CN113706589A - Vehicle-mounted laser radar point cloud registration method and device, electronic equipment and storage medium - Google Patents
Vehicle-mounted laser radar point cloud registration method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113706589A CN113706589A CN202110979418.1A CN202110979418A CN113706589A CN 113706589 A CN113706589 A CN 113706589A CN 202110979418 A CN202110979418 A CN 202110979418A CN 113706589 A CN113706589 A CN 113706589A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- matched
- target
- source
- source point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 239000011159 matrix material Substances 0.000 claims abstract description 81
- 238000013519 translation Methods 0.000 claims abstract description 57
- 238000012937 correction Methods 0.000 claims abstract description 25
- 230000008030 elimination Effects 0.000 claims abstract description 22
- 238000003379 elimination reaction Methods 0.000 claims abstract description 22
- 238000006243 chemical reaction Methods 0.000 claims abstract description 13
- 230000004888 barrier function Effects 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 238000004904 shortening Methods 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/60—Rotation of a whole image or part thereof
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- 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
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
Abstract
The embodiment of the invention discloses a point cloud registration method and device for a vehicle-mounted laser radar, electronic equipment and a storage medium, wherein the point cloud registration method comprises the following steps: controlling the source point cloud to be matched and the target point cloud to be matched to carry out centroid coincidence, and constructing a translation matrix; performing non-angular point elimination correction on the target point cloud to be matched and the source point cloud to be matched, and distributing to obtain a reference target point cloud and a reference source point cloud; constructing a rotation matrix according to the reference source point cloud and the reference target point cloud, and performing translation and rotation conversion matching on the source point cloud to be matched by using the constructed translation matrix and rotation matrix to obtain a target source point cloud; and if the target source point cloud and the target point cloud to be matched do not meet the preset matching condition, acquiring a reference target point set to be matched from the reference target point cloud to be matched, finding out a corresponding point set in the target source point cloud as a new source point cloud to be matched, and returning to continue iterative matching. The method improves the accuracy of point cloud registration, shortens the time of point cloud registration, and further improves the high-precision positioning performance of automatic driving of the vehicle.
Description
Technical Field
The embodiment of the invention relates to the technical field of point cloud registration, in particular to a vehicle-mounted laser radar point cloud registration method and device, electronic equipment and a storage medium.
Background
With the concern of the automobile industry on the automatic driving function of the vehicle, automatic driving becomes a popular technical topic in the automobile industry, the automatic driving technology can be divided into perception fusion, high-precision positioning, planning decision making and control execution, however, the high-precision positioning is an important subject for realizing the automatic driving function, the high-precision positioning realizing means mainly comprise GNSS, matching positioning and IMU, and in the scene lacking GNSS signals, the laser radar point cloud registration technology becomes a necessary way for realizing L4 and even L5 level automatic driving. However, the traditional ICP point cloud coarse registration algorithm has low registration accuracy and long point cloud registration time, which affects the high-precision positioning performance of vehicle automatic driving,
disclosure of Invention
The embodiment of the invention provides a vehicle-mounted laser radar point cloud registration method and device, electronic equipment and a storage medium, and aims to improve the point cloud matching accuracy between a source point cloud and a target point cloud.
In a first aspect, an embodiment of the present invention provides a point cloud registration method for a vehicle-mounted laser radar, including:
controlling the source point cloud to be matched and the target point cloud to be matched to carry out centroid coincidence, and constructing a corresponding translation matrix;
performing non-angular point elimination correction on the target point cloud to be matched to obtain a reference target point cloud; performing non-angular point elimination correction on the source point cloud to be matched to obtain a reference source point cloud;
constructing a corresponding rotation matrix according to the reference source point cloud and the reference target point cloud, and performing translation and rotation conversion matching on the source point cloud to be matched by using the constructed translation matrix and rotation matrix to obtain a target source point cloud;
and if the target source point cloud and the target point cloud to be matched do not meet the preset matching condition, acquiring a reference target point set to be matched from the reference target point cloud to be matched, finding out a corresponding point set in the target source point cloud as a new source point cloud to be matched, and returning to continue iterative matching.
In a second aspect, an embodiment of the present invention further provides a vehicle-mounted lidar point cloud registration apparatus, including:
the translation matrix construction module is used for controlling the source point cloud to be matched and the target point cloud to be matched to carry out centroid superposition and constructing a corresponding translation matrix;
the reference point cloud obtaining module is used for carrying out non-angular point elimination correction on the target point cloud to be matched to obtain a reference target point cloud; performing non-angular point elimination correction on the source point cloud to be matched to obtain a reference source point cloud;
the target source point cloud obtaining module is used for constructing a corresponding rotation matrix according to the reference source point cloud and the reference target point cloud, and performing translation and rotation conversion matching on the source point cloud to be matched by using the constructed translation matrix and rotation matrix to obtain the target source point cloud;
and the new source point cloud to be matched acquiring module is used for acquiring a reference target point set to be matched from the reference target point cloud to be matched if the preset matching condition is not met between the target source point cloud and the target point cloud to be matched, finding out a corresponding point set in the target source point cloud as a new source point cloud to be matched, and returning to continue iterative matching.
