CN117710977B - Dam BIM three-dimensional model semantic quick extraction method and system based on point cloud data - Google Patents
Dam BIM three-dimensional model semantic quick extraction method and system based on point cloud data Download PDFInfo
- Publication number
- CN117710977B CN117710977B CN202410146098.5A CN202410146098A CN117710977B CN 117710977 B CN117710977 B CN 117710977B CN 202410146098 A CN202410146098 A CN 202410146098A CN 117710977 B CN117710977 B CN 117710977B
- Authority
- CN
- China
- Prior art keywords
- model
- point cloud
- dimensional
- cloud data
- dam
- 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
- 238000000605 extraction Methods 0.000 title claims abstract description 25
- 239000007787 solid Substances 0.000 claims abstract description 36
- 239000000463 material Substances 0.000 claims abstract description 24
- 238000012549 training Methods 0.000 claims abstract description 16
- 238000013135 deep learning Methods 0.000 claims abstract description 10
- 238000000034 method Methods 0.000 claims description 35
- 238000013500 data storage Methods 0.000 claims description 8
- 230000011218 segmentation Effects 0.000 claims description 7
- 238000002372 labelling Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000013473 artificial intelligence Methods 0.000 claims description 3
- 230000007547 defect Effects 0.000 claims description 3
- 230000008030 elimination Effects 0.000 claims description 3
- 238000003379 elimination reaction Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000005192 partition Methods 0.000 claims description 3
- 238000011144 upstream manufacturing Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims 1
- 238000007726 management method Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001427 coherent effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a dam BIM three-dimensional model semantic quick extraction method and system based on point cloud data, comprising the following steps: scanning dam point cloud data through a scanner; converting the coordinate system of the field scanning point cloud data into a geodetic coordinate system; eliminating noise of the point cloud data, and splicing the point cloud data after noise reduction; converting the point cloud data into a three-dimensional grid model through a Delaunay triangulation algorithm, and optimizing the grid model; converting the grid model into a solid model through MeshLab; deep learning is carried out on RGB information and reflection intensity through a training set, and relevant material properties are imported into a three-dimensional solid model; exporting the entity model into a file format commonly used by BIM; the invention can quickly build the model and endow material information, and has the characteristics of short time consumption and low labor cost.
Description
Technical Field
The invention relates to the technical field of building information modeling, in particular to a dam BIM three-dimensional model semantic quick extraction method and system based on point cloud data.
Background
Building Information Modeling (BIM) is a building design, construction and management method based on digital technology, and can integrate all aspects of information of a building into a unified three-dimensional model to realize collaborative management of the whole life cycle of the building. The BIM three-dimensional model not only comprises geometric information of a building, but also comprises multidimensional information such as functional information, physical information, cost information and the like of the building.
The point cloud data is a data structure composed of a large number of discrete three-dimensional coordinate points, and can accurately record shape and texture information of the surface of an object. The point cloud data is usually collected by a three-dimensional laser scanner or other measuring instruments, and has wide application in the fields of measuring engineering, cultural heritage protection, virtual reality and the like.
The conversion of the point cloud data into the BIM three-dimensional model is a common BIM application scene, and can be used for digitally modeling the existing building so as to perform the works of design transformation, facility management or history protection. However, the conversion of point cloud data into a BIM three-dimensional model is a complex and time-consuming task, which involves multiple steps of preprocessing of point cloud data, surface modeling, model simplification, semantic analysis, and the like, each of which requires specialized knowledge and skills, and a variety of different algorithms and tools exist. Therefore, how to convert the point cloud data into the BIM three-dimensional model is a technical problem to be solved.
The BIM three-dimensional model is a model capable of integrating various information of a building, wherein the model comprises geometric information and material information of the building, and the problem to be solved is that the BIM model can quickly write relevant material properties on the premise of not setting the material properties by combining coherent parameters of point cloud data. In the prior art, the material information is manually imported, different materials are required to be imported in blocks, and the efficiency is low.
Disclosure of Invention
In order to solve the problems in the prior art, the invention aims to provide the dam BIM three-dimensional model semantic quick extraction method and system based on the point cloud data.
In order to achieve the above purpose, the invention adopts the following technical scheme: a dam BIM three-dimensional model semantic quick extraction method based on point cloud data comprises the following steps:
four three-dimensional laser scanners of fixed points are placed on the left bank and the right bank of the upstream and downstream of the dam, and dam point cloud data are scanned through the placed scanners;
Converting a coordinate system of the field scanning point cloud data into a geodetic coordinate system, so that the point cloud data of different coordinate systems can be spliced;
Noise elimination is carried out on the point cloud data, and the point cloud data after noise reduction is spliced to form a complete dam point cloud model;
Importing the obtained dam point cloud model into BIM software, converting the point cloud data into a three-dimensional grid model through a Delaunay triangulation algorithm, and optimizing the grid model to ensure that the error between the grid model and the dam reaches the standard;
converting the grid model into a solid model through MeshLab;
Deep learning is carried out on the obtained three-dimensional solid model according to RGB information and reflection intensity of the point cloud data through a prepared training set so as to realize semantic quick extraction of the three-dimensional model, and relevant material properties are imported into the three-dimensional solid model;
the solid model is exported into the file format commonly used by BIM.
As a further improvement of the invention, the point cloud data obtained by the three-dimensional laser scanner are not the same coordinate system, and the point cloud coordinate system is matched through an ICP algorithm, specifically as follows:
；
Wherein the method comprises the steps of For source cloud collection,/>For the target point cloud set, will/>Transformed into/>, through constructing least square problemWherein/>Representing the weight of each point,/>And/>Is the required rotational moment and translational vector,/>Representative/>And/>Is a dimension of (c).
As a further improvement of the invention, the point cloud data is subjected to surface reconstruction by a Delaunay triangulation algorithm, and is imported into BIM software to generate a three-dimensional grid model, and meanwhile, classification and segmentation are carried out by different building element types.
As a further improvement of the present invention, the method for generating the three-dimensional mesh model specifically includes: given a plane point set P, a triangulation T is found so that the circumscribed circle of any triangle in T does not contain other points in P, such triangulation is called Delaunay triangulation, and for any triangle ABC, the circumscribed circle is centered onAnd radius/>The following equation is satisfied:
；
wherein, Is the center of a circle/>Constructing a super triangle and randomly selecting an unprocessed point to insert the current triangle, and checking whether the circle center/>, of the circumcircle is satisfiedAnd radius/>If not, performing the overturning operation until all the points are processed, and finally forming the three-dimensional triangular grid model.
As a further improvement of the invention, the training set comprises a plurality of materials and related attributes which are verified through experiments, wherein the materials are solid models which are based on the point cloud reflection intensity and RGB information and are processed through Delaunay triangulation and MeshLab software.
As a further improvement of the invention, the grid model is converted into a solid model with RGB information through MeshLab, then a deep learning method is adopted, and semantic segmentation and feature extraction are carried out on the solid model based on the labeling information of the training set; the method comprises the following steps:
Dividing pixel points in an image into different categories according to RGB color characteristics by using an RGB difference method and a KUN clustering device, comparing a solid model with a training set to obtain material properties of different areas of the solid model, and introducing the material properties into the solid model, wherein the RGB difference method comprises the following formula: let the RGB value of a pixel point be (R, G, B), the difference matrix is: Pixels can be classified into the following categories according to the different elements in the difference matrix: if R-G >0 and R-B >0, then the pixel is considered red; if G-R >0 and G-B >0, then the pixel is considered green; if B-R >0 and B-G >0, then the pixel is considered to be blue; if R-G <0 and G-B <0, then the pixel is considered yellow.
As a further development of the invention, the file formats commonly used are IFCs or RVTs.
The invention also provides a dam BIM three-dimensional model semantic quick extraction system based on the point cloud data, which comprises the following steps:
And a data storage module: the data storage device is used for storing data in the memory of the data storage device and storing the data in different files according to different dam partitions;
A data preprocessing module: the method comprises the steps of eliminating noise points in point cloud data and filtering the point cloud;
And the curved surface reconstruction module is used for: the method comprises the steps of performing curved surface reconstruction on dam point cloud data through a Delaunay triangulation algorithm to obtain a three-dimensional grid model;
and the curved surface model optimization module is used for: the method is used for simplifying, optimizing and repairing the three-dimensional grid model according to the appearance of the dam, and eliminating defects of holes, overlapping and self-intersecting in the model;
and a solid model self-building module: the method is used for converting the grid model into a three-dimensional entity model with RGB information;
Artificial intelligence module: the method is used for carrying out semantic segmentation and feature extraction on the entity model based on the labeling information of the training set by a deep learning method;
and an output module: the BIM three-dimensional model is used for outputting the BIM three-dimensional model and storing the BIM three-dimensional model into a file format which is applicable to BIM.
The beneficial effects of the invention are as follows:
The method can quickly establish the model and endow the material information, has the characteristics of short time consumption and low labor cost, and meanwhile, the material information is not in a single form of the BIM model library, and can endow different properties according to the information of the point cloud data.
Drawings
FIG. 1 is a flow chart of a method according to an embodiment of the present invention;
Fig. 2 is a system block diagram of an embodiment of the present invention.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
Examples
As shown in fig. 1, a method for quickly extracting dam BIM three-dimensional model semantics based on point cloud data comprises the following steps:
Placing four three-dimensional laser scanners at fixed points on left and right upstream banks and left and right downstream banks of the dam, and scanning dam point cloud data through the placed scanners;
Converting a coordinate system of the field scanning point cloud data into a geodetic coordinate system, so that the point cloud data of different coordinate systems can be spliced;
Noise elimination is carried out on the point cloud data, the data accuracy is improved, the geometric shape of the point cloud data is more accurate, and the visualization effect of the three-dimensional model is improved;
splicing the noise-reduced point cloud data to form a complete dam point cloud model;
Importing the obtained dam point cloud model into BIM software, converting the point cloud data into a three-dimensional grid model through a Delaunay triangulation algorithm, and optimizing the grid model to ensure that the error between the grid model and the dam reaches the standard;
Converting the grid model into a solid model through MeshLab, so that the obtained three-dimensional model is more consistent with the dam;
Deep learning is carried out on the obtained three-dimensional solid model according to RGB information and reflection intensity of the point cloud data through a prepared training set so as to realize semantic quick extraction of the three-dimensional model, and relevant material properties are imported into the three-dimensional solid model;
The solid model is exported into a file format commonly used by BIM, such as IFC, RVT, etc.
Four three-dimensional laser scanners adopt fixed point sampling, in order to guarantee the stability and the security of the instrument placed outdoors for a long time, an independent placement device is arranged on the instrument.
The point cloud data obtained by the three-dimensional laser scanner are not the same coordinate system, and the point cloud coordinate system is matched through an ICP algorithm.
The formula of ICP algorithm isWhereinFor source cloud collection,/>For the target point cloud set, will/>Transformed into/>, through constructing least square problemWherein/>Representing the weight of each point,/>And/>Is the required rotational moment and translational vector,/>Representative/>And/>Is usually taken/>, in a three-dimensional point cloud。
And carrying out surface reconstruction on the point cloud data through a Delaunay triangulation algorithm, importing the point cloud data into BIM software to generate a three-dimensional grid model, and classifying and dividing the point cloud data through different building element types.
Given a plane point set P, a triangulation T is found so that the circumscribed circle of any triangle in T does not contain other points in P, such triangulation is called Delaunay triangulation, and for any triangle ABC, the circumscribed circle is centered onAnd radius/>The following equation is satisfied:
；
wherein, Is the center of a circle/>Constructing a super triangle and randomly selecting an unprocessed point to insert the current triangle, and checking whether the circle center/>, of the circumcircle is satisfiedAnd radius/>If not, performing the overturning operation until all the points are processed, and finally forming the three-dimensional triangular grid model.
