WO2024139419A1 - Three-dimensional computer vision-based system and method for modeling complex and irregular building component - Google Patents
Three-dimensional computer vision-based system and method for modeling complex and irregular building component Download PDFInfo
- Publication number
- WO2024139419A1 WO2024139419A1 PCT/CN2023/118691 CN2023118691W WO2024139419A1 WO 2024139419 A1 WO2024139419 A1 WO 2024139419A1 CN 2023118691 W CN2023118691 W CN 2023118691W WO 2024139419 A1 WO2024139419 A1 WO 2024139419A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- mesh
- point cloud
- complex
- cloud data
- special
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 230000001788 irregular Effects 0.000 title claims abstract description 9
- 239000013598 vector Substances 0.000 claims abstract description 20
- 238000007781 pre-processing Methods 0.000 claims abstract description 14
- 239000007787 solid Substances 0.000 claims description 20
- 230000008439 repair process Effects 0.000 claims description 14
- 238000006243 chemical reaction Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 238000005520 cutting process Methods 0.000 claims description 4
- 238000007711 solidification Methods 0.000 claims description 4
- 230000008023 solidification Effects 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 238000009877 rendering Methods 0.000 description 4
- 101001121408 Homo sapiens L-amino-acid oxidase Proteins 0.000 description 2
- 102100026388 L-amino-acid oxidase Human genes 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
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
- G06T17/10—Constructive solid geometry [CSG] using solid primitives, e.g. cylinders, cubes
-
- 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
- G06T17/20—Finite element generation, e.g. wire-frame surface description, tesselation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Definitions
- BIM In the actual lightweight process, BIM also needs to go through a two-stage processing process: 3) geometric optimization conversion of the model by reducing primitives through triangular facets and similarity algorithms; 4) using octrees to quickly remove invisible primitives, reduce the number of drawing objects entering the rendering area, and use multiple levels of detail (LOD) to accelerate the rendering speed of single primitives for rendering processing.
- LOD levels of detail
- a complex special-shaped building component modeling system based on three-dimensional computer vision comprising:
- Point cloud data processing unit including:
- Point cloud data input module used to input point cloud data obtained by 3D laser scanning of complex and special-shaped building components
- a point cloud data preprocessing module performs filtering, denoising, and repair preprocessing on the point cloud data acquired by the point cloud data input module;
- Surface mesh generation unit including:
- a mesh conversion entity module is used to convert the four-sided surface mesh reconstructed by the four-sided surface mesh reconstruction module into a non-uniform rational B-spline to generate a solid model of a complex and special-shaped building component with multiple curved surfaces;
- the complex special-shaped building component modeling system and method based on three-dimensional computer vision provided by the present invention can derive entity models of different levels according to the requirements of the use environment, and can derive entity models with high level of accuracy. Models can also be exported with low-precision lightweight solid models, which are suitable for various application environments, suitable for different degrees of BIM lightweight design and finite element analysis of complex special-shaped components with different requirements, and have the advantage of a wide range of applications.
- FIG. 2 is a flow chart of a method for modeling complex special-shaped building components based on three-dimensional computer vision.
- the entity model hierarchical export unit is used to intelligently classify and export the entity model of the complex special-shaped building component generated by the grid conversion entity module according to the data accuracy level.
- Step 105 cutting the triangular mesh
- the complex special-shaped building component modeling system and method are based on 3D computer vision technology, eliminating the tedious work of traditional manual processing of point cloud data, repairing meshes, and reducing the volume of BIM models, saving modeling time and improving the modeling efficiency of complex special-shaped building components.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Geometry (AREA)
- Computer Graphics (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Processing Or Creating Images (AREA)
Abstract
A three-dimensional computer vision-based system and method for modeling a complex and irregular building component. The method comprises: obtaining point cloud data of a complex and irregular building component by means of scanning; preprocessing the obtained point cloud data; calculating a normal vector of the preprocessed point cloud data; according to a Poisson surface reconstruction algorithm, generating a triangular patch mesh by means of the point cloud data having the normal vector; cropping the triangular patch mesh; repairing the cropped triangular patch mesh to generate a closed triangular patch mesh; reconstructing the closed triangular patch mesh to generate a quadrilateral mesh; converting the reconstructed quadrilateral mesh into non-uniform rational B-splines to generate entity models of multi-curved surfaces; and intelligently classifying and exporting entity models of the complex and irregular building component according to data precision levels. The modeling efficiency of the complex and irregular building component can be increased, entity models of different precision levels can be intelligently classified and exported, and the requirements of lightweightness are met.
