CN114972891A - CAD component automatic identification method and BIM modeling method - Google Patents
CAD component automatic identification method and BIM modeling method Download PDFInfo
- Publication number
- CN114972891A CN114972891A CN202210803775.7A CN202210803775A CN114972891A CN 114972891 A CN114972891 A CN 114972891A CN 202210803775 A CN202210803775 A CN 202210803775A CN 114972891 A CN114972891 A CN 114972891A
- Authority
- CN
- China
- Prior art keywords
- cad
- component
- image
- legend
- building block
- 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
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000012549 training Methods 0.000 claims abstract description 5
- 238000010276 construction Methods 0.000 claims description 14
- 238000012946 outsourcing Methods 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 4
- 230000001172 regenerating effect Effects 0.000 claims description 2
- 238000011960 computer-aided design Methods 0.000 description 85
- 238000005457 optimization Methods 0.000 description 5
- 238000013461 design Methods 0.000 description 2
- 238000012938 design process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000007306 turnover Effects 0.000 description 1
Images
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- 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
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/758—Involving statistics of pixels or of feature values, e.g. histogram matching
-
- 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
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Medical Informatics (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Geometry (AREA)
- Computer Graphics (AREA)
- Image Analysis (AREA)
Abstract
An automatic CAD component identification method comprises the following steps: s1, collecting a plurality of CAD component sample images to form a sample library, and training a prediction algorithm based on the sample library; s2, extracting all CAD building blocks from the original CAD drawing to be identified, and converting all CAD building blocks into building block images; s3, predicting the component image through a prediction algorithm to obtain a prediction result, and extracting a CAD component sample image matched with the prediction result from a sample library as a legend image; s4, determining the arrangement angle of the component image based on the legend image; and S5, analyzing the CAD building block according to the prediction result to obtain the size information of the CAD building block. The invention provides an automatic CAD component identification method and a BIM modeling method, which have the advantages of high identification speed, high efficiency and high accuracy.
Description
Technical Field
The invention relates to the field of computer aided design, in particular to a CAD component automatic identification method and a BIM modeling method.
Background
In the BIM design process, a large number of two-dimensional CAD drawings exist. However, with the development of the design industry nowadays, a three-dimensional BIM model, such as a Revit model, is required as a design delivery object in the building design process. Therefore, many two-dimensional CAD needs to draw a BIM model through BIM rollover. There are a large number of point-like members in the CAD drawing, for example: electrical switches, sockets, lamps, etc., heating and ventilating fans, air outlets, fan coils, etc., water valves for water supply and drainage, toilets, washbasins, etc., and various doors and windows in buildings. Each type of component can reach hundreds or even thousands, and during the process of die-flipping, the designer needs to determine the type of the component according to the appearance of the different components in the CAD and contrasting the corresponding legend. At present, two methods are mainly adopted for the turnover of designers, namely a manual identification method and a software identification method.
The manual identification method mainly comprises the steps that a designer finds CAD building blocks from an original CAD drawing, then compares legends to determine categories, and then determines the sizes in BIM software such as Revit and the like, so that the workload is huge, omission easily occurs, and the situation of identification errors easily occurs.
The software identification method mainly extracts CAD building blocks from an original CAD drawing by BIM software such as Revit and the like, and then identification is carried out by relying on manpower, so that the problems of low efficiency, long time consumption and high error rate exist.
Disclosure of Invention
In order to solve the defects of low efficiency and high error rate in the rollover process in the prior art, the invention provides the CAD component automatic identification method and the BIM modeling method, which have the advantages of high identification speed, high efficiency and high accuracy.
In order to achieve the purpose, the invention adopts the specific scheme that: an automatic CAD component identification method comprises the following steps:
s1, collecting a plurality of CAD component sample images to form a sample library, and training a prediction algorithm based on the sample library;
s2, extracting all CAD building blocks from the original CAD drawing to be identified, and converting all CAD building blocks into building block images;
s3, predicting the component image through a prediction algorithm to obtain a prediction result, and extracting a CAD component sample image matched with the prediction result from a sample library as a legend image;
s4, determining the arrangement angle of the component image based on the legend image;
and S5, analyzing the CAD component block according to the prediction result to obtain the size information of the CAD component block.
