |
| Wang et al. | Fastergicp: Acceptance-rejection sampling based 3d lidar odometry | |
| Dubbelman et al. | Closed-form online pose-chain slam | |
| US11625454B2 (en) | Method and device for 3D shape matching based on local reference frame | |
| CN115100185A (en) | Image processing method, image processing device, computer equipment and storage medium | |
| Han et al. | DiLO: Direct light detection and ranging odometry based on spherical range images for autonomous driving | |
| Xu et al. | Hrbf-fusion: Accurate 3d reconstruction from rgb-d data using on-the-fly implicits | |
| CN110688440A (en) | Map fusion method suitable for less sub-map overlapping parts | |
| Guédon et al. | Scone: Surface coverage optimization in unknown environments by volumetric integration | |
| Aravkin et al. | Student's t robust bundle adjustment algorithm | |
| CN114966576A (en) | Radar external reference calibration method and device based on prior map and computer equipment | |
| CN110910463B (en) | Full-view-point cloud data fixed-length ordered encoding method and equipment and storage medium | |
| Shi et al. | Accurate implicit neural mapping with more compact representation in large-scale scenes using ranging data | |
| CN111113405B (en) | Method for robot to obtain position service and robot | |
| CN117058008A (en) | Remote sensing image geometry and radiation integrated correction method, device, equipment and medium | |
| CN114966578A (en) | Radar external parameter calibration method and device based on shooting equipment and computer equipment | |
| CN117193278A (en) | Method, apparatus, computer device and storage medium for dynamic edge path generation | |
| Ćurković et al. | Enhanced 3D parameterization for integrated shape synthesis by fitting parameter values to point sets | |
| CN114488097A (en) | External parameter calibration method of laser radar, computer equipment and computer storage medium | |
| CN114881850A (en) | Point cloud super-resolution method and device, electronic equipment and storage medium | |
| Goel et al. | Incremental Multimodal Surface Mapping via Self-Organizing Gaussian Mixture Models |
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 |