A method for identifying the depth of bedroom space in architectural specialty

Abstract

The present invention discloses a method for identifying the depth of a bedroom space in an architectural specialty, the method comprising the following steps: S1, parsing a CAD plan; S2, identifying primitives and spaces; S3, obtaining all bedroom spaces; S4, obtaining primitives with furniture layers greater than 1.5 meters; S5, filtering primitives in the bedroom; S6, using straight line primitives to merge into a bed; S7, obtaining a straight line of the bedroom space contour; S8, finding a space contour line perpendicular to the extension line of the long side of the bed and intersecting; S9, finding a space contour line perpendicular to the previous step; S10, obtaining the depth of the space through the lines obtained in the previous two steps. The present invention can automatically obtain space and component information on a CAD drawing by using computer vision technology, and calculate the depth of the bedroom space based on the obtained information, thereby realizing automatic review of relevant specifications for the depth of the bedroom.

Description

Technical Field

[0001] The present invention relates to the field of intelligent recognition of architectural professional CAD drawings in the field of architectural design and construction, and in particular to a method for recognizing the depth space of an architectural professional bedroom space. 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] The architectural professional residential floor plan in the CAD construction drawing is a drawing composed of the walls, doors, windows, stairs, ground and internal functional layout of the new building or structure, using the horizontal projection method and the corresponding legend. Specifically, it is a horizontal section obtained by cutting the house with an imaginary horizontal cutting plane at a position slightly higher than the window sill, removing the upper part, and projecting the remaining part onto the H surface. As an important part of architectural design and construction drawings, the architectural residential floor plan reflects the functional needs, plane layout and the composition relationship of the plane of the building, and is the key link in determining the facade and internal structure of the building. It mainly reflects the plane shape, size, internal layout, ground, specific location and floor area of ​​doors and windows of the building. Therefore, the architectural residential floor plan is an important basis for the construction of new buildings and the layout of the construction site. It is also the basis for designing and planning professional engineering floor plans such as water supply and drainage, strong and weak electricity, HVAC equipment, and drawing pipeline comprehensive drawings. The architectural residential floor plan is divided into the first floor floor plan, standard floor floor plan, top floor plan and roof floor plan. The ground floor plan of a residential building shows the layout of the rooms on the first floor, the building entrance, foyer and stairs, etc. The standard floor plan of a residential building shows the layout of the middle floors. The top floor plan of a residential building shows the floor plan of the highest floor of the house. The roof plan of a residential building shows the horizontal projection of the roof plane.

[0004] With the widespread application of artificial intelligence, some tasks that were previously done manually can be completed by artificial intelligence. The review of CAD construction drawings is a time-consuming and labor-intensive repetitive task, and it is easy for reviewers to miss the review. Artificial intelligence can identify the depth of the bedroom in the CAD construction drawing. With the help of computer vision technology and traditional image processing algorithms, the bedroom depth recognition can be realized, thereby realizing the automatic review of bedroom depth-related specifications. The present invention proposes a recognition method with good generalization performance and high accuracy for obtaining bedroom depth information in the plane construction drawing of a professional building. Summary of the invention

[0005] In view of the above problems, the present invention provides a method for identifying the depth space of a professional bedroom space in an architecture.

[0006] To solve the above technical problems, the present invention is implemented by the following technical solutions: The present invention provides a method for identifying the depth space of a professional bedroom space in a building, the method comprising the following steps:

[0007] S1. Analyze CAD plan;

[0008] S2, the recognized primitive,space;

[0009] S3, get all bedroom spaces;

[0010] S4, obtain the furniture layer element larger than 1.5 meters;

[0011] S5, filtering the graphics elements in the bedroom;

[0012] S6, use straight line graphics to merge into a bed;

[0013] S7, obtaining the bedroom space outline straight line;

[0014] S8. Find the spatial contour line that intersects the extended line of the long side of the bed;

[0015] S9, find the spatial contour line perpendicular to the previous step;

[0016] S10. Obtain the depth space through the lines obtained in the previous two steps.