In a third aspect, an embodiment of the present invention further provides an electronic device, including:
one or more processors;
storage means for storing one or more programs;
the one or more programs are executed by the one or more processors to cause the one or more processors to implement an in-vehicle lidar point cloud registration method as provided in any embodiment of the invention.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the vehicle-mounted lidar point cloud registration method provided in any embodiment of the present invention.
The embodiment of the invention discloses a point cloud registration method and device for a vehicle-mounted laser radar, electronic equipment and a storage medium, wherein the point cloud registration method comprises the following steps: controlling the source point cloud to be matched and the target point cloud to be matched to carry out centroid coincidence, and constructing a translation matrix; performing non-angular point elimination correction on the target point cloud to be matched and the source point cloud to be matched, and distributing to obtain a reference target point cloud and a reference source point cloud; constructing a rotation matrix according to the reference source point cloud and the reference target point cloud, and performing translation and rotation conversion matching on the source point cloud to be matched by using the constructed translation matrix and rotation matrix to obtain a target source point cloud; and if the target source point cloud and the target point cloud to be matched do not meet the preset matching condition, acquiring a reference target point set to be matched from the reference target point cloud to be matched, finding out a corresponding point set in the target source point cloud as a new source point cloud to be matched, and returning to continue iterative matching. The technical effects of improving the accuracy of laser radar point cloud registration, shortening the time of point cloud registration and further improving the high-precision positioning performance of automatic driving of the vehicle are achieved.
The above summary of the present invention is merely an overview of the technical solutions of the present invention, and the present invention can be implemented in accordance with the content of the description in order to make the technical means of the present invention more clearly understood, and the above and other objects, features, and advantages of the present invention will be more clearly understood.
Drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
fig. 1 is a flowchart of a point cloud registration method for a vehicle-mounted laser radar according to an embodiment of the present application;
fig. 2 is a flowchart of a point cloud registration method for a vehicle-mounted laser radar according to a second embodiment of the present application;
fig. 3 is a schematic structural diagram of a vehicle-mounted lidar point cloud registration device provided in the third embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present application.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Before discussing exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the operations (or steps) as a sequential process, many of the operations can be performed in parallel, concurrently or simultaneously. In addition, the order of the operations may be re-arranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figure. The processes may correspond to methods, functions, procedures, subroutines, and the like.
Example one
Fig. 1 is a flowchart of a vehicle-mounted lidar point cloud registration method according to an embodiment of the present invention, where the method is applicable to a case of vehicle-mounted lidar point cloud registration, and the method is performed by a vehicle-mounted lidar point cloud registration apparatus, which may be implemented by software and/or hardware and may be integrated in an electronic device. As shown in fig. 1, the point cloud registration method for the vehicle-mounted lidar in the embodiment includes the following steps:
and S110, controlling the source point cloud to be matched and the target point cloud to be matched to carry out centroid superposition, and constructing a corresponding translation matrix.
The point cloud may be a point data set on the surface of the product appearance, for example, the point data set obtained when the vehicle-mounted laser radar measures the road information may be the point cloud. The source point cloud to be matched can be obtained by the vehicle-mounted laser radar from the source point cloud Q to be matched of the obstacle A. The target point cloud to be matched can be obtained by the point cloud high-precision map.
The centroid may refer to the center of mass of the substance, for example the center of the cloud mass of the source point to be matched, acquired by the vehicle-mounted lidar. The centroid P of the source point cloud to be matched acquired by the vehicle-mounted laser radaroAnd the centroid Q of the target point cloud to be matched acquired by the point cloud high-precision mapoAnd (5) carrying out centroid coincidence and constructing a translation matrix.
The translation matrix may be a matrix obtained by translating the target point cloud to be matched so as to coincide the centroid of the source point cloud to be matched and the centroid of the target point cloud to be matched.
S120, performing non-corner point elimination correction on the target point cloud to be matched to obtain a reference target point cloud; and performing non-corner point elimination and correction on the source point cloud to be matched to obtain a reference source point cloud.
The corner point may be a focal point at the intersection of two lines, or may be a point located on two adjacent objects with different main directions, for example, two points adjacent to a target point to be matched. The non-corner point removing and correcting can be to remove or reserve the non-corner points in the point cloud according to the corner point removing conditions. Removing or reserving non-angular points in the target point cloud to be matched according to angular point removing conditions to obtain a reference target point cloud; and eliminating or reserving non-angular points in the source point cloud to be matched according to angular point eliminating conditions to obtain a reference source point cloud.
