Achieving method of human movement recognition training system

A technology for human action recognition and training system, which is applied in the field of training systems that generate specific human action recognizers, can solve the problems of slow recognition speed and large amount of calculation, and achieves fast recognition speed, easy implementation, and simple logic design and algorithm. reasonable effect

Inactive Publication Date: 2014-01-01
柳州市博源环科科技有限公司
View PDF3 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This algorithm has achieved good results, but it still has some shortcomings, such as the calculation of the feature file is relatively large, the recognition speed is relatively slow, etc.

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
  • Achieving method of human movement recognition training system
  • Achieving method of human movement recognition training system
  • Achieving method of human movement recognition training system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] A method for realizing a human motion recognition training system, comprising the following steps:

[0047] (1) Collection of training information:

[0048] The various action samples that need to be recognized are collected through the depth detection camera and the third-party SDK, and when the collected sample data is stored, the storage format includes the following fields: Action ID (Action ID: Int32), Action Name (Action Name: String), logarithm of motion information frame (Frame Count: Integer), depth information frame (Depth Frame #n: Integer Array) and bone information frame (Skeleton Frame #n: Integer Array);

[0049] (2) Regularization processing of sample data:

[0050]a. Unify the coordinate system, that is, perform coordinate transformation on the depth information data and bone information data of each frame, and unify them into the same world coordinate system;

[0051] b. Discretize the coordinates of bone points, that is, discretize the coordinates o...

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 an achieving method of a human movement recognition training system. The method includes the following steps of (1) collecting training information, (2) normalizing sample data, (3) extracting a characteristic three-dimensional vector set, and (4) recognizing and identifying motions. According to the method, a reduced precision discretization coordinate algorithm is used for simplifying operation information representation and reducing calculation amount of a characteristic extraction algorithm, and meanwhile a multi-level feature matching algorithm is used for accelerating the recognition speed. The achieving method is simple and reasonable in logical design and algorithm, feasible, reliable and easy to achieve.

Description

technical field [0001] The invention belongs to the technical field of computer engineering, and relates to a method for realizing a training system based on machine learning for generating a specific human action recognizer. Background technique [0002] Action recognition is a very popular research field in recent years. Through image capture equipment, the recognition process of human body actions can be completed in a short period of time, and converted into operating instructions for computers and other equipment; thus it is used as an effective input method. Applied to a wide range of applications such as games and movie production. [0003] The first problem to be solved in action recognition is to find the part of the human body. The part of the human body is the basis for action recognition, which is generally called "focus position". Because usually the attention position is exposed parts such as human face and hands, and its color is quite different from the envi...

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 Applications(China)
IPC IPC(8): G06K9/62
Inventor 覃祖茂刘为袁增伟杜怡曼何佳李东娥刘晓黄益农黄华峰
Owner 柳州市博源环科科技有限公司
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
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap