CN114485608B - Local point cloud rapid registration method for high-precision map making - Google Patents
Local point cloud rapid registration method for high-precision map making Download PDFInfo
- Publication number
- CN114485608B CN114485608B CN202111523288.7A CN202111523288A CN114485608B CN 114485608 B CN114485608 B CN 114485608B CN 202111523288 A CN202111523288 A CN 202111523288A CN 114485608 B CN114485608 B CN 114485608B
- Authority
- CN
- China
- Prior art keywords
- point cloud
- plane
- point clouds
- parameters
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
- G01C21/3804—Creation or updating of map data
- G01C21/3807—Creation or updating of map data characterised by the type of data
- G01C21/3815—Road data
- G01C21/3822—Road feature data, e.g. slope data
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
- G01C21/3804—Creation or updating of map data
- G01C21/3807—Creation or updating of map data characterised by the type of data
- G01C21/3811—Point data, e.g. Point of Interest [POI]
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Processing Or Creating Images (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a local point cloud rapid registration method for high-precision map making, which comprises the following steps of: s1: the point cloud plane extracts points in the track point range of the source and target point clouds, a random sampling consistency algorithm is adopted to obtain plane parameters, transformation parameters T1 are obtained by the plane parameters of the source point clouds and the target point clouds, and the source point clouds are transformed by the transformation parameters T1; s2: projecting the transformed source point cloud and target point cloud into a plane, and generating projection maps Is and Ig; s3: and rotating the projection map Is at intervals within a given angle range to obtain Is ', is' and Ig, adopting a template matching algorithm to obtain matching positions and correlation coefficient values, and finally comparing the correlation coefficient values under all rotation angles to obtain the optimal configuration positions and rotation angles to obtain transformation parameters T2. With the scheme of the invention, the time consumption is within 200ms, and the total efficiency is greatly improved for a large number of road point clouds needing registration.
Description
Technical Field
The invention relates to the technical field of point cloud data processing, in particular to a local point cloud rapid registration method for high-precision map making.
Background
In the field of high-precision electronic maps, data collected by each road usually contains laser point cloud data, road elements cannot be completely collected at one time and also need to be updated from time to time, so that one road often has data collected multiple times, and due to factors of gps and inertial navigation precision and point cloud sensor coordinate calculation, the data collected multiple times are often not completely matched, and a registration algorithm is needed to match the point cloud data collected multiple times. And errors generated by gps, inertial navigation and the like are different at different moments, so that the point cloud is required to be divided into a plurality of local areas for registration, and because elements are required to be extracted from the point cloud, the point cloud acquisition range is larger, the point cloud density is also larger, the current mature point cloud registration algorithm is basically divided into icp, ndt and variant algorithms thereof, iteration is required, and high requirements are provided for initial values, so that for a large number of point clouds, iteration cannot reach convergence standards for many times under certain conditions, and the registration time is overlong. Some point cloud registration methods based on deep learning also have good accuracy and recall rate at present, but the methods need a large number of samples to learn, have high requirements on the performance of an operation platform, are difficult to adapt to hundreds of thousands of orders of magnitude of point clouds, and basically avoid a large number of nearest search calculations and data preprocessing algorithms, so that the efficiency is not high.
Disclosure of Invention
The present invention provides a local point cloud fast registration method for high-precision mapping that overcomes or at least partially solves the above-mentioned problems.
According to a first aspect of the present invention, there is provided a local point cloud rapid registration method for high-precision mapping, comprising the steps of:
s1: the point cloud plane extracts points in the track point range of the source and target point clouds, a random sampling consistency algorithm is adopted to obtain plane parameters, transformation parameters T1 are obtained by the plane parameters of the source point clouds and the target point clouds, and the source point clouds are transformed by the transformation parameters T1;
s2: projecting the transformed source point cloud and target point cloud into a plane, and generating projection maps Is and Ig;
s3: and rotating the projection map Is at intervals within a given angle range to obtain Is ', is' and Ig, adopting a template matching algorithm to obtain matching positions and correlation coefficient values, and finally comparing the correlation coefficient values under all rotation angles to obtain the optimal configuration positions and rotation angles to obtain transformation parameters T2.
S4: and synthesizing the transformation parameters T1 and T2 to obtain registration parameters of the source and target point cloud, and finishing registration.