S130, constructing a corresponding rotation matrix according to the reference source point cloud and the reference target point cloud, and performing translation and rotation conversion matching on the source point cloud to be matched by using the constructed translation matrix and rotation matrix to obtain the target source point cloud.
The rotation matrix may be obtained by rotating the reference source point cloud and the reference target point cloud, and obtaining the rotation matrix R when an absolute value of a distance between the reference source point and the reference target point is minimum.
Wherein, alpha, beta and gamma respectively represent the rotation angles of the reference source point cloud along the x, y and z axes.
The target source point cloud may be a new source point cloud Q1 obtained by translating and rotating the to-be-matched source point cloud using a translation matrix and a rotation matrix, where Q1 is RQ + T, where R is the rotation matrix, T is the rotation matrix, and Q is the point cloud with the matching source.
And S140, if the preset matching condition is not met between the target source point cloud and the target point cloud to be matched, acquiring a reference target point set to be matched from the reference target point cloud to be matched, finding out a corresponding point set in the target source point cloud as a new source point cloud to be matched, and returning to continue iterative matching.
The preset matching condition may refer to whether an average distance between the point sets of the target source point cloud and the target point cloud to be matched is smaller than a distance threshold between the set point sets, for example, the preset distance threshold is 0.1 mm; it may also refer to whether a preset number of iterations is reached, for example, whether the number of iterations reaches 10.
Optionally, when the first iterative matching is performed, a source point cloud to be matched of the obstacle is obtained through a vehicle-mounted radar; and acquiring a target point cloud to be matched of the barrier through the point cloud high-precision map. When the iteration is not the first iteration, the source point cloud to be matched is generated by performing iterative matching by using a target source point cloud obtained through translation and rotation; the reference target point set to be matched is obtained from the reference target point cloud to be matched.
According to the point cloud registration method for the vehicle-mounted laser radar, a translation matrix is constructed by controlling the point cloud of a source to be matched and the point cloud of a target to be matched to carry out centroid coincidence; performing non-angular point elimination correction on the target point cloud to be matched and the source point cloud to be matched, and distributing to obtain a reference target point cloud and a reference source point cloud; constructing a rotation matrix according to the reference source point cloud and the reference target point cloud, and performing translation and rotation conversion matching on the source point cloud to be matched by using the constructed translation matrix and rotation matrix to obtain a target source point cloud; and if the target source point cloud and the target point cloud to be matched do not meet the preset matching condition, acquiring a reference target point set to be matched from the reference target point cloud to be matched, finding out a corresponding point set in the target source point cloud as a new source point cloud to be matched, and returning to continue iterative matching. The speed of angular point detection is increased by eliminating and correcting non-angular points, the point cloud registration time is shortened, the accuracy of laser radar point cloud registration is increased, and the performance of automatic driving and high-precision positioning of the vehicle is improved.
Example two
Fig. 2 is a flowchart of another vehicle-mounted lidar point cloud registration method provided in the second embodiment of the present application. Embodiments of the present invention are further optimized on the basis of the above-mentioned embodiments, and the embodiments of the present invention may be combined with various alternatives in one or more of the above-mentioned embodiments. As shown in fig. 2, the point cloud registration method for the vehicle-mounted lidar provided in the embodiment of the present invention may include the following steps:
and S210, preprocessing the source point cloud to be matched and the target point cloud to be matched respectively by adopting Gaussian filtering.
The method comprises the steps of carrying out preprocessing such as denoising on point cloud by adopting Gaussian filtering, wherein the preprocessing comprises but is not limited to carrying out hash point and isolated point processing on the point cloud.
And S220, respectively calculating the mass centers of the source point cloud to be matched and the target point cloud to be matched.
Wherein the centroid of the point cloud is a point whose coordinates are obtained by calculating the average of the values of all points in the cloud. For example, calculating the centroid P of the source point cloud to be matchedo。
Wherein x isi，yi，ziI is the coordinate of each point in the cloud, 1, 2, … …, n.
And S230, controlling the target point cloud to be matched to translate, and constructing and obtaining a corresponding translation matrix when the centroid of the source point cloud to be matched is superposed with the centroid of the target point cloud to be matched.
Translating the target point cloud to be matched to ensure that the centroid of the source point cloud to be matched and the centroid of the target point cloud to be matched coincide to obtain a translation matrix T, wherein T is [ T ═ Tx ty tz]TWherein t isx、ty、tzRespectively representing the point clouds of the target to be matched along the x, y and z axesThe amount of translation.
S240, performing non-corner point elimination correction on the target point cloud to be matched to obtain a reference target point cloud; and performing non-corner point elimination and correction on the source point cloud to be matched to obtain a reference source point cloud.
Optionally, for each target point to be matched in the target point cloud to be matched, determining a target point P to be matched from the target point cloud to be matchediThree target points P to be matched with the shortest distanceia、PibAnd Pic；
Calculating the distances from the target point to be matched to the plane where the three target points to be matched with the shortest distance are located, and obtaining the distance d from the point corresponding to the target point to be matched to the planeP；
And rejecting or reserving the target point to be matched according to the distance between the point corresponding to the target point to be matched and the plane and preset angular point rejection condition information.
The corner point removing condition may be that the target point to be matched is removed if the distance between a point corresponding to the target point to be matched and a plane is smaller than a first preset distance threshold; otherwise, reserving the target point to be matched; i.e. comparing dPAnd dmaxWhen d isP≥dmaxWhen it is, P isiMake reservation, otherwise PiRemoving; the first preset distance threshold is used for judging whether a target point to be matched belongs to an angular point on the barrier or not, and the point cloud matching effect is determined in the testing process.
On the basis of the above embodiment, optionally, the non-corner point removing and correcting are performed on the source point cloud to be matched:
point Q in source point cloud to be matchediSolving the three nearest source points Q to be matchedi1、Qi2And Qi3；
Calculating point Q in source point cloud to be matchediTo Qi1、Qi2And Qi3Distance d of planeQ；
Comparison dQAnd dmaxWhen d isQ≥dmaxThen Q is turned oniMake a reservation, otherwiseWill QiAnd (5) removing.
The non-angular point rejection correction is adopted to improve the angular point detection speed, shorten the point cloud registration time and improve the accuracy of laser radar point cloud registration.
To reference source point cloud QCAnd a reference target point cloud PCPerforming minimum traversal of the absolute value of the distance between the reference source point and the reference target point;
after traversing to the reference source point QCiAnd a reference target point PCiThe absolute value of the distance between the two is minimized to obtain a rotation matrix, i.e. Pair | PCi-QCiTraversing ═ min, and when min is minimum, obtaining a rotation matrix.
S250, constructing a corresponding rotation matrix according to the reference source point cloud and the reference target point cloud, and performing translation and rotation conversion matching on the source point cloud to be matched by using the constructed translation matrix and rotation matrix to obtain the target source point cloud.
Optionally, when the value is at the min minimum, obtaining a rotation matrix R to obtain a coarse registration initial transformation value R, T; carrying out rotation and translation transformation on the point set of the source point cloud Q to be matched by using the obtained rotation matrix R and translation matrix T; and obtaining a new corresponding point set target source point cloud Q1, wherein Q1 is RQ + T.
And S260, if the preset matching condition is not met between the target source point cloud and the target point cloud to be matched, acquiring a reference target point set to be matched from the reference target point cloud to be matched, finding out a corresponding point set in the target source point cloud as a new source point cloud to be matched, and returning to continue iterative matching.
Optionally, an average distance S between the target source point cloud Q1 and a point in the target point cloud P to be matched is calculated, and if the average distance S is greater than a predetermined threshold S1, a point set P is taken from the target point cloud P to be matchediE to Q, finding out a corresponding point set Q1 in a target source point cloud Q1iE.g. Q1; so that | Q1i-PiII ═ min; calculating a rotation matrix R and a translation matrix T; performing rotation and translation transformation on the target source point cloud Q1 by using the obtained rotation matrix R and translation matrix T; obtaining a new corresponding point set target source point cloud Q1, wherein Q1 is RQ + T; calculate Q1 and Point set PiIf S is less than or equal toStopping iterative computation if a preset threshold value or the preset maximum iteration times is larger than the preset maximum iteration times; otherwise, continuing to iterate matching.
The embodiment of the invention provides a point cloud registration method for a vehicle-mounted laser radar, which comprises the steps of obtaining a source point cloud to be matched of an obstacle through a vehicle-mounted radar; acquiring a target point cloud to be matched of the barrier through the point cloud high-precision map; controlling the source point cloud to be matched and the target point cloud to be matched to carry out centroid coincidence, and constructing a translation matrix; performing non-angular point elimination correction on the target point cloud to be matched and the source point cloud to be matched, and distributing to obtain a reference target point cloud and a reference source point cloud; constructing a rotation matrix according to the reference source point cloud and the reference target point cloud, and performing translation and rotation conversion matching on the source point cloud to be matched by using the constructed translation matrix and rotation matrix to obtain a target source point cloud; and if the target source point cloud and the target point cloud to be matched do not meet the preset matching condition, acquiring a reference target point set to be matched from the reference target point cloud to be matched, finding out a corresponding point set in the target source point cloud as a new source point cloud to be matched, and returning to continue iterative matching until the process is finished. The technical scheme adopted by the embodiment of the invention can shorten the running time of the ICP algorithm, so that the source point cloud and the target point cloud are easier to match, the iteration times are reduced, the probability that the original ICP algorithm is easier to fall into a local extreme value is reduced, and the technical effects of improving the accuracy of point cloud registration of the laser radar, shortening the point cloud registration time and further improving the high-precision positioning performance of automatic driving of the vehicle are achieved.
EXAMPLE III
Fig. 3 is a schematic structural diagram of a vehicle-mounted lidar point cloud registration device provided in the third embodiment of the present invention. The device can be suitable for the registration of the point cloud of the vehicle-mounted laser radar, can be realized by software and/or hardware, and is integrated in electronic equipment. The device is used for realizing the point cloud registration method of the vehicle-mounted laser radar provided by the embodiment. As shown in fig. 3, the point cloud registration apparatus for vehicle-mounted lidar provided in this embodiment includes:
the translation matrix construction module 310 is configured to control the source point cloud to be matched and the target point cloud to be matched to perform centroid coincidence, and construct a corresponding translation matrix;
the reference point cloud obtaining module 320 is configured to perform non-corner point elimination and correction on a target point cloud to be matched to obtain a reference target point cloud; performing non-angular point elimination correction on the source point cloud to be matched to obtain a reference source point cloud;
the target source point cloud obtaining module 330 is configured to construct a corresponding rotation matrix according to the reference source point cloud and the reference target point cloud, and perform translation and rotation conversion matching on the source point cloud to be matched by using the constructed translation matrix and rotation matrix to obtain the target source point cloud;
and a new source point cloud to be matched obtaining module 340, configured to obtain a reference target point set to be matched from the reference target point cloud to be matched if the preset matching condition is not satisfied between the target source point cloud and the target point cloud to be matched, find a corresponding point set in the target source point cloud as a new source point cloud to be matched, and return to continue iterative matching.
On the basis of this embodiment, optionally, the apparatus further includes:
the system comprises a to-be-matched point cloud obtaining module, a matching module and a matching module, wherein the to-be-matched point cloud obtaining module is used for obtaining a to-be-matched source point cloud of an obstacle through a vehicle-mounted radar when first iterative matching is carried out; and acquiring a target point cloud to be matched of the barrier through the point cloud high-precision map.
On the basis of this embodiment, optionally, the translation matrix building module further includes:
respectively preprocessing a source point cloud to be matched and a target point cloud to be matched by adopting Gaussian filtering; the preprocessing at least comprises the processing of hash points and isolated points of the point cloud;
respectively calculating the mass centers of the source point cloud to be matched and the target point cloud to be matched;
and controlling the target point cloud to be matched to translate, and constructing and obtaining a corresponding translation matrix when the centroid of the source point cloud to be matched and the centroid of the target point cloud to be matched coincide.
On the basis of this embodiment, optionally, the reference point cloud obtaining module further includes:
determining three target points to be matched with the shortest distance from the target point to be matched from the target point cloud to be matched aiming at each target point to be matched in the target point cloud to be matched;
calculating the distances from the target point to be matched to the plane where the three target points to be matched with the shortest distance are located to obtain the point-to-plane distances corresponding to the target point to be matched;
and rejecting or reserving the target point to be matched according to the distance between the point corresponding to the target point to be matched and the plane and preset angular point rejection condition information.
On the basis of this embodiment, optionally, the reference point cloud obtaining module further includes:
determining three source points to be matched which are closest to the source point to be matched from the source point cloud to be matched aiming at each source point to be matched in the source point cloud to be matched;
calculating the distances from the source point to be matched to the plane where the three source points to be matched with the shortest distance are located to obtain the distance from the point corresponding to the source point to be matched to the plane;
and eliminating or reserving the source point to be matched according to the distance between the point corresponding to the source point to be matched and the plane and preset angular point eliminating condition information.
On the basis of this embodiment, optionally, the target point cloud obtaining module further includes:
performing minimum traversal on the absolute values of the distances between the reference source point and the reference target point for the reference source point cloud and the reference target point cloud;
and obtaining a rotation matrix when the absolute value of the distance between the reference source point and the reference target point is minimum.
The vehicle-mounted laser radar point cloud registration device provided by the embodiment of the invention can execute the vehicle-mounted laser radar point cloud registration method provided by any embodiment of the invention, has corresponding functions and beneficial effects of executing the vehicle-mounted laser radar point cloud registration method, and the detailed process refers to the relevant operation of the vehicle-mounted laser radar point cloud registration method in the embodiment.
