CN116958476B - Building visual modeling method and system based on BIM data - Google Patents
Building visual modeling method and system based on BIM data Download PDFInfo
- Publication number
- CN116958476B CN116958476B CN202310960376.6A CN202310960376A CN116958476B CN 116958476 B CN116958476 B CN 116958476B CN 202310960376 A CN202310960376 A CN 202310960376A CN 116958476 B CN116958476 B CN 116958476B
- Authority
- CN
- China
- Prior art keywords
- building
- dimensional
- data
- boundary
- preset
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000000007 visual effect Effects 0.000 title claims abstract description 82
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 90
- 238000013507 mapping Methods 0.000 claims abstract description 30
- 238000004891 communication Methods 0.000 claims description 33
- 238000012937 correction Methods 0.000 claims description 14
- 230000004927 fusion Effects 0.000 claims description 11
- 230000010354 integration Effects 0.000 claims description 11
- 230000000877 morphologic effect Effects 0.000 claims description 11
- 238000004458 analytical method Methods 0.000 claims description 10
- 230000007797 corrosion Effects 0.000 claims description 9
- 238000005260 corrosion Methods 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 7
- 238000012800 visualization Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 238000013075 data extraction Methods 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 description 11
- 230000000694 effects Effects 0.000 description 7
- 238000013473 artificial intelligence Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
- G06T15/04—Texture mapping
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/176—Urban or other man-made structures
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Geometry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Multimedia (AREA)
- Computer Graphics (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Architecture (AREA)
- Civil Engineering (AREA)
- Databases & Information Systems (AREA)
- Structural Engineering (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention relates to the technical field of digital media, and discloses a building visual modeling method and system based on BIM data, wherein the building visual modeling method comprises the following steps: building space data and building attribute data in BIM data are extracted; extracting building boundaries according to the building space data, and extracting building texture data according to the building attribute data; dividing the structure attribute of the target building to obtain a divided building structure, and constructing a three-dimensional building model corresponding to the divided building structure according to the building boundary and the building attribute data; generating a three-dimensional building hollowed-out model of the three-dimensional building model, and carrying out model refinement on the three-dimensional building hollowed-out model to obtain a three-dimensional refined building hollowed-out model; and carrying out visual texture mapping on the three-dimensional refined building hollowed-out model through a preset multi-level detail algorithm and building texture data to obtain a visual target building. The method can improve the building visual modeling accuracy.
Description
Technical Field
The invention relates to the technical field of digital media, in particular to a building visual modeling method and system based on BIM data.
Background
In recent years, a building is a carrier and image expression of a city, is an important component of the city, and a three-dimensional building model is an important foundation for constructing a digital city, a virtual city and a command city, but in order to improve the accuracy of visual modeling of the building, the building structure needs to be analyzed one by one from multiple dimensions and details so as to accurately model the building.
Most of the existing building modeling technologies realize three-dimensional visual modeling of the whole building based on three-dimensional modeling software. In practical application, only three-dimensional modeling software is used for modeling the whole building, so that the cost is high, the operation is complex, the building modeling is possibly complicated, and the accuracy in building visual modeling is low.
Disclosure of Invention
The invention provides a building visual modeling method and system based on BIM data, and mainly aims to solve the problem of lower accuracy in building visual modeling.
In order to achieve the above object, the present invention provides a building visual modeling method based on BIM data, including:
s1, acquiring BIM data of a target building, and extracting building space data and building attribute data in the BIM data by using a preset remote sensing algorithm;
S2, extracting the building boundary of the target building according to the building space data through a preset boundary constraint algorithm, extracting the building texture data of the target building according to the building attribute data, wherein the extracting the building boundary of the target building according to the building space data through the preset boundary constraint algorithm comprises the following steps:
s21, acquiring building labels of the building space data;
s22, performing morphological corrosion operation on the building label to obtain a building boundary label, and performing morphological expansion operation on the building label to obtain a building parting line label;
s23, calculating the label probability of the building label, the building boundary label and the building dividing line label by using a preset complete convolution network;
s24, calculating the building gray value of the target building according to the label probability through a preset boundary constraint algorithm, wherein the boundary constraint algorithm is as follows:
G＝P u ×(1-P l )×(1-kP h )
wherein G is the building gray value, P u P is the building probability among the tag probabilities l P being a split line probability among the tag probabilities h Boundary probability k in the label probability is boundary constraint weight;
S25, determining a building boundary of the target building according to the gray threshold value and the building gray value;
s3, dividing the structure attribute of the target building according to a preset main building structure attribute to obtain a divided building structure, and constructing a three-dimensional building model corresponding to the divided building structure according to the building boundary and the building attribute data by using a preset three-dimensional semantic reconstruction algorithm;
s4, generating a three-dimensional building hollowed-out model of the three-dimensional building model by using a preset three-dimensional difference integration algorithm, and carrying out model refinement on the three-dimensional building hollowed-out model by using a preset model script running time to obtain a three-dimensional refined building hollowed-out model;
and S5, performing visual texture mapping on the three-dimensional refined building hollowed-out model through a preset multi-level detail algorithm and the building texture data to obtain a visual target building.
Optionally, the extracting building space data and building attribute data in the BIM data by using a preset remote sensing algorithm includes:
extracting remote sensing data of a target building by using the remote sensing algorithm;
performing data fusion on the remote sensing data and the BIM data to obtain building fusion data;
Extracting a metadata information object of the building fusion data, and converting the metadata information object into a document information object;
analyzing a text object in the document information object through a preset element selection model to obtain an element analysis object;
classifying the element analysis objects according to preset building classification attributes to obtain building space data and building attribute data.
Optionally, the determining the building boundary of the target building according to the gray threshold and the building gray value includes:
comparing the gray threshold value with the building gray value to obtain a building mark graph;
dividing the building mark graph according to the gray values from small to large to obtain a building communication area;
calculating the communication value of the building communication areas one by using the following communication value calculation formula:
wherein L is i For the connection value of the ith building connection area, max is the maximum value function, t ij Building mask value, d, for the jth sub-zone in the ith building communication zone ij Building actual mask values for the jth sub-region in the ith building communication region, delta being a building mask control factor;
and when the communication value is larger than a preset communication threshold value, marking the building communication area as a building area, and determining the building boundary of the target building according to the boundary label in the building area.
Optionally, the extracting building texture data of the target building according to the building attribute data includes:
extracting building color attributes in the building attribute data;
converting the RGB color space corresponding to the building color attribute into an HSV color space;
generating a color histogram according to the component values in the HSV color space;
building texture data of the target building is determined from the color histogram.
Optionally, the dividing the structural attribute of the target building according to the preset main building structural attribute to obtain a divided building structure includes:
dividing the main building structure attribute into a wall structure, a door and window structure and a roof structure;
marking a wall body of the target building according to the wall structure, marking a door and window body of the target building according to the door and window structure, and marking a roof body of the target building according to the roof structure;
and taking the wall surface main body, the door and window main body and the roof main body as the dividing building structure.
Optionally, the constructing, by using a preset three-dimensional semantic reconstruction algorithm, a three-dimensional building model corresponding to the partitioned building structure according to the building boundary and the building attribute data includes:
Extracting target building boundaries corresponding to the divided building structures one by one according to the building boundaries;
calculating the confidence coefficient of the boundary point in the boundary of the target building through a preset confidence coefficient algorithm, wherein the confidence coefficient algorithm is as follows:
wherein Z is k Boundary point confidence, n, for the kth boundary point 1k N is the number of boundary points above the boundary in the boundary of the target building 2k The number of boundary points below the boundary in the boundary of the target building;
selecting an optimal boundary point of the boundary of the target building according to the confidence coefficient of the boundary point;
generating a partitioned building topological graph corresponding to the partitioned building structure according to the optimal boundary point;
generating mapping semantic attributes according to the building attribute data by using a preset three-dimensional semantic reconstruction algorithm;
and adding the mapping semantic attribute to the partitioned building topological graph to obtain a three-dimensional building model.
Optionally, the generating the three-dimensional building hollowed-out model of the three-dimensional building model by using a preset three-dimensional difference integrating algorithm includes:
performing grid division on the three-dimensional building model to obtain a three-dimensional building grid;
dividing a building polyhedron of the three-dimensional building model according to the three-dimensional building grid;
Calculating a three-dimensional difference product of the building polyhedron and the three-dimensional building grid by using the three-dimensional difference product algorithm, wherein the three-dimensional difference product algorithm is as follows:
A＝B τ -C σ
wherein A is the three-dimensional difference product and B τ C for the tau-th grid area in the three-dimensional building grid σ A sigma-th polyhedral region in the building polyhedron;
and generating the three-dimensional building hollowed-out model according to the three-dimensional difference product.
Optionally, the model refinement is performed on the three-dimensional building hollowed-out model through a preset model script running time to obtain a three-dimensional refined building hollowed-out model, which includes:
when the model script running time is larger than a preset model running time threshold, performing region optimization on the building polyhedron in the three-dimensional building hollowed-out model to obtain an optimized building polyhedron;
calculating an optimized three-dimensional difference product of the optimized building polyhedron and the three-dimensional building grid;
and carrying out model refinement on the three-dimensional building hollowed-out model according to the optimized three-dimensional difference product to obtain the three-dimensional refined building hollowed-out model.
Optionally, the performing visual texture mapping on the three-dimensional refined building hollowed-out model through a preset multi-level detail algorithm and the building texture data to obtain a visual target building includes:
Performing triangulation on the three-dimensional refined building hollowed-out model to obtain a triangular building area;
matching the triangular building area with the building area in the three-dimensional refined building hollowed-out model to obtain a texture matching area;
mapping the building texture data to the texture matching area to obtain an initial texture map;
and (3) performing color correction on the initial texture map by using a multi-level detail algorithm as follows to obtain a visual target building:
wherein v is l V for the left region of the texture matching region r For the right region of the texture matching region,for the unique color of the left region in the texture matching region, +.>For the unique color of the right-hand region of the texture matching region, +.>For the color correction of the left region in the texture matching region, < >>For the color correction of the right-hand region of the texture matching region, < >>For the color in the texture matching area, +.>For color correction in the texture matching region, λ is the color control factor and argmin is the minimum function.
In order to solve the above problems, the present invention also provides a building visual modeling system based on BIM data, the system comprising:
The building data extraction module is used for acquiring BIM data of a target building and extracting building space data and building attribute data in the BIM data by utilizing a preset remote sensing algorithm;
the building boundary extraction module is used for extracting the building boundary of the target building according to the building space data through a preset boundary constraint algorithm and extracting the building texture data of the target building according to the building attribute data;
the three-dimensional building model construction module is used for dividing the structure attribute of the target building according to the preset main building structure attribute to obtain a divided building structure, and constructing a three-dimensional building model corresponding to the divided building structure according to the building boundary and the building attribute data by utilizing a preset three-dimensional semantic reconstruction algorithm;
the three-dimensional refined building hollowed-out model generation module is used for generating a three-dimensional building hollowed-out model of the three-dimensional building model by using a preset three-dimensional difference integration algorithm, and carrying out model refinement on the three-dimensional building hollowed-out model by using a preset model script running time to obtain the three-dimensional refined building hollowed-out model;
and the visual texture mapping module is used for performing visual texture mapping on the three-dimensional refined building hollowed-out model through a preset multi-level detail algorithm and the building texture data to obtain a visual target building.
According to the embodiment of the invention, the building space data and the building attribute data in the target building BIM data are extracted, so that the building boundary is extracted according to the building space data, and the texture data is extracted according to the building attribute data, thereby being beneficial to more accurately and comprehensively carrying out visual modeling on the building; dividing the main structure of the building to more finely divide the building structure to construct a three-dimensional building model according to the building boundary and the building attribute data; the three-dimensional building model is converted into the three-dimensional hollowed-out model, so that the stereoscopic impression and the visual effect of the three-dimensional building model are enhanced; and carrying out texture mapping on the three-dimensional hollowed-out model through the building texture data so as to obtain a more specific visual target building and improve the visualization of the visual target building. Therefore, the building visual modeling method and system based on BIM data can solve the problem of lower accuracy in building visual modeling.
Drawings
FIG. 1 is a flow chart of a building visual modeling method based on BIM data according to an embodiment of the invention;
FIG. 2 is a flow chart of extracting building boundaries according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart of a partitioning target building according to an embodiment of the present invention;
fig. 4 is a functional block diagram of a building visual modeling system based on BIM data according to an embodiment of the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The embodiment of the application provides a building visual modeling method based on BIM data. The execution subject of the building visual modeling method based on BIM data includes, but is not limited to, at least one of a server, a terminal and the like, which can be configured to execute the method provided by the embodiment of the application. In other words, the building visual modeling method based on BIM data may be performed by software or hardware installed in a terminal device or a server device, and the software may be a blockchain platform. The service end includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server may be an independent server, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.
Referring to fig. 1, a flow chart of a building visual modeling method based on BIM data according to an embodiment of the present invention is shown. In this embodiment, the building visual modeling method based on BIM data includes:
s1, acquiring BIM data of a target building, and extracting building space data and building attribute data in the BIM data by using a preset remote sensing algorithm.
In the embodiment of the invention, the BIM data comprises space data and attribute data, and covers the data expression form (three-dimensional model) of the BIM, wherein the space data comprises the space position, the appearance shape and the like of a building, and the attribute data comprises design parameters, construction parameters, operation and maintenance parameters and the like.
In detail, the BIM data of the target building may be acquired from a pre-stored storage area including, but not limited to, a database, a blockchain, etc., through a computer sentence having a data grabbing function (e.g., java sentence, python sentence, etc.).
Further, in order to accurately model the target building, the corresponding building space data and building attribute data in the target building BIM data need to be extracted to model the building.
In the embodiment of the invention, the building space data comprises the appearance shape, the main body layout structure, the space position and the like of a target building; the building attribute data includes an appearance shape color of a target building, the number of building layers, a layer height, a roof height, an inclination angle, a construction size, and the like.
In the embodiment of the present invention, the extracting building space data and building attribute data in the BIM data by using a preset remote sensing algorithm includes:
extracting remote sensing data of a target building by using the remote sensing algorithm;
performing data fusion on the remote sensing data and the BIM data to obtain building fusion data;
extracting a metadata information object of the building fusion data, and converting the metadata information object into a document information object;
analyzing a text object in the document information object through a preset element selection model to obtain an element analysis object;
classifying the element analysis objects according to preset building classification attributes to obtain building space data and building attribute data.
In detail, the remote sensing algorithm is to acquire remote sensing data of a target building through a crawler, wherein the remote sensing data is mainly used for describing data attributes and is data for describing external forms and internal features of the remote sensing influence data, the remote sensing influence data can be determined through taking time and space range metadata as query conditions, and further, the remote sensing data and BIM data are subjected to data integration to obtain building fusion data, so that the data of the target building can be mastered more comprehensively.
Specifically, the metadata information object refers to structural data extracted from information resources and used for explaining the characteristics and the content of the structural data, the spatial characteristics and the attribute characteristics in the building fusion data are extracted through computer sentences, the metadata information object is converted into document information objects, then the remote sensing metadata in the document information object is extracted through an element selector (CSS) to obtain element analysis objects, and the element analysis objects are classified according to the spatial data and the attribute data in the building classification attribute, so that the building spatial data and the building attribute data are obtained.
Further, the building space data and the building attribute data provide data bases for modeling of the target building, and in order to achieve modeling of the target building, it is necessary to analyze building boundaries of the target building based on the building space data.
S2, extracting the building boundary of the target building according to the building space data through a preset boundary constraint algorithm, and extracting the building texture data of the target building according to the building attribute data.
In one practical application scene, the medium-small-sized buildings are main bodies of cities, and are densely arranged in cities with scarce land due to population aggregation, and are often represented by a large number of similar-sized buildings, so that the buildings are very close in position, when the boundaries of the buildings are extracted, the boundaries are easily affected by the diversification of building structures and the surrounding environment, the boundary extraction precision is reduced, the boundaries of the buildings are possibly unclear, and a plurality of buildings are often adhered, so that the boundary of the building of the target building needs to be extracted by adopting a segmentation algorithm with boundary constraint.
In the embodiment of the invention, the building boundary is used for representing the outline of the target building, the modeling of the target building can be more accurate through the building boundary, the main body outline of the target building is represented, and the interference of the non-building boundary is removed.
In an embodiment of the present invention, referring to fig. 2, the extracting, by a preset boundary constraint algorithm, a building boundary of the target building according to the building space data includes:
s21, acquiring building labels of the building space data;
s22, performing morphological corrosion operation on the building label to obtain a building boundary label, and performing morphological expansion operation on the building label to obtain a building parting line label;
s23, calculating the label probability of the building label, the building boundary label and the building dividing line label by using a preset complete convolution network;
s24, calculating the building gray value of the target building according to the label probability through a preset boundary constraint algorithm, wherein the boundary constraint algorithm is as follows:
G＝P u ×(1-P l )×(1-kP h )
wherein G is the building gray value, P u P is the building probability among the tag probabilities l P being a split line probability among the tag probabilities h Boundary probability k in the label probability is boundary constraint weight;
s25, determining the building boundary of the target building according to the gray threshold value and the building gray value.
In detail, the building label is an area label for marking a target building in a building area, namely, each building label area (1 building pixel and 0 non-building pixel) corresponds to one single building, and then the building label is preprocessed according to morphological origins, namely, morphological corrosion operation is carried out on the building label, corrosion is carried out according to the corrosion size of 3×3, the difference between the corroded building mask area and the original building mask area is taken as a boundary label, wherein the building mask area is formed by shielding a global or local image by using a selected image and a selected image, so that the area or the processing process of image processing is controlled. In addition, morphological expansion operation is applied to the building label, the expansion size is set to be 9 multiplied by 9, the original building label area is subtracted to form a candidate point set of the parting line label, the original building label is subjected to area marking, the candidate point set is traversed, and if at least 2 different buildings exist in the pixel area, the pixel is used as the parting line label. Where building labels and boundary labels are present for each building, split line labels are present only between closely adjacent buildings.
Specifically, the complete convolution network is based on a U-net network, the last layer in the network is modified into three channels, 3 classes corresponding to a building, a boundary and a dividing line are respectively obtained, a Sigmoid activation function is applied to obtain the probability of each class, in order to avoid boundary effects, edges with the width of 24 pixels on 4 sides of a clipping prediction result are needed, the clipped edges do not participate in network optimization, and the calculation amount of backward propagation is reduced.
Further, in the process of converting the building, the dividing line and the boundary 3-class probability value into the building boundary region mark through the boundary constraint algorithm, the 3-class probability value needs to be synthesized into one value through the boundary constraint algorithm, and the building gray value of the target building is obtained, wherein 1-P in the boundary constraint algorithm l Representing parting line constraints, the building should not overlap the parting line, (1-kP) h ) Representing boundary constraint, wherein the pixel at the boundary of the building has less possibility of belonging to the building, and the boundary constraint weight k is the weight for controlling the boundary constraint, and further according to the calculated building gray value and gray threshold value of the target buildingAnd comparing them to obtain the building boundary.
In an embodiment of the present invention, the determining the building boundary of the target building according to the gray threshold and the building gray value includes:
Comparing the gray threshold value with the building gray value to obtain a building mark graph;
dividing the building mark graph according to the gray values from small to large to obtain a building communication area;
calculating the communication value of the building communication areas one by using the following communication value calculation formula:
wherein L is i For the connection value of the ith building connection area, max is the maximum value function, t ij Building mask value, d, for the jth sub-zone in the ith building communication zone ij Building actual mask values for the jth sub-region in the ith building communication region, delta being a building mask control factor;
and when the communication value is larger than a preset communication threshold value, marking the building communication area as a building area, and determining the building boundary of the target building according to the boundary label in the building area.
In detail, when the gray level of the building is greater than the gray threshold, the target building corresponding to the gray level of the building is marked as a building mark graph, the building mark graph is divided according to the sequence from small to large in the building mark graph to obtain a building communication area, if the gray level of the building 1 in the building mark graph is 5, the gray level of the building 2 is 6, and the gray level of the building 3 is 3, the building mark graph is divided according to the sequence of the building 3, the building 1 and the building 2, and the building communication area is obtained according to the sequence from small to large.
Specifically, the interior region is divided in each building mark graph, and then the connected value of each building mark graph is calculated by a connected value calculation formula, whichBuilding mask value t in the connected value calculation formula ij Means the difference between the mask value after expansion operation and the mask value after corrosion operation in the building mark graph, the actual mask value d is built ij The building mask control factor delta is used for controlling the building mask value after expansion operation and corrosion operation; and when the communication value is larger than a preset communication threshold value, marking the building communication area as a building area, so that the building boundary of the target building can be obtained according to the accurate building area.
Further, in order to realize the visualization of the building, texture data of the building needs to be determined according to attribute data of the building, thereby forming a more specific visualized building.
In the embodiment of the invention, the building texture data refer to the building appearance color and the building appearance stripe, and more specific and comprehensive visualization of the building can be realized according to the building texture data.
In an embodiment of the present invention, the extracting building texture data of the target building according to the building attribute data includes:
Extracting building color attributes in the building attribute data;
converting the RGB color space corresponding to the building color attribute into an HSV color space;
generating a color histogram according to the component values in the HSV color space;
building texture data of the target building is determined from the color histogram.
In detail, the building attribute data includes building size and color, that is, the building color attribute in the building attribute data is extracted, the appearance color of the building can be obtained, further, the RGB color space of the appearance color of the building is converted into the HSV color space, the hue, vividness and brightness of the color can be expressed very intuitively, the color comparison is convenient, a color histogram can be generated according to the three component values of hue H, saturation S and brightness V in the HSV space, and further, the building texture data of the target building is determined according to the color value in the color histogram.
Further, the visual appearance of the target building may be presented more specifically based on the building texture data, and a body model structure of the target building may need to be constructed before the visual appearance is visualized.
S3, dividing the structure attribute of the target building according to the preset main building structure attribute to obtain a divided building structure, and constructing a three-dimensional building model corresponding to the divided building structure according to the building boundary and the building attribute data by using a preset three-dimensional semantic reconstruction algorithm.
In the embodiment of the invention, dividing the building structure refers to dividing the main body of the target building, namely dividing the main body into structures such as a wall surface, a roof, a door and a window, and sequentially carrying out three-dimensional modeling on the structures such as the wall surface, the roof, the door and the window, so as to obtain a finer three-dimensional building model of the target building.
In the embodiment of the present invention, referring to fig. 3, the dividing the structural attribute of the target building according to the preset main building structural attribute to obtain the divided building structure includes:
s31, dividing the main building structure attribute into a wall structure, a door and window structure and a roof structure;
s32, marking a wall body of the target building according to the wall structure, marking a door and window body of the target building according to the door and window structure, and marking a roof body of the target building according to the roof structure;
s33, taking the wall surface main body, the door and window main body and the roof main body as the dividing building structure.
In detail, the main building structure attribute includes a wall structure, a roof structure and a door and window structure, and the structure of the target building is divided according to the main building structure attribute, so that the wall main body, the door and window main body and the roof main body are marked, and the divided building structure of the target building is obtained.
Further, three-dimensional modeling is carried out on the wall surface main body, the door and window main body and the roof main body in the divided building structure one by one so as to obtain a three-dimensional building model corresponding to the target building.
In the embodiment of the invention, the three-dimensional building model refers to a virtual target building constructed according to a physical target building so as to realize visual modeling of the building.
In the embodiment of the present invention, the constructing a three-dimensional building model corresponding to the divided building structure according to the building boundary and the building attribute data by using a preset three-dimensional semantic reconstruction algorithm includes:
extracting target building boundaries corresponding to the divided building structures one by one according to the building boundaries;
calculating the confidence coefficient of the boundary point in the boundary of the target building through a preset confidence coefficient algorithm, wherein the confidence coefficient algorithm is as follows:
wherein Z is k Boundary point confidence, n, for the kth boundary point 1k N is the number of boundary points above the boundary in the boundary of the target building 2k The number of boundary points below the boundary in the boundary of the target building;
selecting an optimal boundary point of the boundary of the target building according to the confidence coefficient of the boundary point;
generating a partitioned building topological graph corresponding to the partitioned building structure according to the optimal boundary point;
Generating mapping semantic attributes according to the building attribute data by using a preset three-dimensional semantic reconstruction algorithm;
and adding the mapping semantic attribute to the partitioned building topological graph to obtain a three-dimensional building model.
In detail, the pre-obtained building boundary is extracted according to the wall body, the door and window body and the roof body in the divided building structure to obtain the corresponding target building boundary in the divided building structure, wherein the extraction order is thatThe target building boundary is consistent with the step of extracting the building boundary. And further, calculating the confidence coefficient of each boundary point in the target building boundary through a confidence coefficient algorithm, wherein the boundary points in the target building boundary in the confidence coefficient algorithm refer to the vertexes of the target building boundary, if the target building boundary is a triangle, the target building boundary points are three vertexes of the triangle, and the number n of boundary points above the boundary in the target building boundary 1k Refers to the number of boundary points of the building boundary adjacent to the upper side of the boundary point of the target building, and the number of boundary points n below the boundary in the boundary of the target building 2k The number of boundary points of the building boundary adjacent to the target building boundary at the lower side is negligible, and the confidence of the boundary points in the target building boundary can be calculated. If the number of boundary points above and the number of boundary points below the boundary point 1 in the boundary of the target building are counted, the confidence of the boundary point 1 can be calculated.
Specifically, there may be a boundary point on the boundary line that has no great effect on modeling of the target building, so when the confidence coefficient of the boundary point is required to be greater than a preset confidence coefficient threshold, the boundary point is used as an optimal boundary point of the boundary of the target building, and then a divided building topological graph corresponding to the divided building structure is constructed according to the structure of the real target building according to the optimal boundary point, and building sizes, heights, layers and the like in three-dimensional mapping semantic attributes are mapped into the divided building topological graph to obtain a three-dimensional building model, wherein the three-dimensional mapping semantic attributes are mapping semantic attributes for physical modeling generated by building sizes, heights, layers and the like in building attribute data through a three-dimensional semantic reconstruction algorithm, and the three-dimensional semantic reconstruction algorithm refers to semantic segmentation of the building attribute data in the divided building structure, so as to form semantic attribute information of data modeling.
Further, in order to enhance the stereoscopic impression and visual effect of the three-dimensional building model, the model can reflect the effect that the illumination shadow and the external light irradiate indoors for visual analysis.
S4, generating a three-dimensional building hollowed-out model of the three-dimensional building model by using a preset three-dimensional difference integration algorithm, and carrying out model refinement on the three-dimensional building hollowed-out model by using a preset model script running time to obtain a three-dimensional refined building hollowed-out model.
In the embodiment of the invention, the three-dimensional building hollowed-out model is formed by subtracting a part of areas in the three-dimensional building model so as to generate the three-dimensional building hollowed-out model, thereby facilitating the visual analysis of a target building.
In the embodiment of the present invention, the generating the three-dimensional building hollowed-out model of the three-dimensional building model by using a preset three-dimensional difference integration method includes:
performing grid division on the three-dimensional building model to obtain a three-dimensional building grid;
dividing a building polyhedron of the three-dimensional building model according to the three-dimensional building grid;
calculating a three-dimensional difference product of the building polyhedron and the three-dimensional building grid by using the three-dimensional difference product algorithm, wherein the three-dimensional difference product algorithm is as follows:
A＝B τ -C σ
wherein A is the three-dimensional difference product and B τ C for the tau-th grid area in the three-dimensional building grid σ A sigma-th polyhedral region in the building polyhedron;
and generating the three-dimensional building hollowed-out model according to the three-dimensional difference product.
In detail, the three-dimensional building model is subjected to grid division on the plane of each building model in the three-dimensional grid, so that a three-dimensional building grid corresponding to the three-dimensional building model is obtained, a plurality of building polyhedrons are further divided in the three-dimensional building grid according to uniform equivalent intervals, and then the three-dimensional building polyhedrons are subtracted according to the position areas of the building polyhedrons in the three-dimensional building grid by using a three-dimensional difference integration algorithm, so that a three-dimensional building hollowed-out model is formed, wherein the three-dimensional difference integration algorithm is based on Boolean operation, and the grid areas which are the same as the building polyhedrons in the three-dimensional building network are subtracted.
Further, in order to present a three-dimensional building hollowed-out model with a better effect, the model needs to be thinned according to the running time of a model script.
In the embodiment of the invention, the three-dimensional refined building hollowed-out model refers to a three-dimensional building hollowed-out model with better model effect by reselecting a hollowed-out polyhedron in the three-dimensional building model.
In the embodiment of the present invention, the model refinement is performed on the three-dimensional building hollowed-out model through a preset model script running time to obtain a three-dimensional refined building hollowed-out model, which includes:
when the model script running time is larger than a preset model running time threshold, performing region optimization on the building polyhedron in the three-dimensional building hollowed-out model to obtain an optimized building polyhedron;
calculating an optimized three-dimensional difference product of the optimized building polyhedron and the three-dimensional building grid;
and carrying out model refinement on the three-dimensional building hollowed-out model according to the optimized three-dimensional difference product to obtain the three-dimensional refined building hollowed-out model.
In detail, when the model script running time is greater than a preset model running time threshold, the construction effect of the three-dimensional hollowed-out model is poor, the hollowed-out building polyhedron is required to be selected again, so that a new optimized building polyhedron is obtained, the dividing interval of the divided building polyhedron can be adjusted, the optimized building polyhedron is obtained, the optimized three-dimensional difference product of the optimized building polyhedron and the three-dimensional building grid is recalculated according to the three-dimensional difference product, and the hollowed-out position in the three-dimensional building hollowed-out model is selected again according to the optimized three-dimensional difference product, so that the three-dimensional refined building hollowed-out model is obtained.
Further, after the three-dimensional refined building hollowed-out model is built, texture mapping is needed to be carried out on the building hollowed-out model by utilizing texture data so as to obtain a more specific visual target building.
And S5, performing visual texture mapping on the three-dimensional refined building hollowed-out model through a preset multi-level detail algorithm and the building texture data to obtain a visual target building.
In the embodiment of the invention, the visual target building can be represented as an image, and a structure which is not yet built is displayed, so that people can really know the external landscape and the internal structure of the building through 3D rendering, and the visual target building is more vivid and visual than the traditional design drawing and physical model.
In the embodiment of the present invention, the performing, by using a preset multi-level detail algorithm and the building texture data, a visual texture mapping on the three-dimensional refined building hollowed-out model to obtain a visual target building includes:
performing triangulation on the three-dimensional refined building hollowed-out model to obtain a triangular building area;
matching the triangular building area with the building area in the three-dimensional refined building hollowed-out model to obtain a texture matching area;
Mapping the building texture data to the texture matching area to obtain an initial texture map;
and (3) performing color correction on the initial texture map by using a multi-level detail algorithm as follows to obtain a visual target building:
wherein v is l V for the left region of the texture matching region r For the right region of the texture matching region,for the unique color of the left region in the texture matching region, +.>For the unique color of the right-hand region of the texture matching region, +.>For the color correction of the left region in the texture matching region, < >>For the color correction of the right-hand region of the texture matching region, < >>For the color in the texture matching area, +.>For color correction in the texture matching region, λ is the color control factor and argmin is the minimum function.
In detail, the three-dimensional refined building hollowed-out model is triangulated by using a preset triangulating algorithm to obtain a triangulated triangular building area corresponding to the three-dimensional refined building hollowed-out model, wherein the triangulating algorithm is Delaunay triangulating, namely, a process of generating a triangle set for a given plane point set. And secondly, carrying out texture matching on the triangular building area and a corresponding area in the three-dimensional refined building hollowed-out model to obtain texture matching areas, and further mapping corresponding building texture data in the texture matching areas to the texture matching areas, so as to obtain an initial texture map of each texture matching area.
In particular, in order to make the colors of the buildings in the texture map more specific and accurate, the initial colors in the initial texture map need to be corrected by a multi-level detail algorithm, in the multi-level detail algorithm, each vertex needs to be ensured to belong to only one texture color block, so that the difference of color adjustment between adjacent vertices in the same texture color block can be reduced to the greatest extent according to the color value of the left area and the color value of the right area in the texture matching area, the progressive color adjustment in the texture map is facilitated, and the optimal color correction value g is obtained according to the color value in the texture matching area by a color control factor vj Thereby color correcting the initial texture map according to the color correction value.
Further, visualization of the target building may be achieved based on three-dimensional modeling of the target building, possibly in combination with VR, and architects may virtually visit their designs with their customers, giving them full experience of the project's potential.
According to the embodiment of the invention, the building space data and the building attribute data in the target building BIM data are extracted, so that the building boundary is extracted according to the building space data, and the texture data is extracted according to the building attribute data, thereby being beneficial to more accurately and comprehensively carrying out visual modeling on the building; dividing the main structure of the building to more finely divide the building structure to construct a three-dimensional building model according to the building boundary and the building attribute data; the three-dimensional building model is converted into the three-dimensional hollowed-out model, so that the stereoscopic impression and the visual effect of the three-dimensional building model are enhanced; and carrying out texture mapping on the three-dimensional hollowed-out model through the building texture data so as to obtain a more specific visual target building and improve the visualization of the visual target building. Therefore, the building visual modeling method and system based on BIM data can solve the problem of lower accuracy in building visual modeling.
FIG. 4 is a functional block diagram of a building visual modeling system based on BIM data according to an embodiment of the present invention.
The building visual modeling system 100 based on BIM data according to the present invention may be installed in an electronic device. Depending on the functions implemented, the building visual modeling system 100 based on BIM data may include a building data extraction module 101, a building boundary extraction module 102, a three-dimensional building model construction module 103, a three-dimensional refined building hollowed-out model generation module 104, and a visual texture mapping module 105. The module of the invention, which may also be referred to as a unit, refers to a series of computer program segments, which are stored in the memory of the electronic device, capable of being executed by the processor of the electronic device and of performing a fixed function.
In the present embodiment, the functions concerning the respective modules/units are as follows:
the building data extraction module 101 is configured to obtain BIM data of a target building, and extract building space data and building attribute data in the BIM data by using a preset remote sensing algorithm;
the building boundary extraction module 102 is configured to extract, according to a preset boundary constraint algorithm, a building boundary of the target building according to the building space data, and extract building texture data of the target building according to the building attribute data;
The three-dimensional building model construction module 103 is configured to divide structural attributes of the target building according to preset main building structure attributes to obtain a divided building structure, and construct a three-dimensional building model corresponding to the divided building structure according to the building boundary and the building attribute data by using a preset three-dimensional semantic reconstruction algorithm;
the three-dimensional refined building hollowed-out model generating module 104 is configured to generate a three-dimensional building hollowed-out model of the three-dimensional building model by using a preset three-dimensional difference integration algorithm, and perform model refinement on the three-dimensional building hollowed-out model by using a preset model script running time to obtain a three-dimensional refined building hollowed-out model;
the visual texture mapping module 105 is configured to perform visual texture mapping on the three-dimensional refined building hollowed-out model through a preset multi-level detail algorithm and the building texture data, so as to obtain a visual target building.
In detail, each module in the building visual modeling system 100 based on BIM data in the embodiment of the present invention adopts the same technical means as the building visual modeling method based on BIM data described in fig. 1 to 3, and can generate the same technical effects, which is not described herein.
In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods may be implemented in other ways. For example, the system embodiments described above are merely illustrative, e.g., the division of the modules is merely a logical function division, and other manners of division may be implemented in practice.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof.
The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
The embodiment of the application can acquire and process the related data based on the artificial intelligence technology. Among these, artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use knowledge to obtain optimal results.
Furthermore, it is evident that the word "comprising" does not exclude other elements or steps, and that the singular does not exclude a plurality. Multiple units or systems as set forth in the system claims may also be implemented by means of one unit or system in software or hardware. The terms first, second, etc. are used to denote a name, but not any particular order.
Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.
Claims (10)
1. A building visual modeling method based on BIM data, the method comprising:
s1, acquiring BIM data of a target building, and extracting building space data and building attribute data in the BIM data by using a preset remote sensing algorithm;
s2, extracting the building boundary of the target building according to the building space data through a preset boundary constraint algorithm, extracting the building texture data of the target building according to the building attribute data, wherein the extracting the building boundary of the target building according to the building space data through the preset boundary constraint algorithm comprises the following steps:
s21, acquiring building labels of the building space data;
s22, performing morphological corrosion operation on the building label to obtain a building boundary label, and performing morphological expansion operation on the building label to obtain a building parting line label;
s23, calculating the label probability of the building label, the building boundary label and the building dividing line label by using a preset complete convolution network;
s24, calculating the building gray value of the target building according to the label probability through a preset boundary constraint algorithm, wherein the boundary constraint algorithm is as follows:
G＝P u ×(1-Pl)×(1-kP h )
Wherein G is the building gray value, P u P is the building probability among the tag probabilities l P being a split line probability among the tag probabilities h Boundary probability k in the label probability is boundary constraint weight;
s25, determining a building boundary of the target building according to the gray threshold value and the building gray value;
s3, dividing the structure attribute of the target building according to a preset main building structure attribute to obtain a divided building structure, and constructing a three-dimensional building model corresponding to the divided building structure according to the building boundary and the building attribute data by using a preset three-dimensional semantic reconstruction algorithm;
s4, generating a three-dimensional building hollowed-out model of the three-dimensional building model by using a preset three-dimensional difference integration algorithm, and carrying out model refinement on the three-dimensional building hollowed-out model by using a preset model script running time to obtain a three-dimensional refined building hollowed-out model;
and S5, performing visual texture mapping on the three-dimensional refined building hollowed-out model through a preset multi-level detail algorithm and the building texture data to obtain a visual target building.
2. The building visual modeling method based on BIM data according to claim 1, wherein the extracting building space data and building attribute data in the BIM data using a preset remote sensing algorithm includes:
Extracting remote sensing data of a target building by using the remote sensing algorithm;
performing data fusion on the remote sensing data and the BIM data to obtain building fusion data;
extracting a metadata information object of the building fusion data, and converting the metadata information object into a document information object;
analyzing a text object in the document information object through a preset element selection model to obtain an element analysis object;
classifying the element analysis objects according to preset building classification attributes to obtain building space data and building attribute data.
3. The building visualization modeling method based on BIM data according to claim 1, wherein the determining the building boundary of the target building according to the gray threshold and the building gray value includes:
comparing the gray threshold value with the building gray value to obtain a building mark graph;
dividing the building mark graph according to the gray values from small to large to obtain a building communication area;
calculating the communication value of the building communication areas one by using the following communication value calculation formula:
wherein L is i For the connection value of the ith building connection area, max is the maximum value function, t ij Building mask value, d, for the jth sub-zone in the ith building communication zone ij Building actual mask values for the jth sub-region in the ith building communication region, delta being a building mask control factor;
and when the communication value is larger than a preset communication threshold value, marking the building communication area as a building area, and determining the building boundary of the target building according to the boundary label in the building area.
4. The building visual modeling method based on BIM data according to claim 1, wherein the extracting building texture data of the target building from the building attribute data includes:
extracting building color attributes in the building attribute data;
converting the RGB color space corresponding to the building color attribute into an HSV color space;
generating a color histogram according to the component values in the HSV color space;
building texture data of the target building is determined from the color histogram.
5. The building visual modeling method based on BIM data according to claim 1, wherein the dividing the structural attribute of the target building according to the preset main building structural attribute to obtain the divided building structure includes:
Dividing the main building structure attribute into a wall structure, a door and window structure and a roof structure;
marking a wall body of the target building according to the wall structure, marking a door and window body of the target building according to the door and window structure, and marking a roof body of the target building according to the roof structure;
and taking the wall surface main body, the door and window main body and the roof main body as the dividing building structure.
6. The building visual modeling method based on BIM data according to claim 1, wherein the constructing the three-dimensional building model corresponding to the divided building structure according to the building boundary and the building attribute data using a preset three-dimensional semantic reconstruction algorithm includes:
extracting target building boundaries corresponding to the divided building structures one by one according to the building boundaries;
calculating the confidence coefficient of the boundary point in the boundary of the target building through a preset confidence coefficient algorithm, wherein the confidence coefficient algorithm is as follows:
wherein Z is k Boundary point confidence, n, for the kth boundary point 1k N is the number of boundary points above the boundary in the boundary of the target building 2k The number of boundary points below the boundary in the boundary of the target building;
Selecting an optimal boundary point of the boundary of the target building according to the confidence coefficient of the boundary point;
generating a partitioned building topological graph corresponding to the partitioned building structure according to the optimal boundary point;
generating mapping semantic attributes according to the building attribute data by using a preset three-dimensional semantic reconstruction algorithm;
and adding the mapping semantic attribute to the partitioned building topological graph to obtain a three-dimensional building model.
7. The building visual modeling method based on BIM data according to claim 1, wherein the generating the three-dimensional building hollowed-out model of the three-dimensional building model using a preset three-dimensional difference integration algorithm includes:
performing grid division on the three-dimensional building model to obtain a three-dimensional building grid;
dividing a building polyhedron of the three-dimensional building model according to the three-dimensional building grid;
calculating a three-dimensional difference product of the building polyhedron and the three-dimensional building grid by using the three-dimensional difference product algorithm, wherein the three-dimensional difference product algorithm is as follows:
A＝B τ -C σ
wherein A is the three-dimensional difference product and B τ C for the tau-th grid area in the three-dimensional building grid σ A sigma-th polyhedral region in the building polyhedron;
and generating the three-dimensional building hollowed-out model according to the three-dimensional difference product.
8. The building visual modeling method based on BIM data according to claim 7, wherein the performing model refinement on the three-dimensional building hollow model through a preset model script running time to obtain a three-dimensional refined building hollow model includes:
when the model script running time is larger than a preset model running time threshold, performing region optimization on the building polyhedron in the three-dimensional building hollowed-out model to obtain an optimized building polyhedron;
calculating an optimized three-dimensional difference product of the optimized building polyhedron and the three-dimensional building grid;
and carrying out model refinement on the three-dimensional building hollowed-out model according to the optimized three-dimensional difference product to obtain the three-dimensional refined building hollowed-out model.
9. The building visual modeling method based on BIM data according to claim 1, wherein the performing visual texture mapping on the three-dimensional refined building hollowed-out model through a preset multi-level detail algorithm and the building texture data to obtain a visual target building includes:
performing triangulation on the three-dimensional refined building hollowed-out model to obtain a triangular building area;
matching the triangular building area with the building area in the three-dimensional refined building hollowed-out model to obtain a texture matching area;
Mapping the building texture data to the texture matching area to obtain an initial texture map;
and (3) performing color correction on the initial texture map by using a multi-level detail algorithm as follows to obtain a visual target building:
wherein v is l V for the left region of the texture matching region r For the right region of the texture matching region,for the unique color of the left region in the texture matching region, +.>For the unique color of the right-hand region of the texture matching region, +.>For the color correction of the left region in the texture matching region, < >>For the color correction of the right-hand region of the texture matching region, < >>For the color in the texture matching area, +.>For color correction in the texture matching region, λ is the color control factor and argmin is the minimum function.
10. A building visualization modeling system based on BIM data, the system comprising:
the building data extraction module is used for acquiring BIM data of a target building and extracting building space data and building attribute data in the BIM data by utilizing a preset remote sensing algorithm;
a building boundary extraction module, configured to extract, according to a preset boundary constraint algorithm, a building boundary of the target building according to the building space data, and extract, according to the building attribute data, building texture data of the target building, where the extracting, by a preset boundary constraint algorithm, a building boundary of the target building according to the building space data includes: acquiring building labels of the building space data; performing morphological corrosion operation on the building label to obtain a building boundary label, and performing morphological expansion operation on the building label to obtain a building parting line label; calculating the label probability of the building label, the building boundary label and the building dividing line label by using a preset complete convolution network; calculating the building gray value of the target building according to the label probability through a preset boundary constraint algorithm, wherein the boundary constraint algorithm is as follows:
G＝P u ×(1-P l )×(1-kP h )
Wherein G is the building gray value, P u In the tag probabilityBuilding probability, P l P being a split line probability among the tag probabilities h Boundary probability k in the label probability is boundary constraint weight;
determining a building boundary of the target building according to the gray threshold value and the building gray value;