[0017] Preferably, steps S1 and S2 specifically include: parsing a building plan base map through CAD to obtain graphic elements and identifying various components and various spaces segmented out by combining AI technology and image algorithms.

[0018] Preferably, the step S4 specifically includes: obtaining the graphic element information of all furniture layers through layer screening, and performing size filtering to obtain all straight line graphic elements with a length greater than 1.5 meters.

[0019] Preferably, step S5 specifically includes: further determining whether the straight line primitive obtained in step S4 is in the bedroom space, determining whether the bedroom space outline contains the straight line through the shape ly function, and also including the straight line whose two end points are close to the bedroom outline.

[0020] Preferably, the step S6 specifically includes: merging the screened straight line primitives of the furniture layer to obtain a circumscribed rectangular frame of a 1.5-meter or 1.8-meter bed, and the merging method is as follows:

[0021] S61, first search for line segments with a length of 1.5 meters or 1.8 meters in the furniture straight line primitives screened in step S4, and then search for line segments with a length greater than 1.5 meters or 1.8 meters and an endpoint less than 1 millimeter away from the 1.5-meter or 1.8-meter-long line;

[0022] S62. Obtain the contours of the found lines through the CV method, which is the contour of the bed.

[0023] Preferably, the step S7 specifically includes: obtaining all straight lines constituting the space contour through the space contour obtained in step S3.

[0024] Preferably, step S8 specifically includes: obtaining the long side of the bed obtained in step S6, dividing the spatial contour lines in step S7 into two groups according to the lines parallel and perpendicular to the long side of the bed, and extending the long side of the bed to find the spatial contour line perpendicular to and intersecting with it.

[0025] Preferably, the step S9 specifically includes: extending two intersecting contour lines perpendicular to the long sides, and searching for intersecting contour lines parallel to the long sides.

[0026] Preferably, the step S10 specifically includes: according to the parallel contour line parallel to the long side of the bed found in step S9, the depth space can be obtained by comparing it with the line obtained in step S8.

[0027] 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:

[0028] The present invention discloses a method for identifying the depth of a bedroom space in an architectural specialty. By using computer vision technology, the space and component information on a CAD drawing can be automatically acquired, and the depth of the bedroom space can be calculated based on the acquired information, thereby realizing automatic review of relevant specifications for the bedroom depth. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 is a flow chart of the steps of the present invention;

[0030] Figure 2 It is a flow chart of the steps of the method for merging graphic elements into a bed according to the present invention. DETAILED DESCRIPTION

[0031] 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.

[0032] like Figure 1-2 As shown, the present invention provides a method for identifying the depth space of a professional bedroom space in an architecture, and the method comprises the following steps:

[0033] S1. Analyze CAD plan;

[0034] S2, the recognized primitive,space;

[0035] S3, get all bedroom spaces;

[0036] S4, obtain the furniture layer element larger than 1.5 meters;

[0037] S5, filtering the graphics elements in the bedroom;

[0038] S6, use straight line graphics to merge into a bed;

[0039] S7, obtaining the bedroom space outline straight line;

[0040] S8. Find the spatial contour line that intersects the extended line of the long side of the bed;

[0041] S9, find the spatial contour line perpendicular to the previous step;

[0042] S10. Obtain the depth space through the lines obtained in the previous two steps.

[0043] Among them, steps S1 and S2 specifically include: parsing a building plane base map through CAD to obtain graphic elements and identifying various components and various spaces segmented after combining AI technology and image algorithm;

[0044] Wherein, step S4 specifically includes: obtaining the primitive information of all furniture layers through layer screening, and performing size filtering to obtain all straight line primitives with a length greater than 1.5 meters;

[0045] Step S5 specifically includes: further determining whether the straight line primitive obtained in step S4 is in the bedroom space, determining whether the bedroom space outline contains the straight line through the shape ly function, and also counting the straight line whose two end points are close to the bedroom outline;

[0046] Step S6 specifically includes: merging the straight line primitives of the screened furniture layer to obtain a circumscribed rectangular frame of a 1.5-meter or 1.8-meter bed, and the merging method is as follows:

[0047] S61, first search for line segments with a length of 1.5 meters or 1.8 meters in the furniture straight line primitives screened in step S4, and then search for line segments with a length greater than 1.5 meters or 1.8 meters and an endpoint less than 1 millimeter away from the 1.5-meter or 1.8-meter-long line;

[0048] S62, obtaining the contours of the found lines through the cv method, that is, the contour of the bed;

[0049] Wherein, step S7 specifically includes: obtaining all straight lines constituting the spatial contour through the spatial contour obtained in step S3;

[0050] Step S8 specifically includes: obtaining the long side of the bed obtained in step S6, dividing the spatial contour straight lines in step S7 into two groups according to the straight lines that are parallel to and perpendicular to the long side of the bed, and extending the long side of the bed to find the spatial contour line that is perpendicular to and intersects the long side of the bed;

[0051] Wherein, step S9 specifically includes: extending two intersecting contour lines perpendicular to the long side, and finding an intersecting contour line parallel to the long side.

[0052] Wherein, step S10 specifically includes: according to the parallel contour line parallel to the long side of the bed found in step S9, the depth space can be obtained by comparing it with the line obtained in step S8.

[0053] The present invention provides a method for identifying the depth of a bedroom space in an architectural profession. By using computer vision technology, the space and component information on a CAD drawing can be automatically acquired, and the depth of the bedroom space can be calculated based on the acquired information, thereby realizing automatic review of relevant specifications for the bedroom depth.

[0054] 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 for identifying the depth of a bedroom space in a building, characterized in that: The method comprises the following steps: S1. Analyze CAD plan; S2, the recognized primitive,space; S3, get all bedroom spaces; S4, obtain the furniture layer element larger than 1.5 meters; S5, filtering the graphics elements in the bedroom; S6, use straight line graphics to merge into a bed; S7, obtaining the bedroom space outline straight line; S8. Find the spatial contour line that intersects the extended line of the long side of the bed; S9, find the spatial contour line perpendicular to the previous step; S10, obtaining the depth space through the lines obtained in the previous two steps; The steps S1 and S2 specifically include: parsing a building plane base map through CAD to obtain graphic elements and identifying various components and various spaces segmented after combining AI technology and image algorithms; The step S4 specifically includes: obtaining the primitive information of all furniture layers through layer screening, and performing size filtering to obtain all straight line primitives with a length greater than 1.5 meters; The step S5 specifically includes: further determining whether the straight line primitive obtained in step S4 is in the bedroom space, determining whether the bedroom space outline contains the straight line by using the shapely function, and also including the straight line whose two end points are close to the bedroom outline; The step S6 specifically includes: merging the straight line primitives of the screened furniture layer to obtain a circumscribed rectangular frame of a 1.5-meter or 1.8-meter bed, and the merging method is as follows: S61, first search for line segments with a length of 1.5 meters or 1.8 meters in the furniture straight line primitives screened in step S4, and then search for line segments with a length greater than 1.5 meters or 1.8 meters and an endpoint less than 1 millimeter away from the 1.5-meter or 1.8-meter-long line; S62, obtaining the contours of the found lines through the cv method, that is, the contour of the bed; The step S7 specifically includes: obtaining all straight lines constituting the spatial contour through the spatial contour obtained in step S3; The step S8 specifically includes: obtaining the long side of the bed obtained in step S6, dividing the spatial contour lines in step S7 into two groups according to the lines parallel to and perpendicular to the long side of the bed, and extending the long side of the bed to find a spatial contour line perpendicular to and intersecting the long side of the bed.

2. A method for identifying the depth of a professional bedroom space in a building according to claim 1, characterized in that: The step S9 specifically includes: extending two intersecting contour lines perpendicular to the long side of the bed, and finding an intersecting contour line parallel to the long side of the bed.

3. A method for identifying the depth of a professional bedroom space in a building according to claim 2, characterized in that: The step S10 specifically includes: obtaining the depth space by comparing the contour line parallel to the long side of the bed found in step S9 with the line obtained in step S8.

Images