Example four
Fig. 4 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present application. The embodiment of the application provides electronic equipment, and the vehicle-mounted laser radar point cloud registration device provided by the embodiment of the application can be integrated in the electronic equipment. As shown in fig. 4, the present embodiment provides an electronic device 400, which includes: one or more processors 420; a storage device 410, configured to store one or more programs, when the one or more programs are executed by the one or more processors 420, so that the one or more processors 420 implement the vehicle-mounted lidar point cloud registration method provided in this embodiment of the present application, where the method includes:
controlling the source point cloud to be matched and the target point cloud to be matched to carry out centroid coincidence, and constructing a corresponding translation matrix;
performing non-angular point elimination correction on the target point cloud to be matched to obtain a reference target point cloud; performing non-angular point elimination correction on the source point cloud to be matched to obtain a reference source point cloud;
constructing a corresponding rotation matrix according to the reference source point cloud and the reference target point cloud, and performing translation and rotation conversion matching on the source point cloud to be matched by using the constructed translation matrix and rotation matrix to obtain a target source point cloud;
and if the target source point cloud and the target point cloud to be matched do not meet the preset matching condition, acquiring a reference target point set to be matched from the reference target point cloud to be matched, finding out a corresponding point set in the target source point cloud as a new source point cloud to be matched, and returning to continue iterative matching.
Of course, those skilled in the art can understand that the processor 420 also implements the technical solution of the vehicle-mounted lidar point cloud registration method provided in any embodiment of the present application.
The electronic device 400 shown in fig. 4 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application.
As shown in fig. 4, the electronic device 400 includes a processor 420, a storage device 410, an input device 430, and an output device 440; the number of the processors 420 in the electronic device may be one or more, and one processor 420 is taken as an example in fig. 4; the processor 420, the storage device 410, the input device 430 and the output device 440 in the electronic apparatus may be connected by a bus or other means, and fig. 4 illustrates an example in which the processor, the storage device, the input device 430 and the output device are connected by the bus 440.
The storage device 410 is a computer-readable storage medium, and can be used to store software programs, computer-executable programs, and module units, such as program instructions corresponding to the point cloud registration method of the vehicle-mounted lidar in the embodiment of the present application.
The storage device 410 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the storage 410 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, storage 410 may further include memory located remotely from processor 420, which may be connected 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 means 430 may be used to receive input numbers, character information, or voice information, and to generate key signal inputs related to user settings and function control of the electronic device. The output device 440 may include a display screen, speakers, or other electronic equipment.
The electronic equipment provided by the embodiment of the application can achieve the technical effects of improving the accuracy of laser radar point cloud registration, shortening the point cloud registration time and further improving the high-precision positioning performance of automatic driving of the vehicle.
EXAMPLE five
An embodiment of the present invention provides a computer-readable medium, on which a computer program is stored, where the computer program, when executed by a processor, is configured to perform a vehicle-mounted laser radar point cloud registration method, where the method includes:
controlling the source point cloud to be matched and the target point cloud to be matched to carry out centroid coincidence, and constructing a corresponding translation matrix;
performing non-angular point elimination correction on the target point cloud to be matched to obtain a reference target point cloud; performing non-angular point elimination correction on the source point cloud to be matched to obtain a reference source point cloud;
constructing a corresponding rotation matrix according to the reference source point cloud and the reference target point cloud, and performing translation and rotation conversion matching on the source point cloud to be matched by using the constructed translation matrix and rotation matrix to obtain a target source point cloud;
and if the target source point cloud and the target point cloud to be matched do not meet the preset matching condition, acquiring a reference target point set to be matched from the reference target point cloud to be matched, finding out a corresponding point set in the target source point cloud as a new source point cloud to be matched, and returning to continue iterative matching.
Optionally, the program, when executed by the processor, may be further configured to perform the vehicle-mounted lidar point cloud registration method provided in any embodiment of the present invention.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a Read Only Memory (ROM), an Erasable Programmable Read Only Memory (EPROM), a flash Memory, an optical fiber, a portable CD-ROM, an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. A computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take a variety of forms, including, but not limited to: an electromagnetic signal, an optical signal, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, Radio Frequency (RF), etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A vehicle-mounted laser radar point cloud registration method is characterized by comprising the following steps:
controlling the source point cloud to be matched and the target point cloud to be matched to carry out centroid coincidence, and constructing a corresponding translation matrix;
performing non-angular point elimination correction on the target point cloud to be matched to obtain a reference target point cloud; performing non-angular point elimination correction on the source point cloud to be matched to obtain a reference source point cloud;
constructing a corresponding rotation matrix according to the reference source point cloud and the reference target point cloud, and performing translation and rotation conversion matching on the source point cloud to be matched by using the constructed translation matrix and rotation matrix to obtain a target source point cloud;
and if the preset matching condition is not met between the target source point cloud and the target point cloud to be matched, acquiring a reference target point set from the reference target point cloud, finding out a corresponding point set in the target source point cloud as a new source point cloud to be matched, and returning to continue iterative matching.
