KR20220081776A - Point cloud matching method and point cloud matching device - Google Patents

Abstract

In a point cloud matching method and apparatus for matching a source point cloud and a target point cloud according to embodiments of the present invention, the source point cloud obtained at a first time point and the target point cloud and trajectory data obtained at a second time point after the first time point is received, overlapping points and noise for each of the source point cloud and the target point cloud are removed, and the driving trajectory obtained by the source point cloud and the target point cloud is divided into a plurality of sections based on the trajectory data so that the source point cloud and the target point cloud are plural. is divided into a source point cloud for each section and a target point cloud for each section belonging to each section of The source point cloud for each section and the target point cloud for each section are matched so that the summation is minimized. Accordingly, the source point cloud and the target point cloud are accurately matched, and more accurate high-precision map data can be generated.

Description

Point cloud matching method and point cloud matching device

The present invention relates to a method and apparatus for constructing map data, and more particularly, to a point cloud matching method and a point cloud matching apparatus for constructing map data for a vehicle.

Recently, in order to provide services such as route guidance and automatic driving in vehicles, more precise and high-precision map data is required. On the other hand, the map data construction method using aerial photos is not suitable for the construction of high-precision map data requiring centimeter (cm) level precision, and LIDAR (Light Detection And Ranging) is used to build high-precision map data. For example, high-precision map data may be constructed by collecting a point cloud several times using LIDAR or the like and matching the collected point clouds several times.

However, in matching the point clouds, the conventional matching method matches the point clouds with respect to the entire driving trajectory, so there is a problem in that the position error of the matched point clouds increases as the distance from the starting position of the driving trajectory increases.

SUMMARY OF THE INVENTION One object of the present invention is to provide a point cloud matching method capable of more accurately matching a source point cloud and a target point cloud.

Another object of the present invention is to provide a point cloud matching device capable of more accurately matching a source point cloud and a target point cloud.

However, the object of the present invention is not limited to the above-described objects, and may be expanded in various ways without departing from the spirit and scope of the present invention.

In order to achieve an object of the present invention, in the point cloud matching method of matching a source point cloud and a target point cloud according to embodiments of the present invention, the source point cloud obtained at a first time point and a second time point after the first time point The target point cloud and trajectory data obtained at a point in time are received, overlapping points and noise for each of the source point cloud and the target point cloud are removed, and the driving trajectory obtained by the source point cloud and the target point cloud based on the trajectory data is divided into a plurality of sections, so that the source point cloud and the target point cloud are divided into a source point group for each section and a target point group for each section belonging to each of the plurality of sections, and the source points included in the source point group for each section and the Corresponding point pairs of target points included in the target point group for each section are determined, and the source point group for each section and the target point group for each section are matched so that the sum of the distances of the corresponding point pairs is minimized.

In one embodiment, each of the source point cloud and the target point cloud is obtained through a LiDaR device of a Mobile Mapping System (MMS), and the trajectory data is obtained through a trajectory collection device of the mobile mapping system. can be obtained.

In an embodiment, downsampling may be performed on each of the source point cloud and the target point cloud to remove the overlapping points.

In an embodiment, to perform the downsampling, for each of the source point cloud and the target point cloud, a space in which each point cloud is located is divided into a plurality of voxels having a size corresponding to the error range of the LIDAR device. When two or more points of each point group exist in one voxel among the plurality of voxels, at least one of the two or more points may be removed so that one of the two or more points remains.

In an embodiment, filtering may be performed on each of the source point cloud and the target point cloud to remove the noise.

In one embodiment, to perform the filtering, for a plurality of points of each of the source point cloud and the target point cloud, a predetermined number of neighboring points adjacent to each point are searched, and from each point to the neighboring points an average distance of distances is calculated, an average value and a standard deviation value of the average distances for the plurality of points are calculated, a reference distance is determined based on the average value and the standard deviation value, and the plurality of Among the points, a point having the average distance greater than the reference distance may be removed.

In an embodiment, to perform the filtering, for a plurality of points of each of the source point cloud and the target point cloud, neighboring points having a distance less than or equal to a predetermined distance from each point are searched for, and a minimum distance from the neighboring points A neighboring point plane having , is determined, a distance of each point is calculated from the neighboring point plane, and each point having the calculated distance equal to or greater than a reference distance may be removed.

In an embodiment, the driving trajectory from which the source point cloud and the target point cloud are obtained to divide the source point cloud and the target point cloud into the source point cloud for each section and the target point cloud for each section belonging to each of the plurality of sections, respectively A plurality of dividing points having a predetermined predetermined interval are set in is determined into a plurality of sections, the source point cloud is divided into the source point cloud for each section belonging to each of the plurality of sections, and the target point cloud is divided into the target point group for each section belonging to each of the plurality of sections have.

