Three-dimensional model characteristic extract method based on relevancy information and device thereof

A technology of 3D model and feature extraction, which is applied in character and pattern recognition, image data processing, instruments, etc., can solve the problem that the 3D model does not accurately represent the feature information of the 3D model

Inactive Publication Date: 2012-10-03
BEIHANG UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In the process of realizing the present invention, the inventor found that the feature extraction method of the 3D model in the prior art has at least the following problems: the method considers that the correlation between each projected depth image and the 3D model is the same, and the calculated 3D The feature vector of the model does not accurately represent the feature information of the 3D model

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
  • Three-dimensional model characteristic extract method based on relevancy information and device thereof
  • Three-dimensional model characteristic extract method based on relevancy information and device thereof
  • Three-dimensional model characteristic extract method based on relevancy information and device thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0062] The processing flow of a method for feature extraction of a 3D model based on correlation information provided by this embodiment is as follows: figure 1 As shown, the following processing steps are included:

[0063] Step 11: Obtain six depth images respectively corresponding to the six faces of the 3D model by using the depth buffer algorithm.

[0064] In the embodiment of the present invention, firstly, the depth buffer algorithm is used to obtain six depth images of the three-dimensional model, and the specific processing process mainly includes:

[0065] Perform normalized preprocessing of translation, scaling, and rotation on the 3D model. The normalization of translation makes the center of mass of the 3D model move to the origin, the normalization of scaling makes the average distance from each point on the surface of the 3D model to the center of mass a constant, and the normalization of rotation makes the 3D model The three principal axes of are the x, y, an...

Embodiment 2

[0116] The embodiment of the present invention also provides a feature extraction device for a 3D model based on correlation information, and its specific implementation structure is as follows figure 2 shown, including:

[0117] A correlation acquisition module 21, configured to acquire depth images corresponding to each surface of the three-dimensional model, and calculate the correlation between each depth image and the three-dimensional model;

[0118] A feature vector acquisition module 22, configured to weight the correlation between each depth image and the 3D model calculated by the correlation calculation module into the feature vector corresponding to the surface corresponding to each depth image, Get the eigenvectors of the 3D model.

[0119] Described correlation acquisition module 21 comprises:

[0120] The depth image acquisition module 211 is used to perform normalized preprocessing of translation, scaling, and rotation on the 3D model by using the depth buff...

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 three-dimensional model characteristic extract method based on relevancy information and a device thereof. The method mainly includes: depth images respectively corresponding to each face of a three-dimensional model are acquired, relevancy of each depth image and the three-dimensional model is calculated; the relevancy of each depth image and the three-dimensional model is weighted into the characteristic vector corresponding to the corresponding face of each depth image, so as to obtain the characteristic vector of the three-dimensional model. By utilizing the invention, characteristic extraction can be effectively carried out on the three-dimensional model, and the calculated characteristic vector of the three-dimensional model can accurately show the characteristic information of the three-dimensional model.

Description

technical field [0001] The invention relates to the field of computer applications, in particular to a feature extraction method and device for a three-dimensional model based on correlation information. Background technique [0002] In recent years, with the emergence of more and more 3D models on the Internet, how to retrieve these 3D models has become a key issue. 3D model retrieval refers to retrieving several 3D models most similar to it through an existing 3D model. The similarity of two 3D models refers to the sum of the squares of the distances from any point on the surface of one 3D model to the closest point on the surface of another 3D model in the normalized coordinate system. However, directly comparing the similarity of two 3D models requires a lot of computing time, which is not suitable for the real-time requirements of the current 3D model retrieval system. Therefore, it is necessary to extract features from the 3D models to obtain feature descriptors. Sin...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62G06T7/00
Inventor 冷彪徐州川陈浪石熊璋
Owner BEIHANG UNIV
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