2. The method of claim 1, further comprising:
when the first iterative matching is carried out, a source point cloud to be matched of the barrier is obtained through a vehicle-mounted radar; and acquiring a target point cloud to be matched of the barrier through the point cloud high-precision map.
3. The method of claim 1, wherein controlling the source point cloud to be matched and the target point cloud to be matched to perform centroid coincidence, and constructing a corresponding translation matrix comprises:
respectively preprocessing a source point cloud to be matched and a target point cloud to be matched by adopting Gaussian filtering; the preprocessing at least comprises the processing of hash points and isolated points of the point cloud;
respectively calculating the mass centers of the source point cloud to be matched and the target point cloud to be matched;
and controlling the target point cloud to be matched to translate, and constructing and obtaining a corresponding translation matrix when the centroid of the source point cloud to be matched and the centroid of the target point cloud to be matched coincide.
4. The method of claim 1, wherein the non-corner point rejection correction of the source point cloud to be matched comprises:
determining three target points to be matched with the shortest distance from the target point to be matched from the target point cloud to be matched aiming at each target point to be matched in the target point cloud to be matched;
calculating the distances from the target point to be matched to the plane where the three target points to be matched with the shortest distance are located to obtain the point-to-plane distances corresponding to the target point to be matched;
and rejecting or reserving the target point to be matched according to the distance between the point corresponding to the target point to be matched and the plane and preset angular point rejection condition information.
5. The method of claim 1, wherein the non-corner point rejection correction of the source point cloud to be matched comprises:
determining three source points to be matched which are closest to the source point to be matched from the source point cloud to be matched aiming at each source point to be matched in the source point cloud to be matched;
calculating the distances from the source point to be matched to the plane where the three source points to be matched with the shortest distance are located to obtain the distance from the point corresponding to the source point to be matched to the plane;
and eliminating or reserving the source point to be matched according to the distance between the point corresponding to the source point to be matched and the plane and preset angular point eliminating condition information.
6. The method of claim 1, wherein constructing a corresponding rotation matrix from the reference source point cloud and the reference target point cloud comprises:
performing minimum traversal on the absolute values of the distances between the reference source point and the reference target point for the reference source point cloud and the reference target point cloud;
and obtaining a rotation matrix when the absolute value of the distance between the reference source point and the reference target point is minimum.
7. An on-vehicle lidar point cloud registration apparatus, the apparatus comprising:
the translation matrix construction module is used for controlling the source point cloud to be matched and the target point cloud to be matched to carry out centroid superposition and constructing a corresponding translation matrix;
the reference point cloud obtaining module is used for carrying out non-angular point elimination correction on the target point cloud to be matched to obtain a reference target point cloud; performing non-angular point elimination correction on the source point cloud to be matched to obtain a reference source point cloud;
the target source point cloud obtaining module is used for constructing a corresponding rotation matrix according to the reference source point cloud and the reference target point cloud, and performing translation and rotation conversion matching on the source point cloud to be matched by using the constructed translation matrix and rotation matrix to obtain the target source point cloud;
and the new source point cloud to be matched acquiring module is used for acquiring a reference target point set to be matched from the reference target point cloud to be matched if the preset matching condition is not met between the target source point cloud and the target point cloud to be matched, finding out a corresponding point set in the target source point cloud as a new source point cloud to be matched, and returning to continue iterative matching.
8. The apparatus of claim 7, further comprising:
the system comprises a to-be-matched point cloud obtaining module, a matching module and a matching module, wherein the to-be-matched point cloud obtaining module is used for obtaining a to-be-matched source point cloud of an obstacle through a vehicle-mounted radar when first iterative matching is carried out; and acquiring a target point cloud to be matched of the barrier through the point cloud high-precision map.