Description
本发明涉及建筑工程技术领域，特别涉及一种基于三维计算机视觉的复杂异形建筑构件建模系统及方法。The present invention relates to the technical field of building engineering, and in particular to a complex and special-shaped building component modeling system and method based on three-dimensional computer vision.
在建筑领域中，无论是造型灵动复杂的现代建筑，还是优美复古的历史文化建筑，都存在许多极具特色的复杂异形建筑构件。由于复杂异形建筑构件是一种非规则构件，其形状奇特、具有表面花纹等。为了重建复杂异形建筑构件的实体模型，需要进行建筑信息模型(Building Information Modeling，BIM)设计和结构性能的质量检验。现阶段，常采用传统逆向建模的方法生成复杂异形建筑构件的BIM和有限元分析模型：1)按照设计图纸逆向建模；2)利用三维激光扫描的手段，借助多种逆向工程专业软件协作建模。虽然上述方法重建的实体模型精度较高，但过程繁琐复杂，耗时较大，且模型的存储大小也过大。同时，不同用途的复杂异形建筑构件的实体模型，其精度和存储大小的要求也不尽相同。例如，复杂异形建筑构件的表面花纹和不必要的圆角等对其有限元分析结果基本没有影响，反而增加了有限元分析的时间；为了使模型更加适宜万维网、移动网，常对BIM进行轻量化设计，缩小BIM的体量。且在实际轻量化过程中，BIM还需要经历了两阶段处理过程：3)通过三角面片、相似性算法减少图元等方式对模型进行几何优化转换；4)使用八叉树快速剔除不可见图元，减少进入渲染区域的绘制对象和使用多重细节层次(Levels of Detail，LOD)，加速单图元渲染速度进行渲染处理。但是几何优化转换、渲染处理是BIM轻量化的核心技术，具有一定的技术门槛，要求开发者需要掌握一定的图形技术，且过程繁琐，耗费时间。因此，如何提高复杂异形建筑构件的建模效率成为本领域亟需解决的技术问题。
In the field of architecture, whether it is a modern building with a flexible and complex shape or a beautiful and retro historical and cultural building, there are many unique and complex special-shaped building components. Since complex special-shaped building components are irregular components, they have strange shapes and surface patterns. In order to reconstruct the solid model of complex special-shaped building components, it is necessary to carry out building information modeling (BIM) design and quality inspection of structural performance. At present, the traditional reverse modeling method is often used to generate BIM and finite element analysis models of complex special-shaped building components: 1) reverse modeling according to the design drawings; 2) using three-dimensional laser scanning to collaboratively model with the help of a variety of reverse engineering professional software. Although the solid model reconstructed by the above method has high accuracy, the process is cumbersome and time-consuming, and the storage size of the model is too large. At the same time, the requirements for the accuracy and storage size of the solid models of complex special-shaped building components for different purposes are also different. For example, the surface patterns and unnecessary rounded corners of complex and special-shaped building components have little effect on their finite element analysis results, but increase the time of finite element analysis; in order to make the model more suitable for the World Wide Web and mobile networks, BIM is often designed to be lightweight and reduce the volume of BIM. In the actual lightweight process, BIM also needs to go through a two-stage processing process: 3) geometric optimization conversion of the model by reducing primitives through triangular facets and similarity algorithms; 4) using octrees to quickly remove invisible primitives, reduce the number of drawing objects entering the rendering area, and use multiple levels of detail (LOD) to accelerate the rendering speed of single primitives for rendering processing. However, geometric optimization conversion and rendering processing are the core technologies of BIM lightweighting, which have certain technical thresholds and require developers to master certain graphics technologies. The process is cumbersome and time-consuming. Therefore, how to improve the modeling efficiency of complex and special-shaped building components has become a technical problem that needs to be solved in this field.
发明内容Summary of the invention
本发明的目的是，提供一种基于三维计算机视觉的复杂异形建筑构件建模系统及方法，以解决建模效率低的问题。The purpose of the present invention is to provide a system and method for modeling complex special-shaped building components based on three-dimensional computer vision to solve the problem of low modeling efficiency.
