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

Human motion date recognizing method based on integrated Hidden Markov model leaning method

A technology integrating Hidden Markov and Hidden Markov, applied in character and pattern recognition, instruments, computer parts, etc., can solve the problems of high-dimensional disaster, indistinguishability, and high feature dimension

Inactive Publication Date: 2007-09-12
ZHEJIANG UNIV
View PDF0 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The feature dimensions extracted from motion data are usually very high, and the distance between each data will become almost the same due to the central limit law, which cannot be distinguished from each other, resulting in a high-dimensional disaster (Curse of Dimensionality) problem

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 motion date recognizing method based on integrated Hidden Markov model leaning method
  • Human motion date recognizing method based on integrated Hidden Markov model leaning method
  • Human motion date recognizing method based on integrated Hidden Markov model leaning method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0088] The training samples include 150 walking movements of various types. Attached Figure 4 shows the comparison of the recognition accuracy of walking movements using two learning methods, the weak hidden Markov model and the integrated hidden Markov model. The concrete steps that the method of the present invention is described in detail below this example implementation are as follows:

[0089] (1) Extract all the two-dimensional geometric features of the walking motion by the method described in step 1: extract a two-dimensional geometric feature to express that a right toe is located in front of the plane composed of the left ankle, left hip and root node in the walking motion fixed posture. we define 1≤i≤4 are four three-dimensional points, where 1 ,p 2 ,p 3 >Indicates the datum plane determined by the first three points, and the orientation depends on the order of the three points. Then we define as follows:

[0090]

[0091] Through the above definition, we ...

Embodiment 2

[0124] The training samples include 110 various types of boxing sports. Figure 5 shows the comparison of boxing sports recognition accuracy using two learning methods, the weak hidden Markov model and the integrated hidden Markov model. The concrete steps that the method of the present invention is described in detail below this example implementation are as follows:

[0125] (1) Extract a two-dimensional geometric feature using the method described in step 1 to express a fixed posture in which a right hand is located in front of the plane formed by the left shoulder, left hip and root node in boxing. we define 1≤i≤4 are four three-dimensional points, where 1 ,p 2 ,p 3 , > means the datum plane determined by the first three points, and the orientation depends on the order of the three points. Then we define as follows:

[0126]

[0127] Through the above definition, we define a feature function for any four adjacent joint points as follows:

[0128] ...

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 opens a identification method of human motion data based on integrated hidden Markov model learning method. This method extracts two-dimensional geometric features for capturing data from human motion, and then effectively reducts the dimensionality of movement features data by the introduction of dimension reduction methods of non-linear flow pattern learning, and finally learns the movement of sports database by adoption of Hidden Markov integrated learning based on self-adaptive advance algorithm for achieving fast retrieval of conventional movement. Two-dimensional geometric features extracted by the method well expresses the essential attribute of movement, dimensionality reduction methods of the expansion of nonlinear manifold will successfully map features of high-dimensional movement to low-dimensional space that can reflect the inherent links between data, thus greatly eliminates data redundancy. While this invention can study through drop dimensional data used by methods of integrated Hidden Markov Model learning, makes movement automatically identificate and classificate on the basis of high-precision.

Description

technical field [0001] The invention relates to the field of multimedia human three-dimensional animation, in particular to a recognition method of human motion data based on an integrated hidden Markov model learning method. Background technique [0002] Since the 1990s, with the rise of motion capture technology and the advancement of equipment technology, a large amount of 3D human motion capture data has been generated and widely used in computer animation, games, medical simulation, film special effects and other fields. With the emergence of massive 3D human motion capture databases, how to find the essential features that can correctly express motion information from complex human motions, how to correctly and efficiently identify motion data and efficiently process massive motion data, so as to effectively use Motion capture database becomes a new challenge. [0003] Motion is a harmonious combination of signals of each joint point. A reasonable motion feature descr...

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): G06K9/62
Inventor 庄越挺向坚吴飞
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