Based on the technical scheme of the invention, the following improvements can be made:
optionally, the step S1 includes:
s11: the method comprises the steps of reading point cloud data, dividing the point cloud data into a plurality of grids according to areas, taking point clouds, target point clouds and acquisition track points which need to be registered in the grids, wherein the point clouds needing to be registered are PTSs, the target point clouds are PTSt, setting offset, enabling a point cloud origin to be PT, and enabling a target point cloud range to be larger than a source point cloud range when the point clouds are taken;
s22: establishing a KDTree for point clouds to be registered, searching and collecting all point clouds to be registered in a given radius of a track point, extracting a plane by using a random sampling consistency algorithm, and setting a normal direction and an angle tolerance range of the plane to obtain plane parameters (Sx, sy, sz and Sd); and extracting a cloud plane of the target point to obtain plane parameters (Gx, gy, gz and Gd), obtaining a rotation matrix by using normal vectors (Sx, sy and Sz) and normal vectors (Gx, gy and Gz), obtaining a final transformation parameter T1 by combining intercept Sd and Td, transforming PTSs by using the parameters, setting a certain point of the plane (Gx, gy, gz and Gd) close to an origin as a new origin, translating to obtain PTS's and PTS' T, and recording the translation parameter as D1.
Optionally, the step S2 includes:
the PTS's are projected onto a plane (Gx, gy, gz, gd), the point cloud Is generated into a picture by setting resolution on the plane with an origin as the center, a plurality of point clouds are located in the same pixel, the value of the pixel takes the average value of the intensity of the plurality of point clouds, and a projection picture Is obtained;
and (3) projecting the PTS't onto a plane (Sx, sy, sz, sd), taking an origin point as a center on the plane, setting resolution to generate a picture from the target point clouds, enabling a plurality of target point clouds to fall in the same pixel, taking the average value of the intensities of the plurality of target point clouds by the pixel value, and obtaining a projection picture Ig.
Optionally, in the step S4, after the final transformation parameters T2 and T1 are obtained and the registration of the source point cloud and the target point cloud is completed, the steps S1 to S4 are repeated to obtain the registration of other point clouds.
Compared with two point clouds based on icp and ndt and variants thereof, which are used for registering about 40 ten thousand points, the local point cloud rapid registration method for high-precision map making provided by the invention has the advantages that the time consumption is about in the order of seconds according to different point cloud characteristics, the time consumption is within 200ms by using the scheme of the invention, and the total efficiency is greatly improved for a large number of road point clouds needing registration.
Drawings
Fig. 1 is a flowchart of a local point cloud rapid registration method for high-precision map making according to an embodiment of the present invention.
Detailed Description
The following describes in further detail the embodiments of the present invention with reference to the drawings and examples. The following examples are illustrative of the invention and are not intended to limit the scope of the invention.
Fig. 1 is a flowchart of a local point cloud rapid registration method for high-precision map making according to an embodiment of the present invention, as shown in fig. 1, and provides a local point cloud rapid registration method for high-precision map making, which includes the following steps:
s1: the point cloud plane extracts points in the track point range of the source and target point clouds, a random sampling consistency algorithm is adopted to obtain plane parameters, transformation parameters T1 are obtained by the plane parameters of the source point clouds and the target point clouds, and the source point clouds are transformed by the transformation parameters T1;
s2: projecting the transformed source point cloud and target point cloud into a plane, and generating projection maps Is and Ig;
s3: and rotating the projection map Is at intervals within a given angle range to obtain Is ', is' and Ig, adopting a template matching algorithm to obtain matching positions and correlation coefficient values, and finally comparing the correlation coefficient values under all rotation angles to obtain the optimal configuration positions and rotation angles to obtain transformation parameters T2.
S4: and synthesizing the transformation parameters T1 and T2 to obtain registration parameters of the source and target point cloud, and finishing registration.
Based on the technical scheme of the invention, the following improvements can be made:
wherein, the step S1 includes:
s11: the method comprises the steps of reading point cloud data, dividing the point cloud data into a plurality of grids according to areas, taking point clouds, target point clouds and acquisition track points which need to be registered in the grids, wherein the point clouds needing to be registered are PTSs, the target point clouds are PTSt, setting offset, enabling a point cloud origin to be PT, and enabling a target point cloud range to be larger than a source point cloud range when the point clouds are taken;
s22: establishing a KDTree for point clouds to be registered, searching and collecting all point clouds to be registered in a given radius of a track point, extracting a plane by using a random sampling consistency algorithm, and setting a normal direction and an angle tolerance range of the plane to obtain plane parameters (Sx, sy, sz and Sd); and extracting a cloud plane of the target point to obtain plane parameters (Gx, gy, gz and Gd), obtaining a rotation matrix by using normal vectors (Sx, sy and Sz) and normal vectors (Gx, gy and Gz), obtaining a final transformation parameter T1 by combining intercept Sd and Td, transforming PTSs by using the parameters, setting a certain point of the plane (Gx, gy, gz and Gd) close to an origin as a new origin, translating to obtain PTS's and PTS' T, and recording the translation parameter as D1.
Wherein, the step S2 includes:
the PTS's are projected onto a plane (Gx, gy, gz, gd), the point cloud Is generated into a picture by setting resolution on the plane with an origin as the center, a plurality of point clouds are located in the same pixel, the value of the pixel takes the average value of the intensity of the plurality of point clouds, and a projection picture Is obtained;
and (3) projecting the PTS't onto a plane (Sx, sy, sz, sd), taking an origin point as a center on the plane, setting resolution to generate a picture from the target point clouds, enabling a plurality of target point clouds to fall in the same pixel, taking the average value of the intensities of the plurality of target point clouds by the pixel value, and obtaining a projection picture Ig.
In the step S4, after final transformation parameters T2 and T1 are obtained and registration of the source point cloud and the target point cloud is completed, the steps S1 to S4 are repeated to obtain registration of other point clouds.
It can be appreciated that, in the local point cloud rapid registration method for high-precision map making provided in this embodiment, compared with two point clouds of about 40 ten thousand points registered based on icp and ndt and variants thereof, according to different point cloud characteristics, the time consumption is about the order of seconds on average, while with the scheme of the present invention, the time consumption is within 200ms, and the overall efficiency improvement is very large for a large number of road point clouds needing registration.
Specifically, by way of example, it comprises the following steps:
step 1: the method comprises the steps of reading point cloud data, dividing the point cloud data into a plurality of grids according to areas, taking point clouds PTSs and target point clouds PTSt which need to be registered in the grids and collecting track points PT ((above a road surface), setting offset to enable point cloud origin to be PT, namely PT coordinates to be (0, 0 and 0), and enabling the target point cloud range to be 2m larger than the source point cloud range when taking the point clouds.
Step 2: establishing a KDTree for the PTSs, searching all points PTSs within a radius of 5m of a track point PT, extracting a plane by using a random sampling consistency (RANSAC) algorithm, setting a normal (0, 1) of the plane, and obtaining plane parameters (Sx, sy, sz, sd) in an angle tolerance range of 20 degrees; the target point cloud plane is extracted in the same way, plane parameters (Gx, gy, gz and Gd) are obtained, a rotation matrix is obtained by normal vectors (Sx, sy, sz) and normal vectors (Gx, gy, gz) (a rotation axis is the normal of the plane formed by the two normal vectors, the rotation angle is the included angle of the two normal vectors), a final transformation parameter T1 is obtained by combining intercept Sd and Td, PTSs are transformed by the parameter, and a certain point of the plane (Gx, gy, gz and Gd) close to the origin is set as a new origin. PTS's and PTS't are obtained after translation, and the translation parameter is marked as D1.
Step 3: the PTS's are projected onto a plane (Gx, gy, gz, gd), the point clouds are generated into a picture on the plane by taking an origin as a center and the resolution of (5 cm ), a plurality of point clouds are located in the same pixel, the value of the pixel takes the average value of the intensities of the plurality of point clouds, a projection picture Is obtained, and the picture Ig Is obtained through the same projection.
Step 4: and rotating Is within the (-5) range with the resolution of 0.1 degrees to obtain I's, and matching the I's with Ig by a sampling template matching algorithm to obtain the optimal matching position (Ix, iy) and the correlation coefficient. And (3) taking the best matching position and rotation angle with the largest correlation coefficient in all rotation angles, and converting the bit transformation parameter T2.
Step 5: and synthesizing the transformation parameters obtained in the previous step to obtain a final transformation parameter T2X T1, finishing the registration of the source point cloud and the target point cloud, and repeating the same steps to obtain the registration between other point cloud pairs.
In the foregoing embodiments, the descriptions of the embodiments are focused on, and for those portions of one embodiment that are not described in detail, reference may be made to the related descriptions of other embodiments.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (3)
1. The local point cloud rapid registration method for high-precision map making is characterized by comprising the following steps of:
s1: acquiring a source point cloud and a target point cloud in a track point range, acquiring plane parameters by adopting a random sampling consistency algorithm, acquiring transformation parameters T1 by the plane parameters of the source point cloud and the target point cloud, and transforming the source point cloud by utilizing the transformation parameters T1;
s2: projecting the transformed source point cloud and target point cloud into a plane, and generating projection maps Is and Ig;
s3: rotating the projection graph Is at intervals within a given angle range to obtain Is ', is' and Ig, adopting a template matching algorithm to obtain matching positions and correlation coefficient values, and finally comparing the correlation coefficient values under all rotation angles to obtain the optimal configuration positions and rotation angles to obtain transformation parameters T2;
s4: comprehensively transforming the parameters T1 and T2 to obtain registration parameters of the source and target point cloud, and finishing registration;
the step S1 includes:
s11: the method comprises the steps of reading point cloud data, dividing the point cloud data into a plurality of grids according to areas, taking point clouds, target point clouds and acquisition track points which need to be registered in the grids, wherein the point clouds needing to be registered are PTSs, the target point clouds are PTSt, setting offset, enabling a point cloud origin to be PT, and enabling a target point cloud range to be larger than a source point cloud range when the point clouds are taken;
s22: establishing a KDTree for point clouds to be registered, searching and collecting all point clouds to be registered in a given radius of a track point, extracting a plane by using a random sampling consistency algorithm, and setting a normal direction and an angle tolerance range of the plane to obtain plane parameters (Sx, sy, sz and Sd); and extracting a cloud plane of the target point to obtain plane parameters (Gx, gy, gz and Gd), obtaining a rotation matrix by using normal vectors (Sx, sy and Sz) and normal vectors (Gx, gy and Gz), obtaining a final transformation parameter T1 by combining intercept Sd and Td, transforming PTSs by using the parameters, setting a certain point of the plane (Gx, gy, gz and Gd) close to an origin as a new origin, translating to obtain PTS's and PTS' T, and recording the translation parameter as D1.
2. The method for rapid registration of local point clouds for high-precision mapping according to claim 1, wherein the step S2 comprises:
the PTS's are projected onto a plane (Gx, gy, gz, gd), the point cloud Is generated into a picture by setting resolution on the plane with an origin as the center, a plurality of point clouds are located in the same pixel, the value of the pixel takes the average value of the intensity of the plurality of point clouds, and a projection picture Is obtained;
and (3) projecting the PTS't onto a plane (Sx, sy, sz, sd), taking an origin point as a center on the plane, setting resolution to generate a picture from the target point clouds, enabling a plurality of target point clouds to fall in the same pixel, taking the average value of the intensities of the plurality of target point clouds by the pixel value, and obtaining a projection picture Ig.
3. The method for rapid registration of local point clouds for high-precision map making according to claim 2, wherein in the step S4, after final transformation parameters T2 and T1 are obtained and registration of the source point cloud and the target point cloud is completed, the steps S1 to S4 are repeated to obtain registration of other point clouds.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111523288.7A CN114485608B (en) | 2021-12-13 | 2021-12-13 | Local point cloud rapid registration method for high-precision map making |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111523288.7A CN114485608B (en) | 2021-12-13 | 2021-12-13 | Local point cloud rapid registration method for high-precision map making |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114485608A CN114485608A (en) | 2022-05-13 |
| CN114485608B true CN114485608B (en) | 2023-10-10 |
Family
ID=81494230
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111523288.7A Active CN114485608B (en) | 2021-12-13 | 2021-12-13 | Local point cloud rapid registration method for high-precision map making |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114485608B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102016116572A1 (en) * | 2016-09-05 | 2018-03-08 | Navvis Gmbh | Alignment of point clouds to the modeling of interiors |
| CN110688440A (en) * | 2019-09-29 | 2020-01-14 | 中山大学 | Map fusion method suitable for less sub-map overlapping parts |
| CN110766731A (en) * | 2019-10-21 | 2020-02-07 | 武汉中海庭数据技术有限公司 | Method and device for automatically registering panoramic image and point cloud and storage medium |
| CN111815686A (en) * | 2019-04-12 | 2020-10-23 | 四川大学 | Coarse-to-fine point cloud registration method based on geometric features |