9. An electronic device, comprising:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the vehicle lidar point cloud registration method of any of claims 1-6.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the vehicle lidar point cloud registration method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110979418.1A CN113706589A (en) | 2021-08-25 | 2021-08-25 | Vehicle-mounted laser radar point cloud registration method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110979418.1A CN113706589A (en) | 2021-08-25 | 2021-08-25 | Vehicle-mounted laser radar point cloud registration method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113706589A true CN113706589A (en) | 2021-11-26 |
Family
ID=78654560
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110979418.1A Pending CN113706589A (en) | 2021-08-25 | 2021-08-25 | Vehicle-mounted laser radar point cloud registration method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113706589A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114155415A (en) * | 2021-12-07 | 2022-03-08 | 华东交通大学 | Multi-data fusion vehicle detection method, system, equipment and storage medium |
| CN114485608A (en) * | 2021-12-13 | 2022-05-13 | 武汉中海庭数据技术有限公司 | Local point cloud rapid registration method for high-precision map making |
| CN114758163A (en) * | 2022-06-15 | 2022-07-15 | 福勤智能科技（昆山）有限公司 | Forklift movement control method and device, electronic equipment and storage medium |
| CN115308771A (en) * | 2022-10-12 | 2022-11-08 | 深圳市速腾聚创科技有限公司 | Obstacle detection method and apparatus, medium, and electronic device |
| CN115908517A (en) * | 2023-01-06 | 2023-04-04 | 广东工业大学 | Low-overlap point cloud registration method based on corresponding point matching matrix optimization |
| CN114155415B (en) * | 2021-12-07 | 2024-05-03 | 华东交通大学 | Multi-data fusion vehicle detection method, system, equipment and storage medium |
-
2021
- 2021-08-25 CN CN202110979418.1A patent/CN113706589A/en active Pending
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114155415A (en) * | 2021-12-07 | 2022-03-08 | 华东交通大学 | Multi-data fusion vehicle detection method, system, equipment and storage medium |
| CN114155415B (en) * | 2021-12-07 | 2024-05-03 | 华东交通大学 | Multi-data fusion vehicle detection method, system, equipment and storage medium |
| CN114485608A (en) * | 2021-12-13 | 2022-05-13 | 武汉中海庭数据技术有限公司 | Local point cloud rapid registration method for high-precision map making |
| CN114485608B (en) * | 2021-12-13 | 2023-10-10 | 武汉中海庭数据技术有限公司 | Local point cloud rapid registration method for high-precision map making |
| CN114758163A (en) * | 2022-06-15 | 2022-07-15 | 福勤智能科技（昆山）有限公司 | Forklift movement control method and device, electronic equipment and storage medium |
| CN115308771A (en) * | 2022-10-12 | 2022-11-08 | 深圳市速腾聚创科技有限公司 | Obstacle detection method and apparatus, medium, and electronic device |
| CN115308771B (en) * | 2022-10-12 | 2023-03-14 | 深圳市速腾聚创科技有限公司 | Obstacle detection method and apparatus, medium, and electronic device |
| CN115908517A (en) * | 2023-01-06 | 2023-04-04 | 广东工业大学 | Low-overlap point cloud registration method based on corresponding point matching matrix optimization |
| CN115908517B (en) * | 2023-01-06 | 2023-05-12 | 广东工业大学 | Low-overlapping point cloud registration method based on optimization of corresponding point matching matrix |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113706589A (en) | Vehicle-mounted laser radar point cloud registration method and device, electronic equipment and storage medium | |
| US10627241B2 (en) | Map-centric map matching method and apparatus | |
| CN110561423B (en) | Pose transformation method, robot and storage medium | |
| US20200081105A1 (en) | Method and device for detecting precision of internal parameter of laser radar | |
| CN110609290B (en) | Laser radar matching positioning method and device | |
| EP3875907B1 (en) | Method, apparatus, computing device and computer-readable storage medium for positioning | |
| US10627520B2 (en) | Method and apparatus for constructing reflectance map | |
| US11415993B2 (en) | Method and apparatus for processing driving reference line, and vehicle | |
| CN112086010B (en) | Map generation method, map generation device, map generation equipment and storage medium | |
| CN108170807B (en) | Map data processing method, map drawing method, map data processing device, map drawing device, map data processing equipment and storage medium | |
| WO2022056770A1 (en) | Path planning method and path planning apparatus | |
| CN112700479B (en) | Registration method based on CNN point cloud target detection | |
| CN109313809B (en) | Image matching method, device and storage medium | |
| CN112148033A (en) | Method, device and equipment for determining unmanned aerial vehicle air route and storage medium | |
| CN110782774A (en) | Crowdsourcing road data distributed processing method and device | |
| CN113050660B (en) | Error compensation method, error compensation device, computer equipment and storage medium | |
| CN111964665B (en) | Intelligent vehicle positioning method and system based on vehicle-mounted all-around image and storage medium | |
| CN112379692B (en) | Method, device and equipment for determining unmanned aerial vehicle air route and storage medium | |
| CN115371663A (en) | Laser mapping method and device, electronic equipment and computer readable storage medium | |
| CN113687336A (en) | Radar calibration method and device, electronic equipment and medium | |
| CN113085840A (en) | Parking path determination method and device, vehicle and storage medium | |
| CN114386481A (en) | Vehicle perception information fusion method, device, equipment and storage medium | |
| CN115877349B (en) | Intersection vehicle positioning method and system based on laser radar | |
| CN116753900A (en) | Distance determining method and device and electronic equipment | |
| CN114445464A (en) | Data processing method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |