CN113887508B - Accurate identification method for central line of public corridor space in building professional residence plan - Google Patents
Accurate identification method for central line of public corridor space in building professional residence plan Download PDFInfo
- Publication number
- CN113887508B CN113887508B CN202111238996.6A CN202111238996A CN113887508B CN 113887508 B CN113887508 B CN 113887508B CN 202111238996 A CN202111238996 A CN 202111238996A CN 113887508 B CN113887508 B CN 113887508B
- Authority
- CN
- China
- Prior art keywords
- space
- corridor space
- central line
- door
- layer
- 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
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000010586 diagram Methods 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims description 8
- 238000005516 engineering process Methods 0.000 claims description 5
- 238000013527 convolutional neural network Methods 0.000 claims description 3
- 238000012217 deletion Methods 0.000 claims description 3
- 230000037430 deletion Effects 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 3
- 238000012804 iterative process Methods 0.000 claims description 3
- 238000007639 printing Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 abstract description 2
- 238000010276 construction Methods 0.000 description 18
- 230000009471 action Effects 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005034 decoration Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000009423 ventilation Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Image Analysis (AREA)
Abstract
The invention belongs to the technical field of drawing analysis, and discloses a method for accurately identifying the central line of a public corridor space in a plane diagram of a building professional residence, which comprises the following specific operation steps: s1, firstly, analyzing a CAD drawing to obtain basic information such as primitives, layers and the like in the drawing; s2, recommending the layers to recommended layers of the components according to the basic information obtained in the step 1. The accurate identification method for the central line of the public corridor space in the CAD building professional residential plan can accurately and stably acquire the central lines of all public corridor spaces in the residential plan, thereby providing good conditions for regular examination of the public corridor in the residential plan, facilitating the operation of staff, improving the working efficiency of the staff and being an identification method with good generalization performance and high accuracy.
Description
Technical Field
The invention belongs to the technical field of drawing analysis, and particularly relates to a method for accurately identifying a central line of a public corridor space in a plane view of a building professional residence.
Background
The CAD construction drawing is a drawing which is made by using design software such as AutoCAD and the like to carry out overall layout of engineering projects, external shape, internal arrangement, structural construction, internal and external decoration, material construction, equipment, construction and the like of a building, has the characteristics of complete drawing, accurate expression and specific requirements, is the basis for carrying out engineering construction, programming construction drawing budget and construction organization design, is also an important technical file for carrying out technical management, and can enter a construction stage only by carefully examining the construction drawing before construction, so as to ensure the smooth progress of construction and avoid the influence on a use stage after the construction is completed due to mistakes of the drawing.
The building professional residence plan in CAD construction drawing is a drawing formed by using horizontal projection method and correspondent legend to make wall, door and window, stairs, floor and internal function layout of new building or structure, concretely, after the house is cut by using an imaginary horizontal cutting plane along the position slightly higher than window sill, the upper portion is removed, and the rest portion is orthographic projected toward H face, so that the obtained horizontal section drawing can be used as important component in building design and construction drawing, and can reflect the functional requirements of building, plane layout and its plane composition relationship, and is the key links for determining building elevation and internal structure, and mainly can reflect the conditions of plane shape, size, internal layout, concrete position of floor, door and window and floor area of building, the building house plan is an important basis for construction of a new building and arrangement of construction sites, is also a basis for designing and planning professional engineering plan such as water supply and drainage, strong and weak electricity, heating and ventilation equipment and the like and drawing pipeline comprehensive plan, and is divided into a first-layer plan, a standard-layer plan, a top-layer plan, a roof plan and the like, wherein the first-layer plan of the building house represents arrangement of a first-layer room, a building entrance, a hall, stairs and the like, the standard-layer plan of the building house represents arrangement of middle layers, the top-layer plan of the building house represents the plan of the highest layer of the building, and the roof plan of the building house represents horizontal projection of the roof plane.
With the wide application of artificial intelligence, some work completed by manpower can be completed by artificial intelligence, the examination of CAD construction drawings is a time-consuming and labor-consuming repetitive work, examination personnel are easy to miss, the artificial intelligence can identify the public corridor space in the CAD construction drawings, and accurate identification of the central line of the public corridor space can be realized by means of computer vision technology and a traditional image processing algorithm, so that automatic examination of corridor space, such as examination of corridor length, is realized.