| CN111915661A (en) * | 2020-07-24 | 2020-11-10 | 广州大学 | Point cloud registration method and system based on RANSAC algorithm and computer readable storage medium |
| CN113436238A (en) * | 2021-08-27 | 2021-09-24 | 湖北亿咖通科技有限公司 | Point cloud registration accuracy evaluation method and device and electronic equipment |
| CN113706589A (en) * | 2021-08-25 | 2021-11-26 | 中国第一汽车股份有限公司 | Vehicle-mounted laser radar point cloud registration method and device, electronic equipment and storage medium |
| CN113739786A (en) * | 2021-07-30 | 2021-12-03 | 国网江苏省电力有限公司电力科学研究院 | Indoor environment sensing method, device and equipment for quadruped robot |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9443312B2 (en) * | 2014-08-29 | 2016-09-13 | Leica Geosystems Ag | Line parametric object estimation |
| CN109781119B (en) * | 2017-11-15 | 2020-01-21 | 百度在线网络技术（北京）有限公司 | Laser point cloud positioning method and system |
-
2021
- 2021-12-13 CN CN202111523288.7A patent/CN114485608B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102016116572A1 (en) * | 2016-09-05 | 2018-03-08 | Navvis Gmbh | Alignment of point clouds to the modeling of interiors |
| CN111815686A (en) * | 2019-04-12 | 2020-10-23 | 四川大学 | Coarse-to-fine point cloud registration method based on geometric features |
| CN110688440A (en) * | 2019-09-29 | 2020-01-14 | 中山大学 | Map fusion method suitable for less sub-map overlapping parts |
| CN110766731A (en) * | 2019-10-21 | 2020-02-07 | 武汉中海庭数据技术有限公司 | Method and device for automatically registering panoramic image and point cloud and storage medium |
| CN111915661A (en) * | 2020-07-24 | 2020-11-10 | 广州大学 | Point cloud registration method and system based on RANSAC algorithm and computer readable storage medium |
| CN113739786A (en) * | 2021-07-30 | 2021-12-03 | 国网江苏省电力有限公司电力科学研究院 | Indoor environment sensing method, device and equipment for quadruped robot |
| CN113706589A (en) * | 2021-08-25 | 2021-11-26 | 中国第一汽车股份有限公司 | Vehicle-mounted laser radar point cloud registration method and device, electronic equipment and storage medium |
| CN113436238A (en) * | 2021-08-27 | 2021-09-24 | 湖北亿咖通科技有限公司 | Point cloud registration accuracy evaluation method and device and electronic equipment |
Non-Patent Citations (2)
| Title |
|---|
| Mobile Laser Scanned Point-Clouds for Road Object Detection and Extraction:A Review;Lingfei Ma 等;remote sensing;第10卷(第10期);第1-33页 * |
| 逆向工程光栅投影点云模型配准技术的研究;孟凡文;吴禄慎;罗丽萍;;机床与液压;第38卷(第15期);第1-4、16页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114485608A (en) | 2022-05-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Fan et al. | Pothole detection based on disparity transformation and road surface modeling | |
| KR102068419B1 (en) | Method, apparatus and computer readable medium for adjusting point cloud data collection trajectory | |
| CN111340862B (en) | Point cloud registration method and device based on multi-feature fusion and storage medium | |
| CN112257605A (en) | Three-dimensional target detection method, system and device based on self-labeling training sample | |
| CN109376208A (en) | A kind of localization method based on intelligent terminal, system, storage medium and equipment | |
| CN104299241A (en) | Remote sensing image significance target detection method and system based on Hadoop | |
| CN112132875B (en) | Multi-platform point cloud matching method based on surface features | |
| Huang et al. | A coarse-to-fine algorithm for registration in 3D street-view cross-source point clouds | |
| Jiang et al. | Learned local features for structure from motion of uav images: A comparative evaluation | |
| CN117495891A (en) | Point cloud edge detection method and device and electronic equipment | |
| CN114485608B (en) | Local point cloud rapid registration method for high-precision map making | |
| CN109670557B (en) | Automatic highway point cloud registration method based on rod-shaped structures | |
| CN112581511A (en) | Three-dimensional reconstruction method and system based on approximate vertical scanning point cloud rapid registration | |
| CN114399547B (en) | Monocular SLAM robust initialization method based on multiframe | |
| Zhong et al. | A deep learning-based local feature extraction method for improved image matching and surface reconstruction from Yutu-2 PCAM images on the Moon | |
| Kumar et al. | An efficient method for road tracking from satellite images using hybrid multi-kernel partial least square analysis and particle filter | |
| JP6761388B2 (en) | Estimator and program | |
| CN113781639B (en) | Quick construction method for digital model of large-scene road infrastructure | |
| CN115661218A (en) | Laser point cloud registration method and system based on virtual super point | |
| Sayed et al. | Point clouds reduction model based on 3D feature extraction | |
| CN110148205A (en) | A kind of method and apparatus of the three-dimensional reconstruction based on crowdsourcing image | |
| CN114413882A (en) | Global initial positioning method and device based on multi-hypothesis tracking | |
| CN111009029B (en) | Data processing method and device for three-dimensional reconstruction, electronic equipment and storage medium | |
| CN109934837B (en) | 3D plant leaf contour extraction method, device and system | |
| Méndez et al. | Comparative study of point cloud registration techniques between ICP and others |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |