Building three-dimensional model semantization method

A technology of 3D models and buildings, applied in the field of 3D semantic modeling of buildings, can solve the problems of restricting the development of urban data, and achieve the effect of avoiding real scene shooting

Active Publication Date: 2021-04-27
泰瑞数创科技(北京)股份有限公司
View PDF9 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This limits the development of urban data and the formation of ba

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Building three-dimensional model semantization method
  • Building three-dimensional model semantization method
  • Building three-dimensional model semantization method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] Such as figure 2 Under the geographical coordinate system GL of a certain known provincial capital city A shown, there is a sub-region of interest at the vertex of the vector Oo. Establish the coordinate system L of the geographic sub-region. The origin of L is on floor 5 of local 1, that is, on the xoy plane where the foundation is located. The verticality of the wall and the quality of the coating material on the outer surface of the wall are determined). Part 1 of a certain floor drawing of a 28-story apartment building divided in L (the floor is the first floor). This part 1 belongs to a building in the training set that participated in the construction of the method of this embodiment, and the coordinates of the geometric center c (not shown) of the corresponding building a in the corresponding software drawing under L are used as the building pointer P1, P2, P3..., thus belonging to the establishment of multiple geographic sub-region drawing libraries, and mult...

Embodiment 2

[0040] Then carry out the semantic classification of building functions, use the part 1 in the embodiment 1 as the training image, and the ratio of the actual training training set and the verification set is 2:1. First, classify the types of building functions to form a type text image as the identification unit, use the word "apartment" to select the No. 3 Song typeface, and create a computer-recognizable graphic type picture p ij Such as Figure 4 As shown, as the recognition unit for the classification of buildings such as apartments, the geometric center coordinates of each building in the training set drawings under L are arranged in a matrix M= from west to east and from north to south in L. , where matrix element a m1 means figure 2 The matrix element of a building in the southwest corner of the middle part 1 under L, a m1 Including the geometric center coordinates P of the building m1 , and building component parameters.

[0041] Among them, the building compon...

Embodiment 3

[0048] Continue embodiment 2 for matrix element a m1 Construct a textual semantic model (other matrix element processing methods are the same), including the following steps:

[0049] S3-1 Use 3Dmax software to extract each building component in the architectural drawings, such as figure 2 Including the west exterior wall 2, the south exterior wall 3, the interior wall 4, the floor 5, the beam 6, the window hole 7, and the beam hole 8, obtain the four vertices of each building component closest to a rectangular surface of x-o-y-z under L Coordinates, build matrix m 西外墙 = , m 南外墙 = , m 内墙 = , m 楼层 = , m 梁 = , m 窗洞 = , m 梁洞 = , where b ij22 is the geometric center coordinates of building components (ij=west exterior wall, south exterior wall, interior wall, floor, beam, window opening, beam opening), and its z-axis coordinate is defined as the height of the building under L, other non-zero matrix elements are four vertex coordinates, the four vertices of ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a building three-dimensional model semantization method based on a software drawing. The building three-dimensional model semantization method comprises the steps that S1, a known geographic area coordinate system is established; s2, building function semantic classification; s3, constructing a textualized semantic model; s4, building roof semantic recognition and verification of a textualized semantic model; and S5, judging unknown building types and establishing an unknown city database. According to the method, semantic recognition of the building can be accurately carried out on the city level, so that urban water, electricity and gas and the building are guided, and intelligent management and application of search purposes of other industries are assisted.

Description

technical field [0001] The invention relates to a three-dimensional model semantic method of a building, in particular to a method for organizing a text semantic model of building construction, and belongs to the field of three-dimensional semantic modeling of buildings. Background technique [0002] Building identification is a project of smart city construction, which plays a vital role in the digitization of cities. The previous technology used CAD, 3DMAX, UG and other software to realize the local identification and data tracking of the detailed structure and building components (walls, floors, roofs) and their parameters of a single building individual, but did not identify and classify them. [0003] Three-dimensional semantic modeling is a kind of semantic construction based on the characteristics of different recognition targets, so as to display the corresponding position on the graphic carrier. There are roughly two directions for 3D existing semantic modeling. Th...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06T17/05G06F16/55G06F16/56G06K9/62G06N3/04G06N3/08G06N20/10
CPCG06T17/05G06F16/55G06F16/56G06N20/10G06N3/08G06N3/045G06F18/2411
Inventor 刘俊伟
Owner 泰瑞数创科技(北京)股份有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products