为了解决上述技术问题，本发明提供的技术方案是：一种基于三维计算机视觉的复杂异形建筑构件建模系统，包括：In order to solve the above technical problems, the present invention provides a technical solution: a complex special-shaped building component modeling system based on three-dimensional computer vision, comprising:
点云数据处理单元，包括：Point cloud data processing unit, including:
点云数据输入模块，用于输入通过三维激光扫描复杂异形建筑构件获取的点云数据；Point cloud data input module, used to input point cloud data obtained by 3D laser scanning of complex and special-shaped building components;
点云数据预处理模块，对所述点云数据输入模块获取的点云数据进行滤波、去噪、修补预处理；A point cloud data preprocessing module performs filtering, denoising, and repair preprocessing on the point cloud data acquired by the point cloud data input module;
面片网格生成单元，包括：Surface mesh generation unit, including:
点云法向量计算模块，用于计算所述点云数据预处理模块预处理后的点云数据的法向量；A point cloud normal vector calculation module, used to calculate the normal vector of the point cloud data preprocessed by the point cloud data preprocessing module;
泊松表面重建模块，用于根据所述点云法向量计算模块得到的法向量点云数据生成三角面片网格；A Poisson surface reconstruction module, used to generate a triangular patch mesh according to the normal vector point cloud data obtained by the point cloud normal vector calculation module;
网格裁剪模块，用于将所述泊松表面重建模块生成的三角面片网格进行裁剪；A mesh clipping module, used for clipping the triangular face mesh generated by the Poisson surface reconstruction module;
网格实体化单元，包括：Mesh solidification units, including:
网格修补模块，用于将所述网格裁剪模块裁剪后的三角面片网格进行修补生成闭合的三角面片网格；A mesh repair module, used for repairing the triangular face mesh cut by the mesh cutting module to generate a closed triangular face mesh;
四边面网格重建模块，用于对所述网格修补模块生成的闭合三角面片网格进行重建生成四边面网格；A four-sided mesh reconstruction module, used to reconstruct the closed triangular patch mesh generated by the mesh repair module to generate a four-sided mesh;
网格转换实体模块，用于将所述四边面网格重建模块重建的四边面网格转换成非均匀有理B样条，生成多重曲面的复杂异形建筑构件的实体模型；A mesh conversion entity module is used to convert the four-sided surface mesh reconstructed by the four-sided surface mesh reconstruction module into a non-uniform rational B-spline to generate a solid model of a complex and special-shaped building component with multiple curved surfaces;
实体模型分级导出单元，用于将所述网格转换实体模块生成的复杂异形建筑构件的实体模型按数据精度等级智能分类导出。The entity model hierarchical export unit is used to intelligently classify and export the entity model of the complex special-shaped building component generated by the grid conversion entity module according to the data accuracy level.
为了解决上述技术问题，本发明提供的另一种技术方案是：一种基于三维计算机视觉的复杂异形建筑构件建模方法，
In order to solve the above technical problems, another technical solution provided by the present invention is: a modeling method of complex special-shaped building components based on three-dimensional computer vision,
通过三维激光对复杂异形建筑构件进行扫描，获取复杂异形建筑构件的点云数据；Scan complex and special-shaped building components through 3D laser to obtain point cloud data of complex and special-shaped building components;
对获取的点云数据进行预处理；Preprocess the acquired point cloud data;
计算预处理后的点云数据的法向量；Calculate the normal vector of the preprocessed point cloud data;
根据三维计算机视觉的泊松表面重建算法通过带有法向量的点云数据生成三角面片网格；Generate a triangular patch mesh from point cloud data with normal vectors according to the Poisson surface reconstruction algorithm of three-dimensional computer vision;
对三角面片网格进行裁剪；Clip the triangular patch mesh;
将裁剪后的三角面片网格进行修补，生成闭合的三角面片网格；Repair the cropped triangular patch mesh to generate a closed triangular patch mesh;
对闭合的三角面片网格进行重建，生成四边面网格；Reconstruct the closed triangular face mesh to generate a quadrilateral mesh;
将重建的四边面网格转换成非均匀有理B样条，生成复杂异形建筑构件的多重曲面的复杂异形建筑构件的实体模型；The reconstructed quadrilateral mesh is converted into non-uniform rational B-splines to generate a solid model of a complex and irregular building component with multiple curved surfaces;
将复杂异形建筑构件的实体模型按数据精度等级智能分类导出。The solid models of complex and special-shaped building components are intelligently classified and exported according to the data accuracy level.
进一步地，本发明提供的基于三维计算机视觉的复杂异形建筑构件建模方法，对获取的点云数据进行预处理的方法的步骤包括：对获取的点云数据进行滤波、去噪和修补。Furthermore, in the method for modeling complex and special-shaped building components based on three-dimensional computer vision provided by the present invention, the steps of preprocessing the acquired point cloud data include: filtering, denoising and repairing the acquired point cloud data.
进一步地，本发明提供的基于三维计算机视觉的复杂异形建筑构件建模方法，按数据精度由高到低的顺序对复杂异形建筑构件的实体模型的等级进行智能分类。Furthermore, the complex and special-shaped building component modeling method based on three-dimensional computer vision provided by the present invention intelligently classifies the levels of the entity models of the complex and special-shaped building components in order of data accuracy from high to low.
