Method and system for constructing special-shaped arrangement matrix of urban indoor three-dimensional semantic model

A technology of semantic model and construction method, applied in 3D modeling, image analysis, image enhancement and other directions, can solve the problems of complex algorithm, unable to form urban semantic big data, unable to accurately describe urban architectural semantic model, etc., to achieve efficient construction. Effect

Active Publication Date: 2021-09-24
TERRA DIGITAL CREATING SCI & TECH (BEIJING) CO LTD
View PDF6 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

On the one hand, the existing technology only considers the semantic construction of a single building or a single community building when building an indoor semantic model, which cannot constitute a complete urban semantic big data
On the other hand, although with the aid of mathematical models, such as matrix, it can accurately locate, roughly describe the orientation relationship between buildings, and describe the functional categories of urban buildings (apartment, villa, factory, complex, etc.), and retrieve each The architectural components (such as the roof) of a building can be used to determine the type of architectural style. However, the mathematical matrix cannot accurately d

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
  • Method and system for constructing special-shaped arrangement matrix of urban indoor three-dimensional semantic model
  • Method and system for constructing special-shaped arrangement matrix of urban indoor three-dimensional semantic model
  • Method and system for constructing special-shaped arrangement matrix of urban indoor three-dimensional semantic model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0089] A method for constructing a special-shaped arrangement matrix of a city C indoor three-dimensional semantic model, comprising the following steps:

[0090] S1. Construct the special-shaped arrangement matrix of the semantic model of the building outline of city C;

[0091] S2. Construct the indoor 3D semantic model of the building of city C;

[0092] S3. Embedding the indoor 3D semantic model of the city C building into the corresponding city C building outline semantic model to complete the construction of the city C indoor 3D semantic model.

[0093] Based on urban C remote sensing images, such as figure 1 As shown, using the VGG-16 algorithm without additional layers as the CNN backbone network to extract a series of feature maps obtained by different convolutional layers, the feature map is 1 / 8 of the input image size;

[0094] At the same time, through the image pyramid algorithm FPN, different layers of the CNN backbone network are used to construct a feature py...

Embodiment 2

[0107] The difference between this embodiment and embodiment 1 is that said S1-1 specifically includes said steps S1-1-1-S1-1-3, and includes the following steps:

[0108] S1-1-5, such as image 3 , taking the acquisition of a building as an example, calculated according to Example 1 figure 2 The local feature map F of the building in the white circle of the upper left grid point represents the color RGB value within the frame of the building, and the color RGB value outside the frame is collected; the arithmetic mean value of the song is obtained

[0109] S1-1-6 According to figure 2 The RGB values ​​of a random point outside the frame of the building are R=110, G=96, and B=70, which belong to brown. The average value is 83 as the threshold, and R=83 red and white are selected, and the remote sensing images inside and outside the frame in the remote sensing image are binarized, so that the parts belonging to the ground in the frame are all red and other Some are white. ...

Embodiment 3

[0112] S2 specifically includes:

[0113] S2-1 Obtain the indoor floor plan data of the building involved in the contour extraction in Embodiment 2, wherein the indoor floor plan data is the indoor floor plan data of the specified building, graphical text data, and vectorized files data;

[0114] S2-2 preprocesses the indoor floor plan data to generate basic hierarchical household data; S2-2-1 extracts room boundaries and building outlines included in the indoor floor plan data;

[0115] Wherein, the step of preprocessing the indoor floor plan data includes:

[0116] S2-2-2 Perform wireframe segmentation and closed line completion processing based on the boundary information; and,

[0117] S2-2-3 Supplement information on the indoor floor plan data, wherein the supplementary information includes the address of the designated building, building number, room number, number of floors, room use, house area and the specified Building height information;

[0118] S2-3 Based on t...

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 provides a method for constructing a special-shaped arrangement matrix of an urban indoor three-dimensional semantic model. The method is characterized by comprising the following steps: S1, constructing a special-shaped arrangement matrix of an urban building contour semantic model; s2, constructing an indoor three-dimensional semantic model of the urban building; s3, embedding the urban building indoor three-dimensional semantic model into the corresponding urban building contour semantic model, and completing construction of the urban indoor three-dimensional semantic model. A simplified artificial intelligence network model is utilized to obtain a contour prediction model network of an urban building, an urban building contour semantic model is established, indoor three-dimensional semantics are embedded in the urban building contour semantic model, and an accurate urban three-dimensional semantic model is obtained. The method is simple in algorithm, the actual building position is accurately reflected through the construction method, and spatial distribution visualization and searchability of the urban indoor three-dimensional semantic model are achieved.

Description

technical field [0001] The invention relates to a method for constructing an indoor three-dimensional semantic model, in particular to a method for constructing an indoor three-dimensional semantic model of a city and a system thereof, and belongs to the field of graphical semantic construction. Background technique [0002] The semantic model is to establish a mapping relationship between the construction model and the feature or abstract identifier, and can accurately identify and retrieve the element objects in these models. It has become a popular technology in urban big data and even the realization of smart cities. On the one hand, the existing technology only considers the semantic construction of a single building or a single community building when building an indoor semantic model, which cannot constitute a complete urban semantic big data. On the other hand, although with the aid of mathematical models, such as matrix, it can accurately locate, roughly describe 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): G06T17/00G06T7/90G06T7/136G06T7/13G06T7/11G06F30/13G06F17/16
CPCG06T7/90G06T17/00G06T7/13G06T7/11G06T7/136G06F30/13G06F17/16G06T2207/20016
Inventor 刘俊伟
Owner TERRA DIGITAL CREATING SCI & TECH (BEIJING) CO LTD
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap