Geometric model non-rigid matching method and device using local and global information

A geometric model and global information technology, applied to computer parts, character and pattern recognition, instruments, etc., to achieve the effect of fast speed, improved accuracy and high precision

Pending Publication Date: 2021-03-26
BEIJING UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This restricts adding segment cons...

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
  • Geometric model non-rigid matching method and device using local and global information
  • Geometric model non-rigid matching method and device using local and global information
  • Geometric model non-rigid matching method and device using local and global information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] Such as Figure 4 As shown, this non-rigid matching method of geometric models using local and global information includes the following steps:

[0027] (1) The input is a pair of geometric models representing different poses of the same object, and the data type of the model is a grid type or a point cloud type;

[0028] (2) Calculate the density of each point in the model, and cut the geometric model according to the point density;

[0029] (3) For the segments obtained by segmentation, use the inter-segment error and the intra-segment error to match to obtain the segment matching result;

[0030] (4) Preserve the model through local-global commutativity, which includes segment-related descriptor constraints and segment-related operator commutativity constraints of geometric objects, uses segment matching information, and outputs point matching results.

[0031] The present invention firstly realizes the sub-shape segmentation of the geometric model based on the den...

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

According to the geometric model non-rigid matching method and device using local and global information, left and right symmetrical parts of the shape can be distinguished, and the accuracy of pointmatching is obviously improved. The method comprises the following steps: (1) inputting a pair of geometric models representing different postures of the same object, wherein the data type of the models is a grid type or a point cloud type; (2) calculating the density of each point in the model, and cutting the geometric model according to the density of the points; (3) matching the segments obtained by segmentation by using inter-segment errors and intra-segment errors to obtain a segment matching result; and (4) maintaining a model through local global exchangeability, the model including segment-related descriptor constraints and segment-related operator exchangeability constraints of the geometric object, and outputting a point matching result by using segment matching information.

Description

technical field [0001] The invention relates to the technical field of computer graphics, in particular to a geometric model non-rigid matching method using local and global information, and a geometric model non-rigid matching device using local and global information. Background technique [0002] When the motion of an object is not determined by a single bone, but by the joint motion of multiple bones, the object will undergo non-rigid deformation. For example, when holding an object or snapping fingers, the deformation experienced by the hand is non-rigid deformation. [0003] The non-rigid matching method of geometric models is to find the point-to-point or segment-to-segment correspondence between a pair (or a group) of non-rigid deformation geometric models. The earlier work on geometric model matching can be traced back to 2006, Brostein et al. Introducing generalized multidimensional scaling into surface mapping algorithms for finding minimal distortion embeddings ...

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): G06K9/62G06K9/34
CPCG06V10/267G06V10/757
Inventor 孔德慧李倩星王少帆李敬华尹宝才
Owner BEIJING UNIV OF TECH
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