As a further optimization of the CAD component automatic identification method: in S1, the sample library includes a plurality of sample categories, each sample category includes a plurality of CAD component sample images, and the prediction algorithm employs the YOLO algorithm.
As a further optimization of the CAD component automatic identification method: the specific method of S2 includes:
s21, traversing all CAD component blocks from the original CAD drawing to form a component block set;
s22, traversing the building block set, and performing line segment analysis on each CAD building block to obtain a plurality of construction line segments;
s23, drawing the structural line segment on the background of the second color by the pixel of the first color to obtain the component image, wherein the first color is different from the second color.
As a further optimization of the CAD component automatic identification method: the specific method of S4 includes:
s41, constructing a rectangular coordinate system, and placing the component image and the legend image into the rectangular coordinate system;
s42, projecting the construction line segments in the component image and the legend image on two coordinate axes of a rectangular coordinate system respectively to obtain a component projection histogram and a legend projection histogram;
s43, judging whether the matching degree of the component projection histogram and the legend projection histogram reaches a preset matching threshold, if so, executing S45, otherwise, executing S44;
s44, rotating the component image and regenerating the component projection histogram until the matching degree of the component projection histogram and the legend projection histogram reaches a matching threshold value;
s45, taking 0 ° or the rotation angle of the component image as the arrangement angle of the component image.
As a further optimization of the CAD component automatic identification method: in S43 and S44, the matching threshold is set to 90%.
As a further optimization of the CAD component automatic identification method: the specific method of S5 includes:
s51, determining the minimum outsourcing rectangle of the CAD building block corresponding to the building block image;
s52, determining the size of the minimum outsourcing rectangle;
s53, determining length information and angle information of the construction line segment in the CAD building block according to the size of the minimum outsourcing rectangle and the prediction result;
and S54, integrating the length information and the angle information of all the construction line segments in the CAD building block into the size information of the CAD building block.
A BIM modeling method comprises the following steps:
p1, identifying all the components from the original CAD drawing by the automatic CAD component identification method and determining the position information of the CAD components;
p2, integrating the position information, arrangement angle and size information of the CAD member into parameter information, and storing the parameter information as an intermediate file;
and P3, generating a BIM model according to the intermediate file.
Has the advantages that: the invention realizes the purpose of identifying the CAD component from the original CAD drawing, does not need manual participation in the whole process, realizes automatic identification, has higher efficiency, and can avoid the condition of identification error caused by fatigue and the like in the manual identification process, thereby having higher accuracy.
Drawings
FIG. 1 is a flow chart of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a method for automatically identifying a CAD (Computer Aided Design) component includes S1 to S5.
And S1, collecting a plurality of CAD component sample images to form a sample library, and training a prediction algorithm based on the sample library. The sample images of the CAD member can be selected by referring to standard part images in specific industries. In S1, the sample library includes a plurality of sample categories, each of which includes a plurality of CAD member sample images, each of which is a sample model, and for convenience of subsequent processing, the CAD member sample images are rectangular images, and may be oriented from a center point of the CAD member sample image as an origin, in an upward direction from the origin by 0 °, and have an arrangement angle of CAD members in the CAD member sample images set to 0 °. In this embodiment, the prediction algorithm adopts a YOLO (Real-Time object Detection) algorithm, and after training, the YOLO algorithm can obtain a prediction model.
And S2, extracting all CAD building blocks from the original CAD drawing to be identified, and converting all CAD building blocks into building block images. Specific methods of S2 include S21 to S23.
And S21, traversing all CAD component blocks from the original CAD drawing to form a component block set. In common CAD software such as AutoCAD, CAD building blocks in an original CAD drawing all exist independently, so that all CAD building blocks can be directly traversed.
And S22, traversing the building block set, and performing line segment analysis on each CAD building block to obtain a plurality of construction line segments. The line segment analysis can also be directly performed by using CAD software such as AutoCAD, which belongs to the conventional technology in the field and is not described herein again.
S23, drawing the structural line segment on the background of the second color by the pixel of the first color to obtain the component image, wherein the first color is different from the second color. By making the background in the component image different from the color of the construction line segment, the component image is more convenient to identify, and the specific type of the CAD component block corresponding to the component image is identified. The greater the difference between the first color and the second color, the more advantageous it is to recognize the component image, and in this embodiment, the first color is black and the second color is white. The component image also adopts a rectangular image, so that the subsequent processing is convenient.
And S3, predicting the component image through a prediction algorithm to obtain a prediction result, and extracting a CAD component sample image matched with the prediction result from the sample library to be used as a legend image. Specifically, the component image is input into the prediction model trained in S1, and the component image is predicted by using the prediction model, where the prediction result includes two parts, i.e., a prediction type and a prediction model, where the prediction type is one of all the sample types, and the prediction model is one of all the sample models in the sample type, so that the prediction result points to a specific CAD component sample image, which is a legend image.
S4, determining the arrangement angle of the component image based on the legend image. Specific methods of S4 include S41 to S45.
S41, a rectangular coordinate system is constructed, and the component image and the legend image are placed in the rectangular coordinate system. More specifically, the component image and the legend image are placed in the first quadrant of the rectangular coordinate system, and the length and width of the component image are made parallel to the two coordinate axes, respectively, and it is also possible to make the lower left corner of the component image coincide with the origin of the rectangular coordinate system.
And S42, respectively projecting the structural line segments in the component image and the legend image on two coordinate axes of the rectangular coordinate system to obtain a component projection histogram and a legend projection histogram. The component projection histogram and the legend projection histogram each include two parts, the results of the projection of the construction line segments onto the x-axis and the y-axis, respectively. In the histogram, the abscissa is the position of the pixel constituting the line segment on the x-axis or the y-axis, and the ordinate is the number of pixels at the same position on the x-axis or the y-axis.
S43, judging whether the matching degree of the component projection histogram and the legend projection histogram reaches a preset matching threshold, if so, executing S45, otherwise, executing S44. In S43 and S44, the matching threshold is set to 90%. The degree of matching can be calculated by the number of pixels at the same position on the x-axis or the y-axis. If the matching degree of the component projection histogram and the legend projection histogram directly reaches the matching threshold, it means that the arrangement angle of the component image is the same as that of the legend image, i.e., 0 °.
The calculation method of the matching degree comprises the following steps: firstly, calculating the total number of all pixel points in a histogram, and then dividing the number of the pixel points at each position in the histogram by the total number of the pixel points to obtain the ratio of the number of the pixels at each position; then calculating the difference value between the number ratio of two pixels at the same position in the component projection histogram and the legend projection histogram, and if the ratio of the difference value to the number ratio of the pixels at the position in the legend projection histogram does not exceed 10%, indicating that the component projection histogram and the legend projection histogram are matched at the position; and then calculating a proportion value of the number of the matched positions in the component projection histogram and the legend projection histogram to the total number of the positions in the legend projection histogram, wherein the proportion value is the matching degree, and if the matching degree exceeds 90%, the component projection histogram and the legend projection histogram are matched.
S44, rotate the component image and regenerate the component projection histogram until the degree of matching of the component projection histogram to the legend projection histogram reaches a matching threshold. If the matching degree of the component projection histogram and the legend projection histogram does not reach the matching threshold, the component image needs to be rotated until the matching degree reaches the matching threshold, at this time, the arrangement angle of the component image becomes 0 °, because the arrangement angle of the component image is changed to 0 ° after the component image is rotated, which indicates that the original arrangement angle of the component image is not 0 °, and the rotation angle is the original arrangement angle.
