CN113593021B - Garage point cloud map construction method based on contour segmentation - Google Patents
Garage point cloud map construction method based on contour segmentation Download PDFInfo
- Publication number
- CN113593021B CN113593021B CN202110693155.8A CN202110693155A CN113593021B CN 113593021 B CN113593021 B CN 113593021B CN 202110693155 A CN202110693155 A CN 202110693155A CN 113593021 B CN113593021 B CN 113593021B
- Authority
- CN
- China
- Prior art keywords
- point cloud
- point
- wall surface
- vertical plane
- registration
- 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
- 238000010276 construction Methods 0.000 title claims abstract description 28
- 230000011218 segmentation Effects 0.000 title claims abstract description 16
- 238000000605 extraction Methods 0.000 claims abstract description 29
- 238000000034 method Methods 0.000 claims abstract description 18
- 239000000284 extract Substances 0.000 claims abstract description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 5
- 239000011159 matrix material Substances 0.000 claims description 5
- 230000008901 benefit Effects 0.000 abstract description 4
- 230000008569 process Effects 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 description 9
- 239000000203 mixture Substances 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/05—Geographic models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- 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
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
- G06T7/344—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods involving models
-
- 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
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
- G06T7/75—Determining position or orientation of objects or cameras using feature-based methods involving models
-
- 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
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Remote Sensing (AREA)
- Computer Graphics (AREA)
- Multimedia (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a garage point cloud map construction system based on contour segmentation, which comprises a vertical plane extraction module, an edge wall surface extraction module and a wall surface point cloud registration module which are sequentially connected, wherein continuous point cloud frames scanned by a laser radar are taken as input, the vertical plane in the point cloud frames are segmented by the vertical plane segmentation module, the edge wall surface extraction module extracts edge wall surfaces, and the wall surface point cloud registration module registers two frames of point cloud together so as to process all the point cloud frames and finally obtain a complete point cloud map. Compared with the prior art, the method 1) improves the accuracy of the construction of the point cloud map in the garage and the registration accuracy of two adjacent frames; 2) The method has the advantages that the precision of the construction of the large-range point cloud map is improved under the condition of not depending on other high-precision positioning solutions and high-precision sensor equipment; 3) And under the garage scene with multiple repeated structures, the construction of the point cloud map is realized.
Description
Technical Field
The invention relates to the technical field of high-precision map construction, in particular to a garage point cloud map construction method.
Background
The three-dimensional point cloud map has very wide application prospect, and the application fields of the three-dimensional point cloud map comprise but are not limited to intelligent driving, intelligent home, three-dimensional reconstruction, digital earth, city planning, disaster prevention and reduction, ocean mapping and the like. The currently selectable point cloud map construction schemes comprise a laser SLAM map construction technology, a point cloud splicing composition technology and the like.
The traditional construction technology of the point cloud map in the garage adopts a laser SLAM construction technology. Because the algorithm uses a uniform motion model as motion prediction, the graph construction precision in a short distance can only be ensured, and the accumulated drift error is larger as the running time of the whole system is longer. Under the condition of larger garage scene range, the map constructed by the laser SLAM is insufficient in precision and is not suitable for being used as a map construction basis.
The point cloud splicing and composition technology mainly relies on a point cloud registration algorithm to splice continuous point cloud frames, and compared with laser SLAM, the point cloud splicing and composition technology has the advantage that the accuracy of a stable map in the construction process is higher. When the point cloud splicing composition technology is used, the point cloud registration algorithm is mainly relied on for registering two adjacent frames of point clouds, and when the repeatability of the environment in the garage scene is high, the scanned point cloud structure is high in repeatability, and mismatching is easy to generate only depending on the registration algorithm.
The GPS is not available in the garage scene, so that the problem of mismatching caused by repeated structure in the garage scene cannot be solved by combining the map construction technology of the GPS-RTK in the garage scene.
Disclosure of Invention
In view of the above, the invention provides a garage point cloud map construction system and method based on contour segmentation, which uses continuous point cloud frames scanned by an on-board laser radar sensor, and realizes garage point cloud map construction by processing such as extracting and registering the acquired garage point cloud frames.
