Automatic intelligent recognition system for building construction drawings

Abstract

The invention discloses a building construction drawing automatic intelligent identification system, and the system comprises a drawing obtaining module which is used for obtaining a building image file in an original format; the recognition module is connected with the drawing acquisition module, and the recognition module is used for receiving the building image file acquired by the drawing acquisition module and recognizing component primitives and connection contour lines in the building image file to obtain recognition information; the correction module is connected with the identification module, and the correction module corrects the identification information after receiving the identification information and outputs correction information; and the output module is connected with the correction module, and the output module receives the correction information and outputs a building image topological relation matrix file according to the correction information. Compared with the prior art, the method can solve the problem that drawing, updating and maintenance of the architectural drawings depend on manual drawing of operation and maintenance personnel, and prevents the problems of lack of primitive information and connection contour lines and the like.

Description

Technical Field

[0001] The present invention relates to the technical field of drawing recognition, and particularly to an automatic intelligent recognition system for construction drawings. Background Art

[0002] Construction drawings are detailed drawings used by architects, structural engineers, and other professionals to design and construct buildings. These drawings usually include floor plans, elevations, sections, detail drawings, construction drawings, etc.

[0003] With the development of artificial intelligence technology, computer vision technology has been widely applied in scenarios such as image processing, image recognition, and video semantic understanding. For example, recognizing components in construction drawings is one of its applications. The recognition of construction drawing components is a process of detecting and calibrating the basic combined objects that make up a building in construction drawings. It is an important basis for a machine to understand the specific meaning of construction drawings and perform semantic understanding of construction drawings, and plays an important role in the intelligent review of construction drawings.

[0004] Currently, the drawing and update maintenance of construction drawings still heavily rely on the manual drawing of operation and maintenance personnel. The operation and maintenance personnel need to manually draw the graphic elements of building components in construction drawings by referring to the design drawings and manually input relevant text information. Due to the complexity and diversity of construction drawings, the large number of component types, the large amount of drawing work, low efficiency, and cumbersome maintenance, problems such as missing graphic element information and mismatched positional relationships are likely to occur. At the same time, there are problems of inconsistent graphic standards and large storage space occupied by design drawings. Summary of the Invention

[0005] The purpose of the present invention is to solve the problem that the drawing and update maintenance of construction drawings rely on the manual drawing of operation and maintenance personnel, prevent problems such as missing graphic element information and connection contour lines, and provide an automatic intelligent recognition system for construction drawings.

[0006] To achieve the above purpose, the present invention provides an automatic intelligent recognition system for construction drawings, which includes:

[0007] A drawing acquisition module, which is used to acquire a building image file in the original format;

[0008] An identification module, which is connected to the drawing acquisition module. The identification module is used to receive the building image file acquired by the drawing acquisition module and identify the graphic elements and connection contour lines in the building image file to obtain identification information;

[0009] A correction module, which is connected to the identification module. After receiving the identification information, the correction module corrects the identification information and outputs corrected information;

[0010] An output module, which is connected to the correction module. The output module receives the correction information and outputs a building image topological relationship matrix file according to the correction information.

[0011] As a further description of the above technical solution:

[0012] The drawing acquisition module includes a receiving sub-module and a storage sub-module. The receiving sub-module is used to receive and acquire a building image file in the original format, and the storage sub-module is used to classify and store the received building image file in the original format.

[0013] As a further description of the above technical solution:

[0014] The building image file in the original format is stored in the corresponding folder according to the date and project name.

[0015] As a further description of the above technical solution:

[0016] The recognition module includes a reading sub-module and a processing sub-module:

[0017] The reading sub-module is used to read a building image file in the original format and set it as the first image file;

[0018] The processing sub-module is used to process the first image file to obtain the recognition information.

[0019] As a further description of the above technical solution:

[0020] The processing sub-module includes a component graphic element processing module and a connection contour line processing module;

[0021] The component graphic element processing module uses a graphic element detection model to detect and identify component graphic element targets, obtains the coordinate position information of all component graphic elements, then marks the identified component graphic elements, and assigns endpoint labels to the component graphic elements;

[0022] The connection contour line processing module is used to hide the component graphic elements in the first image file to generate a second image file. The connection contour line processing module uses a connection contour line detection model to detect and identify connection contour line targets, obtains the coordinate position information of all connection contour lines, then marks the identified connection contour lines, and assigns endpoint labels to the connection contour lines.

[0023] As a further description of the above technical solution:

[0024] The correction information includes connection contour line quantity information and component graphic element quantity information.

[0025] As a further description of the above technical solution:

[0026] The output module includes a component graphic element recognition sub-module and a connection profile line recognition sub-module;

[0027] The connection profile line recognition sub-module is used to receive the coordinate position information of the connection profile line and construct the associated matrix information representing the connection relationship between the profile connection lines;

[0028] The component graphic element recognition sub-module receives the profile connection line association matrix information sent by the connection profile line recognition sub-module, and constructs a profile connection line graphic element association matrix representing the connection relationship between the profile connection line and the component graphic element in combination with the coordinate position information of the component graphic element.

[0029] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are as follows: obtaining an original format building image file through the drawing acquisition module; recognizing component graphic elements and connection profile lines in the building image file through the recognition module to obtain recognition information; correcting the recognition information through the correction module and outputting the corrected information; and the output module outputs a building image topological relationship matrix file according to the corrected information. It can improve the efficiency of automatic recognition and conversion of the topological relationship of building drawings and improve the drawing and maintenance efficiency of automated operation and maintenance personnel. Description of the Drawings

[0030] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required in the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0031] Figure 1 It is a schematic structural diagram of an automatic intelligent recognition system for building construction drawings. Detailed Embodiments

[0032] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Usually, the components of the embodiments of the present invention described and illustrated herein can be arranged and designed in various different configurations.

[0033] Accordingly, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0034] It should be noted that like reference numerals and letters denote like items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0035] In the description of the embodiments of the present invention, it should be noted that the orientation or positional relationship indicated by terms such as "upper", "inner", etc. is based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the invention product is customarily placed during use. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention.

[0036] In the description of the present invention, it should also be noted that unless otherwise clearly defined and limited, the terms "set", "install", "connect", and "couple" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a direct connection, or an indirect connection through an intermediate medium, and can also be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0037] Please refer to Figure 1 , the present invention provides an automatic intelligent recognition system for construction drawings, including:

[0038] A drawing acquisition module, which is used to acquire a building image file in the original format;

[0039] An identification module, which is connected to the drawing acquisition module. The identification module is used to receive the building image file acquired by the drawing acquisition module and identify the component graphics and connection contour lines in the building image file to obtain identification information;

[0040] A correction module, which is connected to the identification module. After receiving the identification information, the correction module corrects the identification information and outputs corrected information;

[0041] An output module, which is connected to the correction module. The output module receives the corrected information, and the output module outputs a building image topological relationship matrix file according to the corrected information.

[0042] The drawing acquisition module includes a receiving sub-module and a storage sub-module. The receiving sub-module is used to receive and acquire building image files in the original format, and the storage sub-module is used to classify and store the received building image files in the original format. This facilitates the classification management of building image files and is convenient for operation and maintenance personnel to query.

[0043] The building image files in the original format are stored in the corresponding folders according to the date and project name, which is convenient for operation and maintenance personnel to search.

[0044] The recognition module includes a reading sub-module and a processing sub-module:

[0045] The reading sub-module is used to read the building image files in the original format and set them as the first image files;

[0046] The processing sub-module is used to process the first image files to obtain the recognition information.

[0047] The processing sub-module includes a component primitive processing module and a connection contour line processing module;

[0048] The component primitive processing module uses a primitive detection model to detect and identify component primitive targets, obtains the coordinate position information of all component primitives, then marks the identified component primitives, and assigns endpoint labels to the component primitives;

[0049] The connection contour line processing module is used to hide the component primitives in the first image file to generate a second image file. The connection contour line processing module uses a connection contour line detection model to detect and identify connection contour line targets, obtains the coordinate position information of all connection contour lines, then marks the identified connection contour lines, and assigns endpoint labels to the connection contour lines. The connection contour line detection model uses a convolution module for calculation, utilizes the OpenCV function library for image processing and analysis, and covers the position coordinates of the connection contour lines in the first image file with the image background color to obtain the second image file of the connection contour lines.

[0050] The calibration information includes the connection contour line quantity information and the component primitive quantity information to prevent the missing of connection contour lines and component primitives.

[0051] The output module includes a component primitive recognition sub-module and a connection contour line recognition sub-module;

[0052] The connection contour line recognition sub-module is used to receive the coordinate position information of the connection contour lines and construct the associated matrix information representing the connection relationship between the contour connection lines;

[0053] The component graphic element recognition sub-module receives the contour connection line association matrix information sent by the connection contour line recognition sub-module, and constructs an association matrix representing the connection relationship between the contour connection line and the component graphic element in combination with the coordinate position information of the component graphic element.

[0054] Working principle: The original format of the building image file is obtained through the drawing acquisition module; the component graphic elements and connection contour lines in the building image file are recognized through the recognition module to obtain recognition information; the recognition information is corrected through the correction module and the corrected information is output; the output module outputs the building image topological relationship matrix file according to the corrected information. It can improve the efficiency of automatic recognition and conversion of the topological relationship of building drawings and improve the efficiency of drawing and maintenance of operation and maintenance personnel.

[0055] As mentioned above, only the specific preferred embodiments of the present invention are described, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, makes equivalent substitutions or changes, and should be covered within the protection scope of the present invention.

Claims

1. An automatic intelligent recognition system for building construction drawings, characterized in that: include: A drawing acquisition module, which is used to acquire architectural image files in original format; A recognition module, the recognition module is connected to the drawing acquisition module, and is used to receive the building image file acquired by the drawing acquisition module, and recognize component primitives and connection contours in the building image file to obtain recognition information; A correction module, the correction module is connected to the identification module, and the correction module corrects the identification information after receiving the identification information and outputs the correction information; An output module is connected to the correction module, the output module receives the correction information, and the output module outputs a building image topological relationship matrix file according to the correction information.

2. The automatic intelligent recognition system for building construction drawings according to claim 1 is characterized in that: The drawing acquisition module includes a receiving submodule and a storage submodule. The receiving submodule is used to receive and acquire the architectural image files in the original format, and the storage submodule is used to classify and store the received architectural image files in the original format.

3. The automatic intelligent recognition system for building construction drawings according to claim 2 is characterized in that: The original format architectural image files are stored in corresponding folders according to date and project name.

4. The automatic intelligent recognition system for building construction drawings according to claim 1 is characterized in that: The identification module includes a reading submodule and a processing submodule: The reading submodule is used to read the building image file in the original format and set it as the first image file; The processing submodule is used to process the first image file to obtain the identification information.

5. The automatic intelligent recognition system for building construction drawings according to claim 4 is characterized in that: The processing submodule includes a component primitive processing module and a connection contour processing module; The component primitive processing module detects and identifies the component primitive target using the primitive detection model, obtains the coordinate position information of all component primitives, then marks the identified component primitives, and compiles endpoint labels for the component primitives; The connection contour line processing module is used to hide the component graphics in the first image file and generate a second image file. The connection contour line processing module uses a connection contour line detection model to detect and identify the connection contour line targets, obtain the coordinate position information of all connection contour lines, then mark the identified connection contour lines, and compile endpoint numbers for the connection contour lines.

6. The automatic intelligent recognition system for building construction drawings according to claim 1 is characterized in that: The correction information includes information on the number of connection contour lines and information on the number of component primitives.

7. The automatic intelligent recognition system for building construction drawings according to claim 5 is characterized in that: The output module includes a component primitive recognition submodule and a connection contour recognition submodule; The connection contour line identification submodule is used to receive the coordinate position information of the connection contour lines and construct the correlation matrix information representing the connection relationship between the contour connection lines; The component primitive identification submodule receives the contour connection line association matrix information sent by the connection contour line identification submodule, and constructs a contour connection line primitive association matrix representing the connection relationship between the contour connection line and the component primitive in combination with the coordinate position information of the component primitive.

Images