[go: up one dir, main page]

CN116958477B - A method and system for three-dimensional modeling of building structure based on construction drawings - Google Patents

A method and system for three-dimensional modeling of building structure based on construction drawings Download PDF

Info

Publication number
CN116958477B
CN116958477B CN202310992866.4A CN202310992866A CN116958477B CN 116958477 B CN116958477 B CN 116958477B CN 202310992866 A CN202310992866 A CN 202310992866A CN 116958477 B CN116958477 B CN 116958477B
Authority
CN
China
Prior art keywords
image
building structure
information
building
data
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
Application number
CN202310992866.4A
Other languages
Chinese (zh)
Other versions
CN116958477A (en
Inventor
杨欣
吴伟伟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang Sauer Metal Materials Co ltd
Original Assignee
Zhejiang Sauer Metal Materials Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Zhejiang Sauer Metal Materials Co ltd filed Critical Zhejiang Sauer Metal Materials Co ltd
Priority to CN202310992866.4A priority Critical patent/CN116958477B/en
Publication of CN116958477A publication Critical patent/CN116958477A/en
Application granted granted Critical
Publication of CN116958477B publication Critical patent/CN116958477B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/205—Parsing
    • G06F40/216—Parsing using statistical methods
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; 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
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06N3/082—Learning methods modifying the architecture, e.g. adding, deleting or silencing nodes or connections
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/136—Segmentation; Edge detection involving thresholding
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
    • G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
    • G06V10/763—Non-hierarchical techniques, e.g. based on statistics of modelling distributions
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Computational Linguistics (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Biophysics (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Molecular Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Probability & Statistics with Applications (AREA)
  • Geometry (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Medical Informatics (AREA)
  • Databases & Information Systems (AREA)
  • Computer Graphics (AREA)
  • Processing Or Creating Images (AREA)

Abstract

The invention provides a building structure three-dimensional modeling method and system based on a construction drawing, and relates to the technical field of building models, wherein the method comprises the steps of obtaining two-dimensional line vector data of the construction drawing, and preprocessing the two-dimensional line vector data to form standardized basic data; correcting the standardized basic data according to the wavelet decomposition principle, selecting a building component object, constructing a three-dimensional geometric model of the building component based on the corrected standardized basic data, outlining the basic form of the building structure based on the remote sensing image by using a deep learning algorithm, carrying out association analysis on the three-dimensional geometric model and the basic form of the building structure, and merging overlapped or very-close vector points and vector lines to obtain the complete three-dimensional modeling of the building structure. The invention can improve the modeling efficiency of the building model, further realize the effective integration of construction drawings, facilitate the rapid establishment of the three-dimensional modeling of the building structure and manage the equipment network based on the drawings.