In one embodiment, for each source point among the source points, the source point and the corresponding point pairs are determined between the source points included in the source point group for each section and the target points included in the target point group for each section; Among the target points, when a target point having a minimum distance from the source point is determined as a neighbor point pair, and one target point of the target points belongs to two or more neighbor point pairs among the neighbor point pairs, among the two or more neighbor point pairs The neighboring point pairs remaining by removing at least one may be set as the corresponding point pairs, and a corresponding point pair having a distance greater than or equal to a predetermined corresponding pair reference distance among the corresponding point pairs may be removed as an outlier corresponding point pair.

In an embodiment, at least one of the source point group for each section and the target point group for each section is rotationally moved to match the source point group for each section and the target point group for each section, and the source point group for each section and the target point group for each section At least one of them may be translated.

In order to achieve another object of the present invention, a point cloud matching apparatus for matching a source point cloud and a target point cloud according to embodiments of the present invention receives the source point cloud obtained at a first time point, and receives the source point cloud after the first time point. A point cloud preprocessing block for further receiving the target point cloud obtained at a second time point, and removing overlapping points and noise for each of the source point cloud and the target point group, receiving the locus data obtained at the second time point, and the trajectory Based on data, the driving trajectory obtained by the source point cloud and the target point cloud is divided into a plurality of sections, and the source point cloud and the target point cloud are divided into a source point cloud for each section and a target point cloud for each section belonging to each of the plurality of sections. Section division blocks to be divided respectively, and corresponding point pairs of source points included in the source point group for each section and target points included in the target point group for each section are determined, and the source for each section so that the sum of the distances of the corresponding point pairs is minimized and a point cloud matching block for each section for matching the point cloud with the target point cloud for each section.

In one embodiment, each of the source point cloud and the target point cloud is obtained through a LiDaR device of a Mobile Mapping System (MMS), and the trajectory data is obtained through a trajectory collection device of the mobile mapping system. can be obtained.

In an embodiment, the point cloud preprocessing block may perform downsampling on each of the source point cloud and the target point cloud to remove the overlapping points.

In an embodiment, the point cloud preprocessing block divides, for each of the source point cloud and the target point cloud, a space in which each point cloud is located into a plurality of voxels having a size corresponding to an error range of the LIDAR device. and, when two or more points of each point group exist in one of the plurality of voxels, at least one of the two or more points may be removed so that one of the two or more points remains.

In an embodiment, the point cloud preprocessing block may perform filtering on each of the source point cloud and the target point cloud to remove the noise.

In an embodiment, the point cloud preprocessing block searches for a predetermined number of neighboring points adjacent to each point for a plurality of points of each of the source point cloud and the target point cloud, and from each point to the adjacent points calculating an average distance of distances, calculating an average value and standard deviation value for the average distances for the plurality of points, determining a reference distance based on the average value and the standard deviation value, and Among the points, a point having the average distance greater than the reference distance may be removed.

In an embodiment, the point cloud pre-processing block searches for neighboring points having a distance equal to or less than a predetermined distance from each point for a plurality of points of each of the source point cloud and the target point cloud, and a minimum distance from the neighboring points It is possible to determine a plane of adjacent points with , calculate the distance of each point from the plane of adjacent points, and remove each point having the calculated distance equal to or greater than a reference distance.

In one embodiment, the section division block sets a plurality of division points having a predetermined constant interval in the traveling trajectory from which the source point cloud and the target point cloud are obtained, A plurality of vertical planes perpendicular to the traveling direction are determined, spaces between the plurality of vertical planes are determined as the plurality of sections, and the source point group is defined as the source point group for each section belonging to each of the plurality of sections. and dividing the target point group into the target point group for each section belonging to each of the plurality of sections.

In one embodiment, the point cloud matching block for each section determines, for each source point among the source points, the source point and a target point having a minimum distance from the source point among the target points as a pair of neighboring points, When one target point of the target points belongs to two or more pairs of neighbor points among the pairs of neighbor points, at least one of the two or more pairs of neighbor points is removed to set the remaining neighbor point pairs as the corresponding point pairs, and the corresponding point pairs A pair of corresponding points having a distance equal to or greater than a predetermined corresponding pair reference distance may be removed as an outlier corresponding point pair.

In an embodiment, the point cloud matching block for each section rotates at least one of the source point group for each section and the target point group for each section, and parallel moves at least one of the source point group for each section and the target point group for each section. can

In the point cloud matching method and point cloud matching apparatus for matching a source point cloud and a target point cloud according to embodiments of the present invention, the source point cloud obtained at a first time point and the target obtained at a second time point after the first time point Point cloud and trajectory data are received, overlapping points and noise for each of the source point cloud and the target point cloud are removed, and the driving trajectory obtained by the source point cloud and the target point cloud based on the trajectory data is divided into a plurality of sections. By dividing, the source point cloud and the target point cloud are divided into a source point cloud for each section and a target point cloud for each section belonging to each of the plurality of sections, respectively, and the source points included in the source point group for each section and the target point group for each section are included in the target point group for each section. Corresponding point pairs of the target points are determined, and the source point group for each section and the target point group for each section may be matched so that the sum of the distances of the corresponding point pairs is minimized. Accordingly, since the point cloud registration is performed for each section, a position error of the matched point clouds is reduced, and high-precision map data can be generated. In addition, since high-precision map data is generated by matching a plurality of point clouds, a shaded section of a road may be restored, and a change in road facilities may be detected and updated.

