A human motion recognition system and method based on a smart phone

A technology of human motion recognition and smart phones, applied in pattern recognition in signals, character and pattern recognition, computer components, etc., can solve problems such as inaccurate subjective understanding, and achieve the effect of optimizing calculation energy consumption and high resolution ability

Active Publication Date: 2020-01-17
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In fact, in the traditional medical field, the demand for long-term human motion monitoring is becoming stronger and stronger. For example, the diagnosis of some mental illnesses requires the knowledge of the patient's motion characteristics, and the current technology is mainly through subjective inquiries of patients and their family members. But especially for patients, this subjective understanding is not accurate, because the patient cannot accurately remember or describe the state at that time. In this case, if the device-based human motion recording is used, objective data can be obtained. Help doctors diagnose and treat

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 human motion recognition system and method based on a smart phone
  • A human motion recognition system and method based on a smart phone
  • A human motion recognition system and method based on a smart phone

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0077] Such as figure 1 As shown, the specific implementation process includes two parts and 12 steps:

[0078] In the first part, the working steps of the client:

[0079] Step 1 is that when the user opens the client, the client application starts the main thread, and step 2 is that the main thread starts to try to establish a reliable network connection with the server at the same time. At the same time, in step 3, the main thread starts 3 background services to monitor the orientation sensor, acceleration sensor and gravity sensor respectively. Used for identification. After selecting the training mode, the main thread judges whether the sample is qualified, and if it is qualified, it will be stored in the sample set and used for later training, then go to step 6. If you choose to identify, go to step 5. In step 5, the main thread in the client divides and encodes the collected three sensor data, and uses the sending thread to send the data to the server.

[0080] In ...

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 body action recognition scheme using a smart phone sensor platform. In the present invention, a kind of online human body action recognition system of client / server architecture is designed by using various sensors integrated in smart phones and network connection services, and a posture correction algorithm of multi-sensor information fusion is designed to solve the problem of mobile phone posture inaccuracy. Fixed an issue that caused sensor axis information to be lost. The present invention proposes a feature extraction scheme for acceleration time series by using a sliding window, and uses a multi-core support vector machine for multi-modal information combination classification. The human body action recognition system designed in the present invention using the smart phone sensor platform has versatility and effectiveness.

Description

technical field [0001] The invention relates to mobile portable devices, in particular to mobile phone posture correction algorithms, feature extraction algorithms and machine learning algorithms in human body posture recognition technology based on mobile smart phone sensor data. Background technique [0002] Medical health is receiving more and more attention in today's social life. Now there are many medical monitoring devices, such as smart bracelets that can be seen everywhere. It judges the number of steps by the value of the sensor, and estimates the walking distance and calorie consumption based on the age, gender, height, weight and other information entered by the user. This human motion monitoring method based on threshold judgment has the characteristics of fast speed and simple equipment, and can play a good role in some environments where the accuracy is not high. In such a hot era of smart bracelet technology, the importance of this convenient and portable hu...

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): H04M1/725G06K9/00
CPCH04M1/72454G06V40/20G06F2218/04G06F2218/08G06F2218/12
Inventor 张道强丁毅
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
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