与现有技术相比，本发明的有益效果如下：Compared with the prior art, the present invention has the following beneficial effects:
本发明提供的基于三维计算机视觉的复杂异形建筑构件建模系统及方法，基于三维计算机视觉技术，利用三维激光扫描获取复杂异形建筑构件的点云数据，对获取的点云数据进行预处理、生成三角面片网格、修补三角面片网格、重建四边面网格，将重建的四边面网格转化为多重曲面的复杂异形建筑构件的实体模型，然后将复杂异形建筑构件的实体模型按数据精度等级智能分类导出。该复杂异形建筑构件建模系统及方法基于三维计算机视觉技术，省去了传统人工处理点云数据、修补网格和缩小BIM模型体量等的繁琐工作，节约了建模时间，提高了复杂异形建筑构件的建模效率。The complex and special-shaped building component modeling system and method based on three-dimensional computer vision provided by the present invention, based on three-dimensional computer vision technology, uses three-dimensional laser scanning to obtain point cloud data of complex and special-shaped building components, pre-processes the obtained point cloud data, generates triangular face meshes, repairs triangular face meshes, reconstructs quadrilateral meshes, converts the reconstructed quadrilateral meshes into a solid model of a complex and special-shaped building component with multiple curved surfaces, and then intelligently classifies and exports the solid model of the complex and special-shaped building component according to the data accuracy level. The complex and special-shaped building component modeling system and method are based on three-dimensional computer vision technology, eliminating the tedious work of traditional manual processing of point cloud data, repairing meshes, and reducing the volume of BIM models, saving modeling time and improving the modeling efficiency of complex and special-shaped building components.
本发明提供的基于三维计算机视觉的复杂异形建筑构件建模系统及方法，能够根据使用环境需求导出不同等级的实体模型，可以导出等级精度高的实体
模型，也可以导出等级精度低的轻量化实体模型，适用于各种应用环境，适用于不同程度的BIM轻量化设计和不同要求的复杂异形构件的有限元分析，具有适用范围广泛的优点。The complex special-shaped building component modeling system and method based on three-dimensional computer vision provided by the present invention can derive entity models of different levels according to the requirements of the use environment, and can derive entity models with high level of accuracy. Models can also be exported with low-precision lightweight solid models, which are suitable for various application environments, suitable for different degrees of BIM lightweight design and finite element analysis of complex special-shaped components with different requirements, and have the advantage of a wide range of applications.
图1是基于三维计算机视觉的复杂异形建筑构件建模系统的结构组成关系图；FIG1 is a structural composition relationship diagram of a complex special-shaped building component modeling system based on three-dimensional computer vision;
图2是基于三维计算机视觉的复杂异形建筑构件建模方法的流程图。FIG. 2 is a flow chart of a method for modeling complex special-shaped building components based on three-dimensional computer vision.
下面结合附图对本发明作详细描述：根据下面说明，本发明的优点和特征将更清楚。需说明的是，附图均采用非常简化的形式且均使用非精准的比例，仅用以方便、明晰地辅助说明本发明实施例的目的。The present invention is described in detail below in conjunction with the accompanying drawings: The advantages and features of the present invention will become more apparent from the following description. It should be noted that the accompanying drawings are in very simplified form and in non-precise proportions, and are only used to conveniently and clearly assist in explaining the purpose of the embodiments of the present invention.
请参考图1，本发明实施例提供基于三维计算机视觉的复杂异形建筑构件建模系统，包括点云数据处理单元、面片网格生成单元、网格实体化单元和实体模型分级导出单元，其中：Please refer to FIG1 , an embodiment of the present invention provides a complex and irregular building component modeling system based on three-dimensional computer vision, including a point cloud data processing unit, a patch mesh generation unit, a mesh solidification unit and a solid model hierarchical export unit, wherein:
点云数据处理单元，包括：Point cloud data processing unit, including:
点云数据输入模块，用于输入通过三维激光扫描复杂异形建筑构件获取的点云数据。The point cloud data input module is used to input point cloud data obtained by 3D laser scanning of complex and special-shaped building components.
点云数据预处理模块，对所述点云数据输入模块获取的点云数据进行滤波、去噪、修补预处理。The point cloud data preprocessing module performs filtering, denoising and repair preprocessing on the point cloud data acquired by the point cloud data input module.
面片网格生成单元，包括：Surface mesh generation unit, including:
点云法向量计算模块，用于计算所述点云数据预处理模块预处理后的点云数据的法向量。The point cloud normal vector calculation module is used to calculate the normal vector of the point cloud data preprocessed by the point cloud data preprocessing module.