However, the effects of the present invention are not limited to the above-described effects, and may be variously expanded without departing from the spirit and scope of the present invention.

1 is a flowchart illustrating a point cloud matching method for matching a source point cloud and a target point cloud according to an embodiment of the present invention.
2 is a diagram for explaining an example of downsampling performed on each of a source point cloud and a target point cloud.
FIG. 3 is a diagram for explaining an example of statistical outlier removal (SOR) filtering performed on each of a source point cloud and a target point cloud.
4 is a diagram for explaining an example of noise filtering performed on each of a source point cloud and a target point cloud.
5 is a diagram for explaining an example in which a source point cloud and a target point cloud are divided into a source point cloud for each section and a target point cloud for each section.
6 is a diagram for explaining an example in which a pair of neighboring points of a source point and a target point is determined.
7 is a diagram for describing an example of pairs of corresponding points between source points and target points.
FIG. 8 is a diagram for describing an example in which an outlier corresponding point pair is removed from among the corresponding point pairs.
9 is a view for explaining an example in which rotational movement and parallel movement are performed with respect to at least one of a source point group and a target point group.
10 is a block diagram illustrating a point cloud matching apparatus for matching a source point cloud and a target point cloud according to an embodiment of the present invention.

With respect to the embodiments of the present invention disclosed in the text, specific structural or functional descriptions are only exemplified for the purpose of describing the embodiments of the present invention, and the embodiments of the present invention may be embodied in various forms and the text It should not be construed as being limited to the embodiments described in .

Since the present invention can have various changes and can have various forms, specific embodiments are illustrated in the drawings and described in detail in the text. However, this is not intended to limit the present invention to the specific disclosed form, it should be understood to include all modifications, equivalents and substitutes included in the spirit and scope of the present invention.

Terms such as first, second, etc. may be used to describe various elements, but the elements should not be limited by the terms. The above terms may be used for the purpose of distinguishing one component from another component. For example, without departing from the scope of the present invention, a first component may be referred to as a second component, and similarly, the second component may also be referred to as a first component.

When a component is referred to as being “connected” or “connected” to another component, it is understood that it may be directly connected or connected to the other component, but other components may exist in between. it should be On the other hand, when it is said that a certain element is "directly connected" or "directly connected" to another element, it should be understood that no other element is present in the middle. Other expressions describing the relationship between components, such as "between" and "immediately between" or "neighboring to" and "directly adjacent to", etc., should be interpreted similarly.

The terms used in the present application are only used to describe specific embodiments, and are not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly dictates otherwise. In the present application, terms such as "comprise" or "have" are intended to designate that the described feature, number, step, operation, component, part, or a combination thereof exists, but one or more other features or numbers , it is to be understood that it does not preclude the possibility of the existence or addition of steps, operations, components, parts, or combinations thereof.

In addition, terms such as “~ unit” described in the text mean a unit for processing at least one function or operation, which may be implemented as hardware or software or a combination of hardware and software.

Unless defined otherwise, all terms used herein, including technical and scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Terms such as those defined in commonly used dictionaries should be interpreted as meanings consistent with the context of the related art, and unless explicitly defined in the present application, they are not to be interpreted in an ideal or excessively formal meaning. .

Hereinafter, embodiments of the present invention will be described in more detail with reference to the accompanying drawings. The same or similar reference numerals are used for the same elements in the drawings.

1 is a flowchart illustrating a point cloud matching method for matching a source point cloud and a target point cloud according to an embodiment of the present invention, and FIG. 2 is a diagram for explaining an example of downsampling performed for each of the source point cloud and the target point cloud. , FIG. 3 is a diagram for explaining an example of SOR (Statistical Outlier Removal) filtering performed on each of the source point cloud and the target point cloud, and FIG. 4 is an example of noise filtering performed on each of the source point cloud and the target point cloud. 5 is a diagram for explaining an example in which a source point cloud and a target point cloud are divided into a source point cloud for each section and a target point cloud for each section, and FIG. 6 is a diagram for determining a pair of neighboring points between a source point and a target point It is a diagram for explaining an example, FIG. 7 is a diagram for explaining an example of pairs of corresponding points of source points and target points, and FIG. 8 is a diagram for explaining an example in which an outlier corresponding point pair is removed among the corresponding point pairs. , and FIG. 9 is a diagram for explaining an example in which rotational movement and parallel movement are performed with respect to at least one of a source point group and a target point group.

