CN116934822A - System for autonomously registering and converting refined model based on three-dimensional point cloud data - Google Patents
System for autonomously registering and converting refined model based on three-dimensional point cloud data Download PDFInfo
- Publication number
- CN116934822A CN116934822A CN202311188863.1A CN202311188863A CN116934822A CN 116934822 A CN116934822 A CN 116934822A CN 202311188863 A CN202311188863 A CN 202311188863A CN 116934822 A CN116934822 A CN 116934822A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- cloud data
- registration
- registered
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012545 processing Methods 0.000 claims abstract description 48
- 239000013598 vector Substances 0.000 claims abstract description 25
- 238000000034 method Methods 0.000 claims abstract description 24
- 238000007781 pre-processing Methods 0.000 claims abstract description 24
- 230000008569 process Effects 0.000 claims abstract description 17
- 230000008859 change Effects 0.000 claims description 18
- 230000011218 segmentation Effects 0.000 claims description 17
- 238000013500 data storage Methods 0.000 claims description 9
- 238000012937 correction Methods 0.000 claims description 8
- 230000001174 ascending effect Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims 4
- 238000007670 refining Methods 0.000 abstract description 10
- 230000000694 effects Effects 0.000 abstract description 3
- 230000006978 adaptation Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 5
- 239000011159 matrix material Substances 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000009191 jumping Effects 0.000 description 3
- 238000012163 sequencing technique Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 238000004148 unit process Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
-
- 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
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
-
- 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
Abstract
The invention provides a system for autonomously registering, converting and refining model based on three-dimensional point cloud data, which comprises a data acquisition module, a preprocessing module, a registering module and a refining module, wherein the data acquisition module is used for acquiring the point cloud data, the preprocessing module is used for preprocessing the point cloud data, the registering module is used for registering the preprocessed point cloud data, and the refining module is used for refining based on the registered point cloud data; in the registration process, the system obtains a feature vector by acquiring point cloud data of two areas and processing normal information in the point cloud data, obtains the registration degree based on the feature vector, and registers the two optimal adaptation areas by comparing the registration degree, so that the registration effect of two groups of point cloud data is greatly improved.
Description
Technical Field
The invention relates to the field of image analysis, in particular to a system for autonomously registering, converting and refining a model based on three-dimensional point cloud data.
Background
With the development of three-dimensional digitizing technology, the acquisition and processing of three-dimensional point cloud data have become important means for research and application in many fields, however, the three-dimensional point cloud data acquired by different acquisition devices and different acquisition environments and conditions often have problems of registration errors, noise interference and the like, which limit the application range and precision of the three-dimensional point cloud data, and in order to solve the problems, an automatic registration technology is generated, and can automatically align a plurality of point cloud data by utilizing characteristic information in the point cloud data, so that the representation of the point cloud data under a unified coordinate system is realized, thereby providing convenience for subsequent processing and analysis;
many point cloud registration systems have been developed, and the existing registration system is found to have a method as disclosed in publication number CN109859256B, a three-dimensional point cloud registration method based on automatic corresponding point matching, the method comprising: extracting local geometric features of the model by adopting a depth mapping method to obtain a depth matrix of a point set in the model; performing dimension reduction processing on the depth matrix by adopting a convolution self-encoder to extract a feature matrix; selecting matching points by adopting an iterative processing mode according to the feature matrix; the RANSAC algorithm is adopted to register the two point clouds, matching points in the two point clouds can be directly found by the method, and the registration is carried out according to the matching points. However, the system can directly find matching points, and although the registration speed is high, the effect of mismatching is easy to generate in some special cases, so that the whole point cloud data is in misregistration.
Disclosure of Invention
The invention aims at providing a system for autonomously registering and converting a refined model based on three-dimensional point cloud data.
The invention adopts the following technical scheme:
a system for autonomously registering and converting a refinement model based on three-dimensional point cloud data comprises a data acquisition module, a preprocessing module, a registration module and a refinement module;
the data acquisition module is used for acquiring point cloud data, the preprocessing module is used for preprocessing the point cloud data, the registration module is used for registering the preprocessed point cloud data, and the refinement module is used for performing refinement processing based on the registered point cloud data;
the registration module comprises a data storage unit, a calculation processing unit and a change processing unit, wherein the data storage unit is used for storing normal angle data of a registration area and a to-be-registered area, the calculation processing unit calculates feature vectors of the registration area and the to-be-registered area according to the normal angle data, calculates registration degree according to the two feature vectors, the registration area and the to-be-registered area are respectively selected from basic point cloud data and to-be-registered point cloud data, the registration area and the to-be-registered area with the highest registration degree are determined by traversing the registration area and the to-be-registered area, the change processing unit calculates a change process from the to-be-registered area to the registration area, carries out change processing on the to-be-registered point cloud data according to the same change process, and combines the to-be-registered point cloud data into the basic point cloud data;
further, the registering area and the area to be registered are both composed of a target point cloud and a neighborhood point thereof, the distances between the target point cloud and the neighborhood point are ordered from small to large, and then the normal included angles between the target point cloud and the neighborhood point are ordered in a corresponding mode to obtain a sequenceStored in a data storage unit;
further, the feature vector Ca is calculated by the following formula:
；
wherein ,for the ascending order of time, & lt + & gt>For the descending order of times, +.>For the longest lifting length->For the sequence->Is used for the average value of (a),for the sequence->Maximum value of>For the sequence->Minimum value->For the sequence->Standard deviation of (2);
the degree of registrationCalculated according to the following formula:
；
wherein , and />Feature vectors respectively representing the registration area and the area to be registered;
further, the preprocessing module comprises an invalid processing unit and a normal correction unit, wherein the invalid processing unit is used for removing invalid point clouds in acquired data, and the normal correction unit is used for correcting normal information in the point cloud data;
further, the refinement module comprises a segmentation unit and a curved surface processing unit, wherein the segmentation unit is used for segmenting all the point cloud data into a plurality of curved surfaces, and the curved surface processing unit performs refinement processing on the point cloud data of each curved surface.
The beneficial effects obtained by the invention are as follows:
according to the system, the point cloud data are preprocessed before registration, invalid points and correction normals are removed, reliable data are provided for subsequent registration, in the registration process, normal information of two point cloud areas is reordered, feature vectors of the two areas are obtained through information processing obtained through ordering, the registration degree is obtained based on the feature vector processing, finally, the two areas with the largest registration degree are obtained through traversing the areas, the registration accuracy is greatly improved, and after registration, a model obtained through converting the point cloud data is finer through adding refined point clouds.
For a further understanding of the nature and the technical aspects of the present invention, reference should be made to the following detailed description of the invention and the accompanying drawings, which are provided for purposes of reference only and are not intended to limit the invention.
Drawings
FIG. 1 is a schematic diagram of the overall structural framework of the present invention;
fig. 2 is a schematic diagram of a registration module according to the present invention;
FIG. 3 is a schematic diagram of a pretreatment module according to the present invention;
FIG. 4 is a schematic diagram of a refinement module of the present invention;
fig. 5 is a schematic diagram of a point cloud data registration process according to the present invention.
Detailed Description
The following embodiments of the present invention are described in terms of specific examples, and those skilled in the art will appreciate the advantages and effects of the present invention from the disclosure herein. The invention is capable of other and different embodiments and its several details are capable of modification and variation in various respects, all without departing from the spirit of the present invention. The drawings of the present invention are merely schematic illustrations, and are not intended to be drawn to actual dimensions. The following embodiments will further illustrate the related art content of the present invention in detail, but the disclosure is not intended to limit the scope of the present invention.
Embodiment one: the embodiment provides a system for autonomously registering and converting a refinement model based on three-dimensional point cloud data, which comprises a data acquisition module, a preprocessing module, a registration module and a refinement module, and is combined with fig. 1;
the data acquisition module is used for acquiring point cloud data, the preprocessing module is used for preprocessing the point cloud data, the registration module is used for registering the preprocessed point cloud data, and the refinement module is used for performing refinement processing based on the registered point cloud data;
referring to fig. 2, the registration module includes a data storage unit, a calculation processing unit and a change processing unit, where the data storage unit is configured to store normal angle data of a registration area and a to-be-registered area, the calculation processing unit calculates feature vectors of the registration area and the to-be-registered area according to the normal angle data, calculates a registration degree according to the two feature vectors, the registration area and the to-be-registered area are respectively selected from basic point cloud data and to-be-registered point cloud data, determines a registration area and a to-be-registered area with a highest registration degree by traversing the registration area and the to-be-registered area, and the change processing unit calculates a change process from the to-be-registered area to the registration area, performs change processing on the to-be-registered point cloud data according to the same change process, and merges the to-be-registered point cloud data into the basic point cloud data;
the registering area and the area to be registered are both composed of a target point cloud and a neighborhood point thereof, the distances between the target point cloud and the neighborhood point are ordered from small to large, and then the normal included angles between the target point cloud and the neighborhood point are ordered in a corresponding mode to obtain the orderColumn ofStored in a data storage unit;
the feature vector Ca is calculated by the following formula:
；
wherein ,for the ascending order of time, & lt + & gt>For the descending order of times, +.>For the longest lifting length->For the sequence->Is used for the average value of (a),for the sequence->Maximum value of>For the sequence->Minimum value->For the sequence->Standard deviation of (2);
the degree of registrationCalculated according to the following formula:
；
wherein , and />Feature vectors respectively representing the registration area and the area to be registered;
referring to fig. 3, the preprocessing module includes an invalidation processing unit and a normal correction unit, the invalidation processing unit is used for removing invalid point clouds in the acquired data, and the normal correction unit is used for correcting normal information in the point cloud data;
referring to fig. 4, the refinement module includes a segmentation unit and a surface processing unit, where the segmentation unit is configured to segment all the point cloud data into a plurality of surfaces, and the surface processing unit performs refinement processing on the point cloud data of each surface.
Embodiment two: the embodiment comprises the whole content of the first embodiment, and provides a system for autonomously registering, converting and refining a model based on three-dimensional point cloud data, which comprises a data acquisition module, a preprocessing module, a registration module and a refining module;
the data acquisition module is used for acquiring point cloud data, the preprocessing module is used for preprocessing the point cloud data, the registration module is used for registering the preprocessed point cloud data, and the refinement module is used for performing refinement processing based on the registered point cloud data;
the data acquisition module comprises a shooting unit and a storage unit, wherein the shooting unit shoots an object in multiple angles by adopting a structured light camera, the data shot in each angle is stored in the storage unit as a group of point cloud data, and each point cloud data comprises the position and normal line information of the point;
the preprocessing module performs preprocessing including invalid point removal and normal line correction;
the preprocessing module removes invalid points according to position information in the point cloud data, firstly selects one target point cloud data, and calculates the distance d between the rest point cloud data in the same group of point cloud data and the target point cloud data:
；
wherein ,for location information in the target point cloud data, +.>Position information in the other point cloud data;
the preprocessing module counts point cloud data with the distance d smaller than a distance threshold value, takes the points as neighborhood points of the target point cloud data, and deletes the target point cloud data as invalid points when the number n of the neighborhood points is smaller than a neighbor point threshold value;
the preprocessing module acquires normal information in target point cloud data and neighborhood point data thereof, and processes the normal information according to the following formula:
；
wherein ,represents normal unit vector in target point cloud, +.>A normal unit vector representing the i-th neighborhood point,representation vector->Sum vector->Included angle between->Representing the angle of departure;
when the deviation angle is larger than a threshold value, normal line information is processed according to the following formula:
；
wherein ,representing a cusp index angle;
when the cusp index angle is larger than a threshold value, correcting the normal line of the target point cloud;
the preprocessing module calculates a new normal line direction vector of the target point cloud according to the following formula：
；
Will beIntercepting a new normal line unit vector serving as a target point cloud after unit length;
referring to fig. 5, the process of registering the point cloud data by the registration module includes the following steps:
s1, acquiring a group of point cloud data called basic point cloud data, and determining a reference coordinate system according to the basic point cloud data;
s2, acquiring another group of point cloud data, namely point cloud data to be aligned;
s3, acquiring a registration area from the basic point cloud data, wherein the registration area consists of a target point cloud and neighborhood points thereof, sequencing the distances between the target point cloud and the neighborhood points from small to large, and sequencing the normal included angles between the target point cloud and the neighborhood points in a corresponding mode to obtain a sequence；
S4, comparing sequencesTwo adjacent values of (a) to obtain the ascending order of +.>Number of descending order->And the longest lifting lengthThe sum of the ascending times and the descending times is the number of the neighborhood points minus one, and the longest ascending length is the maximum value of continuous ascending or continuous descending times;
s5, calculating to obtain a sequenceMean value of>Maximum->Minimum->And standard deviation->；
S6, calculating a characteristic vector Ca of the registration area according to the following formula:
；
s7, acquiring a region to be registered from the point cloud data with registration, calculating a feature vector of the region to be registered in the same mode as the basic point cloud data, and calculating the registration degree of the registration region and the time of the region to be registered according to the following formula：
；
wherein , and />Feature vectors respectively representing the registration area and the area to be registered;
s8, repeating the step S7 until the point cloud data to be registered is traversed, and recording the region to be registered with the largest registration degree;
s9, repeating the steps S3 to S8, and selecting the largest registration degree, the corresponding registration region and the region to be registered from all registration degrees recorded in the step S8;
s10, calculating a change process from a region to be registered to a registration region, wherein the change process comprises a translation process and a rotation process;
s11, processing the residual data of the point cloud data to be registered by using the same change process;
s12, combining the point cloud data to be registered and the basic point cloud data into new basic point cloud data;
s13, repeating the steps S2 to S12, and processing all the point cloud data;
the refining module comprises a segmentation unit and a curved surface processing unit, wherein the segmentation unit is used for segmenting all the point cloud data into a plurality of curved surfaces, and the curved surface processing unit is used for refining the point cloud data of each curved surface;
the process of splitting the point cloud data by the splitting unit comprises the following steps:
s21, acquiring each point cloud data as the deviation angle information when the point cloud is a target point cloud;
s22, taking the point cloud with the deviation angle larger than the segmentation threshold value as a first segmentation point cloud set;
s23, selecting one point cloud with the largest deviation angle from the first segmentation point cloud set as an extension point, and transferring the extension point from the first segmentation point cloud set to the second segmentation point cloud set;
s24, selecting a point cloud with the largest deviation angle from the neighborhood points of the extension points to replace the point cloud as a new extension point;
s25, if the new extension point is in the second segmentation point cloud set, jumping to the step S26, otherwise, transferring the extension point from the first segmentation point cloud set to the second segmentation point cloud set and jumping back to the step S24;
s26, judging that point clouds in the current second segmentation point cloud set segment all the point clouds into the number of curved surfaces, if the number is smaller than the preset number, jumping back to the step S23, otherwise, entering the step S27;
s27, dividing all the point clouds into a plurality of curved surfaces according to the point clouds in the second dividing point cloud set;
the curved surface processing unit processes each point cloud in a curved surface in one round according to the following steps:
s31, selecting two other point clouds to form a triangle with the smallest area;
s32, calculating the area of the triangle, ending the processing of the point cloud data when the area is smaller than the refinement threshold value, otherwise, entering step S33;
s33, adding a refined point cloud into the curved surface, and refining the space coordinates of the point cloudThe method comprises the following steps:
；
wherein ,、/> and />Spatial coordinates of three point clouds;
refiningNormal vector of point cloudThe method comprises the following steps:
；
wherein ,、/> and />The unit normal vector is three point clouds;
and the curved surface processing unit performs a new round of the same processing on the point cloud data in the curved surface until the area of each point cloud obtained in the step S32 is smaller than the refinement threshold value.
The foregoing disclosure is only a preferred embodiment of the present invention and is not intended to limit the scope of the invention, so that all equivalent technical changes made by applying the description of the present invention and the accompanying drawings are included in the scope of the present invention, and in addition, elements in the present invention can be updated as the technology develops.
Claims (5)
1. The system for autonomously registering and converting the refinement model based on the three-dimensional point cloud data is characterized by comprising a data acquisition module, a preprocessing module, a registration module and a refinement module;
the data acquisition module is used for acquiring point cloud data, the preprocessing module is used for preprocessing the point cloud data, the registration module is used for registering the preprocessed point cloud data, and the refinement module is used for performing refinement processing based on the registered point cloud data;
the registration module comprises a data storage unit, a calculation processing unit and a change processing unit, wherein the data storage unit is used for storing normal angle data of a registration area and a to-be-registered area, the calculation processing unit calculates feature vectors of the registration area and the to-be-registered area according to the normal angle data, calculates registration degree according to the two feature vectors, the registration area and the to-be-registered area are respectively selected from basic point cloud data and to-be-registered point cloud data, the registration area and the to-be-registered area with the highest registration degree are determined by traversing the registration area and the to-be-registered area, the change processing unit calculates a change process from the to-be-registered area to the registration area, carries out change processing on the to-be-registered point cloud data according to the same change process, and combines the to-be-registered point cloud data into the basic point cloud data.
2. The system for autonomous registration transformation refinement model based on three-dimensional point cloud data as defined in claim 1, wherein the registration area and the area to be registered are each composed of a target point cloud and a neighborhood point thereof, the distances between the target point cloud and the neighborhood point are ordered from small to large, and then normal included angles between the target point cloud and the neighborhood point are ordered in a corresponding manner to obtain a sequenceStored in the data storage unit.
3. The system for autonomous registration transformation refinement model based on three-dimensional point cloud data according to claim 2, wherein the feature vector Ca is calculated by:
；
wherein ,for the ascending order of time, & lt + & gt>For the descending order of times, +.>Is the longest literDecrease length (decrease)>For the sequence->Average value of>For the sequence->Maximum value of>For the sequence->Minimum value->For the sequence->Standard deviation of (2);
the degree of registrationCalculated according to the following formula:
；
wherein , and />Feature vectors representing the registration region and the region to be registered, respectively.
4. A system for autonomous registration transformation refinement model based on three-dimensional point cloud data as defined in claim 3, wherein the preprocessing module comprises an invalidation processing unit and a normal correction unit, the invalidation processing unit is used for removing invalid point cloud in acquired data, and the normal correction unit is used for correcting normal information in the point cloud data.
5. The system for autonomous registration transformation refinement model based on three-dimensional point cloud data as claimed in claim 4, wherein the refinement module comprises a segmentation unit and a surface processing unit, the segmentation unit is used for segmenting all point cloud data into a plurality of surfaces, and the surface processing unit performs refinement processing on the point cloud data of each surface.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311188863.1A CN116934822B (en) | 2023-09-15 | 2023-09-15 | System for autonomously registering and converting refined model based on three-dimensional point cloud data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311188863.1A CN116934822B (en) | 2023-09-15 | 2023-09-15 | System for autonomously registering and converting refined model based on three-dimensional point cloud data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116934822A true CN116934822A (en) | 2023-10-24 |
| CN116934822B CN116934822B (en) | 2023-12-05 |
Family
ID=88377437
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311188863.1A Active CN116934822B (en) | 2023-09-15 | 2023-09-15 | System for autonomously registering and converting refined model based on three-dimensional point cloud data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116934822B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070057942A1 (en) * | 2005-09-13 | 2007-03-15 | Siemens Corporate Research Inc | Method and Apparatus for the Rigid Registration of 3D Ear Impression Shapes with Skeletons |
| CN103236064A (en) * | 2013-05-06 | 2013-08-07 | 东南大学 | Point cloud automatic registration method based on normal vector |
| CN104299260A (en) * | 2014-09-10 | 2015-01-21 | 西南交通大学 | Contact network three-dimensional reconstruction method based on SIFT and LBP point cloud registration |
| US20160162732A1 (en) * | 2014-12-03 | 2016-06-09 | Fuji Xerox Co., Ltd. | Information processing apparatus and non-transitory computer readable medium |
| CN109685841A (en) * | 2019-01-03 | 2019-04-26 | 上海狮迈科技有限公司 | Threedimensional model and the method for registering and system for putting cloud |
| US20200388044A1 (en) * | 2019-06-06 | 2020-12-10 | Zhejiang University | Plant point cloud acquisition, registration and optimization method based on tof camera |
| US20220084221A1 (en) * | 2019-02-11 | 2022-03-17 | Siemens Aktiengesellschaft | An apparatus and a method for performing a data driven pairwise registration of three-dimensional point clouds |
| CN115496784A (en) * | 2022-08-11 | 2022-12-20 | 西安航天时代精密机电有限公司 | Point cloud registration method based on normalized four-dimensional feature vector |
| CN115546025A (en) * | 2022-10-08 | 2022-12-30 | 贵州师范大学 | Method, device and equipment for realizing simulation splicing for object fragments |
| CN115797418A (en) * | 2022-09-27 | 2023-03-14 | 湖南科技大学 | Complex mechanical part measurement point cloud registration method and system based on improved ICP |
| WO2023045455A1 (en) * | 2021-09-21 | 2023-03-30 | 西北工业大学 | Non-cooperative target three-dimensional reconstruction method based on branch reconstruction registration |
| CN116363427A (en) * | 2023-03-28 | 2023-06-30 | 国网四川省电力公司超高压分公司 | Automatic three-dimensional point cloud classification algorithm |
| CN116452648A (en) * | 2023-06-15 | 2023-07-18 | 武汉科技大学 | Point cloud registration method and system based on normal vector constraint correction |
-
2023
- 2023-09-15 CN CN202311188863.1A patent/CN116934822B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070057942A1 (en) * | 2005-09-13 | 2007-03-15 | Siemens Corporate Research Inc | Method and Apparatus for the Rigid Registration of 3D Ear Impression Shapes with Skeletons |
| CN103236064A (en) * | 2013-05-06 | 2013-08-07 | 东南大学 | Point cloud automatic registration method based on normal vector |
| CN104299260A (en) * | 2014-09-10 | 2015-01-21 | 西南交通大学 | Contact network three-dimensional reconstruction method based on SIFT and LBP point cloud registration |
| US20160162732A1 (en) * | 2014-12-03 | 2016-06-09 | Fuji Xerox Co., Ltd. | Information processing apparatus and non-transitory computer readable medium |
| CN109685841A (en) * | 2019-01-03 | 2019-04-26 | 上海狮迈科技有限公司 | Threedimensional model and the method for registering and system for putting cloud |
| US20220084221A1 (en) * | 2019-02-11 | 2022-03-17 | Siemens Aktiengesellschaft | An apparatus and a method for performing a data driven pairwise registration of three-dimensional point clouds |
| US20200388044A1 (en) * | 2019-06-06 | 2020-12-10 | Zhejiang University | Plant point cloud acquisition, registration and optimization method based on tof camera |
| WO2023045455A1 (en) * | 2021-09-21 | 2023-03-30 | 西北工业大学 | Non-cooperative target three-dimensional reconstruction method based on branch reconstruction registration |
| CN115496784A (en) * | 2022-08-11 | 2022-12-20 | 西安航天时代精密机电有限公司 | Point cloud registration method based on normalized four-dimensional feature vector |
| CN115797418A (en) * | 2022-09-27 | 2023-03-14 | 湖南科技大学 | Complex mechanical part measurement point cloud registration method and system based on improved ICP |
| CN115546025A (en) * | 2022-10-08 | 2022-12-30 | 贵州师范大学 | Method, device and equipment for realizing simulation splicing for object fragments |
| CN116363427A (en) * | 2023-03-28 | 2023-06-30 | 国网四川省电力公司超高压分公司 | Automatic three-dimensional point cloud classification algorithm |
| CN116452648A (en) * | 2023-06-15 | 2023-07-18 | 武汉科技大学 | Point cloud registration method and system based on normal vector constraint correction |
Non-Patent Citations (5)
| Title |
|---|
| BINGWEI HE等: "An automatic registration algorithm for the scattered point clouds based on the curvature feature", 《OPTICS & LASER TECHNOLOGY》, vol. 46, pages 53 - 60 * |
| JACOPO SERAFIN等: "NICP: Dense normal based point cloud registration", 《2015 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS)》, pages 742 - 749 * |
| 汪霞;赵银娣;王坚;: "一种低重叠率激光点云的配准方法", 测绘科学, no. 12, pages 130 - 136 * |
| 石颖: "基于三维点云数据的桥梁空间形态及力学性能分析", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》, pages 034 - 106 * |
| 税午阳;周明全;武仲科;邓擎琼;: "数据配准的颅骨面貌复原方法", 计算机辅助设计与图形学学报, no. 04, pages 607 - 614 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116934822B (en) | 2023-12-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110223348B (en) | Robot scene self-adaptive pose estimation method based on RGB-D camera | |
| CN107301654B (en) | Multi-sensor high-precision instant positioning and mapping method | |
| CN110097093B (en) | Method for accurately matching heterogeneous images | |
| CN110340891B (en) | Mechanical arm positioning and grabbing system and method based on point cloud template matching technology | |
| CN110807809B (en) | Light-weight monocular vision positioning method based on point-line characteristics and depth filter | |
| CN106530347B (en) | Stable high-performance circle feature detection method | |
| CN108597009B (en) | Method for detecting three-dimensional target based on direction angle information | |
| CN109903319B (en) | Multi-resolution-based fast iteration closest point registration algorithm | |
| CN107862735B (en) | RGBD three-dimensional scene reconstruction method based on structural information | |
| CN112233181A (en) | 6D pose recognition method and device and computer storage medium | |
| CN109559346B (en) | Method for positioning and dividing part to be measured in 3D point cloud measurement and scanner | |
| CN108830888B (en) | Coarse matching method based on improved multi-scale covariance matrix characteristic descriptor | |
| CN112396595A (en) | Semantic SLAM method based on point-line characteristics in dynamic environment | |
| CN112652020B (en) | Visual SLAM method based on AdaLAM algorithm | |
| CN115880364A (en) | Robot pose estimation method based on laser point cloud and visual SLAM | |
| CN111739071B (en) | Initial value-based rapid iterative registration method, medium, terminal and device | |
| CN112929626A (en) | Three-dimensional information extraction method based on smartphone image | |
| CN113409332B (en) | Building plane segmentation method based on three-dimensional point cloud | |
| CN113313200B (en) | Point cloud precision matching method based on normal constraint | |
| CN112508885B (en) | Method and system for detecting three-dimensional central axis of bent pipe | |
| CN116468786B (en) | Semantic SLAM method based on point-line combination and oriented to dynamic environment | |
| CN116934822B (en) | System for autonomously registering and converting refined model based on three-dimensional point cloud data | |
| CN117237428A (en) | Data registration method, device and medium for three-dimensional point cloud | |
| CN113592958A (en) | Monocular vision based AUV docking station optical guiding method | |
| CN113688816A (en) | Calculation method of visual odometer for improving ORB feature point extraction |
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 |