泊松表面重建模块，用于根据所述点云法向量计算模块得到的法向量点云数据生成三角面片网格。The Poisson surface reconstruction module is used to generate a triangular patch mesh according to the normal vector point cloud data obtained by the point cloud normal vector calculation module.
网格裁剪模块，用于将所述泊松表面重建模块生成的三角面片网格进行裁剪。The mesh clipping module is used to clip the triangular face mesh generated by the Poisson surface reconstruction module.
网格实体化单元，包括：
Mesh solidification units, including:
网格修补模块，用于将所述网格裁剪模块裁剪后的三角面片网格进行修补生成闭合的三角面片网格。The mesh repair module is used to repair the triangular patch mesh cut by the mesh cutting module to generate a closed triangular patch mesh.
四边面网格重建模块，用于对所述网格修补模块生成的闭合三角面片网格进行重建生成四边面网格。The four-sided surface mesh reconstruction module is used to reconstruct the closed triangular surface mesh generated by the mesh repair module to generate a four-sided surface mesh.
网格转换实体模块，用于将所述四边面网格重建模块重建的四边面网格转换成Nurbs(非均匀有理B样条)，生成多重曲面的复杂异形建筑构件的实体模型。The mesh conversion entity module is used to convert the quadrilateral mesh reconstructed by the quadrilateral mesh reconstruction module into Nurbs (non-uniform rational B-spline) to generate a solid model of a complex and special-shaped building component with multiple curved surfaces.
实体模型分级导出单元，用于将所述网格转换实体模块生成的复杂异形建筑构件的实体模型按数据精度等级智能分类导出。The entity model hierarchical export unit is used to intelligently classify and export the entity model of the complex special-shaped building component generated by the grid conversion entity module according to the data accuracy level.
请参考图2，本发明实施例还提供一种基于三维计算机视觉的复杂异形建筑构件建模方法，可以包括以下步骤：Referring to FIG. 2 , an embodiment of the present invention further provides a method for modeling a complex and irregularly shaped building component based on three-dimensional computer vision, which may include the following steps:
步骤101，通过三维激光对复杂异形建筑构件进行扫描，获取复杂异形建筑构件的点云数据。Step 101, scanning the complex and special-shaped building components by three-dimensional laser to obtain point cloud data of the complex and special-shaped building components.
步骤102，对获取的点云数据进行预处理。为了提高建模精度，对获取的点云数据进行预处理的方法可以包括对获取的点云数据进行滤波、去噪和修补。Step 102: pre-processing the acquired point cloud data. In order to improve the modeling accuracy, the method of pre-processing the acquired point cloud data may include filtering, denoising and repairing the acquired point cloud data.
步骤103，计算预处理后的点云数据的法向量；Step 103, calculating the normal vector of the preprocessed point cloud data;
步骤104，根据三维计算机视觉的泊松表面重建算法通过带有法向量的点云数据生成三角面片网格；Step 104, generating a triangular face mesh from the point cloud data with normal vectors according to a Poisson surface reconstruction algorithm of three-dimensional computer vision;
步骤105，对三角面片网格进行裁剪；Step 105, cutting the triangular mesh;
步骤106，将裁剪后的三角面片网格进行修补，生成闭合的三角面片网格；Step 106, repairing the cropped triangular face mesh to generate a closed triangular face mesh;
步骤107，对闭合的三角面片网格进行重建，生成四边面网格；Step 107, reconstructing the closed triangular face mesh to generate a quadrilateral mesh;
步骤108，将重建的四边面网格转换成Nurbs(非均匀有理B样条)，生成复杂异形建筑构件的多重曲面的复杂异形建筑构件的实体模型；Step 108, converting the reconstructed quadrilateral mesh into Nurbs (non-uniform rational B-spline) to generate a solid model of the complex special-shaped building component with multiple curved surfaces of the complex special-shaped building component;
步骤109，将复杂异形建筑构件的实体模型按数据精度等级智能分类导出。可以按数据精度由高到低的顺序对复杂异形建筑构件的实体模型的等级进行智能分类。Step 109, intelligently classify and export the entity model of the complex and special-shaped building component according to the data accuracy level. The level of the entity model of the complex and special-shaped building component can be intelligently classified in the order of data accuracy from high to low.
本发明实施例提供的基于三维计算机视觉的复杂异形建筑构件建模系统及
方法，基于三维计算机视觉技术，利用三维激光扫描获取复杂异形建筑构件的点云数据，对获取的点云数据进行预处理、生成三角面片网格、修补三角面片网格、重建四边面网格，将重建的四边面网格转化为多重曲面的复杂异形建筑构件的实体模型，然后将复杂异形建筑构件的实体模型按数据精度等级智能分类导出。该复杂异形建筑构件建模系统及方法基于三维计算机视觉技术，省去了传统人工处理点云数据、修补网格和缩小BIM模型体量等的繁琐工作，节约了建模时间，提高了复杂异形建筑构件的建模效率。A complex and special-shaped building component modeling system based on three-dimensional computer vision provided by an embodiment of the present invention and The method, based on 3D computer vision technology, uses 3D laser scanning to obtain point cloud data of complex special-shaped building components, pre-processes the obtained point cloud data, generates triangular face meshes, repairs triangular face meshes, reconstructs quadrilateral meshes, converts the reconstructed quadrilateral meshes into solid models of complex special-shaped building components with multiple curved surfaces, and then intelligently classifies and exports the solid models of complex special-shaped building components according to data accuracy levels. The complex special-shaped building component modeling system and method are based on 3D computer vision technology, eliminating the tedious work of traditional manual processing of point cloud data, repairing meshes, and reducing the volume of BIM models, saving modeling time and improving the modeling efficiency of complex special-shaped building components.
本发明实施例提供的基于三维计算机视觉的复杂异形建筑构件建模系统及方法，能够根据使用环境需求导出不同等级的实体模型，可以导出等级精度高的实体模型，也可以导出等级精度低的轻量化实体模型，适用于各种应用环境，适用于不同程度的BIM轻量化设计和不同要求的复杂异形构件的有限元分析，具有适用范围广泛的优点。The complex and special-shaped building component modeling system and method based on three-dimensional computer vision provided by the embodiments of the present invention can export solid models of different levels according to the requirements of the use environment. It can export solid models with high level of precision and lightweight solid models with low level of precision. It is suitable for various application environments, suitable for different degrees of BIM lightweight design and finite element analysis of complex and special-shaped components with different requirements, and has the advantage of a wide range of applications.
本发明不限于上述具体实施方式，显然，上述所描述的实施例是本发明实施例的一部分实施例，而不是全部的实施例。基于所描述的本发明的实施例，本领域普通技术人员所获得的所有其他实施例，都属于本发明保护的范围。本领域的技术人员可以对本发明进行其他层次的修改和变动。如此，若本发明的这些修改和变动属于本发明权利要求书的范围之内，则本发明也意图包括这些改动和变动在内。
The present invention is not limited to the above-mentioned specific implementation modes. Obviously, the above-mentioned embodiments are only some embodiments of the embodiments of the present invention, but not all embodiments. Based on the described embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of the present invention. Those skilled in the art can make other levels of modifications and changes to the present invention. In this way, if these modifications and changes of the present invention fall within the scope of the claims of the present invention, the present invention is also intended to include these changes and changes.
Claims (4)
- 一种基于三维计算机视觉的复杂异形建筑构件建模系统，其特征在于，包括：A complex and special-shaped building component modeling system based on three-dimensional computer vision, characterized by comprising:点云数据处理单元，包括：Point cloud data processing unit, including:点云数据输入模块，用于输入通过三维激光扫描复杂异形建筑构件获取的点云数据；Point cloud data input module, used to input point cloud data obtained by 3D laser scanning of complex and special-shaped building components;点云数据预处理模块，对所述点云数据输入模块获取的点云数据进行滤波、去噪、修补预处理；A point cloud data preprocessing module performs filtering, denoising, and repair preprocessing on the point cloud data acquired by the point cloud data input module;面片网格生成单元，包括：Surface mesh generation unit, including:点云法向量计算模块，用于计算所述点云数据预处理模块预处理后的点云数据的法向量；A point cloud normal vector calculation module, used to calculate the normal vector of the point cloud data preprocessed by the point cloud data preprocessing module;泊松表面重建模块，用于根据所述点云法向量计算模块得到的法向量点云数据生成三角面片网格；A Poisson surface reconstruction module, used to generate a triangular patch mesh according to the normal vector point cloud data obtained by the point cloud normal vector calculation module;网格裁剪模块，用于将所述泊松表面重建模块生成的三角面片网格进行裁剪；A mesh clipping module, used for clipping the triangular face mesh generated by the Poisson surface reconstruction module;网格实体化单元，包括：Mesh solidification units, including:网格修补模块，用于将所述网格裁剪模块裁剪后的三角面片网格进行修补生成闭合的三角面片网格；A mesh repair module, used for repairing the triangular face mesh cut by the mesh cutting module to generate a closed triangular face mesh;四边面网格重建模块，用于对所述网格修补模块生成的闭合三角面片网格进行重建生成四边面网格；A four-sided mesh reconstruction module, used to reconstruct the closed triangular patch mesh generated by the mesh repair module to generate a four-sided mesh;网格转换实体模块，用于将所述四边面网格重建模块重建的四边面网格转换成非均匀有理B样条，生成多重曲面的复杂异形建筑构件的实体模型；A mesh conversion entity module is used to convert the four-sided surface mesh reconstructed by the four-sided surface mesh reconstruction module into a non-uniform rational B-spline to generate a solid model of a complex and special-shaped building component with multiple curved surfaces;实体模型分级导出单元，用于将所述网格转换实体模块生成的复杂异形建筑构件的实体模型按数据精度等级智能分类导出。The entity model hierarchical export unit is used to intelligently classify and export the entity model of the complex special-shaped building component generated by the grid conversion entity module according to the data accuracy level.
