A method to finely divide the entrance hall from the large living room space in CAD drawings

Through the precise segmentation method and image processing technology of CAD drawings, the entrance hall in the large space of the living room is identified and divided, and the problem of difficult to identify the entrance hall in the CAD drawings is solved, and efficient and accurate entrance division is achieved, supporting subsequent research and review.

CN114723943BActive Publication Date: 2024-11-19PINLAN (HANGZHOU) TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202111531164.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-12-15
Publication Date
2024-11-19
Estimated Expiration
2041-12-15

AI Technical Summary

Technical Problem

In the CAD construction drawings, the living room, entrance hall and dining room often have no obvious boundary in the same area, making it difficult to finely divide the entrance hall from the large space, and artificial intelligence review is time-consuming and labor-intensive, and there is a lack of efficient identification methods.

Method used

Through the precise segmentation method of residential space on CAD drawings, we can find the rectangular space of the living room and the corridor/stairwell, judge that the adjacent rectangular space is the entrance space, combine the opencv library for element scaling, edge detection and regular matching, and identify civil engineering connections. Lines and doors realize the fine division of the entrance hall.

Benefits of technology

It realizes efficient and precise division of the entrance space in the CAD drawings, with a wide coverage, provides a solid foundation for subsequent research and review, and reduces the time-consuming process of artificial intelligence review.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114723943B_ABST
    Figure CN114723943B_ABST
Patent Text Reader

Abstract

The present invention discloses a method for finely dividing a porch from a large living room space in a CAD drawing, the method comprising the following steps: S1, obtaining a large living room space, a corridor, a stairwell, an anteroom, and a door from the drawing; S2, finding the largest inscribed rectangle of the large living room space, obtaining the remaining living room space and a large rectangular space; S3, dividing the living room into n rectangles; S4, obtaining the civil engineering lines of all doors through the steps in the method for accurate segmentation of residential space on the patented CAD drawing; S5, finding the door separating the original large living room space from the corridor / stairwell / anteroom, and this door is the entrance door; S6, judging which rectangular space is adjacent to the obtained entrance door, and the adjacent rectangular space is the divided porch space. The present invention can efficiently and accurately divide all porch spaces in the drawing frame, fills the technical gap of identifying porch spaces in CAD drawings, and provides a solid foundation for subsequent porch space research, review, etc.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of CAD drawing recognition and traditional image processing, and in particular to a method for finely dividing a porch in a CAD drawing. Background Art

[0002] CAD construction drawings are drawings that use AutoCAD software to show the overall layout of the project, the building's exterior shape, interior layout, structural structure, interior and exterior decoration, material methods, equipment, and construction. CAD construction drawings are complete, accurate, and specific. They are the basis for engineering construction, construction drawing budgets, and construction organization design. They are also important technical documents for technical management. Before construction, the construction drawings need to be carefully reviewed before entering the construction phase. The purpose is to ensure the smooth progress of the construction and avoid the impact of errors in the drawings on the use phase after the completion of the construction.

[0003] Living room spaces often appear in CAD construction drawings, and in most living room drawings, the living room, entrance hall, and dining room are drawn in the same area, with no obvious dividing lines between them, making it difficult to separate the entrance hall from the large mixed space. With the rise of artificial intelligence, a large number of projects involving manual participation can be replaced by artificial intelligence, among which the review of CAD construction drawings is a time-consuming and labor-intensive repetitive task. In order to facilitate the review of CAD construction drawings by artificial intelligence, it is necessary to accurately identify the components in the drawings. The present invention is aimed at the fine division of the entrance hall space in the CAD drawings, and proposes a method for dividing the entrance hall space with a wide coverage and high accuracy. Summary of the invention

[0004] In view of the above problems, the present invention provides a method for finely dividing the entrance hall from the large living room space in the CAD drawing.

[0005] To solve the above technical problems, the present invention is implemented by the following technical solutions: The present invention provides a method for finely dividing the entrance hall from the large living room space in the CAD drawing, and the method comprises the following steps:

[0006] S1. The large living room space and the corridor / stairwell / front room are obtained by accurately dividing the residential space on the CAD drawing;

[0007] S2. Find the largest inscribed rectangle in the living room to obtain the remaining living room space and a large rectangular space;

[0008] S3, repeat step S2 until a complete living room space is divided into n non-overlapping rectangular spaces;

[0009] S4. Obtain the civil engineering lines of all doors through the steps in the method of accurate segmentation of residential space on the CAD drawing;

[0010] S5. Find the door that separates the original living room from the corridor / stairwell / front room. This door is the entrance door.