The invention is realized by the following technical scheme:
the system comprises a vertical plane extraction module, an edge wall surface extraction module and a wall surface point cloud registration module which are sequentially connected, wherein:
the continuous point cloud frames scanned by the laser radar are used as input, the vertical plane segmentation module segments the vertical planes in the point cloud frames, and the edge wall surface extraction module extracts the edge wall surface, namely, the vertical plane point cloud set obtained in the step 1 is obtained by utilizing an alpha-shape algorithm
And->
Extracting the edge contour of the middle point set, wherein the extraction is +.>
And->
Edge wall face set->
And->
The wall surface point cloud registration module firstly extracts the edge wall surface set ++ ∈of the step 2>
And->
Merging into two wall point clouds W t-1 And W is t Registering two frames of point clouds together, i.e. for W using ICP algorithm t-1 And W is t Performing point cloud registration, i.e. inputting point cloud W t-1 、W t The method comprises the steps of carrying out a first treatment on the surface of the Calculating a feature descriptor of each point; finding out corresponding points in the two point clouds; the corresponding points are removed by the existing method, pose change estimation is realized, a transformation matrix T is calculated, and the final registration result is P t-1 And P t And (3) processing all the point cloud frames to finally obtain the complete point cloud map.
A garage point cloud map construction method based on contour segmentation comprises the following steps:
step 1: assuming that the current time is t, extracting a specific component from data with a large amount of noise from the point cloud conforming to the point cloud model as pre-registration two-frame point cloud P t-1 And P t The point cloud obtained after noise filtering is
And->
The point cloud model is a plane point cloud perpendicular to an xOy coordinate plane of a coordinate system of the point cloud currently extracted;
for the filtered two-frame point cloud
And->
Point cloud using RanSaC algorithm>
And->
Extracting vertical plane to obtain two vertical plane point clouds +.>
And->
Step 1.3: building vertical planar point clouds
And->
Index I of (2) t-1 、I t ；
Step 2: edge wall surface extraction is carried out, namely, the vertical plane point cloud set obtained in the step 1 is utilized by an alpha-shape algorithm
And->
Extracting the edge contour of the middle point set, wherein the extraction is +.>
And->
Edge wall face set->
And
step 3: performing wall point cloud registration, namely:
step 3.1, firstly collecting the edge wall surface extracted in the step 2
And->
Merging into two wall point clouds W t-1 And W is t ；
Step 3.2: pair W using ICP algorithm t-1 And W is t Performing point cloud registration, i.e. inputting point cloud W t-1 、W t The method comprises the steps of carrying out a first treatment on the surface of the Calculating a feature descriptor of each point; finding out corresponding points in the two point clouds; the corresponding points are removed by the existing method, pose change estimation is realized, a transformation matrix T is calculated, and the final registration result is P t-1 And P t The ICP registration step of the registration result is shown in figure 3, and the final registration result is P t-1 And P t Is a result of the registration of (a).
Compared with the prior art, the invention can achieve the following beneficial effects:
1) The accuracy of the construction of the point cloud map in the garage is improved, and the registration accuracy of two adjacent frames is improved;
2) The method has the advantages that the precision of the construction of the large-range point cloud map is improved under the condition of not depending on other high-precision positioning solutions and high-precision sensor equipment;
3) And under the garage scene with multiple repeated structures, the construction of the point cloud map is realized.
Drawings
Fig. 1 is a schematic structural diagram of a garage point cloud map construction system based on contour segmentation.
Fig. 2 is a schematic flow chart of a garage point cloud map construction method based on contour segmentation.
Fig. 3 is a flow chart of an ICP registration algorithm.
Detailed Description
The technical scheme of the invention is further described in detail below with reference to the attached drawings and specific embodiments.
Fig. 1 is a schematic structural diagram of a garage point cloud map building system based on contour segmentation according to the present invention. The system comprises a vertical plane extraction module 10, an edge wall extraction module 20 and a wall point cloud registration module 30. And the continuous point cloud frames scanned by the laser radar are used as input, then the vertical planes in the point cloud frames are segmented by the vertical plane segmentation module, then the edge wall surface is extracted by the edge wall surface extraction module, two frames of point clouds are registered together by the wall surface point cloud registration module, and finally the complete point cloud map is obtained by processing all the point cloud frames. Wherein:
the vertical plane extraction module is used for extracting a vertical plane set in the point cloud by using a RanSaC algorithm, and the wall point cloud set is a subset of the set.
The edge wall surface extraction module integrates the vertical planes extracted before according to frames, calculates the mass center of each vertical plane, concentrates the mass center in a coordinate system, projects the mass center to an xoy plane, and extracts the edge wall surface through an alpha-shape algorithm.
The wall surface point cloud registration module is used for preprocessing the extracted wall surface, fusing the point clouds of the same wall surface, registering the preprocessed wall surface point cloud results, and taking the registration result as a final registration result between two frames of point clouds.
As shown in fig. 2, the implementation flow of the garage point cloud map construction method based on contour segmentation specifically comprises the following steps:
step 1: assuming the current time is t, using RanSaC (Random Sample Consensus) algorithm to pre-register two adjacent frames P according to a preset parameter model t-1 And P t The point cloud conforming to the point cloud model in the point cloud extracts a specific component, namely a vertical plane point cloud set, from data with a large amount of noise
And->
Step 1.1: and removing the vehicle point cloud and other noise points in the point cloud frame. The point cloud can generate completely invalid points of the acquisition equipment due to the acquisition equipment during acquisition, and the points are eliminated through conditional filtering of fixed parameters. Taking the currently used data as an example: the data are collected by a Velodyne-32 laser radar carried by a three-box type north automobile, and the range of conditional filtering parameters in the data is-2<x<1.5、-0.7<y<0.7、-1.5<z<0. In addition, invalid points in the point cloud frame need to be eliminated, and the method of removerNaNFromPointCloud in PCL (Point Cloud Library) can be used for completing invalid point elimination. The point cloud obtained after the filtering in the step is
And P f ；
Step 1.2: for the filtered two-frame point cloud
And->
Performing plane extraction, including:
the parameters in the RanSaC algorithm were set as follows:
(1) Determining a minimum sampling number M;
(2) Determining a reference vector
(3) The extraction model is set to a constant sacmod_parall_plane, which represents the extraction mode as PARALLEL to the reference vector;
point cloud using RanSaC algorithm according to the parameters set above
And->
Extracting vertical plane to obtain two vertical plane point clouds +.>
And->
Namely, extracting a vertical plane perpendicular to an xOy coordinate plane under a laser radar coordinate system by using a RanSaC algorithm;
step 1.3: building vertical planar point clouds
And->
Index I of (2) t-1 、I t To->
For example, a->
The elements in the index I are started by t, and the index I is built by taking the extraction time sequence as the distinction t For example +.>
The nth extracted vertical plane in (a) is at index I t The indication content in (a) is P t,n The subsequent treatment and use are convenient;
step 2: extracting edge wall surfaces, and extracting edge wall surface sets from the vertical plane point cloud sets obtained in the step 1 by using an alpha-shape algorithm to obtain
For example, the edge wall is extracted from it>
Is provided with->
The number of the elements is N t S is used i (i＝1,2,3,……,N t ) To represent a vertical plane point cloud +.>
Is a vertical plane of the first frame; the alpha-shape algorithm is a method for abstracting the visual shape of the alpha-shape algorithm from a discrete space point set, and specifically, the outline of a stack of unordered discrete points is found out through the algorithm;
step 2.1: representing a vertical plane by centroid, calculating a vertical plane point cloud set
Each vertical plane S of (a) i Centroid m of (2) i The formula is as follows:
wherein p is j Is a vertical plane S i Is a dot in (2);
storing centroid m with planar point cloud sequence number as index i (x, y, z) then mapping it to an xOy coordinate plane to reduce its coordinates to m' i (x,y)；
Step 2.2: edge wall extraction, i.e. using the alpha-shape algorithm on the vertical plane point clouds obtained in step 1
And->
Extracting the edge contour of the center-of-mass point set of the middle vertical plane, wherein the extracted edge contour is +.>
And->
Edge wall face set->
And->
Step 3: registering the wall point cloud, namely firstly collecting the edge wall surface set extracted in the step 2
And->
Integrating the two point clouds, registering by using Iterative Closest Point (ICP) algorithm, calculating feature descriptors for each point in the two input point clouds to be registered, searching corresponding points in the two point clouds according to the feature descriptors, removing corresponding points which do not meet the requirements, and calculating pose transformation between the two point clouds by using the rest points;
step 3.1: the wall point cloud integration, namely combining the edge wall surfaces extracted in the step 2 by using an addition heavy-load method in PCL, and combining a plurality of edge wall surfaces extracted from the same vertical plane point cloud into two wall point clouds W t-1 And W is t The formula for merging is as follows:
wherein M is t-1 And M t Respectively is
And->
The number of elements in the middle edge wall set;
step 3.2: pair W using ICP algorithm t-1 And W is t Performing point cloud registration, wherein the final registration result is P t-1 And P t Is a result of the registration of (a).
As shown in fig. 3, a flow chart of the ICP registration algorithm is shown. The specific steps of the registration algorithm include:
input point cloud W t-1 、W t The method comprises the steps of carrying out a first treatment on the surface of the Calculating a feature descriptor of each point; finding out corresponding points in the two point clouds; and removing corresponding points by using the existing method, realizing pose change estimation, and calculating a transformation matrix T.
The invention has the advantages that: (1) Only the laser point cloud frame acquired by the laser radar sensor is needed, and other sensors such as an IMU (inertial measurement unit) are not needed to be used for maintaining the graph construction precision; (2) The contour extraction is used for ensuring the matching of two frames of point clouds in the registration process, so that the mismatching caused by a repetitive structure when the point cloud splicing composition technology is directly used is avoided; (3) Because the contour extraction uses the traditional point cloud processing algorithm, more calculation force can be saved.
Claims (2)
1. The garage point cloud map construction system based on contour segmentation is characterized by comprising a vertical plane extraction module, an edge wall surface extraction module and a wall surface point cloud registration module which are sequentially connected, wherein:
the continuous point cloud frames scanned by the laser radar are used as input, the vertical plane segmentation module segments vertical planes in the continuous point cloud frames, the current moment is assumed to be t, and specific components of point clouds conforming to the point cloud model are extracted from data with a large amount of noise to serve as pre-registration two-frame point clouds P t-1 And P t The point cloud obtained after noise filtering is
And->
The point cloud model is a plane point cloud of an xOy coordinate plane perpendicular to a coordinate system of the point cloud currently extracted, and the edge wall surface extraction module extracts an edge wall surface, namely, a vertical plane point cloud set obtained from the vertical plane segmentation module by using an alpha-shape algorithm>
And->
Extracting the edge contour of the middle point set, wherein the extraction is +.>
And->
Edge wall surface set in (a)
And->
The wall surface point cloud registration module firstly extracts edges extracted by the edge wall surface extraction moduleEdge wall surface set
And->
Merging into two wall point clouds W t-1 And W is t Registering two frames of point clouds together, i.e. for W using ICP algorithm t-1 And W is t Performing point cloud registration, i.e. inputting point cloud W t-1 、W t The method comprises the steps of carrying out a first treatment on the surface of the Calculating a feature descriptor of each point; finding out two point clouds W t-1 And W is t Corresponding points in (a); removing corresponding points to realize pose change estimation, calculating a transformation matrix T, and obtaining a final registration result which is P t-1 And P t And (3) processing all the point cloud frames to finally obtain the complete point cloud map.
2. The garage point cloud map construction method based on contour segmentation is characterized by comprising the following steps of:
step 1: assuming that the current time is t, extracting a specific component from data with a large amount of noise from the point cloud conforming to the point cloud model as pre-registration two-frame point cloud P t-1 And P t The point cloud obtained after noise filtering is
And->
The point cloud model is a plane point cloud perpendicular to an xOy coordinate plane of a coordinate system of the point cloud currently extracted;
for the filtered two-frame point cloud
And->
Point cloud using RanSaC algorithm>
And->
Extracting vertical plane to obtain two vertical plane point clouds +.>
And->
Building vertical planar point clouds
And->
Index I of (2) t-1 、I t Index I is constructed by taking the extraction time sequence as the distinction t ，
The nth extracted vertical plane in (a) is at index I t The indication content in (a) is P t,n ；
Step 2: edge wall surface extraction is carried out, namely, the vertical plane point cloud set obtained in the step 1 is utilized by an alpha-shape algorithm
And->
Extracting the edge contour of the middle point set, wherein the extraction is +.>
And->
Edge wall face set->
And->
Step 3: performing wall point cloud registration, namely:
step 3.1, firstly collecting the edge wall surface extracted in the step 2
And->
Merging into two wall point clouds W t-1 And W is t ；
Step 3.2: pair W using ICP algorithm t-1 And W is t Performing point cloud registration, i.e. inputting point cloud W t-1 、W t The method comprises the steps of carrying out a first treatment on the surface of the Calculating a feature descriptor of each point; finding out two point clouds W t-1 、W t Corresponding points in (a); removing corresponding points to realize pose change estimation, calculating a transformation matrix T, and obtaining a final registration result which is P t-1 And P t And (3) processing all the point cloud frames to finally obtain the complete point cloud map.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110693155.8A CN113593021B (en) | 2021-06-22 | 2021-06-22 | Garage point cloud map construction method based on contour segmentation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110693155.8A CN113593021B (en) | 2021-06-22 | 2021-06-22 | Garage point cloud map construction method based on contour segmentation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113593021A CN113593021A (en) | 2021-11-02 |
