Method and system for classification of walking and standing still based on micro-inertia technology

A motion classification and standing still technology, which is applied in character and pattern recognition, medical science, diagnosis, etc., can solve problems such as classification that no one has proposed, and achieve the goal of avoiding track estimation errors, simple and effective algorithms, and reducing the amount of calculation Effect

Active Publication Date: 2021-10-01
INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, the motion types of motion classification based on micro-inertia technology mainly include: walking, running, climbing stairs, descending stairs, forward / backward / sideways walking and running, standing, etc. Classification and Classification Methods Proposed
However, in the pedestrian track deduction system based on micro-inertia technology, if the standing still movement is regarded as normal walking, it may cause relatively large errors

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
  • Method and system for classification of walking and standing still based on micro-inertia technology
  • Method and system for classification of walking and standing still based on micro-inertia technology
  • Method and system for classification of walking and standing still based on micro-inertia technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] Preferred embodiments of the present invention are described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present invention, and are not intended to limit the protection scope of the present invention.

[0046] At present, the main methods for motion classification of micro-inertial technology are: decision tree, hidden Markov model (HMM), support vector machine (SVM), multi-layer perceptron (MLP), bidirectional long short-term memory recurrent neural network ( BLSTM-RNN) etc. The classification model adopted in the present invention is a fully connected neural network, that is, a multi-layer perceptron (MLP) model. Compared with the traditional method of directly classifying the motion data of the inertial sensor, the method of the present invention requires the data of the inertial sensor to be divided according to steps in advance, and 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 belongs to the technical field of motion classification, and specifically relates to a walking and standing still motion classification method and system based on micro-inertia technology, aiming to solve the problem of accurate recognition of walking and standing still. The method of the present invention includes S1, obtaining a Sampling data of the step action, the data including the acceleration and angular velocity data of the step action; S2, unifying the sampling data into gait data of the same size; S3, calculating the acceleration and angular velocity of the step action based on the gait data The modulus value of angular velocity, and obtain step data matrix; S4, described step data matrix is ​​spliced ​​into vector by row as the characteristic vector of this step; S5, described step characteristic vector input pre-built gait classification model carries out this step Classification of action sports. The invention can effectively identify walking motion and stepping motion, effectively avoid track estimation error, and reduce calculation amount and algorithm complexity at the same time, so that the algorithm is simple and effective.

Description

technical field [0001] The invention belongs to the technical field of motion classification, and in particular relates to a walking and standing motion classification method and system based on micro-inertia technology. Background technique [0002] With the development of micro-electro-mechanical systems (MEMS), especially the development of micro-inertial technology, the use of micro-inertial sensors for pedestrian trajectory deduction and motion analysis has broad application prospects. At present, quite a few pedestrian trajectory deduction systems based on micro-inertial technology have been designed at home and abroad, and many of them have classified various types of motion in the trajectory deduction system. Motion classification can provide more motion information for the trajectory derivation system, and plays an important role in improving the accuracy of the trajectory. [0003] At present, the motion types of motion classification based on micro-inertia techno...

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): G06K9/62A61B5/11
CPCA61B5/1123G06F18/214G06F18/24
Inventor 杜清秀吴源朱海兵汤淑明
Owner INST OF AUTOMATION CHINESE ACAD OF SCI
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