the three-dimensional building model construction module is used for dividing the structure attribute of the target building according to the preset main building structure attribute to obtain a divided building structure, and constructing a three-dimensional building model corresponding to the divided building structure according to the building boundary and the building attribute data by utilizing a preset three-dimensional semantic reconstruction algorithm;
the three-dimensional refined building hollowed-out model generation module is used for generating a three-dimensional building hollowed-out model of the three-dimensional building model by using a preset three-dimensional difference integration algorithm, and carrying out model refinement on the three-dimensional building hollowed-out model by using a preset model script running time to obtain the three-dimensional refined building hollowed-out model;
and the visual texture mapping module is used for performing visual texture mapping on the three-dimensional refined building hollowed-out model through a preset multi-level detail algorithm and the building texture data to obtain a visual target building.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310960376.6A CN116958476B (en) | 2023-07-31 | 2023-07-31 | Building visual modeling method and system based on BIM data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310960376.6A CN116958476B (en) | 2023-07-31 | 2023-07-31 | Building visual modeling method and system based on BIM data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116958476A CN116958476A (en) | 2023-10-27 |
| CN116958476B true CN116958476B (en) | 2024-03-15 |
Family
ID=88447384
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310960376.6A Active CN116958476B (en) | 2023-07-31 | 2023-07-31 | Building visual modeling method and system based on BIM data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116958476B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106127857A (en) * | 2016-06-24 | 2016-11-16 | 南京林业大学 | Synthetic data drives the on-board LiDAR data modeling method with model-driven |
| CN106339820A (en) * | 2016-08-31 | 2017-01-18 | 中国电建集团昆明勘测设计研究院有限公司 | Marine structure observed behavior multi-dimensional analysis method based on virtual reality and system |
| CN109410327A (en) * | 2018-10-09 | 2019-03-01 | 鼎宸建设管理有限公司 | A kind of three-dimension tidal current method based on BIM and GIS |
| CN109918751A (en) * | 2019-02-26 | 2019-06-21 | 华中师范大学 | A kind of building three-dimensional Semantic Modeling Method based on CityGML extension |
| CN110827402A (en) * | 2020-01-13 | 2020-02-21 | 武大吉奥信息技术有限公司 | Method and system for simplifying three-dimensional model of similar building based on rasterization technology |
| CN114092775A (en) * | 2021-11-23 | 2022-02-25 | 中国人民解放军战略支援部队航天工程大学士官学校 | Method, system and equipment for extracting window of supervision type building |
| CN114818056A (en) * | 2022-04-06 | 2022-07-29 | 深圳市同鑫科技有限公司 | Traffic data integration method, device, equipment and medium based on BIM technology |
| CN115147555A (en) * | 2022-08-02 | 2022-10-04 | 福建天蒙建设有限公司 | Building object frame model fine three-dimensional modeling method and system |
| CN116310192A (en) * | 2022-12-28 | 2023-06-23 | 江苏省测绘研究所 | Urban building three-dimensional model monomer reconstruction method based on point cloud |
| CN116503572A (en) * | 2023-04-24 | 2023-07-28 | 河北志晟信息技术股份有限公司 | Intelligent recruitment platform and space modeling method thereof |
-
2023
- 2023-07-31 CN CN202310960376.6A patent/CN116958476B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106127857A (en) * | 2016-06-24 | 2016-11-16 | 南京林业大学 | Synthetic data drives the on-board LiDAR data modeling method with model-driven |
| CN106339820A (en) * | 2016-08-31 | 2017-01-18 | 中国电建集团昆明勘测设计研究院有限公司 | Marine structure observed behavior multi-dimensional analysis method based on virtual reality and system |
| CN109410327A (en) * | 2018-10-09 | 2019-03-01 | 鼎宸建设管理有限公司 | A kind of three-dimension tidal current method based on BIM and GIS |
| CN109918751A (en) * | 2019-02-26 | 2019-06-21 | 华中师范大学 | A kind of building three-dimensional Semantic Modeling Method based on CityGML extension |
| CN110827402A (en) * | 2020-01-13 | 2020-02-21 | 武大吉奥信息技术有限公司 | Method and system for simplifying three-dimensional model of similar building based on rasterization technology |
| CN114092775A (en) * | 2021-11-23 | 2022-02-25 | 中国人民解放军战略支援部队航天工程大学士官学校 | Method, system and equipment for extracting window of supervision type building |
| CN114818056A (en) * | 2022-04-06 | 2022-07-29 | 深圳市同鑫科技有限公司 | Traffic data integration method, device, equipment and medium based on BIM technology |
| CN115147555A (en) * | 2022-08-02 | 2022-10-04 | 福建天蒙建设有限公司 | Building object frame model fine three-dimensional modeling method and system |
| CN116310192A (en) * | 2022-12-28 | 2023-06-23 | 江苏省测绘研究所 | Urban building three-dimensional model monomer reconstruction method based on point cloud |
| CN116503572A (en) * | 2023-04-24 | 2023-07-28 | 河北志晟信息技术股份有限公司 | Intelligent recruitment platform and space modeling method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116958476A (en) | 2023-10-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111563442B (en) | Slam method and system for fusing point cloud and camera image data based on laser radar | |
| US20200340813A1 (en) | Map feature extraction system for computer map visualizations | |
| CN109829399B (en) | Vehicle-mounted road scene point cloud automatic classification method based on deep learning | |
| US20190377981A1 (en) | System and Method for Generating Simulated Scenes from Open Map Data for Machine Learning | |
| CN105893972B (en) | Automatic monitoring method for illegal building based on image and implementation system thereof | |
| CN113449594B (en) | Multilayer network combined remote sensing image ground semantic segmentation and area calculation method | |
| US20180225539A1 (en) | Systems and methods for extracting information about objects from scene information | |
| CN111815776A (en) | Three-dimensional building fine geometric reconstruction method integrating airborne and vehicle-mounted three-dimensional laser point clouds and streetscape images | |
| US7983474B2 (en) | Geospatial modeling system and related method using multiple sources of geographic information | |
| US20110202326A1 (en) | Modeling social and cultural conditions in a voxel database | |
| CN116843845A (en) | Spatial data integration method and system applied to digital twin city | |
| CN112085835B (en) | Three-dimensional cartoon face generation method and device, electronic equipment and storage medium | |
| CN114758337A (en) | Semantic instance reconstruction method, device, equipment and medium | |
| CN110992366A (en) | Image semantic segmentation method and device and storage medium | |
| CN112242002B (en) | Object identification and panoramic roaming method based on deep learning | |
| CN117351521B (en) | Digital twinning-based power transmission line bird detection method, system, medium and equipment | |
| CN116343103B (en) | Natural resource supervision method based on three-dimensional GIS scene and video fusion | |
| CN112148820B (en) | Underwater terrain data identification and service method and system based on deep learning | |
| CN112528508A (en) | Electromagnetic visualization method and device | |
| CN114519819B (en) | Remote sensing image target detection method based on global context awareness | |
| CN114049462A (en) | Three-dimensional model monomer method and device | |
| CN114820975A (en) | Three-dimensional scene simulation reconstruction system and method based on all-element parameter symbolization | |
| Parente et al. | Integration of convolutional and adversarial networks into building design: A review | |
| Petschnigg et al. | Point based deep learning to automate automotive assembly simulation model generation with respect to the digital factory | |
| CN116206068B (en) | Three-dimensional driving scene generation and construction method and device based on real data set |
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 |