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

Three-dimensional model retrieval method based on LSTM network multi-modal information fusion

A three-dimensional model, multi-modal technology, applied in digital data information retrieval, three-dimensional object recognition, character and pattern recognition, etc., can solve problems affecting algorithm performance, achieve accurate retrieval results, comprehensive description, and ensure scientific and accurate sexual effect

Pending Publication Date: 2019-08-23
TIANJIN UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Experiments show that the choice of different viewpoints can significantly affect the performance of view-based algorithms

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 retrieval method based on LSTM network multi-modal information fusion
  • Three-dimensional model retrieval method based on LSTM network multi-modal information fusion
  • Three-dimensional model retrieval method based on LSTM network multi-modal information fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0113] The specific implementation steps are as follows:

[0114] 101: For a given 3D model, normalization processing needs to be performed first, and then its views arranged in order are extracted;

[0115] 1) First of all, it is necessary to use the NPCA method to normalize the 3D model data to ensure that the direction of the 3D model is out of the given orientation, and the scale of the 3D model is within a given size space;

[0116] 2) When using the OpenGL visualization tool to extract the views of the 3D model, take the Z axis as the rotation axis, and extract a view every 30 degrees of rotation angle.

[0117] 102: For the view sequence, extract its view features; further, it is also necessary to extract the skeleton features containing structured information; when extracting, use a parallel computing method to increase the speed of calculating features;

[0118] Use the pre-trained VGG-16 network structure to complete the extraction process of the view features of th...

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 three-dimensional model retrieval method based on LSTM network multi-modal information fusion, and the method comprises the steps: for a given three-dimensional model, extracting a plurality of views of the three-dimensional model arranged according to a rotation angle sequence; extracting skeleton characteristics of a plurality of views in a multi-task and multi-angle manner, and obtaining structured information of the three-dimensional model according to the skeleton characteristics; extracting view feature vectors of a plurality of views, and inputting the view feature vectors into a layer of LSTM network structure; checking whether other feature vectors need to be extracted continuously or not; connecting the skeleton feature vector with the view feature vector subjected to one layer of LSTM to form a new feature vector, and inputting the new feature vector into a second layer of LSTM network structure for fusion; checking whether other to-be-fused featurevectors exist or not, if yes, forming a new feature vector again and inputting the new feature vector into the next layer of LSTM network structure for fusion; and taking the output of the last fusion as the final feature vector Q of the three-dimensional model, and finishing the final detection process of the three-dimensional model in combination with a similarity measurement method.

Description

technical field [0001] The invention relates to a three-dimensional model retrieval method. In particular, it relates to a 3D model retrieval method based on LSTM network multimodal information fusion. Background technique [0002] In recent years, thanks to the rapid development of related technologies, the number of 3D models has developed rapidly. On the one hand, the emergence and development of depth cameras make it possible to obtain 3D models by collecting the real world; on the other hand, the enhancement of graphics card and CPU performance, as well as the emergence of 3D modeling software, make virtual modeling simple and easy. . In addition, the rapid development of the Internet makes the dissemination of models easier and faster [1]-[4] . In view of this, 3D models are more and more widely used in various industries [6][7] . In the process of actual use, with the gradual increase of the 3D model database and the particularity of the 3D model data, it become...

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): G06K9/00G06K9/62G06F16/583
CPCG06F16/583G06V20/64G06F18/22
Inventor 刘安安龙行健聂为之
Owner TIANJIN 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