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

Segmentation Method of Human Movement Sequence Based on Least Squares Distance Feature Curve

A technology of human motion and least squares, applied in the field of data reuse technology, can solve problems such as low efficiency, high cost of motion segments, and rarely used, so as to achieve the effect of improving accuracy

Active Publication Date: 2016-03-30
DALIAN UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although directly capturing human motion segments or manually segmenting motion sequences can obtain motion segments with fixed semantics, due to the complexity and variety of human motion and the huge amount of motion data, obtaining motion segments through these two methods is not only costly And it is inefficient and rarely used in practical applications

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
  • Segmentation Method of Human Movement Sequence Based on Least Squares Distance Feature Curve
  • Segmentation Method of Human Movement Sequence Based on Least Squares Distance Feature Curve
  • Segmentation Method of Human Movement Sequence Based on Least Squares Distance Feature Curve

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The technical solution of the present invention is: first, calculate the least squares distance between each frame data in the motion sequence and a fixed posture template, simplify the motion sequence into a motion characteristic curve, use wavelet filter to carry out denoising processing to the characteristic curve; Then extract the main extremum points in the motion curve, define the part between the adjacent extremum points as the kinetic element unit, and obtain a kinetic element sequence; finally, perform similar clustering on the kinetic element units, according to the hierarchy of human motion Structural features, using the characteristic that different semantic actions are composed of different motion units in different orders, divide the motion sequence into motion segments with specific semantic features, and perform boundary detection on each semantic segment to realize semantic actions precise segmentation. attached figure 1 Shown is the algorithm flow cha...

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 least square distance characteristic curve-based human motion sequence segmentation method. In the method, least square distances among human motion postures are introduced as characteristics of human motion data on the basis of capturing data by human motions so as to define similarity among the postures; human motion sequences are simplified into a motion curve and then are segmented into motion fragments with specific semantics by analyzing a human motion law. The similarity of the human motion postures defined by the method complies with a subjective judgment of a human body, and segmentation effects are consistent with a manual segmentation result substantively, thus providing data guarantee and technical support for data reuse technologies, such as motion data retrieval and synthesis.

Description

technical field [0001] The invention relates to an intelligent processing of three-dimensional human body capture data, which is mainly used for data reuse technologies such as retrieval and synthesis of motion data. Background technique [0002] With the development of computer animation technology, using motion capture data to drive character models to generate animation has become a key technology in 3D animation production. In recent years, motion capture technology has developed rapidly, and motion capture equipment has gradually become popular. With the accumulation of motion capture data and the continuous expansion of data scale, many commercial and non-commercial motion capture databases have emerged to provide users with rich data resources. However, due to the high cost of commercial motion capture equipment, high operation and maintenance costs, and time-consuming and labor-intensive data acquisition process, the cost of data acquisition is relatively high. At 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
Patent Type & Authority Patents(China)
IPC IPC(8): G06F17/30
Inventor 张强刘瑞魏小鹏
Owner DALIAN 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