Referring to FIG. 1 , in a point cloud matching method of matching a source point cloud 110 and a target point cloud 120 , a source point cloud 110 obtained at a first time point and a second time point obtained after the first time point The target point cloud 120 and trajectory data 130 may be received (S140). In one embodiment, each of the source point cloud 110 and the target point cloud 120 is obtained through a LiDaR device of a Mobile Mapping System (MMS), and the trajectory data 130 is the mobile mapping system. can be obtained through a trajectory collection device of For example, the lidar device may be a Velodyne LiDAR, a HDL-32 channel LiDAR, or the like, but is not limited thereto. Also, for example, the trajectory collecting device may be a Global Positioning System (GPS) and/or a Global Navigation Satellite System/Inertial Navigation System (GNSS/INS) device, but is not limited thereto. Meanwhile, the source point cloud 110 is a point cloud obtained when the vehicle equipped with the mobile mapping system drives along the driving trajectory at the first time point, and the target point cloud 120 and the trajectory data 130 are the mobile mapping system The on-board vehicle may be point cloud and trajectory data acquired at the second time point after the first time point (eg, several days, months, or years after the first time point).

Duplicate points and noise for each of the source point cloud 110 and the target point group 120 may be removed ( S150 ). In an embodiment, downsampling is performed on each of the source point cloud 110 and the target point cloud 120 to remove the overlapping points, and filtering is performed on each of the source point cloud 110 and the target point cloud 120 to remove the noise. can be performed.

For example, in order to perform the downsampling, a space in which each point cloud is located is divided into a plurality of voxels as shown in 210 of FIG. The overlapping point 230 may be removed so that only one point remains. That is, the downsampling is performed for each of the source point cloud 110 and the target point cloud 120 , and the space in which each point cloud is located corresponds to the error range of the LIDAR device as shown in 210 of FIG. 2 . may be divided into the plurality of voxels having Also, as shown in 220 of FIG. 2 , when two or more points 230 of each point group exist in each voxel, the two or more points 230 are determined as the overlapping points, and the two or more points 230 are the overlapping points. At least one of the two or more points 230 may be removed so that one of the above points 230 remains. For example, only one point close to the center point of each voxel among the two or more points 230 may remain, and the remaining points may be removed. On the other hand, the lidar device has a certain error range, and two or more points 230 existing in each voxel having a size corresponding to the error range may be the erroneously obtained overlapping points, and downsampling using these voxels is performed. Through this, the overlapping point can be removed.

In an embodiment, as shown in FIG. 3 , Statistical Outlier Removal (SOR) filtering may be performed to remove the noise of each of the source point cloud 110 and the target point group 120 . For example, as shown in FIG. 3 , the SPR filtering is performed on each of the source point cloud 110 and the target point cloud 120, and a plurality of points 310, 320, 330, 340, 350, For 360 and 370 , a predetermined number of adjacent points 320 , 330 , 340 , 350 , 360 , 370 adjacent to each point 310 (including but not limited to six in the example of FIG. 3 ) are is searched, and the average distance of the distances d0, d1, d2, d3, d4, d5 from each point 310 to the neighboring points 320, 330, 340, 350, 360, 370 can be calculated. . As such, the average distance is determined as the average distance of the points 310, and this average distance may be determined for all point clouds in each point group. Also, an average value and a standard deviation value for the average distances of all the point clouds may be calculated, and a reference distance may be determined based on the average value and the standard deviation value. In an embodiment, the reference distance may be determined as the sum of the average value and N times the standard deviation value (N is a real number equal to or greater than 0). For example, the reference distance may be determined as a sum of the average value and the standard deviation value. In this case, about 68% of the average distances may be equal to or less than the reference distance. In another example, the reference distance may be determined as a sum of two times the average value and the standard deviation value, and in this case, about 95% of the average distances may be equal to or less than the reference distance. Also, among all the point clouds of each point group, a point having the average distance greater than the reference distance may be removed. Accordingly, for each of the source point cloud 110 and the target point cloud 120 , points far from other points may be removed as erroneously acquired noise.

In another embodiment, as shown in FIG. 4 , noise filtering may be performed to remove the noise of each of the source point cloud 110 and the target point cloud 120 . For example, as shown in FIG. 4 , the noise filtering is performed on each of the source point cloud 110 and the target point cloud 120, and a plurality of points 410, 420, 430, 440, 450, For 460 , neighboring points 420 , 430 , 440 , 450 , 460 having a distance less than or equal to a predetermined distance (not limited to, but not limited to, about 20 cm in the example of FIG. 4 ) from each point 410 are A nearby point plane 470 having a minimum distance from the nearby points 420 , 430 , 440 , 450 and 460 may be determined by searching and performing plane fitting. Also, the distance of each point 410 from the neighboring point plane 470 may be calculated, and each point 410 for which the calculated distance is greater than or equal to a reference distance (predetermined according to embodiments) may be removed. Meanwhile, the neighboring point search, plane fitting, and removal of points greater than or equal to the reference distance may be performed for all point clouds of each point group. Accordingly, for each of the source point cloud 110 and the target point cloud 120 , a point far from the nearby point plane 470 may be removed as erroneously acquired noise.

For each of the source point cloud 110 and the target point cloud 120 , the SOR filtering shown in FIG. 3 is performed, the noise filtering shown in FIG. 4 is performed, or the noise filtering shown in FIG. 3 is performed, according to embodiments. Both the SOR filtering and the noise filtering shown in FIG. 4 may be performed.