Description

Construction drawing-based building structure three-dimensional modeling method and system
Technical Field
The invention relates to the technical field of building models, in particular to a building structure three-dimensional modeling method and system based on a construction drawing.
Background
The building design mode comprises two-dimensional drawing design and BIM (Building Information Modeling, building information model) design, wherein the two-dimensional drawing design mode is widely adopted by design departments and construction units, specifically, the application of a two-dimensional plane design drawing is mainly adopted, and the local position expresses the design intention in a section mode.
When the Revit software is used for building information modeling at the present stage, the repeated and mechanized labor reduces the production efficiency of engineers to a certain extent, especially in some engineering projects with regular structural arrangement. The number of the engineering project drawings is hundreds to thousands of drawings, the number of the engineering project drawings is tens to tens, the volume of the drawings is large, the information contained in the building drawings cannot be fully utilized in the process of identifying the building drawings in the prior art, the identification objects are too few, the details of the building drawings are not identified, the identification precision of the building objects is low, the details of the building are difficult to display, the precision of a generated three-dimensional model of the building is not high, when the building is multi-layer, the structures of each floor have differences and similarities, and when the building is modeled in the prior art, the similar parts of each floor are not subjected to pre-optimization processing, so that the data volume required to be processed in modeling is large, and the modeling efficiency of the building is not high.
Disclosure of Invention
The invention aims to provide a building structure three-dimensional modeling method and system based on a construction drawing so as to solve the problems. In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
in a first aspect, the present application provides a three-dimensional modeling method for a building structure based on a construction drawing, including:
Two-dimensional line vector data of a building construction drawing are obtained and preprocessed to form standardized basic data, wherein the standardized basic data comprise geometric information and non-geometric information of all components;
correcting the standardized basic data according to the wavelet decomposition principle, selecting a building component object, and constructing a three-dimensional geometric model of the building component based on the corrected standardized basic data;
the basic form of the building structure is outlined by utilizing a deep learning algorithm based on the remote sensing image, wherein the basic form comprises the position, the size and the azimuth of the building structure;
And carrying out association analysis on the three-dimensional geometric model and the basic form of the building structure, merging overlapped or closely-spaced vector points and vector lines, and integrating according to the actual geographic space position information to obtain the three-dimensional modeling of the complete building structure.
Preferably, the two-dimensional line vector data of the building construction drawing is obtained and preprocessed to form standardized basic data, wherein the standardized basic data comprises geometric information and non-geometric information of all components, and the standardized basic data comprises:
the method comprises the steps of obtaining a first image in a building construction drawing, and processing the first image based on a threshold segmentation algorithm, wherein the calculation formula is as follows:
When the Gray value of a certain pixel point is Gray (i, j) which is greater than or equal to the threshold value T, the Gray value of the pixel point Out (i, j) corresponding to the output image is set to 255, namely white;
The method comprises the steps of carrying out Gaussian filtering denoising treatment on a processed first image to obtain a denoised second image, carrying out feature extraction on the second image to obtain word frequency feature information of a building construction drawing, and recording the word frequency feature information as standardized basic data, wherein the method comprises the steps of adding category screening conditions according to geometric information and non-geometric information of components, screening out components belonging to the same category from all the components, and dividing all the components into beams, plates, columns and walls by adding different category screening conditions.
Preferably, the feature extraction is performed on the second image to obtain word frequency feature information of the building construction drawing, where the feature extraction includes:
Extracting scale-invariant features of all types of images in a second image by using a scale-invariant feature conversion extraction algorithm, and taking the scale-invariant features as visual vocabulary vectors, wherein the second image comprises a wall graph, a door and window graph, a column graph, a stair graph, a roof graph and a plate graph;
combining words with similar word senses or repeated word senses of the extracted visual word vectors by using a K-Means clustering algorithm to construct a set containing main standardized basic words;
Performing image feature quantization on the second image based on a set containing main standardized basic words, wherein each image in the second image is replaced by the standardized basic words in the set through the visual words extracted by the scale-invariant feature extraction algorithm;
and counting the occurrence frequency of the main standardized basic vocabulary in the second image, and expressing the second image as a K-dimension value vector, namely word frequency characteristic information of the building construction drawing.
Preferably, the building structure basic form is outlined by using a deep learning algorithm based on the remote sensing image, wherein the basic form comprises the position, the size and the azimuth of the building structure, and the method comprises the following steps:
A first control command is sent, wherein the first control command is a command for controlling the unmanned aerial vehicle to detect building information, and the unmanned aerial vehicle is provided with a camera system, a ranging system and a GPS positioning system;
Receiving image data returned by the unmanned aerial vehicle, wherein the image data comprises video information which is acquired by a camera system and contains ground building structure feature information and the geographic position of a building structure where the unmanned aerial vehicle is located in the detection process and is determined by a GPS positioning system;
intercepting a remote sensing image of a building structure from image data and establishing a first training set, wherein the first training set comprises contour information, style information and size information of the building structure, and marking by using a marking tool;
And inputting the first training set into a target detection network for repeated iterative computation to obtain an optimal building structure model, namely the basic form of the building structure.
Preferably, the correlation analysis is performed on the three-dimensional geometric model and the basic form of the building structure, which comprises the following steps:
Determining a reference sequence of the three-dimensional geometric model and marking the reference sequence as a parent sequence;
Carrying out grey correlation analysis on the data information in the basic form of the three-dimensional geometric model and the building structure, wherein the grey correlation analysis comprises carrying out dimensionless treatment on the data information in the basic form of the building structure, wherein the dimensionless treatment comprises carrying out averaging and initialization to obtain first data information after the dimensionless tempering treatment;
Calculating a gray correlation coefficient value between the parent sequence and the first data information based on the first data information;
and sorting the association degrees according to the association degrees between the three-dimensional geometric model obtained by calculating the gray association coefficient values and the data information in the basic form of the building structure, and extracting if the value superposition effect is better when the association degrees are larger.
In a second aspect, the present application further provides a three-dimensional modeling system for a building structure based on a construction drawing, including:
The acquisition module is used for acquiring two-dimensional line vector data of a building construction drawing and preprocessing the two-dimensional line vector data to form standardized basic data, wherein the standardized basic data comprises geometric information and non-geometric information of all components;
The construction module is used for correcting the standardized basic data according to the wavelet decomposition principle, selecting a building component object and constructing a three-dimensional geometric model of the building component based on the corrected standardized basic data;
the outlining module is used for outlining the basic form of the building structure based on the remote sensing image by utilizing a deep learning algorithm, wherein the basic form comprises the position, the size and the azimuth of the building structure;
and the integration module is used for carrying out association analysis on the three-dimensional geometric model and the basic form of the building structure, merging overlapped or closely-spaced vector points and vector lines, and integrating according to the actual geographic space position information to obtain the complete three-dimensional modeling of the building structure.
In a third aspect, the present application further provides a three-dimensional modeling apparatus for a building structure based on a construction drawing, including:
a memory for storing a computer program;
And the processor is used for realizing the three-dimensional modeling method of the building structure based on the construction drawing when executing the computer program.
In a fourth aspect, the present application further provides a readable storage medium, on which a computer program is stored, the computer program implementing the steps of the building structure three-dimensional modeling method based on a construction drawing, when executed by a processor.
The beneficial effects of the invention are as follows:
The method can improve the modeling efficiency of the building model, further realize the effective integration of the construction drawing, facilitate the rapid establishment of the three-dimensional modeling of the building structure and manage the equipment network based on the drawing, and pretreat the construction drawing to generate the three-dimensional model of the building with high precision and high modeling efficiency.
According to the invention, the image segmentation is carried out on the places irrelevant to the identification of the first image in the construction drawing, so that the first image is processed later, the influence of some irrelevant images on the first image is avoided, and the optimal segmentation effect is achieved by continuously adjusting the threshold value, so that the drawing is clearer.
The invention carries out Gaussian filtering noise reduction operation on the construction drawing so as to eliminate the influence of image noise. In addition, the image can enhance the edge characteristics after being subjected to Gaussian filtering treatment, and the subsequent segmentation treatment is facilitated.
The invention can describe and extract local features in the construction drawing, namely the second image through a scale-invariant feature conversion algorithm, has certain invariance to image translation, rotation, scaling and the like, and also has certain stability to brightness transformation, affine transformation and image noise, and the scale-invariant feature conversion algorithm can be used for carrying out feature vector multi-quantization and rapid extraction on the construction drawing, can meet the real-time requirement and is convenient to fuse with other feature vectors.
The invention adopts wavelet decomposition principle to represent the building structure vector data, corrects errors, lays a solid foundation for the three-dimensional modeling of the subsequent building structure, reduces the errors of the building structure data, and provides a basis for the subsequent data simplification.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the embodiments of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a three-dimensional modeling method for a building structure based on a construction drawing according to an embodiment of the invention;
FIG. 2 is a schematic structural diagram of a three-dimensional modeling system for a building structure based on a construction drawing according to an embodiment of the present invention;
Fig. 3 is a schematic structural diagram of a three-dimensional modeling device for a building structure based on a construction drawing according to an embodiment of the present invention.
In the figure, 701, an acquisition module, 7011, an acquisition unit, 7012, a processing unit, 70121, an extraction unit, 70122, a merging unit, 70123, a quantization unit, 70124, a statistics unit, 702, a construction module, 703, a outlining module, 7031, a sending unit, 7032, a receiving unit, 7033, a building unit, 7034, a first calculation unit, 704, an integration module, 7041, a determination unit, 7042, an analysis unit, 7043, a second calculation unit, 7044, a sequencing unit, 800, a building structure three-dimensional modeling device based on a construction drawing, 801, a processor, 802, a memory, 803, a multimedia component, 804, an I/O interface, 805, and a communication component.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. 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.
It should be noted that like reference numerals and letters refer to like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures. Meanwhile, in the description of the present invention, the terms "first", "second", and the like are used only to distinguish the description, and are not to be construed as indicating or implying relative importance.
Example 1:
the embodiment provides a building structure three-dimensional modeling method based on a construction drawing.
Referring to fig. 1, the method is shown to include step S100, step S200, step S300, and step S400.
S100, two-dimensional line vector data of a building construction drawing are obtained and preprocessed to form standardized basic data, wherein the standardized basic data comprise geometric information and non-geometric information of all components.
It will be appreciated that the present step S100 includes S101 and S102, where:
s101, acquiring a first image in a building construction drawing, and processing the first image based on a threshold segmentation algorithm, wherein the calculation formula is as follows:
When the Gray value of a certain pixel point is Gray (i, j) which is greater than or equal to the threshold value T, the Gray value of the pixel point Out (i, j) corresponding to the output image is set to 255, namely white;
It should be noted that, some of the drawings are drawings and are backgrounds irrelevant to the establishment of the three-dimensional model, so that image segmentation is needed to be performed on places irrelevant to the identification of the first image in the construction drawing, so that the first image is processed later, and the influence of some irrelevant images on the first image is avoided. The optimal segmentation effect is achieved by continuously adjusting the threshold value, so that the drawing is clearer.
S102, performing Gaussian filtering denoising treatment on the processed first image to obtain a denoised second image, performing feature extraction on the second image to obtain word frequency feature information of a building construction drawing, and recording the word frequency feature information as standardized basic data, wherein the method comprises the steps of adding category screening conditions according to geometric information and non-geometric information of components, screening out components belonging to the same category from all the components, and dividing all the components into beams, plates, columns and walls by adding different category screening conditions.
The noise reduction operation is performed using gaussian filtering to eliminate the influence of image noise. In addition, the image can enhance the edge characteristics after being subjected to Gaussian filtering treatment, and the subsequent segmentation treatment is facilitated. The method comprises the steps of carrying out additive type screening according to geometric information and non-geometric information of the components, wherein the additive type screening comprises screening engineering quantity computing systems of building envelope structures, concrete columns, beams, walls and plates, and enabling participating parties to quickly and accurately acquire engineering quantity and manufacturing cost data in an engineering implementation stage, so that fine control of engineering cost is possible.
In step S102, feature extraction is performed on the second image to obtain word frequency feature information of the building construction drawing, where the feature information includes S1021, S1022, S1023, and S1024, where:
S1021, extracting scale-invariant features of all types of images in a second image by using a scale-invariant feature conversion extraction algorithm, and taking the scale-invariant features as visual vocabulary vectors, wherein the second image comprises a wall graph, a door and window graph, a column graph, a stair graph, a roof graph and a board graph;
It can be understood that the scale-invariant feature transformation algorithm can describe and extract local features in the construction drawing, namely the second image, has certain invariance to image translation, rotation, scaling and the like, and also has certain stability to brightness transformation, affine transformation and image noise, and the scale-invariant feature transformation algorithm can be used for carrying out feature vector multi-quantization and rapid extraction on the construction drawing, can meet the real-time requirement and is convenient to fuse with other feature vectors.
S1022, merging words with similar word senses or repeated words of the extracted visual word vectors by using a K-Means clustering algorithm to construct a set containing main standardized basic words;
it should be noted that, because the feature points extracted from the images of each construction drawing by the scale-invariant feature transformation algorithm are different, the images are extracted by the word bag model extraction algorithm, so that the extracted image features, that is, the repeated vocabulary or feature value vector dimensions are the same, are ensured.
S1023, carrying out image feature quantization on the second image based on a set containing main standardized basic words, wherein each image in the second image is replaced by the standardized basic words in the set through the visual words extracted by the scale-invariant feature extraction algorithm;
S1024, counting the occurrence frequency of the main standardized basic vocabulary in the second image, and representing the second image as a K-dimension value vector, namely word frequency characteristic information of the building construction drawing.
It should be noted that, the K-means clustering algorithm uses K as a parameter, divides the second image set into K categories, and uses the minimum distance from each sample to the center of the category, that is, the highest similarity, then the highest similarity is the most frequently occurring, and the second image set is sequentially arranged.
S200, correcting the standardized basic data according to a wavelet decomposition principle, selecting a building component object, and constructing a three-dimensional geometric model of the building component based on the corrected standardized basic data.
It can be understood that the wavelet decomposition principle is adopted to represent the building structure vector data in the step, so that errors are corrected, a solid foundation is laid for three-dimensional modeling of the subsequent building structure, and meanwhile, errors of the building structure data are reduced, and a basis is provided for the subsequent data simplification.
S300, outlining basic forms of the building structure based on the remote sensing image by using a deep learning algorithm, wherein the basic forms comprise positions, sizes and orientations of the building structure.
It will be appreciated that the present step S300 includes steps S301, S302, S303 and S304, wherein:
S301, a first control command is sent, wherein the first control command is a command for controlling an unmanned aerial vehicle to detect building information, and the unmanned aerial vehicle is provided with a camera system, a ranging system and a GPS positioning system;
s302, receiving image data returned by the unmanned aerial vehicle, wherein the image data comprises video information which is acquired by a camera system and contains ground building structure feature information and the geographic position of a building structure where the unmanned aerial vehicle is located in the detection process and is determined by a GPS positioning system;
S303, capturing a remote sensing image of the building structure from the image data and establishing a first training set, wherein the first training set comprises contour information, style information and size information of the building structure, and marking by using a marking tool;
s304, inputting the first training set into a target detection network for repeated iterative computation to obtain an optimal building structure model, namely a basic form of the building structure.
It should be noted that, the Mask R-CNN network architecture in the target detection network is adopted, the processed image data is input into the preset neural network for rolling and pooling, each pixel image in the first training set is processed to obtain the set number of interested areas, then the building mechanism and the background are divided and the frame is optimized to obtain the optimized interested areas, and then the optimized interested areas are classified and regressed through the convolution layer to generate the optimal building structure model.
S400, carrying out association analysis on the three-dimensional geometric model and the basic form of the building structure, merging overlapped or closely-spaced vector points and vector lines, and integrating according to the actual geographic space position information to obtain the complete three-dimensional modeling of the building structure.
It will be appreciated that the present step S400 includes steps S401, S402, S403 and S404, wherein:
s401, determining a reference sequence of the three-dimensional geometric model to be marked as a parent sequence;
S402, carrying out gray correlation analysis on the data information in the three-dimensional geometric model and the basic form of the building structure, wherein the gray correlation analysis comprises carrying out dimensionless treatment on the data information in the basic form of the building structure, wherein the dimensionless treatment comprises carrying out averaging and initialization to obtain first data information after the dimensionless tempering treatment;
S403, calculating a gray correlation coefficient value between the parent sequence and the first data information based on the first data information;
s404, sorting the association degrees according to the association degrees between the three-dimensional geometric model obtained by calculation of the gray association coefficient values and the data information in the basic form of the building structure, and extracting if the value overlapping effect is better when the association degrees are larger.
It can be understood that the above steps are to calculate the association degree between the three-dimensional geometric model and the data information in the basic form of the building structure, further determine the association relation between the three-dimensional geometric model and the basic form of the building structure, research the association degree between the data information in the basic form of the three-dimensional geometric model and the basic form of the building structure (the association degree between the parent sequence and the characteristic sequence), measure the association degree between the data through the association degree (i.e. the association degree), further make an auxiliary judgment decision, judge the association degree between the three-dimensional geometric model and the data information in the basic form of the building structure, sort the evaluation objects according to the gray association degree, establish the association order of the evaluation objects, the higher the association degree is, the better the evaluation result is, the better the superposition effect is, the overlapped or closely-spaced vector points and vector lines are combined, and comprehensively integrate according to the actual geographic space position information, thus obtaining the three-dimensional modeling of the complete building structure. The method has the advantages of less calculated amount, neglecting the limitation of subjective ideas, being applicable to irregular models or data in forms, improving the modeling efficiency of building models, further realizing effective integration of construction drawings, facilitating rapid establishment of three-dimensional modeling of building structures, and managing equipment networks based on the drawings.
Example 2:
As shown in fig. 2, the present embodiment provides a three-dimensional modeling system for a building structure based on a construction drawing, and the system described with reference to fig. 2 includes an acquisition module 701, a construction module 702, a outlining module 703, and an integration module 704, where:
The acquisition module 701 is used for acquiring two-dimensional line vector data of a building construction drawing and preprocessing the two-dimensional line vector data to form standardized basic data, wherein the standardized basic data comprises geometric information and non-geometric information of all components;
The construction module 702 is used for correcting the standardized basic data according to the wavelet decomposition principle, selecting a building component object, and constructing a three-dimensional geometric model of the building component based on the corrected standardized basic data;
The outlining module 703 is used for outlining the basic form of the building structure based on the remote sensing image by using a deep learning algorithm, wherein the basic form comprises the position, the size and the azimuth of the building structure;
And the integration module 704 is used for carrying out association analysis on the three-dimensional geometric model and the basic form of the building structure, merging overlapped or closely-spaced vector points and vector lines, and integrating according to the actual geographic space position information to obtain the three-dimensional modeling of the complete building structure.
Specifically, the acquisition module 701 includes an acquisition unit 7011 and a processing unit 7012:
The acquiring unit 7011 is configured to acquire a first image in a building construction drawing, process the first image based on a threshold segmentation algorithm, and calculate the following formula:
When the Gray value of a certain pixel point is Gray (i, j) which is greater than or equal to the threshold value T, the Gray value of the pixel point Out (i, j) corresponding to the output image is set to 255, namely white;
As shown in fig. 2, the present embodiment of the present invention is a processing unit 7012, configured to perform gaussian filtering denoising processing on a processed first image to obtain a denoised second image, perform feature extraction on the second image to obtain word frequency feature information of a building construction drawing, record the word frequency feature information as standardized basic data, wherein the standard basic data includes adding a class screening condition according to geometric information and non-geometric information of a component, and screen out components belonging to the same class from all the components, and by adding different class screening conditions, all the components can be classified into beams, plates, columns and walls.
Specifically, the processing unit 7012 includes an extracting unit 70121, a merging unit 70122, a quantizing unit 70123, and a statistics unit 70124, where:
The extraction unit 70121 is used for extracting the scale-invariant features of all the class images in the second image by using a scale-invariant feature conversion extraction algorithm and taking the scale-invariant features as visual vocabulary vectors, wherein the second image comprises a wall graph, a door and window graph, a column graph, a stair graph, a roof graph and a plate graph;
The merging unit 70122 is used for merging words with similar word senses or repeated words of the extracted visual word vectors by using a K-Means clustering algorithm to construct a set containing main standardized basic words;
The quantization unit 70123 is configured to perform image feature quantization on the second image based on a set including a main standardized basic vocabulary, where each image in the second image is replaced by the standardized basic vocabulary in the set by using the visual vocabulary extracted by the scale-invariant feature extraction algorithm;
The statistics unit 70124 is used for counting the occurrence frequency of the main standardized basic vocabulary in the second image and representing the second image as a K-dimension value vector, namely word frequency characteristic information of the building construction drawing.
Specifically, the outlining module 703 includes a transmitting unit 7031, a receiving unit 7032, a establishing unit 7033, and a first calculating unit 7034, wherein:
The transmitting unit 7031 is used for transmitting a first control command, wherein the first control command is a command for controlling the unmanned aerial vehicle to detect building information, and the unmanned aerial vehicle is provided with a camera system, a ranging system and a GPS positioning system;
The receiving unit 7032 is used for receiving image data returned by the unmanned aerial vehicle, wherein the image data comprises video information comprising ground building structure characteristic information acquired by a camera system and the geographic position of a building structure where the unmanned aerial vehicle is positioned in the detection process, which is determined by a GPS positioning system;
The building unit 7033 is used for intercepting remote sensing images of the building structure from the image data and building a first training set, wherein the first training set comprises contour information, style information and size information of the building structure and is marked by a marking tool;
The first calculating unit 7034 is configured to input the first training set into the target detection network to perform multiple iterative computations, so as to obtain an optimal building structure model, i.e. a basic form of the building structure.
Specifically, the integrating unit includes a determining unit 7041, an analyzing unit 7042, a second calculating unit 7043, and a sorting unit 7044, wherein:
A determining unit 7041 for determining a reference sequence of the three-dimensional geometric model to be referred to as a parent sequence;
The analysis unit 7042 is used for carrying out gray correlation analysis on the three-dimensional geometric model and the data information in the basic form of the building structure, wherein the gray correlation analysis comprises carrying out dimensionless treatment on the data information in the basic form of the building structure, and the dimensionless treatment comprises carrying out averaging and initialization to obtain first data information after the dimensionless tempering treatment;
A second calculation unit 7043 for calculating a gray correlation coefficient value between the parent sequence and the first data information based on the first data information;
The sorting unit 7044 is used for sorting the association degree according to the association degree between the three-dimensional geometric model obtained by calculation of the gray association coefficient value and the data information in the basic form of the building structure, and extracting the larger the association degree is, the better the value overlapping effect is.
It should be noted that, regarding the system in the above embodiment, the specific manner in which the respective modules perform the operations has been described in detail in the embodiment regarding the method, and will not be described in detail herein.
Example 3:
Corresponding to the above method embodiment, in this embodiment, a three-dimensional modeling apparatus for a building structure based on a construction drawing is further provided, and a three-dimensional modeling apparatus for a building structure based on a construction drawing described below and a three-dimensional modeling method for a building structure based on a construction drawing described above may be referred to correspondingly with each other.
Fig. 3 is a block diagram of a three-dimensional modeling apparatus 800 for a building structure based on a construction drawing, according to an exemplary embodiment. As shown in fig. 3, the construction drawing-based three-dimensional modeling apparatus 800 for a building structure includes a processor 801 and a memory 802. The construction drawing based building structure three-dimensional modeling apparatus 800 further includes one or more of a multimedia component 803, an i/O interface 804, and a communication component 805.
The processor 801 is configured to control the overall operation of the three-dimensional modeling apparatus 800 for building structures based on construction drawings, so as to complete all or part of the steps in the three-dimensional modeling method for building structures based on construction drawings. The memory 802 is used to store various types of data to support operation of the construction drawing-based building structure three-dimensional modeling apparatus 800, which may include, for example, instructions for any application or method operating on the construction drawing-based building structure three-dimensional modeling apparatus 800, as well as application-related data, such as contact data, messages, pictures, audio, video, and so forth. The Memory 802 may be implemented by any type or combination of volatile or non-volatile Memory devices, such as static random access Memory (Static Random Access Memory, SRAM for short), electrically erasable programmable Read-Only Memory (ELECTRICALLY ERASABLE PROGRAMMABLE READ-Only Memory, EEPROM for short), erasable programmable Read-Only Memory (Erasable Programmable Read-Only Memory, EPROM for short), programmable Read-Only Memory (Programmable Read-Only Memory, PROM for short), read-Only Memory (ROM for short), magnetic Memory, flash Memory, magnetic disk, or optical disk. The multimedia component 803 may include a screen and an audio component. Wherein the screen may be, for example, a touch screen, the audio component being for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 802 or transmitted through the communication component 805. The audio assembly further comprises at least one speaker for outputting audio signals. The I/O interface 804 provides an interface between the processor 801 and other interface modules, which may be a keyboard, mouse, or buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 805 is configured to perform wired or wireless communication between the three-dimensional modeling apparatus 800 for a building structure based on a construction drawing and other apparatuses. Wireless communication, such as Wi-Fi, bluetooth, near field communication (Near FieldCommunication, NFC for short), 2G, 3G, or 4G, or a combination of one or more thereof, and thus the corresponding communication component 805 may include a Wi-Fi module, a bluetooth module, or an NFC module.
In an exemplary embodiment, the construction drawing based architecture three-dimensional modeling apparatus 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), digital signal processors (DIGITALSIGNAL PROCESSOR DSPs), digital signal processing devices (DIGITAL SIGNAL Processing Device DSPDs), programmable logic devices (Programmable Logic Device PLDs), field programmable gate arrays (Field Programmable GATE ARRAY FPGAs), controllers, microcontrollers, microprocessors, or other electronic components for performing the construction drawing based architecture three-dimensional modeling method described above.
In another exemplary embodiment, a computer readable storage medium is also provided, comprising program instructions which, when executed by a processor, implement the steps of the construction drawing based building structure three-dimensional modeling method described above. For example, the computer readable storage medium may be the memory 802 described above including program instructions executable by the processor 801 of the construction drawing based three-dimensional modeling apparatus 800 to perform the construction drawing based three-dimensional modeling method of a construction drawing based three-dimensional modeling method described above.
Example 4:
Corresponding to the above method embodiment, a readable storage medium is further provided in this embodiment, and a readable storage medium described below and a building structure three-dimensional modeling method based on a construction drawing described above may be referred to correspondingly.
The readable storage medium stores a computer program which, when executed by a processor, implements the steps of the building structure three-dimensional modeling method based on the construction drawing of the method embodiment.
The readable storage medium may be a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, which may store various program codes.
In conclusion, the method can improve the modeling efficiency of the building model, further realize effective integration of the construction drawing, facilitate rapid establishment of three-dimensional modeling of the building structure and manage equipment networks based on the drawing, pre-process the construction drawing, generate a three-dimensional model of the building with high precision and high modeling efficiency, and use Gaussian filtering noise reduction operation on the construction drawing to eliminate the influence of image noise. In addition, the image can strengthen edge characteristics after Gaussian filtering treatment, is beneficial to subsequent segmentation treatment, has certain invariance to image translation, rotation, scaling and the like in a construction drawing through a scale-invariant characteristic conversion algorithm, also has certain stability to brightness transformation, affine transformation and image noise, can meet the requirement of instantaneity, is convenient to fuse with other characteristic vectors, lays a solid foundation for three-dimensional modeling of a subsequent building structure, reduces errors of building structure data, and provides a basis for subsequent data simplification.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.

Claims (6)

1.一种基于施工图纸的建筑结构三维建模方法，其特征在于，包括：1. A method for three-dimensional modeling of a building structure based on construction drawings, characterized by comprising: 获取建筑施工图纸的二维线矢量数据，并对其进行预处理，形成标准化基础数据，其中标准化基础数据包括所有构件的几何信息和非几何信息；Obtaining two-dimensional line vector data of building construction drawings and preprocessing them to form standardized basic data, wherein the standardized basic data includes geometric information and non-geometric information of all components; 根据小波分解原理将标准化基础数据进行修正，选取建筑构件对象，基于修正后的标准化基础数据，构造建筑构件的三维几何模型；The standardized basic data is modified according to the wavelet decomposition principle, the building component objects are selected, and the three-dimensional geometric model of the building component is constructed based on the modified standardized basic data; 基于遥感影像利用深度学习算法勾勒建筑结构基本形态，其中包括建筑结构的位置、尺寸及方位；Using deep learning algorithms based on remote sensing images to outline the basic form of building structures, including the location, size and orientation of the building structures; 针对三维几何模型和建筑结构基本形态进行关联分析，对重叠或者相距很近的矢量点、矢量线进行合并，并按照实际地理空间位置信息进行整合，得到完整的建筑结构的三维建模；Conduct correlation analysis on the 3D geometric model and the basic form of the building structure, merge the overlapping or closely spaced vector points and vector lines, and integrate them according to the actual geographic space location information to obtain a complete 3D model of the building structure; 其中，所述基于遥感影像利用深度学习算法勾勒建筑结构基本形态，其中包括建筑结构的位置、尺寸及方位，其中包括：The method of using deep learning algorithms based on remote sensing images to outline the basic form of the building structure, including the location, size and orientation of the building structure, includes: 发送第一控制命令，其中第一控制命令为控制无人机进行建筑信息探测的命令，所述无人机带有摄像系统、测距系统和GPS定位系统；Sending a first control command, wherein the first control command is a command for controlling a drone to detect building information, wherein the drone is equipped with a camera system, a distance measurement system, and a GPS positioning system; 接收无人机回传的影像数据，其中影像数据包括摄像系统采集到的包含地面建筑结构特征信息的视频信息以及GPS定位系统确定的无人机在探测过程中所在的建筑结构的地理位置；Receive image data sent back by the drone, where the image data includes video information containing ground building structure feature information collected by the camera system and the geographical location of the building structure where the drone is located during the detection process determined by the GPS positioning system; 从影像数据中截取建筑结构遥感影像并建立第一训练集，其中第一训练集包括建筑结构的轮廓信息、样式信息和尺寸信息，并利用标注工具进行标注；Extracting remote sensing images of building structures from image data and establishing a first training set, wherein the first training set includes contour information, style information and size information of the building structures, and annotating them using an annotation tool; 将第一训练集输入至目标检测网络中进行多次迭代计算，得到最优建筑结构模型，即建筑结构基本形态；The first training set is input into the target detection network for multiple iterative calculations to obtain the optimal building structure model, that is, the basic form of the building structure; 其中，采用目标检测网络中的Mask R-CNN网络架构，将处理好的影像数据输入至预设的神经网络进行卷积和池化，对第一训练集中的每个像素图像进行处理，得到设定感兴趣的区域的数量，将建筑物机构和背景分割以及边框优化，得到优化后的感兴趣区域，通过卷积层进行分类、回归处理，生成最优建筑结构模型；The Mask R-CNN network architecture in the target detection network is used to input the processed image data into the preset neural network for convolution and pooling. Each pixel image in the first training set is processed to obtain the number of regions of interest, segment the building structure and the background, and optimize the border to obtain the optimized region of interest. The convolution layer is used for classification and regression processing to generate the optimal building structure model. 其中，所述针对三维几何模型和建筑结构基本形态进行关联分析，其中包括：The correlation analysis between the three-dimensional geometric model and the basic form of the building structure includes: 确定三维几何模型的参考序列记作母序列；The reference sequence for determining the three-dimensional geometric model is recorded as the parent sequence; 将三维几何模型和建筑结构基本形态中的数据信息进行灰色关联分析，其中包括对建筑结构基本形态中的数据信息进行无量纲化处理，其中无量纲化处理包括进行均值化和初值化，得到无量钢化处理后的第一数据信息；Performing grey correlation analysis on the data information of the three-dimensional geometric model and the basic form of the building structure, including dimensionless processing of the data information of the basic form of the building structure, wherein the dimensionless processing includes averaging and initialization, and obtaining first data information after dimensionless tempering processing; 基于第一数据信息，计算母序列和第一数据信息之间的灰色关联系数值；Based on the first data information, calculating a grey correlation coefficient value between the parent sequence and the first data information; 根据灰色关联系数值计算得到的三维几何模型和建筑结构基本形态中的数据信息之间的关联度，对关联度进行排序，关联度越大的值重合效果越好，则进行提取；According to the correlation between the three-dimensional geometric model and the data information in the basic form of the building structure calculated by the grey correlation value, the correlation is sorted, and the value with a larger correlation has a better coincidence effect, and then it is extracted; 其中，通过计算三维几何模型和建筑结构基本形态中的数据信息之间的关联度，进而确定两者之间的联系关系，进而研究三维几何模型和建筑结构基本形态中的数据信息的关联性大小，并通过关联度进行度量数据之间的关联程度，从而进行辅助判断决策；判断三维几何模型和建筑结构基本形态中的数据信息之间的关联性，根据灰色关联度大小，对评价对象进行排序，建立评价对象的关联序列，关联度越大，其评价结果越好，评价结果越好，重合效果越好，则对重叠或者重合或者相距很近的矢量点、矢量线进行合并，并按照实际地理空间位置信息进行综合整合，得到完整的建筑结构的三维建模。Among them, by calculating the correlation between the data information in the three-dimensional geometric model and the basic form of the building structure, the connection between the two is determined, and then the correlation between the data information in the three-dimensional geometric model and the basic form of the building structure is studied, and the degree of correlation between the data is measured by the correlation degree, so as to assist in decision-making; the correlation between the data information in the three-dimensional geometric model and the basic form of the building structure is judged, and the evaluation objects are sorted according to the size of the gray correlation degree, and a correlation sequence of the evaluation objects is established. The greater the correlation degree, the better the evaluation result, the better the evaluation result, and the better the coincidence effect. The overlapping or coincident or very close vector points and vector lines are merged, and comprehensive integration is carried out according to the actual geographic space location information to obtain a complete three-dimensional modeling of the building structure. 2.根据权利要求1所述的基于施工图纸的建筑结构三维建模方法，其特征在于，所述获取建筑施工图纸的二维线矢量数据，并对其进行预处理，形成标准化基础数据，其中标准化基础数据包括所有构件的几何信息和非几何信息，其中包括：2. The method for three-dimensional modeling of building structures based on construction drawings according to claim 1 is characterized in that the two-dimensional line vector data of the building construction drawings is obtained and preprocessed to form standardized basic data, wherein the standardized basic data includes geometric information and non-geometric information of all components, including: 获取建筑施工图纸中的第一图像，基于阈值分割算法对第一图像进行处理，其计算公式如下： 式中，输入图像某个像素点的灰度值为Gray（i，j）小于阈值T时为背景，其输出图像所对应像素点Out（i，j）的灰度值则被设置为0，即黑色；当某个像素点的灰度值为Gray（i，j）大于或者等于阈值T时为背景，其输出图像所对应像素点Out（i，j）的灰度值则被设置为255，即白色；The first image in the building construction drawing is obtained, and the first image is processed based on the threshold segmentation algorithm, and the calculation formula is as follows: In the formula, when the gray value of a pixel point in the input image is Gray (i, j) less than the threshold value T, it is the background, and the gray value of the corresponding pixel point Out (i, j) in the output image is set to 0, that is, black; when the gray value of a pixel point is Gray (i, j) greater than or equal to the threshold value T, it is the background, and the gray value of the corresponding pixel point Out (i, j) in the output image is set to 255, that is, white; 将处理后的第一图像进行高斯滤波去噪处理，得到去噪后的第二图像，对第二图像进行特征提取，得到建筑施工图纸的词频特征信息，将词频特征信息记作标准化基础数据，其中包括根据构件的几何信息和非几何信息添加类别筛选条件，从所有的所述构件中筛选出属于同一类别的构件；通过添加不同的类别筛选条件，可以将所有构件可以划分为梁类、板类、柱类和墙类。The processed first image is subjected to Gaussian filtering denoising to obtain a denoised second image, and feature extraction is performed on the second image to obtain word frequency feature information of the building construction drawing, and the word frequency feature information is recorded as standardized basic data, which includes adding category filtering conditions according to the geometric information and non-geometric information of the components, and filtering out components belonging to the same category from all the components; by adding different category filtering conditions, all components can be divided into beams, plates, columns and walls. 3.根据权利要求2所述的基于施工图纸的建筑结构三维建模方法，其特征在于，所述对第二图像进行特征提取，得到建筑施工图纸的词频特征信息，其中包括：3. The method for three-dimensional modeling of a building structure based on construction drawings according to claim 2 is characterized in that the feature extraction of the second image is performed to obtain word frequency feature information of the building construction drawings, which includes: 利用尺度不变特征转换提取算法，提取第二图像中所有类别图像的尺度不变特征并当作视觉词汇向量，其中第二图像包括关于墙图、门窗图、柱图、楼梯图、屋顶图和板图；Utilizing a scale-invariant feature conversion extraction algorithm, scale-invariant features of all categories of images in a second image are extracted and used as visual vocabulary vectors, wherein the second image includes images of walls, doors and windows, columns, stairs, roofs, and boards; 利用K-Means聚类算法将提取到的视觉词汇向量的词义相近或者重复出现的词汇进行合并，构建包含主要标准化基础词汇的集合；The K-Means clustering algorithm is used to merge the words with similar meanings or repeated occurrences in the extracted visual vocabulary vectors to construct a set containing the main standardized basic words; 基于包含主要标准化基础词汇的集合对第二图像进行图像特征量化，其中第二图像中的每一张图像均通过尺度不变特征提取算法提取到的视觉词汇以集合中的标准化基础词汇替代；quantizing image features of the second image based on a set including main standardized basic words, wherein each image in the second image is replaced by a standardized basic word in the set using a visual word extracted by a scale-invariant feature extraction algorithm; 统计主要标准化基础词汇在第二图像中出现的频次，并将第二图像表示为一个K维数值向量，即建筑施工图纸的词频特征信息。The frequencies of occurrence of the main standardized basic words in the second image are counted, and the second image is represented as a K-dimensional numerical vector, namely, the word frequency feature information of the building construction drawing. 4.一种基于施工图纸的建筑结构三维建模系统，其特征在于，包括：4. A three-dimensional modeling system for building structures based on construction drawings, characterized by comprising: 获取模块：用于获取建筑施工图纸的二维线矢量数据，并对其进行预处理，形成标准化基础数据，其中标准化基础数据包括所有构件的几何信息和非几何信息；Acquisition module: used to acquire the two-dimensional line vector data of the building construction drawings and pre-process them to form standardized basic data, where the standardized basic data includes the geometric information and non-geometric information of all components; 构造模块：用于根据小波分解原理将标准化基础数据进行修正，选取建筑构件对象，基于修正后的标准化基础数据，构造建筑构件的三维几何模型；Construction module: used to modify the standardized basic data according to the wavelet decomposition principle, select the building component object, and construct the three-dimensional geometric model of the building component based on the modified standardized basic data; 勾勒模块：用于基于遥感影像利用深度学习算法勾勒建筑结构基本形态，其中包括建筑结构的位置、尺寸及方位；Outlining module: used to outline the basic form of building structures based on remote sensing images using deep learning algorithms, including the location, size and orientation of the building structures; 整合模块：用于针对三维几何模型和建筑结构基本形态进行关联分析，对重叠或者相距很近的矢量点、矢量线进行合并，并按照实际地理空间位置信息进行整合，得到完整的建筑结构的三维建模；Integration module: used to conduct correlation analysis on the 3D geometric model and the basic form of the building structure, merge the overlapping or closely spaced vector points and vector lines, and integrate them according to the actual geographic space location information to obtain a complete 3D modeling of the building structure; 所述勾勒模块，其中包括：The outline module includes: 发送单元：用于发送第一控制命令，其中第一控制命令为控制无人机进行建筑信息探测的命令，所述无人机带有摄像系统、测距系统和GPS定位系统；A sending unit: used for sending a first control command, wherein the first control command is a command for controlling a drone to detect building information, wherein the drone is provided with a camera system, a distance measurement system and a GPS positioning system; 接收单元：用于接收无人机回传的影像数据，其中影像数据包括摄像系统采集到的包含地面建筑结构特征信息的视频信息以及GPS定位系统确定的无人机在探测过程中所在的建筑结构的地理位置；Receiving unit: used to receive the image data sent back by the drone, where the image data includes the video information containing the characteristic information of the ground building structure collected by the camera system and the geographical location of the building structure where the drone is located during the detection process determined by the GPS positioning system; 建立单元：用于从影像数据中截取建筑结构遥感影像并建立第一训练集，其中第一训练集包括建筑结构的轮廓信息、样式信息和尺寸信息，并利用标注工具进行标注；Establishment unit: used for intercepting the remote sensing image of the building structure from the image data and establishing a first training set, wherein the first training set includes the outline information, style information and size information of the building structure, and annotates it using an annotation tool; 第一计算单元：用于将第一训练集输入至目标检测网络中进行多次迭代计算，得到最优建筑结构模型，即建筑结构基本形态；The first calculation unit is used to input the first training set into the target detection network for multiple iterative calculations to obtain the optimal building structure model, that is, the basic form of the building structure; 所述整合模块，其中包括：The integration module includes: 确定单元：用于确定三维几何模型的参考序列记作母序列；Determine unit: The reference sequence used to determine the three-dimensional geometric model is recorded as the parent sequence; 分析单元：用于将三维几何模型和建筑结构基本形态中的数据信息进行灰色关联分析，其中包括对建筑结构基本形态中的数据信息进行无量纲化处理，其中无量纲化处理包括进行均值化和初值化，得到无量钢化处理后的第一数据信息；Analysis unit: used for performing grey correlation analysis on the data information in the three-dimensional geometric model and the basic form of the building structure, including dimensionless processing of the data information in the basic form of the building structure, wherein the dimensionless processing includes averaging and initialization to obtain the first data information after dimensionless toughening processing; 第二计算单元：用于基于第一数据信息，计算母序列和第一数据信息之间的灰色关联系数值；A second calculation unit is used to calculate a grey correlation coefficient value between the mother sequence and the first data information based on the first data information; 排序单元：用于根据灰色关联系数值计算得到的三维几何模型和建筑结构基本形态中的数据信息之间的关联度，对关联度进行排序，关联度越大的值重合效果越好，则进行提取；Sorting unit: used to sort the correlation between the three-dimensional geometric model and the data information in the basic form of the building structure calculated according to the gray correlation value, and the larger the correlation, the better the overlap effect, and then the value is extracted; 其中，通过计算三维几何模型和建筑结构基本形态中的数据信息之间的关联度，进而确定两者之间的联系关系，进而研究三维几何模型和建筑结构基本形态中的数据信息的关联性大小，并通过关联度进行度量数据之间的关联程度，从而进行辅助判断决策；判断三维几何模型和建筑结构基本形态中的数据信息之间的关联性，根据灰色关联度大小，对评价对象进行排序，建立评价对象的关联序列，关联度越大，其评价结果越好，评价结果越好，重合效果越好，则对重叠或者重合或者相距很近的矢量点、矢量线进行合并，并按照实际地理空间位置信息进行综合整合，得到完整的建筑结构的三维建模。Among them, by calculating the correlation between the data information in the three-dimensional geometric model and the basic form of the building structure, the connection between the two is determined, and then the correlation between the data information in the three-dimensional geometric model and the basic form of the building structure is studied, and the degree of correlation between the data is measured by the correlation degree, so as to assist in decision-making; the correlation between the data information in the three-dimensional geometric model and the basic form of the building structure is judged, and the evaluation objects are sorted according to the size of the gray correlation degree, and a correlation sequence of the evaluation objects is established. The greater the correlation degree, the better the evaluation result, the better the evaluation result, and the better the coincidence effect. The overlapping or coincident or very close vector points and vector lines are merged, and comprehensive integration is carried out according to the actual geographic space location information to obtain a complete three-dimensional modeling of the building structure. 5.根据权利要求4所述的基于施工图纸的建筑结构三维建模系统，其特征在于，所述获取模块，其中包括：5. The building structure three-dimensional modeling system based on construction drawings according to claim 4, characterized in that the acquisition module comprises: 获取单元：用于获取建筑施工图纸中的第一图像，基于阈值分割算法对第一图像进行处理，其计算公式如下： 式中，输入图像某个像素点的灰度值Gray（i，j）为小于阈值T时为背景，其输出图像所对应像素点Out（i，j）的灰度值则被设置为0，即黑色；当某个像素点的灰度值为Gray（i，j）大于或者等于阈值T时为背景，其输出图像所对应像素点Out（i，j）的灰度值则被设置为255，即白色；The acquisition unit is used to acquire the first image in the building construction drawing and process the first image based on the threshold segmentation algorithm. The calculation formula is as follows: In the formula, when the gray value Gray (i, j) of a pixel in the input image is less than the threshold T, it is the background, and the gray value of the corresponding pixel Out (i, j) in the output image is set to 0, that is, black; when the gray value Gray (i, j) of a pixel is greater than or equal to the threshold T, it is the background, and the gray value of the corresponding pixel Out (i, j) in the output image is set to 255, that is, white; 处理单元：用于将处理后的第一图像进行高斯滤波去噪处理，得到去噪后的第二图像，对第二图像进行特征提取，得到建筑施工图纸的词频特征信息，将词频特征信息记作标准化基础数据，其中包括根据构件的几何信息和非几何信息添加类别筛选条件，从所有的所述构件中筛选出属于同一类别的构件；通过添加不同的类别筛选条件，可以将所有构件可以划分为梁类、板类、柱类和墙类。Processing unit: used for performing Gaussian filtering denoising on the processed first image to obtain a denoised second image, performing feature extraction on the second image to obtain word frequency feature information of the building construction drawing, and recording the word frequency feature information as standardized basic data, including adding category screening conditions according to the geometric information and non-geometric information of the components, and screening out components belonging to the same category from all the components; by adding different category screening conditions, all components can be divided into beams, plates, columns and walls. 6.根据权利要求5所述的基于施工图纸的建筑结构三维建模系统，其特征在于，所述处理单元，其中包括：6. The building structure three-dimensional modeling system based on construction drawings according to claim 5, characterized in that the processing unit comprises: 提取单元：用于利用尺度不变特征转换提取算法，提取第二图像中所有类别图像的尺度不变特征并当作视觉词汇向量，其中第二图像包括关于墙图、门窗图、柱图、楼梯图、屋顶图和板图；Extraction unit: used for extracting scale-invariant features of all categories of images in the second image using a scale-invariant feature conversion extraction algorithm and using them as visual vocabulary vectors, wherein the second image includes images of walls, doors and windows, columns, stairs, roofs and boards; 合并单元：用于利用K-Means聚类算法将提取到的视觉词汇向量的词义相近或者重复出现的词汇进行合并，构建包含主要标准化基础词汇的集合；Merging unit: used to merge the words with similar meanings or repeated appearances in the extracted visual vocabulary vectors using the K-Means clustering algorithm to construct a set containing the main standardized basic words; 量化单元：用于基于包含主要标准化基础词汇的集合对第二图像进行图像特征量化，其中第二图像中的每一张图像均通过尺度不变特征提取算法提取到的视觉词汇以集合中的标准化基础词汇替代；A quantization unit: configured to quantize image features of the second image based on a set comprising main standardized basic words, wherein each image in the second image is replaced by a standardized basic word in the set using a visual word extracted by a scale-invariant feature extraction algorithm; 统计单元：用于统计主要标准化基础词汇在第二图像中出现的频次，并将第二图像表示为一个K维数值向量，即建筑施工图纸的词频特征信息。Statistical unit: used to count the frequency of occurrence of main standardized basic words in the second image, and represent the second image as a K-dimensional numerical vector, that is, the word frequency feature information of the building construction drawing.
CN202310992866.4A 2023-08-08 2023-08-08 A method and system for three-dimensional modeling of building structure based on construction drawings Active CN116958477B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310992866.4A CN116958477B (en) 2023-08-08 2023-08-08 A method and system for three-dimensional modeling of building structure based on construction drawings

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310992866.4A CN116958477B (en) 2023-08-08 2023-08-08 A method and system for three-dimensional modeling of building structure based on construction drawings

Publications (2)

Publication Number Publication Date
CN116958477A CN116958477A (en) 2023-10-27
CN116958477B true CN116958477B (en) 2024-12-20

Family

ID=88458371

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310992866.4A Active CN116958477B (en) 2023-08-08 2023-08-08 A method and system for three-dimensional modeling of building structure based on construction drawings

Country Status (1)

Country Link
CN (1) CN116958477B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117455895B (en) * 2023-11-27 2025-01-14 朋友电力科技有限公司 Preparation device and preparation method for realizing wire clamp
CN118520573A (en) * 2024-07-23 2024-08-20 中铁一局集团建筑安装工程有限公司 BIM model modeling method, system, equipment and storage medium

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6813377B1 (en) * 1999-08-06 2004-11-02 Cognex Corporation Methods and apparatuses for generating a model of an object from an image of the object
CN109710963A (en) * 2018-11-05 2019-05-03 陈树铭 3D rapid modeling system and method based on architectural 2D CAD drawings
WO2022064242A1 (en) * 2020-09-22 2022-03-31 Sarabi Soroush The method of automatic 3d designing of constructions and colonies in an smart system using a combination of machine scanning and imaging and machine learning and reconstruction of 3d model through deep learning and with the help of machine learning methods

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105138780A (en) * 2015-09-01 2015-12-09 北京海颐威工程技术有限公司 Device for rapidly establishing three-dimensional building information model
CN112598796B (en) * 2020-12-28 2024-03-22 华东交通大学 Method for constructing and automatically updating three-dimensional building information model based on generalized point cloud
US11625553B2 (en) * 2021-06-01 2023-04-11 Buildingestimates.Com Limited Rapid and accurate modeling of a building construction structure including estimates, detailing, and take-offs using artificial intelligence
CN114863020B (en) * 2022-04-29 2023-03-28 北京工业大学 Three-dimensional model construction method and device, electronic equipment and storage medium

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6813377B1 (en) * 1999-08-06 2004-11-02 Cognex Corporation Methods and apparatuses for generating a model of an object from an image of the object
CN109710963A (en) * 2018-11-05 2019-05-03 陈树铭 3D rapid modeling system and method based on architectural 2D CAD drawings
WO2022064242A1 (en) * 2020-09-22 2022-03-31 Sarabi Soroush The method of automatic 3d designing of constructions and colonies in an smart system using a combination of machine scanning and imaging and machine learning and reconstruction of 3d model through deep learning and with the help of machine learning methods

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
具有误差修正的线矢量数据小波变换;马伯宁等;计算机辅助设计与图形学学报;20111115;第23卷(第11期);第1825-1829页 *

Also Published As

Publication number Publication date
CN116958477A (en) 2023-10-27

Similar Documents

Publication Publication Date Title
CN116958477B (en) A method and system for three-dimensional modeling of building structure based on construction drawings
CN108875522B (en) Face clustering method, device and system and storage medium
CN110781970B (en) Classifier generation method, device, equipment and storage medium
CN108564102A (en) Image clustering evaluation of result method and apparatus
CN117422936B (en) Remote sensing image classification method and system
CN114926766B (en) Identification method and device, equipment and computer readable storage medium
JP2015099559A (en) Image processing apparatus, image processing method, and program
CN112419202A (en) Automatic recognition system of wild animal images based on big data and deep learning
CN113129299A (en) Template determination method and device, computer equipment and storage medium
CN112348011A (en) A vehicle damage assessment method, device and storage medium
CN115392937A (en) User fraud risk identification method and device, electronic equipment and storage medium
CN114445716B (en) Key point detection method, key point detection device, computer device, medium, and program product
CN119538377B (en) A method and system for modeling digital twins of smart buildings
CN115690554A (en) Target identification method, system, electronic device and storage medium
CN115294636A (en) Face clustering method and device based on self-attention mechanism
CN108898067B (en) Method and device for determining association degree of person and object and computer-readable storage medium
CN109543716B (en) K-line form image identification method based on deep learning
CN118354192A (en) Thermodynamic diagram model-based camera parameter adjustment method and device and computer equipment
CN114842198B (en) Intelligent damage assessment method, device, equipment and storage medium for vehicle
CN114511545B (en) Method, device, equipment and readable storage medium for detecting key paint uniformity
CN116206276A (en) Linear object recognition method and device, vehicle and equipment
CN107437086A (en) The control method and device of vehicle pass-through
CN114494682A (en) Object position prediction method, device, equipment and storage medium
CN119227913B (en) Agriculture and forestry monitoring integrated system and method based on multisource remote sensing data
CN116612474B (en) Object detection method, device, computer equipment and computer readable storage medium

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