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

Human Behavior Recognition Method

A recognition method and behavior technology, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve the problems of inability to analyze various human behaviors in various occasions, large amount of data calculation, and inconvenient collection, etc., to achieve Increased flexibility and practicability, small amount of collected data, and high classification efficiency

Inactive Publication Date: 2015-11-18
SHAANXI NORMAL UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these existing analysis methods usually have the following deficiencies: First, the existing acceleration-based human behavior recognition methods often need to collect acceleration data of various joints such as the neck and limbs of the human body for analysis, which is not only inconvenient to collect, but also complex in system and difficult to calculate. large amount
Second, in terms of analysis results, the existing methods can only analyze human behavior for a specific purpose, such as monitoring whether the human body falls, monitoring the type of sign language according to the acceleration of fingers, etc., and cannot universally analyze various human behaviors. Behavior thus applies to a variety of situations

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 Behavior Recognition Method
  • Human Behavior Recognition Method
  • Human Behavior Recognition Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] (1) Determine the behavior classification standard

[0040] Pre-set 5 types of behavior categories, namely static, leg shaking, twisting left and right, swinging left and right, standing up and sitting down, the acceleration acquisition device is installed on the waist of the human body, and the acceleration acquisition device is installed on the waist of the human body to collect the X, Y, Z directions when standing still. The corresponding acceleration value a X 、a Y 、a Z , to calculate the acceleration sample variance S in the X direction when standing still X , Y-direction acceleration sample variance S Y , the acceleration sample variance S in the Z directionZ , repeat the acquisition several times, and take the average value, respectively According to a X 、a Y 、a Z Calculate the acceleration vector magnitude SVM and sample variance Ssvm, take the average constitutes a column vector of standard values ​​corresponding to standing still In the same way,...

Embodiment 2

[0079] In the human body behavior recognition method in Embodiment 1, the m-type behavior categories in step 1 are divided into static, walking, running, going upstairs, and downstairs, and other steps are the same as in Embodiment 1.

Embodiment 3

[0081] In the human body behavior recognition method in Embodiment 1, the behavior categories of m types in step 1 can be three types, namely jumping, walking, and running, and other steps are the same as in Embodiment 1.

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 human behavior recognition method which mainly includes steps of acquiring human waist acceleration information by an acceleration acquisitor worn on the human waist within a certain sampling cycle, generating behavior classification membership array according to the acquired human waist acceleration data and analyzing category of the human behavior. Only a small quantity of data are required to be acquired, the acquisition process is simple and convenient, the human behavior category and quantity can be increased or decreased optionally according to proper environments and occasions, so that flexibility and practicability of the human behavior recognition method are improved. Further, the human behavior recognition method is simple and convenient, high in classification efficiency and accuracy, and capable of realizing simultaneous analysis of a large number of tested groups; analysis result is saved in a database and can be checked by observers conveniently; the human behavior recognition method can be used for realizing classification of different human behavior recognition in multiple fields and occasions such as teaching, medicine science, security, man-machine interaction and the like.

Description

technical field [0001] The invention belongs to the technical field of intelligent information processing, and specifically relates to a recognition method for generating a behavior classification model based on the basic idea of ​​fuzzy mathematics and analyzing human behavior categories. Background technique [0002] The analysis and understanding of human behavior has great application value and important research significance in the fields of teaching, medicine, security, human-computer interaction and so on. For example, in the field of teaching, by analyzing the behavior of students in the classroom, it is helpful to improve the quality of students' learning; in the field of medicine, by analyzing the behavior of patients, it can provide support for medical diagnosis and treatment, so as to make active and effective treatment; In the field of security, through the analysis of abnormal human behavior, abnormal situations can be effectively avoided. [0003] At home and...

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 吴晓军马悦
Owner SHAANXI NORMAL UNIV