The training set comprises a plurality of materials and related attributes which are verified through experiments, wherein the materials are solid models which are based on the point cloud reflection intensity and RGB information and are processed through Delaunay triangulation and MeshLab software.
Converting the grid model into a solid model with RGB information through MeshLab, and then adopting a deep learning method to perform semantic segmentation and feature extraction on the solid model based on the labeling information of the training set. The principle is that an RGB difference method and a KUN clustering device are used for classifying pixel points in an image into different categories according to RGB color characteristics, a solid model is compared with a training set to obtain material properties of different areas of the solid model, and the material properties are imported into the solid model, wherein the RGB difference method formula is as follows: let the RGB value of a pixel point be (R, G, B), the difference matrix is: Pixels can be classified into the following categories according to the different elements in the difference matrix: if R-G >0 and R-B >0, then the pixel is considered red; if G-R >0 and G-B >0, then the pixel is considered green; if B-R >0 and B-G >0, then the pixel is considered to be blue; if R-G <0 and G-B <0, then the pixel is considered yellow.
As shown in fig. 2, this embodiment further provides a rapid extraction system for dam BIM three-dimensional model semantics based on point cloud data, including:
and a data storage module: for storing data in the memory of the data storage device and in different files according to the different dam partitions.
A data preprocessing module: the method is used for eliminating noise in the point cloud data and filtering the point cloud to improve the practicability of the obtained point cloud data.
And the curved surface reconstruction module is used for: and the method is used for reconstructing the curved surface of the dam point cloud data through a Delaunay triangulation algorithm to obtain a three-dimensional grid model.
And the curved surface model optimization module is used for: the method is used for simplifying, optimizing and repairing the three-dimensional grid model according to the appearance of the dam, and eliminating defects such as holes, overlapping, self-intersecting and the like in the model.
And a solid model self-building module: the method is used for converting the grid model into a three-dimensional solid model with RGB information.
Artificial intelligence module: the method is used for carrying out semantic segmentation and feature extraction on the entity model based on the labeling information of the training set through a deep learning method.
And an output module: for outputting the BIM three-dimensional model and saving it in a file format suitable for BIM use, such as IFC, RVT, etc.
The foregoing examples merely illustrate specific embodiments of the invention, which are described in greater detail and are not to be construed as limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention.
Claims (8)
1. A dam BIM three-dimensional model semantic quick extraction method based on point cloud data is characterized by comprising the following steps:
four three-dimensional laser scanners of fixed points are placed on the left bank and the right bank of the upstream and downstream of the dam, and dam point cloud data are scanned through the placed scanners;
Converting a coordinate system of the field scanning point cloud data into a geodetic coordinate system, so that the point cloud data of different coordinate systems can be spliced;
Noise elimination is carried out on the point cloud data, and the point cloud data after noise reduction is spliced to form a complete dam point cloud model;
Importing the obtained dam point cloud model into BIM software, converting the point cloud data into a three-dimensional grid model through a Delaunay triangulation algorithm, and carrying out optimization treatment on the three-dimensional grid model so that the error between the three-dimensional grid model and the dam reaches the standard;
Converting the three-dimensional grid model into a three-dimensional entity model through MeshLab;
Deep learning is carried out on the obtained three-dimensional solid model according to RGB information and reflection intensity of the point cloud data through a prepared training set so as to realize semantic quick extraction of the three-dimensional solid model, and relevant material properties are imported into the three-dimensional solid model;
the three-dimensional solid model is exported into a file format commonly used by BIM.
2. The rapid extraction method of dam BIM three-dimensional model semantics based on point cloud data according to claim 1, wherein the point cloud data obtained by the three-dimensional laser scanner is not the same coordinate system, and the point cloud coordinate system is matched by an ICP algorithm, specifically comprising the following steps:
Where p= { P 1,p2,...,pn } is the source cloud set, q= { Q 1,q2,...qn } is the target cloud set, and Q is transformed into P through the constructed least squares problem, where w i represents the weight of each point, R and t are the required rotational moment and translational vector, and d represents the dimensions of x and y.
