Human body motion capturing data retrieval method based on bionic pattern recognition

A technology of bionic pattern recognition and human motion, applied in the field of human motion capture, can solve the problems of low calculation efficiency, limited promotion and application, etc., achieve good robustness, ensure retrieval efficiency, and avoid a large number of redundant calculations

Active Publication Date: 2012-07-04
DALIAN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the disadvantage of this method is that the computational efficiency is low
Limit the promotion and application of this method

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 motion capturing data retrieval method based on bionic pattern recognition
  • Human body motion capturing data retrieval method based on bionic pattern recognition
  • Human body motion capturing data retrieval method based on bionic pattern recognition

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0021] A human body motion capture data retrieval method based on bionic pattern recognition, comprising loading a human body motion capture data retrieval system developed based on C++ programming language and OpenGL graphics library into a computer and constructing and initializing a human body motion capture database. The concrete implementation mode of step is as follows:

[0022] 1. A group of shared BVH format motion capture databases obtained online can be used as a platform to implement the method of the present invention. In the following descriptions of the present invention, this database is used as an example. The database includes hundreds of sports data in standard BVH format, which are stored in a specific directory in the form of files, and the file names are marked according to different collectors and collection sequences. For example, 12_01.bvh represents the first one of the 12th collector. Action, the sports data does not contain a text description of the ...

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 human motion capture data retrieval method based on biomimetic pattern recognition, which relates to the technical field of human motion capture, in particular to a method for representing, extracting and retrieving characteristics in optical human motion capture data. The method is to introduce the biomimetic pattern recognition theory, to extract main characteristics in motion data first to construct characteristic vectors, to construct a 'super-sausage' coverage area in a corresponding higher dimensional space aiming at characteristic vectors of a certain type of retrieval conditions, to define coverage sequences, to further evaluate the similarity of the coverage sequences, and to realize retrieval of the motion capture data finally. The retrieval method is suitable for retrieving the human motion capture data after actual test, and has good practicality and robustness.

Description

technical field [0001] The invention relates to the technical field of human motion capture, in particular to a feature representation, extraction and retrieval method in optical human motion capture data. Background technique [0002] With the development of computer software and hardware technology, human motion capture technology has gradually developed into an important means of data acquisition in the fields of virtual reality, computer vision, film and television animation production, etc. Emerging disciplines that interpenetrate and cross each other have expanded the field of computer applications, enriched the research content in the fields of computer animation and virtual reality, and have important theoretical value. Human body motion capture technology has a wide range of practical application values, and can be applied to many industries such as industry, agriculture, transportation, culture, education, health, and sports, especially in the fields of medicine, s...

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 魏小鹏肖伯祥张强
Owner DALIAN UNIV
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
Try Eureka
PatSnap group products