[0011] S6. For the rectangular space obtained in step S3, determine which rectangular space is adjacent to the entrance door obtained in step S5. The adjacent rectangular space is the divided entrance space.

[0012] Preferably, the method for accurately segmenting the residential space on the CAD drawing in step S1 and step S4 specifically comprises the following steps:

[0013] S11. Collect the layers of walls, columns, doors and windows drawn in the CAD construction drawings designed by different design institutes, as well as the texts marked in various residential spaces in the CAD construction drawings;

[0014] S12, parse each CAD drawing to obtain a number of drawing frames, and obtain the layers contained in each drawing frame and the graphics elements drawn in each layer, and classify and store the graphics element information contained in each layer according to the objects to which the layers belong collected in step S11;

[0015] S13, scaling the size of the parsed CAD drawing frame by a certain proportion, and using the numpy computing library in the python language to create a proportionally scaled black background map;

[0016] S14, after scaling the wall and column elements obtained in step S12 according to the scaling ratio in step S13, all the elements are drawn on the black base map created in step S13 using bright colors using the opencv library in the python language;

[0017] S15, integrating the door and window graphic element information in step S12 respectively, and merging the overlapping graphic elements into one component;

[0018] S16, comparing the component with the wall and column elements, finding the two nearest parallel wall and column elements, and connecting the midpoints of the two wall and column elements to obtain a civil engineering connection line that can represent the spatial distribution of each component;

[0019] S17, scaling the civil engineering lines according to the scaling ratio in step S13, the same as step S14, and using the opencv library to draw the base map modified in step S14;

[0020] S18, performing edge detection based on the Canny operator on the base map containing the civil engineering lines corresponding to the walls, columns, doors, and windows drawn in step S17, and obtaining all closed contours;

[0021] S19. For all the texts in the frame parsed in step S12, according to the texts of various types of residential spaces collected in S11, use regular matching to find the residential space type corresponding to the text, and name the outline where the space type is located as this type.

[0022] It can be seen from the above description of the present invention that, compared with the prior art, the present invention has the following advantages:

[0023] The present invention provides a method for finely dividing the entrance hall from the large living room space in a CAD drawing, which can efficiently and accurately divide all the entrance hall spaces in the drawing frame, fills the technical gap in identifying the entrance hall space in the CAD drawing, and provides a solid foundation for subsequent research and review of the entrance hall space. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a flow chart of the steps of the present invention;

[0025] Figure 2 is a flowchart of specific steps of an embodiment of the present invention;

[0026] Figure 3 It is a flow chart of the method steps for accurately segmenting residential space on CAD drawings of the present invention;

[0027] Figure 4 is a CAD plan view of an embodiment of the present invention;

[0028] Figure 5 It is a rendering of an embodiment of the present invention. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0030] like Figure 1-2 As shown, the present invention provides a method for finely dividing the entrance hall from the large living room space of the CAD drawing, and the method comprises the following steps:

[0031] S1. The large living room space and the corridor / stairwell / front room are obtained by accurately dividing the residential space on the CAD drawing;

[0032] S2. Find the largest inscribed rectangle in the living room to obtain the remaining living room space and a large rectangular space;

[0033] S3, repeat step S2 until a complete living room space is divided into n non-overlapping rectangular spaces;

[0034] S4. Obtain the civil engineering lines of all doors through the steps in the method of accurate segmentation of residential space on the CAD drawing;

[0035] S5. Find the door that separates the original living room from the corridor / stairwell / front room. This door is the entrance door.

[0036] S6. For the rectangular space obtained in step S3, determine which rectangular space is adjacent to the entrance door obtained in step S5. The adjacent rectangular space is the divided entrance space.