Based on the trajectory data 130 , the driving trajectory obtained by the source point cloud 110 and the target point cloud 120 is divided into a plurality of sections so that the source point cloud 110 and the target point cloud 120 are generated in each of the plurality of sections. It may be divided into a source point group for each section and a target point group for each section belonging to (S160).

For example, as shown in FIG. 5 , the driving trajectory in which the source point cloud 110 is obtained at the first time point and the target point cloud 120 obtained at the second time point after the first time point is obtained; That is, a plurality of dividing points 511, 512, 513, 514, 515 having a predetermined constant interval (about 100 m in the example of FIG. 5 , but not limited thereto) in the driving trajectory indicated by the target point cloud 120 , 516, 517, 518, 519) is set, and at a plurality of dividing points 511, 512, 513, 514, 515, 516, 517, 518, 519) a plurality of vertical planes perpendicular to the traveling direction of the driving trajectory (521, 522, 523, 514, 525, 526, 527, 528, 529) can be determined. Meanwhile, although each vertical plane is represented by a line in FIG. 5 for convenience of explanation, each vertical plane may be a plane. Spaces between the plurality of vertical planes 521 , 522 , 523 , 514 , 525 , 526 , 527 , 528 , 529 are determined as the plurality of sections, and the source point cloud 110 is located in each of the plurality of sections. It may be divided into the source point cloud for each section to which it belongs, and the target point group 120 may be divided into the target point group for each section belonging to each of the plurality of sections. In this way, the source point group 110 and the target point group 120 may be divided into the source point group for each section and the target point group for each section along the driving trajectory indicated by the target point group 120 .

For the source point group for each section and the target point group for each section, corresponding to each other belonging to each section, corresponding point pairs of the source points included in the source point group for each section and the target points included in the target point group for each section may be determined ( S170).

For example, as shown in FIG. 6 , for each source point 610 among the source points of the source point group for each section, a source point 610 and target points 621 and 622 of the target point group for each section , 623 , 624 , and 625 , a target point 621 having a minimum distance from the source point 610 may be determined as a pair of neighboring points. Meanwhile, since the neighbor point pair is determined for each source point 610 , a single target point 621 may be included in two or more neighbor point pairs. A neighbor point pair having a target point not included in other neighbor point pairs may be set as the corresponding point pair. On the other hand, when one target point of the target points belongs to two or more pairs of neighbor points among the pair of neighbor points, the pair of neighbor points left by removing at least one of the pairs of neighbor points may be set as the pairs of corresponding points. . Accordingly, as shown in FIG. 7 , the corresponding point pairs include non-overlapping source points 711 , 712 , 713 , 714 , 715 and non-overlapping target points 721 , 722 , 723 , 724 , 725 . can do.

In an embodiment, an outlier corresponding point pair among the corresponding point pairs may be removed. For example, as shown in FIG. 8 , a corresponding pair reference distance is predetermined according to embodiments, and the distances between the source points 813 , 814 , 815 and the target points 823 , 824 , 825 are Corresponding point pairs that are less than the corresponding pair reference distance are maintained as inlier corresponding point pairs, and the corresponding point pairs in which the distances between the source points 811 and 812 and the target points 821 and 822 are greater than or equal to the corresponding pair reference distance are outlier ( outlier) can be removed as a pair of corresponding points.

The source point group for each section and the target point group for each section may be matched so that the sum of the distances of the corresponding point pairs is minimized (S180). In an embodiment, rotational movement and/or parallel movement may be performed on at least one of the source point group for each section and the target point group for each section so that the sum of the distances of the corresponding point pairs is minimized.

In the example of FIG. 9 , reference numeral 910 denotes a source point cloud for each section, and 930 denotes a target point group for each section. For example, as shown in FIG. 9 , as rotational movement is performed on the target point group 930 for each section, the rotationally moved target point group 950 for each section is derived, and then the rotationally moved target point group for each section ( Parallel movement is performed with respect to 950 , so that the target point group 930 for each section may come close to the source point group 910 for each section. Accordingly, the sum of the distances of the corresponding point pairs of the matched source point group 910 for each section and the target point group 930 for each section can be minimized. Meanwhile, in FIG. 9 , an example in which the target point group 930 for each section is rotated and moved in parallel to approximate the source point group 910 for each section is shown, but in another embodiment, the source point group for each section 910 is the target for each section It may be rotated and moved in parallel to approximate the point cloud 930 .

As such, the point clouds matched for each section are merged, the source point cloud 110 and the target point cloud 120 are matched with respect to the entire driving route, and high-precision map data can be generated.

As described above, in the point cloud matching method of matching the source point cloud 110 and the target point cloud 120 according to embodiments of the present invention, overlapping points for each of the source point cloud 110 and the target point cloud 120 and noise are removed, so that the accuracy of each of the source point cloud 110 and the target point group 120 may be improved. In addition, in the point cloud matching method according to the embodiments of the present invention, since the point cloud matching is performed for each section, a position error of the matched point clouds can be reduced, and more accurate high-precision map data can be generated. In addition, in the point cloud matching method according to embodiments of the present invention, a plurality of runs (of a vehicle equipped with a mobile mapping system) at a plurality of time points, not a point cloud obtained by a single run Since the high-precision map data is generated by matching the point clouds (that is, the source point cloud 110 and the target point cloud 120) of A change in road facilities (eg, lanes, crosswalks, signs, etc.) between a plurality of time points is detected, and the changed road facilities may be updated with the latest road facilities.

10 is a block diagram illustrating a point cloud matching apparatus for matching a source point cloud and a target point cloud according to an embodiment of the present invention.

Referring to FIG. 10 , a point cloud matching apparatus 1000 for matching a source point cloud and a target point cloud according to an embodiment of the present invention includes a point cloud preprocessing block 1010 , a section division block 1020 , and a point cloud matching block 1030 for each section. may include

The point cloud preprocessing block 1010 receives the source point cloud obtained at a first time through the lidar device 1060 of the mobile mapping system 1050 and through the lidar device 1060 of the mobile mapping system 1050 . The target point cloud obtained at a second time point after the first time point may be further received. For example, the lidar device 1060 may be a Velodyne LiDAR, a HDL-32 channel LiDAR, or the like, but is not limited thereto.

The point cloud preprocessing block 1010 may remove overlapping points and noise for each of the source point cloud and the target point cloud. In an embodiment, the point cloud preprocessing block 1010 may perform downsampling on each of the source point cloud and the target point cloud to remove the overlapping points. For example, in the point cloud preprocessing block 1010 , for each of the source point cloud and the target point cloud, a space in which each point cloud is located is configured by a plurality of voxels having a size corresponding to an error range of the lidar device 1060 . ), and when two or more points of each point group exist in one voxel among the plurality of voxels, at least one of the two or more points is removed so that one of the two or more points remains. can Also, in an embodiment, the point cloud preprocessing block 1010 may perform filtering on each of the source point cloud and the target point cloud to remove the noise. In one example, the point cloud preprocessing block 1010 searches for a predetermined number of neighboring points adjacent to each point for a plurality of points of each of the source point cloud and the target point cloud, and from each point to the neighboring points calculate an average distance of distances of , calculate an average value and standard deviation value for the average distances for the plurality of points, determine a reference distance based on the average value and the standard deviation value, and Among the points of , a point having the average distance greater than the reference distance may be removed. Such filtering may be referred to as Statistical Outlier Removal (SOR) filtering. In another example, the point cloud preprocessing block 1010 searches for neighboring points having a distance less than or equal to a predetermined distance from each point for a plurality of points of each of the source point cloud and the target point cloud, and a minimum distance from the neighboring points A neighboring point plane having a distance may be determined, a distance of each point may be calculated from the neighboring point plane, and each point having the calculated distance equal to or greater than a reference distance may be removed. Such filtering may be referred to as noise filtering. In some embodiments, the SOR filtering may be performed, the noise filtering may be performed, or both the SOR filtering and the noise filtering may be performed on each of the source point cloud and the target point cloud.

The section division block 1020 may receive the trajectory data acquired at the second time point through the trajectory collecting device 1070 of the mobile mapping system 1050 . For example, the trajectory collecting device 1070 may be a Global Positioning System (GPS) and/or a Global Navigation Satellite System/Inertial Navigation System (GNSS/INS) device, but is not limited thereto.

The section division block 1020 divides the driving trajectory obtained by the source point cloud and the target point cloud into a plurality of sections based on the trajectory data, and divides the source point group and the target point group into a section belonging to each of the sections. It can be divided into a source point cloud for each and a target point cloud for each section, respectively. For example, the section division block 1020 sets a plurality of division points having a predetermined constant interval in the traveling trajectory from which the source point cloud and the target point cloud are obtained, and sets the driving trajectory at the plurality of division points. A plurality of vertical planes perpendicular to the traveling direction are determined, spaces between the plurality of vertical planes are determined as the plurality of sections, and the source point group is defined as the source point group for each section belonging to each of the plurality of sections. and dividing the target point group into the target point group for each section belonging to each of the plurality of sections.

The point cloud matching block 1030 for each section may determine pairs of corresponding points between the source points included in the source point group for each section and the target points included in the target point group for each section. For example, the point cloud matching block 1030 for each section determines, with respect to each source point among the source points, the source point and the target point having the minimum distance from the source point among the target points as a pair of neighboring points, When one target point of the target points belongs to two or more pairs of neighbor points among the pairs of neighbor points, at least one of the two or more pairs of neighbor points is removed to set the remaining neighbor point pairs as the corresponding point pairs, and the corresponding point pairs A pair of corresponding points having a distance equal to or greater than a predetermined corresponding pair reference distance may be removed as an outlier corresponding point pair.

Also, the point cloud matching block 1030 for each section may match the source point group for each section and the target point group for each section such that the sum of the distances of the corresponding point pairs is minimized. For example, the point cloud matching block 1030 for each section rotates at least one of the source point group for each section and the target point group for each section, and parallel moves at least one of the source point group for each section and the target point group for each section. , the source point cloud for each section and the target point cloud for each section may be matched. In this way, the point clouds matched for each section are merged, the source point cloud and the target point cloud are matched with respect to the entire driving route, and high-precision map data can be generated.

As described above, in the point cloud matching apparatus 1000 for matching the source point cloud and the target point cloud according to the embodiments of the present invention, overlapping points and noise for each of the source point cloud and the target point cloud are removed, so that the Accuracy of each of the source point cloud and the target point cloud may be improved. In addition, in the point cloud matching apparatus 1000 according to embodiments of the present invention, since point cloud matching is performed for each section, a position error of the matched point clouds is reduced, and more accurate high-precision map data can be generated. In addition, in the point cloud matching apparatus 1000 according to embodiments of the present invention, a plurality of runs (of a vehicle equipped with the mobile mapping system 1050 ) at a plurality of viewpoints, not a point cloud obtained through a single run Since the high-precision map data is generated by matching a plurality of point clouds (that is, the source point cloud and the target point cloud) obtained with A change in road facilities (eg, lanes, crosswalks, signs, etc.) between the plurality of time points is sensed, and the changed road facilities may be updated with the latest road facilities.

In the above, the point cloud matching method and the point cloud matching apparatus according to the embodiments of the present invention have been described with reference to the drawings, but the above description is exemplary and common knowledge in the technical field without departing from the technical spirit of the present invention. It may be modified and changed by those who have it.

The present invention can be applied to a method and apparatus for constructing high-precision map data. Although the above has been described with reference to the embodiments of the present invention, those skilled in the art can variously modify and change the present invention within the scope without departing from the spirit and scope of the present invention described in the claims below. You will understand that you can.

1000: point cloud matching device
1010: point cloud preprocessing block
1020: segmentation block
1030: Point cloud matching block by interval
1050: mobile mapping system
1060: lidar device
1070: trajectory collecting device

Claims (20)

