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

Complementary method for 3D human motion data with time-series stability and low-rank structure

A technology of human motion and structural characteristics, applied in the field of three-dimensional human motion data completion, to achieve the effect of rapid completion

Active Publication Date: 2016-03-30
ZHEJIANG UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the work of Lai et al., only the low-rank structural characteristics of 3D human motion data are considered, and their model uses the SVT method for optimal solution, and there are certain shortcomings in speed

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
  • Complementary method for 3D human motion data with time-series stability and low-rank structure
  • Complementary method for 3D human motion data with time-series stability and low-rank structure
  • Complementary method for 3D human motion data with time-series stability and low-rank structure

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0054] Select 4 segments of human motion from the public 3D human motion data set CMU human motion data set, including walking, jumping, dancing and Tai Chi. Since most of the data in the CMU dataset are relatively pure and complete motion sequences, we simulate the real noise situation and generate two different missing data:

[0055] a) Randomly missing data, which is generated by randomly missing 40% of the data items;

[0056] b) Regularly missing data, 30% of the data is regularly lost, and each loss lasts for 60 frames, including 10 different marker points.

[0057] Combine the method proposed in this patent with other existing 3D human motion data complement methods: linear interpolation method (Linear), spline interpolation method (Spline), linear dynamic system method (Dynammo) and the low-level method proposed by Lai et al. Rank method (SVT), for comparison. The root mean variance is used as a measure to compare the completion effects of different methods.

[0058...

Embodiment 2

[0060] The MotionAnalysisEagle-4 digital real-time capture system of Moshen Company was used to collect three human motion sequences including walk, run and jump, with a total of 3178 frames. The parameter settings are the same as the previous example, and the comparison results of different methods are displayed in the form of key frames in the Figures 9 to 11 . The results show that when compared with the three-dimensional motion data to be completed, the output result of the method of the present invention can correctly complete the data, and even when dealing with long-term missing points, the completion result is still correct, and there will be no failure of the method Condition.

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 human motion data complementing method for maintaining a smooth and steady timing sequence and low-rank structural characteristics. The method is based on the characteristics of maintaining the smooth and steady timing sequence and the low-rank structural characteristics of three-dimension human motion data. Firstly, a section of three-dimension human motion sequence to be complemented is expressed as a three-dimensional motion data matrix form; secondly, a corresponding two-value mask matrix and a smooth constraint matrix are set according to the motion data matrix; thirdly, an augmentation Lagrangian scalar-multiplication method is adopted to optimize and solve a robust low-rank matrix filling mathematical model with a smooth and stable stored time sequence and a low-rank structural characteristic; at last, complementation is carried out on original three-dimensional human motion data according to an optimization result, and therefore complementation for incomplete three-dimensional human motion data is achieved. According to the method, rapid complementation for a single-section human motion sequence can be rapidly achieved without supporting of a data base, and meanwhile, certain resistance to noise is obtained.

Description

technical field [0001] The invention relates to three-dimensional human motion data completion and low-rank matrix filling, in particular to a three-dimensional human motion data complement method that maintains time sequence stability and low-rank structural characteristics. Background technique [0002] 3D human motion data acquisition and generation technology can be directly applied to the fields of virtual reality, 3D character animation production, human-computer interaction, human motion simulation, sports training analysis, medical sports rehabilitation, etc. Supported by 3D human motion data, it has important research and application value. [0003] However, even in the current commercial 3D human body motion capture equipment, due to the self-occlusion of the performer's body limbs, the occlusion of clothing, etc., the phenomenon of missing part of the human body markers often occurs. In order to solve this problem, various 3D human motion data completion methods ...

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): G06T7/20
Inventor 肖俊冯银付庄越挺计明明
Owner ZHEJIANG 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