| CN113593021B true CN113593021B (en) | 2023-06-09 |
Family
ID=78244338
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110693155.8A Active CN113593021B (en) | 2021-06-22 | 2021-06-22 | Garage point cloud map construction method based on contour segmentation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113593021B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9251417B1 (en) * | 2014-10-15 | 2016-02-02 | Hrl Laboratories, Llc | Fast open doorway detection for autonomous robot exploration |
| CN108917761A (en) * | 2018-05-07 | 2018-11-30 | 西安交通大学 | A kind of accurate positioning method of unmanned vehicle in underground garage |
| CN110274602A (en) * | 2018-03-15 | 2019-09-24 | 奥孛睿斯有限责任公司 | Indoor map method for auto constructing and system |
| CN112164145A (en) * | 2020-10-30 | 2021-01-01 | 武汉大学 | Method for rapidly extracting indoor three-dimensional line segment structure based on point cloud data |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9189862B2 (en) * | 2010-06-10 | 2015-11-17 | Autodesk, Inc. | Outline approximation for point cloud of building |
| CN109325998B (en) * | 2018-10-08 | 2023-06-30 | 香港理工大学 | Indoor 3D modeling method, system and related device based on point cloud data |
| US11074701B2 (en) * | 2019-12-13 | 2021-07-27 | Reconstruct Inc. | Interior photographic documentation of architectural and industrial environments using 360 panoramic videos |
-
2021
- 2021-06-22 CN CN202110693155.8A patent/CN113593021B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9251417B1 (en) * | 2014-10-15 | 2016-02-02 | Hrl Laboratories, Llc | Fast open doorway detection for autonomous robot exploration |
| CN110274602A (en) * | 2018-03-15 | 2019-09-24 | 奥孛睿斯有限责任公司 | Indoor map method for auto constructing and system |
| CN108917761A (en) * | 2018-05-07 | 2018-11-30 | 西安交通大学 | A kind of accurate positioning method of unmanned vehicle in underground garage |
| CN112164145A (en) * | 2020-10-30 | 2021-01-01 | 武汉大学 | Method for rapidly extracting indoor three-dimensional line segment structure based on point cloud data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113593021A (en) | 2021-11-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110223348B (en) | Robot scene self-adaptive pose estimation method based on RGB-D camera | |
| CN112634451B (en) | Outdoor large-scene three-dimensional mapping method integrating multiple sensors | |
| CN102519481B (en) | Implementation method of binocular vision speedometer | |
| CN106595659A (en) | Map merging method of unmanned aerial vehicle visual SLAM under city complex environment | |
| CN109579825B (en) | Robot positioning system and method based on binocular vision and convolutional neural network | |
| CN112129281B (en) | High-precision image navigation positioning method based on local neighborhood map | |
| CN114332348B (en) | Track three-dimensional reconstruction method integrating laser radar and image data | |
| CN115240047A (en) | Laser SLAM method and system fusing visual loopback detection | |
| CN111860651A (en) | Monocular vision-based semi-dense map construction method for mobile robot | |
| CN114563000B (en) | Indoor and outdoor SLAM method based on improved laser radar odometer | |
| CN115421158A (en) | Self-supervision learning solid-state laser radar three-dimensional semantic mapping method and device | |
| CN113673400A (en) | Real scene three-dimensional semantic reconstruction method and device based on deep learning and storage medium | |
| CN112946679A (en) | Unmanned aerial vehicle surveying and mapping jelly effect detection method and system based on artificial intelligence | |
| CN116429116A (en) | Robot positioning method and equipment | |
| CN113593021B (en) | Garage point cloud map construction method based on contour segmentation | |
| CN113959437A (en) | Measuring method and system for mobile measuring equipment | |
| CN116124161B (en) | LiDAR/IMU fusion positioning method based on priori map | |
| CN117029870A (en) | Laser odometer based on road surface point cloud | |
| Zhang et al. | Accurate real-time SLAM based on two-step registration and multimodal loop detection | |
| CN110634160A (en) | Method for constructing target three-dimensional key point extraction model and recognizing posture in two-dimensional graph | |
| CN115861481A (en) | SLAM system based on real-time dynamic object of laser inertia is got rid of | |
| CN115113170A (en) | Laser radar edge feature prediction method based on indoor feature degradation environment | |
| CN113239936B (en) | Unmanned aerial vehicle visual navigation method based on deep learning and feature point extraction | |
| CN113483769B (en) | Vehicle self-positioning method, system, equipment and medium based on particle filter | |
| CN112001223B (en) | Rapid virtualization construction method for real environment map |
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 |