3. The rapid extraction method of dam BIM three-dimensional model semantics based on point cloud data according to claim 1, wherein the point cloud data is subjected to surface reconstruction by a Delaunay triangulation algorithm, imported into BIM software to generate a three-dimensional grid model, and classified and segmented by different building component types.
4. The rapid extraction method of dam BIM three-dimensional model semantics based on point cloud data as claimed in claim 3, wherein the generation method of the three-dimensional grid model is specifically as follows: given a set of planar points P, a triangulation T is found such that the circumscribed circle of any triangle in T does not contain other points in P, such triangulation is known as Delaunay triangulation, and for any triangle ABC, its circumscribed circle center O and radius R satisfy the following equation:
Wherein (x 0,y0) is the coordinate of the circle center O, constructing a super triangle, randomly selecting an unprocessed point to insert the current triangle, checking whether the equation of the circle center O and the radius R of the circumscribed circle is satisfied, if not, performing the overturning operation until all the points are processed, and finally forming the three-dimensional triangular grid model.
5. The rapid extraction method of dam BIM three-dimensional model semantics based on point cloud data according to claim 1, wherein the training set comprises a plurality of materials and related attributes through experimental verification, wherein the materials are solid models which are based on point cloud reflection intensity and RGB information and processed through Delaunay triangulation and MeshLab software.
6. The rapid extraction method of dam BIM three-dimensional model semantics based on point cloud data according to claim 1, which is characterized in that a grid model is converted into a solid model with RGB information through MeshLab, then a deep learning method is adopted, and semantic segmentation and feature extraction are carried out on the solid model based on the labeling information of a training set; the method comprises the following steps:
Dividing pixel points in an image into different categories according to RGB color characteristics by using an RGB difference method and a KNN clustering device, comparing a solid model with a training set to obtain material properties of different areas of the solid model, and introducing the material properties into the solid model, wherein the RGB difference method comprises the following formula: let the RGB value of a pixel point be (R, G, B), the difference matrix is: Pixels can be classified into the following categories according to the different elements in the difference matrix: if R-G >0 and R-B >0, then the pixel is considered red; if G-R >0 and G-B >0, then the pixel is considered green; if B-R >0 and B-G >0, then the pixel is considered to be blue; if R-G <0 and G-B <0, then the pixel is considered yellow.
7. The rapid extraction method of dam BIM three-dimensional model semantics based on point cloud data according to claim 1, wherein the commonly used file format is IFC or RVT.
8. A dam BIM three-dimensional model semantic quick extraction system based on point cloud data is characterized by comprising the following steps:
And a data storage module: the data storage device is used for storing data in the memory of the data storage device and storing the data in different files according to different dam partitions;
A data preprocessing module: the method comprises the steps of eliminating noise points in point cloud data and filtering the point cloud;
And the curved surface reconstruction module is used for: the method comprises the steps of performing curved surface reconstruction on dam point cloud data through a Delaunay triangulation algorithm to obtain a three-dimensional grid model;
and the curved surface model optimization module is used for: the method is used for simplifying, optimizing and repairing the three-dimensional grid model according to the appearance of the dam, and eliminating defects of holes, overlapping and self-intersecting in the model;
And a solid model self-building module: the three-dimensional grid model is used for converting the three-dimensional grid model into a three-dimensional entity model with RGB information;