- 一种基于三维计算机视觉的复杂异形建筑构件建模方法，其特征在于，包括：A method for modeling complex special-shaped building components based on three-dimensional computer vision, characterized by comprising:通过三维激光对复杂异形建筑构件进行扫描，获取复杂异形建筑构件的点 云数据；Scan complex and special-shaped building components through 3D laser to obtain the point information of complex and special-shaped building components. Cloud data;对获取的点云数据进行预处理；Preprocess the acquired point cloud data;计算预处理后的点云数据的法向量；Calculate the normal vector of the preprocessed point cloud data;根据三维计算机视觉的泊松表面重建算法通过带有法向量的点云数据生成三角面片网格；Generate a triangular patch mesh from point cloud data with normal vectors according to the Poisson surface reconstruction algorithm of three-dimensional computer vision;对三角面片网格进行裁剪；Clip the triangular patch mesh;将裁剪后的三角面片网格进行修补，生成闭合的三角面片网格；Repair the cropped triangular patch mesh to generate a closed triangular patch mesh;对闭合的三角面片网格进行重建，生成四边面网格；Reconstruct the closed triangular face mesh to generate a quadrilateral mesh;将重建的四边面网格转换成非均匀有理B样条，生成多重曲面的复杂异形建筑构件的实体模型；The reconstructed quadrilateral mesh is converted into non-uniform rational B-splines to generate a solid model of a complex and irregular building component with multiple curved surfaces;将复杂异形建筑构件的实体模型按数据精度等级智能分类导出。The solid models of complex and special-shaped building components are intelligently classified and exported according to the data accuracy level.
- 根据权利要求2所述的基于三维计算机视觉的复杂异形建筑构件建模方法，其特征在于，对获取的点云数据进行预处理的方法的步骤包括：对获取的点云数据进行滤波、去噪和修补。According to the method for modeling complex and special-shaped building components based on three-dimensional computer vision as described in claim 2, it is characterized in that the steps of the method for preprocessing the acquired point cloud data include: filtering, denoising and repairing the acquired point cloud data.
- 根据权利要求2所述的基于三维计算机视觉的复杂异形建筑构件建模方法，其特征在于，按数据精度由高到低的顺序对复杂异形建筑构件的实体模型的等级进行智能分类。 The method for modeling complex and special-shaped building components based on three-dimensional computer vision according to claim 2 is characterized in that the levels of the entity models of complex and special-shaped building components are intelligently classified in order of data accuracy from high to low.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211734461.2A CN115937458A (en) | 2022-12-30 | 2022-12-30 | Three-dimensional computer vision-based complex special-shaped building component modeling system and method |
| CN202211734461.2 | 2022-12-30 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2024139419A1 true WO2024139419A1 (en) | 2024-07-04 |
Family
ID=86552517
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2023/118691 WO2024139419A1 (en) | 2022-12-30 | 2023-09-14 | Three-dimensional computer vision-based system and method for modeling complex and irregular building component |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115937458A (en) |
| WO (1) | WO2024139419A1 (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115937458A (en) * | 2022-12-30 | 2023-04-07 | 上海建工四建集团有限公司 | Three-dimensional computer vision-based complex special-shaped building component modeling system and method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105225266A (en) * | 2014-06-06 | 2016-01-06 | 北京易景盈达科技有限公司 | A kind of method of carrying out reality and theoretical interactive modeling based on abnormal curved surface |
| CN110782527A (en) * | 2019-10-09 | 2020-02-11 | 北京建筑大学 | Building modeling method and device |
| CN113768668A (en) * | 2021-09-08 | 2021-12-10 | 佳木斯大学 | Modeling method for designing personalized medical mandible model based on TPMS |
| US20220301192A1 (en) * | 2021-03-22 | 2022-09-22 | Everypoint, Inc. | Performing Object Modeling By Combining Visual Data From Images With Motion Data Of The Image Acquisition Device |
| CN115131523A (en) * | 2022-07-01 | 2022-09-30 | 中国科学院软件研究所 | Three-dimensional point cloud generation surface method based on iterative Poisson surface reconstruction |
| CN115937458A (en) * | 2022-12-30 | 2023-04-07 | 上海建工四建集团有限公司 | Three-dimensional computer vision-based complex special-shaped building component modeling system and method |
-
2022
- 2022-12-30 CN CN202211734461.2A patent/CN115937458A/en active Pending
-
2023
- 2023-09-14 WO PCT/CN2023/118691 patent/WO2024139419A1/en unknown
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105225266A (en) * | 2014-06-06 | 2016-01-06 | 北京易景盈达科技有限公司 | A kind of method of carrying out reality and theoretical interactive modeling based on abnormal curved surface |
| CN110782527A (en) * | 2019-10-09 | 2020-02-11 | 北京建筑大学 | Building modeling method and device |
| US20220301192A1 (en) * | 2021-03-22 | 2022-09-22 | Everypoint, Inc. | Performing Object Modeling By Combining Visual Data From Images With Motion Data Of The Image Acquisition Device |
| CN113768668A (en) * | 2021-09-08 | 2021-12-10 | 佳木斯大学 | Modeling method for designing personalized medical mandible model based on TPMS |
| CN115131523A (en) * | 2022-07-01 | 2022-09-30 | 中国科学院软件研究所 | Three-dimensional point cloud generation surface method based on iterative Poisson surface reconstruction |
| CN115937458A (en) * | 2022-12-30 | 2023-04-07 | 上海建工四建集团有限公司 | Three-dimensional computer vision-based complex special-shaped building component modeling system and method |
Non-Patent Citations (1)
| Title |
|---|
| LIU TAO; GAO YUAN; QIN PINLE; WANG LIFANG: "Improved and Optimized Poisson Reconstruction Algorithm Based on Point Cloud Library", APPLICATION RESEARCH OF COMPUTERS, CHENGDU, CN, vol. 35, no. 3, 31 March 2018 (2018-03-31), CN , pages 940 - 943, 948, XP009555663, ISSN: 1001-3695 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115937458A (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2024139419A1 (en) | Three-dimensional computer vision-based system and method for modeling complex and irregular building component | |
| EP1645979A1 (en) | Method and program for generating volume data from boundary representation data | |
| Pérez et al. | A comparison of hole-filling methods in 3D | |
| Guo et al. | Application of computer aided modeling design in the expression techniques of sculpture art space | |
| Hur et al. | STL file generation with data reduction by the delaunay triangulation method in reverse engineering | |
| Wei et al. | GeoDualCNN: Geometry-supporting dual convolutional neural network for noisy point clouds | |
| CN117475110B (en) | Semantic three-dimensional reconstruction method and device for blade, electronic equipment and storage medium | |
| Denk et al. | Subdivision Surface mid-surface reconstruction of topology optimization results and thin-walled shapes using surface skeletons | |
| Wang et al. | A novel method for surface mesh smoothing: applications in biomedical modeling | |
| Canas et al. | Surface remeshing in arbitrary codimensions | |
| CN111179420B (en) | Three-dimensional city model optimization method and system | |
| CN113806892A (en) | Reverse engineering-based propeller digital design and processing method | |
| CN105844713A (en) | Parametric surface reconstruction method based on manifold | |
| CN113112417A (en) | Spray workpiece modeling method based on three-dimensional point cloud | |
| Miao et al. | Curvature estimation of point-sampled surfaces and its applications | |
| JP2000251095A (en) | Method and device for dividing area of polygon mesh and information recording medium | |
| Tang et al. | Improved fast 3D reconstruction algorithm based on laser scanning point cloud | |
| Gao et al. | A fast algorithm for delaunay based surface reconstruction | |
| Hamoud | Enhancement of Sliced Layer Contour for Reconstructing A 3D Model Using Solid Freeform Fabrication | |
| Song et al. | Integrated Quality Mesh Generation for Poisson Surface Reconstruction in HPC Applications | |
| Cui et al. | Hole Inpainting Algorithm for Half-Organized Point Cloud Obtained by Structured-Light Section System | |
| Ran et al. | Geometry texture synthesis based on Laplacian texture image | |
| Huang et al. | A GPU based interactive modeling approach to designing fine level features | |
| CN112434476A (en) | LBM preprocessing efficient algorithm based on STL file | |
| Wang | Integrated CAD/CAM and numerical simulation based on subdivision methods |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 23909354 Country of ref document: EP Kind code of ref document: A1 |