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

Feature analysis method for three-dimensional point cloud under hyperbolic conformal mapping

A technology of 3D point cloud and conformal mapping, applied in image analysis, image data processing, 3D modeling, etc., can solve problems such as complex calculations, and achieve the effect of expanding the scope of application

Inactive Publication Date: 2019-12-06
TAIYUAN NORMAL UNIV
View PDF1 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Most of the existing methods are designed in Euclidean space or spherical space to design the Litsch flow, there are only approximate mapping results with the original surface or the calculation is too complicated to be directly used to solve practical application problems

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
  • Feature analysis method for three-dimensional point cloud under hyperbolic conformal mapping
  • Feature analysis method for three-dimensional point cloud under hyperbolic conformal mapping
  • Feature analysis method for three-dimensional point cloud under hyperbolic conformal mapping

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0065] Applying a feature analysis method of 3D point cloud under hyperbolic conformal mapping to the BU3DFER 3D face data set of the State University of New York at Binghamton, the United States can realize the recognition of facial expressions. The specific implementation steps are as follows:

[0066] Step 1: For the given 3D point cloud data, use the Delaunay triangulation algorithm to triangulate it to create a discrete surface; directly extract the 3D people in the BU3DFER 3D face dataset of the State University of New York at Binghamton face surface;

[0067] Step 2: For discrete surfaces with non-negative Euler's characteristic number, use the convolutional network to estimate the key point position of the discrete surface with non-negative Euler's characteristic number. Calibrate the point line; use the BU3DFER three-dimensional face dataset of the State University of New York at Binghamton, USA, and extract the main facial feature points according to step 2, such as ...

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 feature analysis method for a three-dimensional point cloud under hyperbolic conformal mapping. A universal framework and algorithm for conformal structure measurement in hyperbolic geometric space are provided, so that three-dimensional point clouds of any depletion can be conformally mapped into a hyperbolic Poincare model consistently, and a hyperbolic conformal feature descriptor is constructed by calculating coordinates of a basic domain in a Taihe miller space. Finally, the method provided by the invention is applied to a public face data set BU3DFER to realizeface expression recognition. Experimental results show that compared with conformal features of the Euclidean geometric space, the feature descriptors in the hyperbolic space provided by the inventionare not sensitive to singular point selection, and the recognition rate of facial expressions is effectively improved; compared with other non-conformal feature descriptors, the method provided by the invention has the advantage that the number of required facial feature points is remarkably reduced under the condition of keeping the same recognition rate.

Description

technical field [0001] The invention relates to the technical field of feature extraction methods, in particular to a feature analysis method of a three-dimensional point cloud under hyperbolic conformal mapping. Background technique [0002] 3D point cloud can approximate the original surface, and has important application value in many fields such as medical imaging, computer vision and 3D printing, and has attracted the attention of many researchers. The feature representation, segmentation, registration and classification of 3D point cloud , Recognition, Retrieval, Rendering and Reconstruction and other aspects of theoretical and applied research work has become a research hotspot in geometry and algebraic topology and other disciplines. Among them, the feature representation of 3D point cloud is a necessary prerequisite for other related research work. How to extract the representative features of 3D point cloud, and effectively reduce the complexity of the algorithm t...

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): G06T17/20G06T7/73
CPCG06T17/205G06T7/73G06T2207/10028
Inventor 阴桂梅况立群韩燮郭广行
Owner TAIYUAN NORMAL 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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com