Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method for reconstructing Chinese ancient building meaning model and component gallery from single image

A single image, semantic model technology, applied in the field of reconstructing ancient Chinese architectural semantic models and component libraries from a single image, can solve problems such as the inability to generate meaningful architectural model components, the inability to change the model, and the high cost of large-scale models.

Inactive Publication Date: 2012-06-27
BEIHANG UNIV
View PDF3 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, image-based modeling is difficult to handle model details, and it is expensive to generate large-scale models
However, most existing methods can only generate 3D models, but cannot generate meaningful architectural model components, and the generated models cannot be changed into new models.

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 for reconstructing Chinese ancient building meaning model and component gallery from single image
  • Method for reconstructing Chinese ancient building meaning model and component gallery from single image
  • Method for reconstructing Chinese ancient building meaning model and component gallery from single image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031]The specific implementation manner of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0032] The technical solution adopted by the present invention to solve the technical problems existing in the prior art is: a method for reconstructing the semantic model and component library of ancient Chinese architecture from a single image, and the specific implementation steps of the method are as follows:

[0033] Step (1) preprocesses a single image and interactively segments building facades into meaningful parts, such as roofs, façades, platforms, and so on. Then, we calculate the tangent direction of the roof tiles, and finally obtain the projection matrix of the camera; then obtain the direction of the roof tiles, and then calibrate the image to restore the three-dimensional size of the building;

[0034] Step (A1) preprocessing:

[0035] First, in preprocessing, we interactively segment building facades into meaning...

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 brings forward a method for reconstructing a Chinese ancient building meaning model and a component gallery from a single image and is aimed at generating a complete, reusable three-dimensional building component gallery with correct meaning, the three-dimensional building component gallery is used for generating a three-dimensional building model, and a large scale city model can be generated. The method brings forward a method for automatically determining a roofing tile direction, and an image is calibrated according to symmetry and the roofing tile direction of a building. In order to identify a construction component in the image, a roof is automatically segmented into roofing tiles based on repeatability of the roofing tiles, then based on a position and width of an inner side column pointed out by a user, an outside column is identified. A dimension and texture of the construction component are automatically obtained from the calibrated and segmented image, the building component is generated, and a shape grammar compiler rapidly and automatically generates a three-dimensional Chinese ancient building model and a changed scene from the three-dimensional building component and shape grammar.

Description

technical field [0001] The invention belongs to the technical field of computer virtual reality and image-based modeling, specifically belongs to the field of identifying image calibration and segmentation, generating building components, and generating three-dimensional building models, and particularly relates to a method for reconstructing semantic models and component libraries of ancient Chinese buildings from a single image . Background technique [0002] As an important part of human civilization and world cultural heritage, ancient Chinese architecture has its unique structural characteristics. Two official classics, Zao Fa Shi (Song) and Engineering Practice Rules (Qing), describe most of the features of ancient Chinese architecture. However, the terms used in these two books are not modern and difficult for ordinary people to understand. Mr. Liang Sicheng, a master architect, studied ancient Chinese architecture (refer to "Liang Sicheng. Qing-style construction e...

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): G06T17/00
Inventor 赵沁平齐越侯飞
Owner BEIHANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products