[0037] like Figure 3 As shown, the present invention provides a method for finely dividing the entrance hall from the large living room space in the CAD drawing. The method for accurately dividing the residential space on the CAD drawing in step S1 and step S4 specifically includes the following steps:

[0038] S11. Collect the layers of walls, columns, doors and windows drawn in the CAD construction drawings designed by different design institutes, as well as the texts marked in various residential spaces in the CAD construction drawings;

[0039] S12, parse each CAD drawing to obtain a number of drawing frames, and obtain the layers contained in each drawing frame and the graphics elements drawn in each layer, and classify and store the graphics element information contained in each layer according to the objects to which the layers belong collected in step S11;

[0040] S13, scaling the size of the parsed CAD drawing frame by a certain proportion, and using the numpy computing library in the python language to create a proportionally scaled black background map;

[0041] S14, after scaling the wall and column elements obtained in step S12 according to the scaling ratio in step S13, all the elements are drawn on the black base map created in step S13 using bright colors using the opencv library in the python language;

[0042] S15, integrating the door and window graphic element information in step S12 respectively, and merging the overlapping graphic elements into one component;

[0043] S16, comparing the component with the wall and column elements, finding the two nearest parallel wall and column elements, and connecting the midpoints of the two wall and column elements to obtain a civil engineering connection line that can represent the spatial distribution of each component;

[0044] S17, scaling the civil engineering lines according to the scaling ratio in step S13, the same as step S14, and using the opencv library to draw the base map modified in step S14;

[0045] S18, performing edge detection based on the Canny operator on the base map containing the civil engineering lines corresponding to the walls, columns, doors, and windows drawn in step S17, and obtaining all closed contours;

[0046] S19. For all the texts in the frame parsed in step S12, according to the texts of various types of residential spaces collected in S11, use regular matching to find the residential space type corresponding to the text, and name the outline where the space type is located as this type.

[0047] The present invention provides a method for finely dividing the entrance hall from the large living room space in a CAD drawing, which can identify the entrance hall space in various drawing methods, has a wide coverage and high recognition accuracy, and the identified entrance hall space can be conveniently used in subsequent research, such as whether a sufficient number of lamps are placed in the entrance hall, etc.

[0048] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method to finely divide the entrance hall from the large living room space in the CAD drawing. It is characterized in that The method comprises the following steps: S1. The large living room space and the corridor / stairwell / front room are obtained by accurately dividing the residential space on the CAD drawing; S2. Find the largest inscribed rectangle in the living room to obtain the remaining living room space and a large rectangular space; S3, repeat step S2 until a complete living room space is divided into n non-overlapping rectangular spaces; S4. Obtain the civil engineering lines of all doors through the steps in the method of accurate segmentation of residential space on the CAD drawing; S5. Find the door that separates the original living room from the corridor / stairwell / front room. This door is the entrance door. S6, for the rectangular space obtained in step S3, determine which rectangular space is adjacent to the entrance door obtained in step S5, and the adjacent rectangular space is the divided entrance space; The method for accurately segmenting residential space on the CAD drawings in step S1 and step S4 specifically comprises the following steps: S11. Collect the layers of walls, columns, doors and windows drawn in the CAD construction drawings designed by different design institutes, as well as the texts marked in various residential spaces in the CAD construction drawings; S12, parse each CAD drawing to obtain a number of drawing frames, and obtain the layers contained in each drawing frame and the graphics elements drawn in each layer, and classify and store the graphics element information contained in each layer according to the objects to which the layers belong collected in step S11; S13, scaling the size of the parsed CAD drawing frame by a certain proportion, and using the numpy computing library in the python language to create a proportionally scaled black background map; S14, after scaling the wall and column elements obtained in step S12 according to the scaling ratio in step S13, all the elements are drawn on the black base map created in step S13 using bright colors using the opencv library in the python language; S15, integrating the door and window graphic element information in step S12 respectively, and merging the overlapping graphic elements into one component; S16, comparing the component with the wall and column elements, finding the two nearest parallel wall and column elements, and connecting the midpoints of the two wall and column elements to obtain a civil engineering connection line that can represent the spatial distribution of each component; S17, scaling the civil engineering lines according to the scaling ratio in step S13, the same as step S14, and using the opencv library to draw the base map modified in step S14; S18, performing edge detection based on the Canny operator on the base map containing the civil engineering lines corresponding to the walls, columns, doors, and windows drawn in step S17, and obtaining all closed contours; S19. For all the texts in the frame parsed in step S12, according to the texts of various types of residential spaces collected in S11, use regular matching to find the residential space type corresponding to the text, and name the outline where the space type is located as this type.