Artificial intelligence module: the method is used for carrying out semantic segmentation and feature extraction on the three-dimensional entity model based on the labeling information of the training set by a deep learning method;
And an output module: the method is used for outputting the BIM three-dimensional entity model and storing the BIM three-dimensional entity model into a file format which is applicable to BIM.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410146098.5A CN117710977B (en) | 2024-02-02 | 2024-02-02 | Dam BIM three-dimensional model semantic quick extraction method and system based on point cloud data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410146098.5A CN117710977B (en) | 2024-02-02 | 2024-02-02 | Dam BIM three-dimensional model semantic quick extraction method and system based on point cloud data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117710977A CN117710977A (en) | 2024-03-15 |
| CN117710977B true CN117710977B (en) | 2024-04-26 |
Family
ID=90162713
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410146098.5A Active CN117710977B (en) | 2024-02-02 | 2024-02-02 | Dam BIM three-dimensional model semantic quick extraction method and system based on point cloud data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117710977B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110807571A (en) * | 2019-09-19 | 2020-02-18 | 同济大学 | Building engineering quality control system based on combination of 3d laser sensing and BIM |
| JP2021156016A (en) * | 2020-03-27 | 2021-10-07 | 株式会社フジタ | Construction work supporting system and construction work supporting method |
| CN113487721A (en) * | 2021-06-18 | 2021-10-08 | 浙江大学 | Automatic prefabricated part identification method based on three-dimensional point cloud |
| CN113868733A (en) * | 2021-09-01 | 2021-12-31 | 浙江大学 | Automatic existing structure BIM model generation method based on three-dimensional point cloud |
| WO2022088676A1 (en) * | 2020-10-29 | 2022-05-05 | 平安科技（深圳）有限公司 | Three-dimensional point cloud semantic segmentation method and apparatus, and device and medium |
| CN115294294A (en) * | 2022-10-10 | 2022-11-04 | 中国电建集团山东电力建设第一工程有限公司 | Pipeline BIM (building information modeling) model reconstruction method and system based on depth image and point cloud |
| WO2022263860A1 (en) * | 2021-06-18 | 2022-12-22 | Pointfuse Limited | Pointcloud processing, especially for use with building intelligence modelling (bim) |
| EP4174792A1 (en) * | 2021-10-29 | 2023-05-03 | Geosat | Method for scene understanding and semantic analysis of objects |
| CN116258835A (en) * | 2023-05-04 | 2023-06-13 | 武汉大学 | Point cloud data three-dimensional reconstruction method and system based on deep learning |
| CN116385680A (en) * | 2023-03-30 | 2023-07-04 | 宁波市水利水电规划设计研究院有限公司 | Three-dimensional immersive dam safety monitoring method and system based on UE technology |
| KR102561303B1 (en) * | 2023-02-21 | 2023-07-28 | (주)원빔그룹 | Method, device and system for providing construction management solution through linkage between architectural design bim data and construction schedule |
| CN116975956A (en) * | 2023-06-16 | 2023-10-31 | 同济大学 | Automatic completion BIM model generation method considering deviation and deformation correction |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9070216B2 (en) * | 2011-12-14 | 2015-06-30 | The Board Of Trustees Of The University Of Illinois | Four-dimensional augmented reality models for interactive visualization and automated construction progress monitoring |
| US20190026400A1 (en) * | 2017-07-18 | 2019-01-24 | Fuscoe Engineering, Inc. | Three-dimensional modeling from point cloud data migration |
-
2024
- 2024-02-02 CN CN202410146098.5A patent/CN117710977B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110807571A (en) * | 2019-09-19 | 2020-02-18 | 同济大学 | Building engineering quality control system based on combination of 3d laser sensing and BIM |
| JP2021156016A (en) * | 2020-03-27 | 2021-10-07 | 株式会社フジタ | Construction work supporting system and construction work supporting method |
| WO2022088676A1 (en) * | 2020-10-29 | 2022-05-05 | 平安科技（深圳）有限公司 | Three-dimensional point cloud semantic segmentation method and apparatus, and device and medium |
| CN113487721A (en) * | 2021-06-18 | 2021-10-08 | 浙江大学 | Automatic prefabricated part identification method based on three-dimensional point cloud |
