Human behavior recognition method based on accelerometer

A technology of accelerometer and recognition method, which is applied in character and pattern recognition, calculation, computer parts and other directions, and can solve the problems of time-consuming and labor-intensive human behavior sample data and increased development cost of human behavior model

Active Publication Date: 2014-01-08
SOUTH CHINA UNIV OF TECH
View PDF4 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, manual calibration of human behavior sample data is time-consuming and laborious
Using the linear discriminant analysis model for training requires a large

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 based on accelerometer
  • Human behavior recognition method based on accelerometer
  • Human behavior recognition method based on accelerometer

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0088] In order to clearly illustrate the effectiveness of the present invention for human behavior recognition based on accelerometers, as figure 1 As shown, in this embodiment, a test of human behavior recognition is carried out, and compared with the classic linear discriminant analysis (LDA).

[0089] The test data selects the common SCUT NAA data set. The South China University of Technology's natural human action based on accelerometer (SCUT NAA) database is the first public human action database based on a three-axis accelerometer. The database is collected under completely natural conditions with only one triaxial accelerometer placed on the belt of the collector, including 1278 samples from 44 different collectors (34 males, 10 females). 10 types of actions. These movements cover a large range of motion, such as static movements such as sitting, lighter movements such as walking, and vigorous movements such as jumping and running.

[0090] In addition, we extracted ...

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 behavior recognition and classification method based on an accelerometer. The method includes the first step of collecting human behavior samples as a training set, the second step of searching for a projection matrix U which is optimal for the recognition and classification of the training set, the third step of carrying projection on no-labeled data, and the fourth step of classifying the projected data by using a minimum distance classifier to obtain a recognition result. According to the human behavior recognition method, a partial approximate linear hypothesis is carried out on adjacent blocks formed by labeled data so as to enable the distance between different types of samples on the blocks to be large enough, positional sequence information of the same type of samples is reserved as far as possible through class sigmoid function penalty factors, and finally a global objective function is established on the basis of the objective functions on all blocks. The human behavior recognition method can reserve the information of the distance between the samples in a higher dimensional space properly, and reduces dependence of recognition models on artificial tagging samples, and the recognition effect is superior to a representative human behavior recognition method based on linear discriminant analysis.

Description

technical field [0001] The invention relates to a pattern recognition and artificial intelligence technology, in particular to an accelerometer-based human behavior recognition method. Background technique [0002] Human action recognition is a complex problem that spans many disciplines and has received great attention in the field of industrial informatization. The basic steps include acquisition of perceptual signals, information processing and pattern classification. In recent years, many effective methods have been proposed to automatically recognize human actions. These methods can be classified into two categories: one is based on computer vision, and the other is based on accelerometers. Human behavior analysis systems based on computer vision do not work well in industrial environments because they are very sensitive to lighting conditions. In recent years, the application of accelerometer-based human behavior recognition in industrial environments has received m...

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 陶大鹏金连文黎小凤
Owner SOUTH CHINA UNIV OF TECH
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