In the point cloud matching method of matching a source point cloud and a target point cloud,
receiving the source point cloud obtained at a first time point and the target point cloud and trajectory data obtained at a second time point after the first time point;
removing overlapping points and noise for each of the source point cloud and the target point cloud;
Based on the trajectory data, the driving trajectory obtained by the source point cloud and the target point cloud is divided into a plurality of sections, and the source point cloud and the target point group are divided into the source point cloud and the target for each section belonging to each of the plurality of sections. dividing each into a point cloud;
determining pairs of corresponding points between source points included in the source point group for each section and target points included in the target point group for each section; and
and matching the source point cloud for each section and the target point cloud for each section such that the sum of the distances of the corresponding point pairs is minimized. The method of claim 1 , wherein each of the source point cloud and the target point cloud is obtained through a LiDaR device of a Mobile Mapping System (MMS),
The point cloud matching method, characterized in that the trajectory data is obtained through a trajectory collecting device of the mobile mapping system. The method of claim 1, wherein removing the overlapping points and the noise for each of the source point cloud and the target point cloud comprises:
and performing downsampling on each of the source point cloud and the target point cloud to remove the overlapping points. The method of claim 3, wherein the performing the downsampling comprises:
dividing a space in which each point cloud is located into a plurality of voxels having a size corresponding to an error range of a lidar device for each of the source point cloud and the target point cloud; and
and when two or more points of each point group exist in one voxel of the plurality of voxels, removing at least one of the two or more points so that one of the two or more points remains. A point cloud matching method with The method of claim 1, wherein removing the overlapping points and the noise for each of the source point cloud and the target point cloud comprises:
and performing filtering on each of the source point cloud and the target point cloud to remove the noise. The method of claim 5, wherein performing the filtering comprises:
searching for a predetermined number of neighboring points adjacent to each point for a plurality of points of each of the source point cloud and the target point cloud;
calculating an average distance of distances from each point to the neighboring points;
calculating an average value and a standard deviation value for the average distances for the plurality of points;
determining a reference distance based on the average value and the standard deviation value; and
and removing a point having the average distance greater than the reference distance from among the plurality of points. The method of claim 5, wherein performing the filtering comprises:
searching for neighboring points having a distance equal to or less than a predetermined distance from each point with respect to a plurality of points of each of the source point cloud and the target point cloud;
determining a nearby point plane having a minimum distance from the nearby points;
calculating the distance of each point from the neighboring point plane; and
and removing each point where the calculated distance is equal to or greater than a reference distance. According to claim 1, wherein the step of dividing the source point group and the target point group into the source point group for each section and the target point group for each section belonging to each of the plurality of sections, respectively,
setting a plurality of division points having predetermined constant intervals on the driving trajectory obtained by the source point cloud and the target point cloud;
determining a plurality of vertical planes perpendicular to a traveling direction of the traveling trajectory at the plurality of dividing points;
determining spaces between the plurality of vertical planes as the plurality of sections;
dividing the source point cloud into the source point cloud for each section belonging to each of the plurality of sections; and
and dividing the target point cloud into target point clouds for each section belonging to each of the plurality of sections. The method of claim 1, wherein the determining of pairs of corresponding points between the source points included in the source point group for each section and the target points included in the target point group for each section comprises:
determining, for each source point among the source points, the source point and a target point having a minimum distance from the source point among the target points as a pair of neighboring points;
when one target point of the target points belongs to two or more pairs of neighbor points among the pair of neighbor points, removing at least one of the two or more pairs of neighbor points to set the remaining pairs of neighbor points as the pair of corresponding points; and
and removing a corresponding point pair having a distance equal to or greater than a predetermined corresponding pair reference distance from among the corresponding point pairs as an outlier corresponding point pair. The method of claim 1, wherein the matching of the source point cloud for each section and the target point cloud for each section comprises:
rotating at least one of the source point group for each section and the target point group for each section; and
and moving at least one of the source point group for each section and the target point group for each section in parallel. A point cloud matching device for matching a source point cloud and a target point cloud, comprising:
receiving the source point cloud obtained at a first time point, further receiving the target point cloud obtained at a second time point after the first time point, and removing overlapping points and noise for each of the source point cloud and the target point cloud point cloud preprocessing block;
Receive the trajectory data obtained at the second time point, divide the driving trajectory obtained by the source point cloud and the target point cloud into a plurality of sections based on the trajectory data to divide the source point cloud and the target point cloud into the plurality of sections a section division block for dividing each section into a source point cloud for each section and a target point cloud for each section belonging to each section; and
Corresponding point pairs of the source points included in the source point group for each section and the target points included in the target point group for each section are determined, and the source point group for each section and the target point group for each section are selected so that the sum of the distances of the corresponding point pairs is minimized. A point cloud matching device including a point cloud matching block for each section to be matched. The method of claim 11 , wherein each of the source point cloud and the target point cloud is obtained through a LiDaR device of a Mobile Mapping System (MMS),
The point cloud matching device, characterized in that the trajectory data is obtained through a trajectory collecting device of the mobile mapping system. The method of claim 11, wherein the point cloud preprocessing block comprises:
The point cloud matching apparatus of claim 1, wherein downsampling is performed on each of the source point cloud and the target point cloud to remove the overlapping points. The method of claim 13, wherein the point cloud preprocessing block comprises:
For each of the source point cloud and the target point cloud, a space in which each point cloud is located is divided into a plurality of voxels having a size corresponding to an error range of the lidar device,
When two or more points of each point group exist in one voxel of the plurality of voxels, at least one of the two or more points is removed so that one of the two or more points remains. Device. The method of claim 11, wherein the point cloud preprocessing block comprises:
The point cloud matching apparatus, characterized in that filtering is performed on each of the source point cloud and the target point cloud to remove the noise. The method of claim 15, wherein the point cloud preprocessing block,
For a plurality of points of each of the source point cloud and the target point cloud, search for a predetermined number of neighboring points adjacent to each point;
Calculate the average distance of the distances from each point to the neighboring points,
calculating an average value and a standard deviation value for the average distances for the plurality of points;
determining a reference distance based on the average value and the standard deviation value;
and removing a point having the average distance greater than the reference distance from among the plurality of points. The method of claim 15, wherein the point cloud preprocessing block,
For a plurality of points of each of the source point cloud and the target point cloud, search for neighboring points having a distance equal to or less than a predetermined distance from each point;
determine a neighboring point plane having a minimum distance from the neighboring points,
calculating the distance of each point from the nearby point plane,
The point cloud matching device, characterized in that the calculated distance is greater than or equal to a reference distance is removed. The method of claim 11, wherein the section division block comprises:
setting a plurality of division points having a predetermined constant interval in the driving trajectory obtained by the source point cloud and the target point cloud,
determining a plurality of vertical planes perpendicular to the traveling direction of the traveling trajectory at the plurality of dividing points,
determining spaces between the plurality of vertical planes as the plurality of sections,
dividing the source point cloud into the source point cloud for each section belonging to each of the plurality of sections,
and dividing the target point cloud into target point clouds for each section belonging to each of the plurality of sections. The method of claim 11, wherein the point cloud matching block for each section comprises:
For each source point among the source points, the source point and the target point having a minimum distance from the source point among the target points are determined as a pair of neighboring points,
If one target point of the target points belongs to two or more pairs of neighbor points among the pair of neighbor points, removing at least one of the two or more pairs of neighbor points to set the remaining pairs of neighbor points as the corresponding point pairs,
A point cloud matching apparatus, characterized in that, among the corresponding point pairs, a corresponding point pair having a distance equal to or greater than a predetermined corresponding pair reference distance is removed as an outlier corresponding point pair. The method of claim 11, wherein the point cloud matching block for each section comprises:
Rotating and moving at least one of the source point group for each section and the target point group for each section,
The point cloud matching device, characterized in that parallel movement of at least one of the source point group for each section and the target point group for each section.

Images