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

Human body modeling method based on deformable ellipsoid model

A technology of ellipsoid model and modeling method, which is applied in the field of computer vision, can solve problems such as not reflecting key details well and low image matching accuracy, and achieve high precision, simple calculation, and good robustness

Inactive Publication Date: 2019-09-13
NANJING UNIV OF SCI & TECH
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, existing modeling methods for human body parts are difficult to describe with parametric models, cannot well reflect the key details in the motion process, and have low matching accuracy with actual images

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
  • Human body modeling method based on deformable ellipsoid model
  • Human body modeling method based on deformable ellipsoid model
  • Human body modeling method based on deformable ellipsoid model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0068] figure 2 A simple oval-shaped limb model is shown, but this model cannot accommodate the effects of skin changes on a human limb, such as stretching versus modeling. Therefore, in the present invention, we modify this and introduce the deformation function m(z):

[0069] m(z)=(dz+(dz) 2 +1) -1

[0070] This deformation function is unique because it results in a change in the shape of the ellipsoid, resembling a trumpet-like extended limb. image 3 Different functional forms are shown, while our functional form is more suitable for human limb segments. Linear "dz" caused positive and negative Z-axis ellipsoid non-uniformity and different geometrical changes. Figure 4 The resulting shape change is shown for m values ​​with different semi-major axes. When "m(z)=0", the equation simplifies to an ellipse, which is a special case of a limb in a stretched or relaxed state. The choice of "m(z)" depends on the shape and size that best represent the actual limb structure...

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 human body limb modeling method based on a deformable ellipsoid model. The method includes: modifying a standard implicit formula of the three-dimensional ellipsoid accordingto the geometrical shape of the limb skeleton, introducing a deformation function, and establishing a deformation model; and establishing a relationship between the deformation model and an actual limb image by using a distance transformation method, and performing accurate matching on the deformation model. According to the method, the three-dimensional ellipsoid can be established in limb muscledeformation, and the difference between a complex detail-based surface model and a simplified volume shape-based model is made up; the method is suitable for human tracking, motion analysis, gait recognition and other applications, limb modeling is independent of the whole human body, and the method can be easily integrated to any human body model.

Description

technical field [0001] The invention belongs to the technical field of computer vision, in particular to a human body modeling method based on a deformable ellipsoid model. Background technique [0002] Motion research in computer vision mainly focuses on the analysis of rigid body motion. For the more general non-rigid body motion in real life, scholars' research is still at a very immature stage. Of course, non-rigid human body modeling has achieved some success in the past dozen years, but their complexity and increased control parameters have caused shortcomings of one kind or another. K.Akita proposed the generalized cone model of limbs and D.Hogg proposed the elliptic cylinder model. Both are driven by at least 3 parameters, one is the length of the axis and the other is the cross-section of the major and minor axes. Nahas et al. use b-spline surfaces to represent human body parts and facial information through control point management. Petland et al. introduced a m...

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 Applications(China)
IPC IPC(8): G06T19/20
CPCG06T19/20G06T2219/2021G06T2219/2016
Inventor 米尔纳张苪潘海朗
Owner NANJING UNIV OF SCI & TECH
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