Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Real-time evaluation method of human body motion sequences

An evaluation method and technology of human motion, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve the problem of ignoring the temporal and spatial structure information of local motion blocks

Inactive Publication Date: 2016-10-12
北京九艺同兴科技有限公司
View PDF5 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Existing action feature extraction methods generally include global spatiotemporal information, but ignore local motion blocks and their spatiotemporal structure information, and the distribution of such motion blocks in three dimensions of space and time constitutes a complete action

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
  • Real-time evaluation method of human body motion sequences
  • Real-time evaluation method of human body motion sequences
  • Real-time evaluation method of human body motion sequences

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0113]Embodiment: The present invention uses two "Stand up" in the Florence3D-Action action data set to evaluate action similarity.

[0114] (1) Express the action in the form of multiple joint sequences: and

[0115] (2) Use the difference-based interval interpolation wavelet to perform periodic extension on P, and use the method in step 2 of the previous section to solve the wavelet coefficients to obtain key frames.

[0116] (3) Calculate the DTW matching of P and Q, and obtain the key frame of Q according to the key frame of P and the result of DTW matching, as shown in step 3.

[0117] (4) Calculate the average distance between key frames and normalize it to obtain the similarity scores of P and Q, as shown in step 4.

[0118] Firstly, the present invention is based on the change of the action block in the front and back frames, and extends the action segment based on the interval interpolation wavelet of the difference, so as to ensure that the signals inside and ou...

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 relates to a real-time evaluation method of human body motion sequences. Boundary extension is carried out on the motion sequences by employing interpolating wavelet based on difference, thereby reducing boundary effect; a wavelet coefficient is calculated, thereby obtaining key frames; features of the motions are described through the key frames; the distance between two motion sequences is calculated by employing a DTW distance measurement function; finally the distance is normalized, thereby obtaining a similarity score of the two motions. The method has the advantages that the boundary effect is reduced by employing the interval interpolating wavelet, thereby obtaining the more accurate key frames, and further the more accurate motion evaluation is realized.

Description

technical field [0001] The invention relates to a human body action similarity evaluation calculation, in particular to a real-time evaluation method of a human body action sequence, belonging to the field of human action evaluation. Background technique [0002] In order to perform action similarity evaluation, it is necessary to extract features that can fully characterize the motion, time, space, and shape information of the action. Bobick and Davis proposed to use motion energy image (Motion Energy Image, MEI) and motion history image (Motion History Image, MHI) as spatio-temporal templates, and used Mahalanobis distance to measure the similarity between templates. MEI superimposes binary images based on the time axis, and uses the superimposed overall shape and position to describe human movements. Its shortcoming is that it does not take the time sequence of the movement into consideration. The MHI establishes a motion history function for each pixel, reflecting the 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): G06F19/00
CPCG16Z99/00
Inventor 张瑞萱汪成峰王庆张凯强
Owner 北京九艺同兴科技有限公司
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
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