Unlock instant, AI-driven research and patent intelligence for your innovation.

Classification method of human motion states based on class hierarchical mechanism

A technology of human motion and state classification, applied in computer parts, character and pattern recognition, instruments, etc., can solve problems such as the decline of the correct rate of human behavior pattern recognition and the inconsistency of data characteristics.

Active Publication Date: 2016-12-07
BEIJING UNIV OF TECH
View PDF5 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At the same time, due to the differences in human behavior patterns among different subjects, the action samples of the same action category generated by different subjects also have inconsistent data characteristics.
The above situation has resulted in a decline in the accuracy of human behavior pattern recognition that includes multiple categories

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
  • Classification method of human motion states based on class hierarchical mechanism
  • Classification method of human motion states based on class hierarchical mechanism
  • Classification method of human motion states based on class hierarchical mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] The patented invention will be further described in detail below with reference to the embodiments and accompanying drawings. It should be noted that the implementation of the patented invention is not limited thereto.

[0044] Such as figure 1 As shown, the specific implementation steps of a classification method for human motion state based on the category-hierarchical mechanism are as follows:

[0045] Step 1. Design an experimental paradigm that includes different types of actions, and use a data acquisition device that includes a three-axis acceleration sensor and a three-axis gyroscope sensor to collect corresponding types of action samples according to the experimental paradigm. The present invention defines human motion state as lying, sitting, standing, walking, brisk walking, running, upstairs, downstairs, turning around, lying to sitting, sitting to standing, standing to sitting, sitting to lying down 13 different types of actions.

[0046] Step 2. According...

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

A classification method of human motion states based on a class hierarchical mechanism includes design of different classes of actions and action sample collection, sample segmentation and class annotation of different classes of actions, action sample data preprocessing, action sample feature extraction, and feature selection based action data, classifier construction based on the class hierarchical mechanism, classification method validation, and the like. The invention takes the class hierarchical mechanism as the core, and aims at reducing the phenomenon of misclassification of test samples due to the influence of other class training samples on a classifier in the classification process, so as to improve the recognition accuracy of the human motion states and the recall rate. The invention can be used as a core classification method for any human motion state recognition, and has strong versatility and portability.

Description

technical field [0001] The present invention relates to the technical field of motion state monitoring, in particular to a method for classifying human body motion state based on a category layering mechanism, which aims to reduce the phenomenon of misjudgment of test sample categories due to the influence of classifiers on other types of training samples during the classification process, To achieve the purpose of improving the accuracy and recall rate of human motion state recognition. The invention can be used as a core classification method for any kind of human motion state recognition, and has strong versatility and portability. Background technique [0002] In today's society, the accelerated pace of life and increased work pressure make more and more people in a sub-health state. In this way, people pay more and more attention to their health status and take various measures to improve their health status, such as adjusting their work and rest rhythm, eating a reaso...

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
CPCG06F18/241
Inventor 万志江钟宁李东佩何强闫建卓
Owner BEIJING UNIV OF TECH