S45, taking 0 ° or the rotation angle of the component image as the arrangement angle of the component image. Since the main part in the component image is the CAD component block, the arrangement angle of the component image is actually the arrangement angle of the CAD component block, and is also the arrangement angle of the CAD component.
And S5, analyzing the CAD component block according to the prediction result to obtain the size information of the CAD component block. Specific methods of S5 include S51 to S54.
And S51, determining the minimum outsourcing rectangle of the CAD building block corresponding to the building block image.
And S52, determining the size of the minimum outsourcing rectangle.
And S53, determining length information and angle information of the construction line segment in the CAD building block according to the size of the minimum outsourcing rectangle and the prediction result.
And S54, integrating the length information and the angle information of all the construction line segments in the CAD building block into the size information of the CAD building block.
The arrangement angle of the CAD component block, the length information and the angle information of all the construction line segments in the CAD component block are obtained, the type and the model of the CAD component block are determined, the purpose of identifying the CAD component from an original CAD drawing is achieved, manual participation is not needed in the whole process, automatic identification is achieved, efficiency is high, the situation of identification errors caused by fatigue and the like in the manual identification process can be avoided, and therefore accuracy is high.
Based on the CAD component automatic identification method, the invention also provides a BIM (Building Information Modeling) Modeling method, which comprises P1-P3.
P1, identifying all the components from the original CAD drawing by one of the above-mentioned CAD component automatic identification methods, and determining the position information of the CAD components. The position information is the position of the CAD component in the original CAD drawing, can be determined based on the coordinate origin of the original CAD drawing, belongs to conventional means, and is not described any more.
P2, integrating the position information, arrangement angle, and size information of the CAD member into parameter information, and storing the parameter information as an intermediate file.
And P3, generating a BIM model according to the intermediate file. In this embodiment, the intermediate file may be input to Revit software, and the position information of the CAD component is converted into the model position in Revit by a method of converting the coordinates of the original CAD drawing into the coordinates in Revit, so that Revit can be quickly and automatically modeled by the intermediate file, and the BIM modeling speed is greatly increased.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (7)
1. An automatic CAD component identification method is characterized by comprising the following steps:
s1, collecting a plurality of CAD component sample images to form a sample library, and training a prediction algorithm based on the sample library;
s2, extracting all CAD building blocks from the original CAD drawing to be identified, and converting all CAD building blocks into building block images;
s3, predicting the component image through a prediction algorithm to obtain a prediction result, and extracting a CAD component sample image matched with the prediction result from a sample library as a legend image;
s4, determining the arrangement angle of the component image based on the legend image;
and S5, analyzing the CAD component block according to the prediction result to obtain the size information of the CAD component block.
2. The method of claim 1, wherein in step S1, the sample library includes a plurality of sample categories, each sample category includes a plurality of CAD component sample images, and the prediction algorithm employs a YOLO algorithm.
3. The CAD member automatic identification method according to claim 1, wherein the specific method of S2 comprises:
s21, traversing all CAD component blocks from the original CAD drawing to form a component block set;
s22, traversing the building block set, and performing line segment analysis on each CAD building block to obtain a plurality of construction line segments;
s23, drawing the structural line segment on the background of the second color by the pixel of the first color to obtain the component image, wherein the first color is different from the second color.
4. The CAD member automatic identification method according to claim 1, wherein the specific method of S4 comprises:
s41, constructing a rectangular coordinate system, and placing the component image and the legend image into the rectangular coordinate system;
s42, projecting the construction line segments in the component image and the legend image on two coordinate axes of a rectangular coordinate system respectively to obtain a component projection histogram and a legend projection histogram;
s43, judging whether the matching degree of the component projection histogram and the legend projection histogram reaches a preset matching threshold, if so, executing S45, otherwise, executing S44;
s44, rotating the component image and regenerating the component projection histogram until the matching degree of the component projection histogram and the legend projection histogram reaches a matching threshold value;
s45, taking 0 ° or the rotation angle of the component image as the arrangement angle of the component image.
5. The CAD structural member automatic identification method of claim 4, wherein in S43 and S44, the matching threshold is set to 90%.
6. The CAD member automatic identification method according to claim 1, wherein the specific method of S5 comprises:
s51, determining the minimum outsourcing rectangle of the CAD building block corresponding to the building block image;
s52, determining the size of the minimum outsourcing rectangle;
s53, determining length information and angle information of the construction line segment in the CAD building block according to the size of the minimum outsourcing rectangle and the prediction result;
and S54, integrating the length information and the angle information of all the construction line segments in the CAD building block into the size information of the CAD building block.
7. A BIM modeling method is characterized by comprising the following steps:
p1, identifying all the components from the original CAD drawing by a CAD component automatic identification method as claimed in claim 1, and determining the position information of the CAD components;
p2, integrating the position information, arrangement angle and size information of the CAD member into parameter information, and storing the parameter information as an intermediate file;
and P3, generating a BIM model according to the intermediate file.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210803775.7A CN114972891B (en) | 2022-07-07 | 2022-07-07 | Automatic identification method for CAD (computer aided design) component and BIM (building information modeling) method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210803775.7A CN114972891B (en) | 2022-07-07 | 2022-07-07 | Automatic identification method for CAD (computer aided design) component and BIM (building information modeling) method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114972891A true CN114972891A (en) | 2022-08-30 |
| CN114972891B CN114972891B (en) | 2024-05-03 |
Family
ID=82967756
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210803775.7A Active CN114972891B (en) | 2022-07-07 | 2022-07-07 | Automatic identification method for CAD (computer aided design) component and BIM (building information modeling) method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114972891B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109191576A (en) * | 2018-09-06 | 2019-01-11 | 宁波睿峰信息科技有限公司 | A kind of figure layer classification method that architectural drawing is converted to three-dimensional BIM model |
| CN110909650A (en) * | 2019-11-15 | 2020-03-24 | 清华大学 | CAD drawing identification method and device based on domain knowledge and target detection |
| WO2020164282A1 (en) * | 2019-02-14 | 2020-08-20 | 平安科技（深圳）有限公司 | Yolo-based image target recognition method and apparatus, electronic device, and storage medium |
| US20200349724A1 (en) * | 2019-05-03 | 2020-11-05 | Procore Technologies, Inc. | Pattern Matching Tool |
| CN112380608A (en) * | 2020-11-19 | 2021-02-19 | 温岭市第一建筑工程有限公司 | Method and system for rapidly determining building model based on BIM |
| CN112528369A (en) * | 2020-12-09 | 2021-03-19 | 四川蓉信开工程设计有限公司 | CAD graph drawing method based on revit |
| US20210173981A1 (en) * | 2018-08-20 | 2021-06-10 | Bricsys Nv | Automatic parametrization of a cad model |
| CN113158321A (en) * | 2021-05-21 | 2021-07-23 | 西安建筑科技大学 | BIM-based pile foundation engineering digital-analog visualization method |
| CN113901539A (en) * | 2021-09-08 | 2022-01-07 | 长沙泛一参数信息技术有限公司 | Automatic identification and application method for shaft network of CAD drawing of building and structure |
| CN114511669A (en) * | 2021-12-23 | 2022-05-17 | 上海品览数据科技有限公司 | Storage method for AI automatic graph and Revit three-dimensional modeling docking data |
-
2022
- 2022-07-07 CN CN202210803775.7A patent/CN114972891B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210173981A1 (en) * | 2018-08-20 | 2021-06-10 | Bricsys Nv | Automatic parametrization of a cad model |
| CN109191576A (en) * | 2018-09-06 | 2019-01-11 | 宁波睿峰信息科技有限公司 | A kind of figure layer classification method that architectural drawing is converted to three-dimensional BIM model |