Disclosure of Invention
The invention aims to provide a method for accurately identifying the central line of a public corridor space in a plane view of a building professional residence, so as to solve the problems in the prior art.
In order to achieve the above object, the present invention provides the following technical solutions: a method for accurately identifying the central line of a public corridor space in a building professional residence plan comprises the following specific operation steps:
s1, firstly, analyzing a CAD drawing to obtain basic information such as primitives, layers and the like in the drawing;
s2, recommending the layer to the recommended layer of the component according to the basic information obtained in the step 1;
S3, acquiring wall posts, door and window layers and other related information from the recommended layers in the step 2;
S4, merging the door and window layer primitives in the step 3, and obtaining a door and window component bbox after merging;
S5, according to all door and window components bbox obtained in the step 4, digging out small pictures of all doors and windows from the base picture printed by the drawing;
s6, sending the door and window component small diagram obtained in the step 5 into MobileNet V a deep convolutional neural network for classification, and obtaining the accurate category of the door and window component after classification;
s7, printing the wall column graphic element in the step 3 on a base map, and combining the door and window component information in the step 6, performing space segmentation by utilizing image processing, and acquiring the function of each space;
S8, acquiring a public pavement space from all the spaces in the step 7, and then digging out a small image of the space;
s9, scaling the small image in the step 8 by using an image processing technology;
S10, transmitting the scaled small image in the step 9 into a Zhang-Suen refinement algorithm to obtain a central line of the corridor space;
S11, scaling the central line obtained in the step 10, so as to obtain the central line of the corridor space in the original image;
S12, extending the center line obtained in the step 11, and further obtaining an end point of the end of the corridor space;
and S13, saving the center line obtained in the step 11 and the corridor space end point obtained in the step 12.
Preferably, the graphic element in the step S1 refers to graphic data, and corresponds to an entity visible on the drawing interface; the layer refers to films containing elements such as characters or figures, and a Zhang An film is sequentially stacked together to form the final effect of the page, and the layer can accurately position the elements on the page; text, pictures, tables and plug-ins can be added into the layers, and the layers can be nested inside.
Preferably, the component is an actual replaceable part of the system, which performs a specific function, meets a set of interface standards, and implements a set of interfaces, and represents a part of the physical implementation of the system, including software code or its equivalent, in a pattern, the component being represented as a rectangle with labels.
Preferably, in step S6, bbox refers to a regression frame, where predicted frame values are input initially, and the original classification problem is just to input a graph, but now for the input graph, there is also its position information in the original graph; the input graph can learn and extract the feature vector through a convolution network; one goal of the target detection is to expect the last binding box and ground truth to coincide.
Preferably, the Mobile Net V1 in step S6 refers to the network architecture published by Google, and the main innovation point is to replace the common convolution with a depth separable convolution, and to reduce the number of parameters by using a width multiplier, which can trade off better data throughput while sacrificing very little accuracy.
Preferably, the Zhang-Suen refinement algorithm in step S10 generally refers to an iterative algorithm, and the whole iterative process is divided into two steps: the first step is to circulate all foreground pixel points and mark the pixel points meeting the following conditions as deletion; the second Step is very similar to Step One, the conditions 1 and 2 are completely consistent, the conditions 3 and 4 are slightly different, the pixel P1 meeting the following conditions is marked as deleted, the two steps are circulated until no pixel is marked as deleted in the two steps, and the output result is the skeleton after the binary image is thinned.
The beneficial effects of the invention are as follows:
The accurate identification method for the central line of the public corridor space in the CAD building professional residential plan can realize the accurate identification of the central line of the public corridor space by means of a computer vision technology and a traditional image processing algorithm, so that the automatic examination of the corridor space is realized, the central lines of all the public corridor spaces in the residential plan can be accurately and stably obtained, good conditions are provided for the regular examination of the public corridor in the residential plan, the operation of workers is facilitated, the working efficiency of the workers is improved, and the identification method is an identification method with good generalization performance and high accuracy.
Drawings
FIG. 1 is a flow chart diagram of the overall common corridor centerline identification process of the present invention;
FIG. 2 is a schematic diagram of a center line of a common corridor accurately identified to be in a complex form on a drawing sheet;
FIG. 3 is a schematic diagram of the invention accurately identifying the center line of a Z-shaped common corridor on a drawing;
FIG. 4 is a schematic diagram of the invention for accurately identifying the center line of a straight-line common corridor on a drawing.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1 to 4, in an embodiment of the present invention, a method for accurately identifying a center line of a common corridor space in a plane view of a building professional residence includes the following specific operation steps:
s1, firstly, analyzing a CAD drawing to obtain basic information such as primitives, layers and the like in the drawing;
s2, recommending the layer to the recommended layer of the component according to the basic information obtained in the step 1;
S3, acquiring wall posts, door and window layers and other related information from the recommended layers in the step 2;
S4, merging the door and window layer primitives in the step 3, and obtaining a door and window component bbox after merging;
S5, according to all door and window components bbox obtained in the step 4, digging out small pictures of all doors and windows from the base picture printed by the drawing;
s6, sending the door and window component small diagram obtained in the step 5 into MobileNet V a deep convolutional neural network for classification, and obtaining the accurate category of the door and window component after classification;
s7, printing the wall column graphic element in the step 3 on a base map, and combining the door and window component information in the step 6, performing space segmentation by utilizing image processing, and acquiring the function of each space;
S8, acquiring a public pavement space from all the spaces in the step 7, and then digging out a small image of the space;
s9, scaling the small image in the step 8 by using an image processing technology;
S10, transmitting the scaled small image in the step 9 into a Zhang-Suen refinement algorithm to obtain a central line of the corridor space;
S11, scaling the central line obtained in the step 10, so as to obtain the central line of the corridor space in the original image;
S12, extending the center line obtained in the step 11, and further obtaining an end point of the end of the corridor space;
and S13, saving the center line obtained in the step 11 and the corridor space end point obtained in the step 12.
Wherein, the graphic element in the step S1 refers to graphic data, and corresponds to an entity visible on a drawing interface; the layer refers to films containing elements such as characters or figures, and a Zhang An film is sequentially stacked together to form the final effect of the page, and the layer can accurately position the elements on the page; text, pictures, tables and plug-ins can be added into the layers, and the layers can be nested inside.
Wherein the component is the actual replaceable part of the system, which performs the specified function, meets a set of interface standards, and enables a set of interfaces, and represents a portion of the system physical implementation, including software code or its equivalent, in a pattern represented by a rectangle with labels.
In step S6, bbox refers to a regression frame, where a predicted frame value is input initially, and the original classification problem is to input only one graph, but the input graph has the position information of the input graph in the original graph; the input graph can learn and extract the feature vector through a convolution network; one goal of the target detection is to expect the last binding box and ground truth to coincide.
The Mobile Net V1 in step S6 refers to a network architecture published by Google, and the main innovation point is to replace the common convolution with the depth separable convolution, and reduce the number of parameters by using a width multiplier, which can trade off better data throughput while sacrificing very little accuracy.
The Zhang-Suen refinement algorithm in step S10 generally refers to an iterative algorithm, and the whole iterative process is divided into two steps: the first step is to circulate all foreground pixel points and mark the pixel points meeting the following conditions as deletion; the second Step is very similar to Step One, the conditions 1 and 2 are completely consistent, the conditions 3 and 4 are slightly different, the pixel P1 meeting the following conditions is marked as deleted, the two steps are circulated until no pixel is marked as deleted in the two steps, and the output result is the skeleton after the binary image is thinned.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (6)
1. A method for accurately identifying the central line of a public corridor space in a building professional residence plan is characterized by comprising the following steps of: the specific operation steps of the method for accurately identifying the central line of the public corridor space in the building professional residence plan are as follows:
s1, firstly, analyzing a CAD drawing to obtain primitive and layer basic information in the drawing;
S2, recommending the layer to the recommended layer of the component according to the basic information acquired in the step S1;
S3, acquiring wall column and door and window layer related information from the recommended layer in the step S2;
s4, merging the door and window layer primitives in the step S3, and obtaining a door and window component bbox after merging;
S5, according to all door and window components bbox obtained in the step S4, digging out small pictures of all doors and windows from the base picture printed by the drawing;
S6, sending the door and window component small diagram obtained in the step S5 into MobileNet V a deep convolutional neural network for classification, and obtaining the accurate category of the door and window component after classification;
S7, printing the wall column graphic element in the step S3 on a base map, and performing space segmentation by utilizing image processing in combination with the door and window component information in the step S6 to obtain the function of each space;
s8, acquiring a public pavement space from all the spaces in the step S7, and then digging out a small image of the space;
S9, scaling the small image in the step S8 by using an image processing technology;
S10, transmitting the scaled small image in the step S9 into a Zhang-Suen refinement algorithm to obtain a central line of the corridor space;
S11, scaling the central line obtained in the step S10, so as to obtain the central line of the corridor space in the original image;
S12, extending the center line obtained in the step S11, and further obtaining an end point of the end of the corridor space;
and S13, saving the center line obtained in the step S11 and the corridor space end points obtained in the step 12.
2. A method of accurately identifying a center line of a common corridor space in a building professional residential floor plan as claimed in claim 1, wherein: the graphic element in the S1 step refers to graphic data, and corresponds to an entity visible on a drawing interface; the layer refers to films containing text or graphic elements, and one Zhang An film is sequentially stacked together to form the final effect of the page, and the layer can accurately position the elements on the page; text, pictures, tables and plug-ins can be added into the layers, and the layers can be nested inside.
3. A method of accurately identifying a center line of a common corridor space in a building professional residential floor plan as claimed in claim 1, wherein: the component is the actual replaceable part of the system that performs the specified function, meets a set of interface standards, and enables a set of interfaces, and represents a portion of the physical implementation of the system, including software code or its equivalent, in a pattern represented as a rectangle with labels.
4. A method of accurately identifying a center line of a common corridor space in a building professional residential floor plan as claimed in claim 1, wherein: in step S6, bbox is a regression frame, a predicted frame value is input at first, and only one graph is input for the original classification problem, but the position information of the input graph in the original graph is also provided; the input graph can learn and extract the feature vector through a convolution network; one goal of the target detection is to expect the last binding box and ground truth to coincide.
5. A method of accurately identifying a center line of a common corridor space in a building professional residential floor plan as claimed in claim 1, wherein: the Mobile Net V1 in step S6 refers to the network architecture published by Google, and the main innovation point is to replace the common convolution with the depth separable convolution, and to reduce the number of parameters by using the width multiplier, which can trade off better data throughput while sacrificing very little accuracy.
6. A method of accurately identifying a center line of a common corridor space in a building professional residential floor plan as claimed in claim 1, wherein: the Zhang-Suen refinement algorithm in step S10 generally refers to an iterative algorithm, and the whole iterative process is divided into two steps: the first step is to circulate all foreground pixel points and mark the pixel points meeting the following conditions as deletion; the second Step is very similar to Step One, the conditions 1 and 2 are completely consistent, the conditions 3 and 4 are slightly different, the pixel P1 meeting the following conditions is marked as deleted, the two steps are circulated until no pixel is marked as deleted in the two steps, and the output result is the skeleton after the binary image is thinned.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111238996.6A CN113887508B (en) | 2021-10-25 | 2021-10-25 | Accurate identification method for central line of public corridor space in building professional residence plan |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111238996.6A CN113887508B (en) | 2021-10-25 | 2021-10-25 | Accurate identification method for central line of public corridor space in building professional residence plan |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113887508A CN113887508A (en) | 2022-01-04 |
| CN113887508B true CN113887508B (en) | 2024-05-14 |
Family
ID=79013539
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111238996.6A Active CN113887508B (en) | 2021-10-25 | 2021-10-25 | Accurate identification method for central line of public corridor space in building professional residence plan |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113887508B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114547813B (en) * | 2022-01-10 | 2024-05-03 | 上海品览数据科技有限公司 | Automatic laying method of heating branch pipes in heating main pipe plan of heating ventilation major |
| CN114626167B (en) * | 2022-01-14 | 2024-04-26 | 上海品览数据科技有限公司 | Automatic laying method for floor heating in heating plan of heating and ventilation major |
| CN114241509B (en) * | 2022-02-24 | 2022-07-08 | 江西少科智能建造科技有限公司 | Space segmentation method, system, storage medium and equipment based on construction drawing |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002228414A (en) * | 2001-01-31 | 2002-08-14 | Hitachi Plant Eng & Constr Co Ltd | Method and apparatus for measuring three-dimensional position |
| JP2003316835A (en) * | 2002-04-24 | 2003-11-07 | Kajima Corp | Building production information integration system |
| CN109724603A (en) * | 2019-01-08 | 2019-05-07 | 北京航空航天大学 | A kind of Indoor Robot air navigation aid based on environmental characteristic detection |
| CN112989452A (en) * | 2021-01-20 | 2021-06-18 | 上海品览智造科技有限公司 | Accurate identification method for component lead marking text in CAD water supply and drainage professional drawings |
-
2021
- 2021-10-25 CN CN202111238996.6A patent/CN113887508B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002228414A (en) * | 2001-01-31 | 2002-08-14 | Hitachi Plant Eng & Constr Co Ltd | Method and apparatus for measuring three-dimensional position |
| JP2003316835A (en) * | 2002-04-24 | 2003-11-07 | Kajima Corp | Building production information integration system |
| CN109724603A (en) * | 2019-01-08 | 2019-05-07 | 北京航空航天大学 | A kind of Indoor Robot air navigation aid based on environmental characteristic detection |
| CN112989452A (en) * | 2021-01-20 | 2021-06-18 | 上海品览智造科技有限公司 | Accurate identification method for component lead marking text in CAD water supply and drainage professional drawings |
Non-Patent Citations (1)
| Title |
|---|
| 基于DXF数据的建筑物三维建模;张国栋;刘东峰;程昱;孙粤辉;;计算机技术与发展;20121210(第12期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113887508A (en) | 2022-01-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113887508B (en) | Accurate identification method for central line of public corridor space in building professional residence plan | |
| CN109993827B (en) | Elevation view identification method for converting building drawing into three-dimensional BIM model | |
| EP3543960B1 (en) | Information processing device, information processing method, and program | |
| Kopsida et al. | Real-time volume-to-plane comparison for mixed reality–based progress monitoring | |
| Gimenez et al. | Reconstruction of 3D building information models from 2D scanned plans | |
| Roh et al. | An object-based 3D walk-through model for interior construction progress monitoring | |
| CN112883798B (en) | Method for identifying components in plane graph space of building specialty based on deep learning | |
| Henricsson | The role of color attributes and similarity grouping in 3-D building reconstruction | |
| Cao et al. | Facade geometry generation from low-resolution aerial photographs for building energy modeling | |
| CN104077447B (en) | Urban three-dimensional space vector modeling method based on paper plane data | |
| CN114022895B (en) | Accurate identification method for house type in building professional residence plan | |
| CN112883801A (en) | Accurate identification method for household distribution box system diagram subgraph in CAD distribution system diagram | |
| CN112989923A (en) | Method for accurately judging whether shielding exists in neutral plane window in CAD elevation graph | |
| Yu et al. | Architectural facade recognition and generation through generative adversarial networks | |
| CN114022894B (en) | Method for accurately identifying stairway front room in CAD drawing | |
| Dogan et al. | CitySeek: towards urban daylight models based on GIS data and semi-automated image processing | |
| Li et al. | Classification of photo-realistic 3D window views in a high-density city: The case of Hong Kong | |
| CN114547813B (en) | Automatic laying method of heating branch pipes in heating main pipe plan of heating ventilation major | |
| CN113971813A (en) | Accurate identification method for parking spaces in construction professional general plane construction drawing and underground garage construction drawing | |
| CN114005134A (en) | Component identification method in electrical professional illumination plane graph based on deep learning | |
| CN114626167B (en) | Automatic laying method for floor heating in heating plan of heating and ventilation major | |
| CN114282332B (en) | Automatic arrangement method of water collector in heating plan of heating and ventilation major | |
| CN114626122B (en) | Automatic arrangement method of stairwell radiator in heating main pipe plan view of heating and ventilation major | |
| Shon et al. | Identifying the exterior image of buildings on a 3D map and extracting elevation information using deep learning and digital image processing | |
| CN114494714B (en) | Accurate identification method for building contour of building major general plane map building |
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 |