| WO2022263860A1 (en) * | 2021-06-18 | 2022-12-22 | Pointfuse Limited | Pointcloud processing, especially for use with building intelligence modelling (bim) |
| CN113868733A (en) * | 2021-09-01 | 2021-12-31 | 浙江大学 | Automatic existing structure BIM model generation method based on three-dimensional point cloud |
| EP4174792A1 (en) * | 2021-10-29 | 2023-05-03 | Geosat | Method for scene understanding and semantic analysis of objects |
| CN115294294A (en) * | 2022-10-10 | 2022-11-04 | 中国电建集团山东电力建设第一工程有限公司 | Pipeline BIM (building information modeling) model reconstruction method and system based on depth image and point cloud |
| KR102561303B1 (en) * | 2023-02-21 | 2023-07-28 | (주)원빔그룹 | Method, device and system for providing construction management solution through linkage between architectural design bim data and construction schedule |
| CN116385680A (en) * | 2023-03-30 | 2023-07-04 | 宁波市水利水电规划设计研究院有限公司 | Three-dimensional immersive dam safety monitoring method and system based on UE technology |
| CN116258835A (en) * | 2023-05-04 | 2023-06-13 | 武汉大学 | Point cloud data three-dimensional reconstruction method and system based on deep learning |
| CN116975956A (en) * | 2023-06-16 | 2023-10-31 | 同济大学 | Automatic completion BIM model generation method considering deviation and deformation correction |
Non-Patent Citations (2)
| Title |
|---|
| BIM技术在公路隧道正向设计中的应用研究;曹建涛;《中国优秀硕士学位论文全文数据库 工程科技II辑》;20200115;C034-719 * |
| Semi-automated visualization method for visual inspection of buildings on BIM using 3D point cloud;Moonyoung Choi等;《Journal of Building Engeering》;20240131;第81卷;正文1-16 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117710977A (en) | 2024-03-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Boulch | ConvPoint: Continuous convolutions for point cloud processing | |
| Pintus et al. | A survey of geometric analysis in cultural heritage | |
| Zheng et al. | Non-local scan consolidation for 3D urban scenes | |
| Malinverni et al. | Deep learning for semantic segmentation of 3D point cloud | |
| CN111008422B (en) | Building live-action map making method and system | |
| CN111932671A (en) | Three-dimensional solid model reconstruction method based on dense point cloud data | |
| US20140192050A1 (en) | Three-dimensional point processing and model generation | |
| US20050093875A1 (en) | Synthesis of progressively-variant textures and application to arbitrary surfaces | |
| Rieck et al. | Multivariate data analysis using persistence-based filtering and topological signatures | |
| Biasotti et al. | SHREC'18 track: Recognition of geometric patterns over 3D models | |
| CN111784840B (en) | LOD (line-of-sight) level three-dimensional data singulation method and system based on vector data automatic segmentation | |
| Yu et al. | Artificial intelligence for Dunhuang cultural heritage protection: the project and the dataset | |
| Jiang et al. | Local and global structure for urban ALS point cloud semantic segmentation with ground-aware attention | |
| Shah et al. | Simulated annealing-based fitting of CAD models to point clouds of mechanical parts’ assemblies | |
| Wang et al. | Object verification based on deep learning point feature comparison for scan-to-BIM | |
| US20220391553A1 (en) | Building information modeling systems and methods | |
| Hu et al. | Geometric feature enhanced line segment extraction from large-scale point clouds with hierarchical topological optimization | |
| CN115797568A (en) | Modeling method and device based on three-dimensional GIS and BIM integration | |
| CN117710977B (en) | Dam BIM three-dimensional model semantic quick extraction method and system based on point cloud data | |
| Pellis et al. | Assembling an image and point cloud dataset for heritage building semantic segmentation | |
| CN110096484A (en) | A kind of 3D model batch deriving method based on Revit | |
| Zhao et al. | A 3D modeling method for buildings based on LiDAR point cloud and DLG | |
| Liu et al. | Research on building data acquisition methods in smart city | |
| Dai et al. | MDC-Net: A multi-directional constrained and prior assisted neural network for wood and leaf separation from terrestrial laser scanning | |
| Shah et al. | User-driven computer-assisted reverse engineering of editable CAD assembly models |
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 |