Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A kind of motion training method based on mems sensor

A training method and sensor technology, applied in sports accessories, gymnastics equipment and other directions, can solve problems such as difficult to judge human body movements and cannot accurately identify human movements, etc., to achieve targeted training, good guidance effect, and good use effect.

Active Publication Date: 2020-09-15
重庆电政信息科技有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, the use of image sensors for action recognition cannot accurately identify human actions when the light is poor, and it is difficult to make standardized judgments on human actions, and it is impossible to provide effective standard action guidance

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
  • A kind of motion training method based on mems sensor

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] The preferred embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings, so that the advantages and features of the present invention can be more easily understood by those skilled in the art, so as to define the protection scope of the present invention more clearly.

[0026] A kind of motion training method based on MEMS sensor, such as figure 1 shown, including the following steps:

[0027] S1: Establish a standard action database and an action recognition model based on multiple standard action data.

[0028] S2: Label the human actions in the standard action data to form labeled action data, and then use the deep learning algorithm to train the labeled action data and output the training results. In the present invention, the deep learning algorithm used is a convolutional neural network algorithm, which can continuously reduce the dimensionality of the image recognition problem with a huge amount of data,...

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 the field of human body action recognition technology, and aims to provide a motion action training method based on MEMS sensors. The technical solution disclosed by the invention includes: establishing a standard action database and an action recognition model based on a plurality of standard action data; labeling human actions in the standard action data to form labeledaction data, and then training the labeled action data by using a deep learning algorithm and outputting training results; correcting the action recognition model according to the training results; aplurality of MEMS sensors collecting and outputting current user action data of different body parts of a user in real time; and recognizing the current user action data, then inputting the current user action data into the action recognition model for calculation, and outputting action correction information. The motion action training method of the invention can judge the actions of the user andgive the action correction information. In this way, the user can easily grasp the standard of the actions thereof, and the guiding effect is good.

Description

technical field [0001] The invention relates to the technical field of human action recognition, in particular to a MEMS sensor-based exercise action training method. Background technique [0002] Action recognition technology is widely used in competitive sports, health checks, medical research, pedestrian navigation and rescue, etc. At present, human action recognition based on visual recognition technology is usually used. In the prior art, image sensors such as CCD (Charge-coupled Device, charge-coupled device) or CMOS (Complementary Metal Oxide Semiconductor, Complementary Metal Oxide Semiconductor) sensors are mainly used to collect user action images, and then the collected visual images are analyzed by the processor. , processing, to realize the feature extraction of user action images, and to complete the action recognition process. [0003] However, the use of image sensors for motion recognition cannot accurately recognize human body motions when the light is poo...

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): A63B24/00
CPCA63B24/0062A63B24/0075A63B2220/836
Inventor 李丰
Owner 重庆电政信息科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com