Yoga motion recognition method based on multiple acceleration sensors

An acceleration sensor and action recognition technology, applied in the field of yoga action recognition based on multiple acceleration sensors, can solve the problems of high computational complexity, poor real-time data processing capability, high implementation cost, etc., and achieves low computational complexity, reliable parameters, Achieving low-cost effects

Active Publication Date: 2019-05-10
SUN YAT SEN UNIV
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The primary purpose of the present invention is to provide a yoga action recognition method based on multiple acceleration sensors, which solves the problems of high computational complexity, high implementation cost and poor real-time data processing ability in traditional action recognition methods. The technical solution of the present invention is as follows:

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
  • Yoga motion recognition method based on multiple acceleration sensors
  • Yoga motion recognition method based on multiple acceleration sensors
  • Yoga motion recognition method based on multiple acceleration sensors

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] see figure 1 , a yoga action recognition method based on multiple three-dimensional acceleration sensors, the method flow is as follows:

[0046] figure 1 It is the overall structure diagram of the system. The present invention adopts a plurality of acceleration sensors to collect the acceleration data in the X, Y, and Z directions of the specific positions of the wrists of both hands, the ankles of both feet, the forehead, and the chest. When the user performs an action, first, the three-axis accelerometer senses the change of acceleration, and sends the collected data to the microprocessor; then, the microprocessor packages the data of the three-axis accelerometer, and transmits it through wireless transmission technologies such as Bluetooth. Send it to the mobile phone client; then, the client receives the data collected from different sensors, uses time synchronization technology to align the data, and arranges all the aligned data into a sample data matrix S, and ...

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 yoga motion recognition method based on multiple acceleration sensors. The yoga motion recognition method comprises the steps that acceleration data of an accelerometer in the X direction, the Y direction and the Z direction are collected through the accelerometer arranged on a yoga sporter; the acceleration data is sent to the microprocessor, and the microprocessor packages the acceleration data and sends the acceleration data to the client through a wireless transmission technology; after receiving the data, the client performs alignment processing on the data, arranges all the aligned data into a sample data matrix, then preprocesses the sample data matrix, and extracts a sample characteristic matrix representing actions; and matching the input sample feature matrix with a standard action feature matrix stored in a database to realize yoga action recognition. Three-dimensional acceleration data are collected, a standard feature sequence is constructed for action recognition and analysis, parameters are reliable, simple and feasible, the calculation complexity is low, the requirement for relevant hardware is low, and the implementation cost is low.

Description

technical field [0001] The present invention relates to the field of human motion recognition, and more specifically, to a method for recognizing yoga motions based on multiple acceleration sensors. Background technique [0002] The era of national fitness has come. People pay more and more attention to their physical and mental health. Yoga movements use ancient and easy-to-master techniques to improve people's physical, psychological, emotional and spiritual abilities. It is a way to achieve harmony and unity of body, mind and spirit. Therefore, yoga is favored by more and more people. However, people's life rhythm is very fast, and usually there is not enough time to find a professional yoga teacher to systematically learn technical exercises such as yoga, and people urgently need to learn through smart devices such as mobile phones. Therefore, it is very necessary to develop related motion recognition and correction systems on ordinary smart phones. [0003] The curren...

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): G06K9/00G06K9/62
Inventor 黄晓林嘉良保延翔
Owner SUN YAT SEN UNIV
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