| WO2020164282A1 (en) * | 2019-02-14 | 2020-08-20 | 平安科技（深圳）有限公司 | Yolo-based image target recognition method and apparatus, electronic device, and storage medium |
| US20200349724A1 (en) * | 2019-05-03 | 2020-11-05 | Procore Technologies, Inc. | Pattern Matching Tool |
| CN110909650A (en) * | 2019-11-15 | 2020-03-24 | 清华大学 | CAD drawing identification method and device based on domain knowledge and target detection |
| CN112380608A (en) * | 2020-11-19 | 2021-02-19 | 温岭市第一建筑工程有限公司 | Method and system for rapidly determining building model based on BIM |
| CN112528369A (en) * | 2020-12-09 | 2021-03-19 | 四川蓉信开工程设计有限公司 | CAD graph drawing method based on revit |
| CN113158321A (en) * | 2021-05-21 | 2021-07-23 | 西安建筑科技大学 | BIM-based pile foundation engineering digital-analog visualization method |
| CN113901539A (en) * | 2021-09-08 | 2022-01-07 | 长沙泛一参数信息技术有限公司 | Automatic identification and application method for shaft network of CAD drawing of building and structure |
| CN114511669A (en) * | 2021-12-23 | 2022-05-17 | 上海品览数据科技有限公司 | Storage method for AI automatic graph and Revit three-dimensional modeling docking data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114972891B (en) | 2024-05-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bassier et al. | Unsupervised reconstruction of Building Information Modeling wall objects from point cloud data | |
| Kopsida et al. | Real-time volume-to-plane comparison for mixed reality–based progress monitoring | |
| JP7376233B2 (en) | Semantic segmentation of 2D floor plans using pixel-wise classifiers | |
| Ochmann et al. | Automatic reconstruction of parametric building models from indoor point clouds | |
| CN114241509B (en) | Space segmentation method, system, storage medium and equipment based on construction drawing | |
| CN116168351B (en) | Inspection method and device for power equipment | |
| Kim et al. | Automated extraction of geometric primitives with solid lines from unstructured point clouds for creating digital buildings models | |
| Pan et al. | Recovering building information model from 2D drawings for mechanical, electrical and plumbing systems of ageing buildings | |
| CN103837135B (en) | Workpiece inspection method and system thereof | |
| CN110555122A (en) | Building plan wall vectorization method based on segmented rectangles | |
| CN114972891B (en) | Automatic identification method for CAD (computer aided design) component and BIM (building information modeling) method | |
| CN112528384A (en) | BIM-based electromechanical professional component comprehensive arrangement method, system and medium | |
| CN117094242A (en) | Concentration prediction method, concentration prediction device, electronic device, and computer-readable storage medium | |
| Hong et al. | A marker-less assembly stage recognition method based on corner feature | |
| CN116721230A (en) | Method, device, equipment and storage medium for constructing three-dimensional live-action model | |
| CN116051771A (en) | Automatic photovoltaic BIM roof modeling method based on unmanned aerial vehicle oblique photography model | |
| CN114359222A (en) | Method for detecting arbitrary polygon target, electronic device and storage medium | |
| CN114898119A (en) | Building outline drawing method, device, equipment and medium | |
| CN111260723B (en) | Barycenter positioning method of bar and terminal equipment | |
| CN113129299A (en) | Template determination method and device, computer equipment and storage medium | |
| CN116091365B (en) | Triangular surface-based three-dimensional model notch repairing method, triangular surface-based three-dimensional model notch repairing device, triangular surface-based three-dimensional model notch repairing equipment and medium | |
| CN112231787B (en) | Wall auxiliary drawing method and device applied to home decoration system | |
| CN114581890B (en) | Method and device for determining lane line, electronic equipment and storage medium | |
| CN117806496B (en) | Comprehensive pipe rack dynamic virtual inspection method and system based on virtual reality technology | |
| CN107908832B (en) | Air conditioning system model identification and conversion method and terminal equipment |
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 |