Sleep state monitoring energy-saving elderly-assisting system based on deep learning image recognition

A sleep state, image recognition technology, applied in transmission systems, character and pattern recognition, acquisition/recognition of facial features, etc., can solve problems such as electricity safety, and achieve the effects of low cost, simple system installation, and low technical requirements

Inactive Publication Date: 2019-12-03
NORTHEAST DIANLI UNIVERSITY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the deficiencies of the prior art, provide a sleep state monitoring energy-saving system for the elderly based on deep learning image recognition, and solve the problem of electricity safety caused by not being able to accompany the elderly for a long time; the present invention uses human eye state recognition and detection technology Analyze the image with body recognition detection technology, can quickly judge whether the user is in a sleeping state, and can remotely control the TV on and off, which has the advantages of energy saving for home appliances and helping children understand the living conditions of the elderly

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
  • Sleep state monitoring energy-saving elderly-assisting system based on deep learning image recognition
  • Sleep state monitoring energy-saving elderly-assisting system based on deep learning image recognition
  • Sleep state monitoring energy-saving elderly-assisting system based on deep learning image recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0068] This embodiment discloses a sleep state monitoring system based on deep learning image recognition, please refer to the attached figure 1 As shown, it includes a front-end device 10, a small server 11, a power control module 13 and a back-end device 12; the front-end device 10 is connected to the small server 11 through the network, and the small server 11 is connected to the power control module 13 and the back-end device 12 through the network respectively ; The back-end equipment 12 is also connected to the front-end equipment 10 through the network;

[0069] The front-end device 10 is used to collect image information in front of the TV 14, and transmits the collected image information to the small server 11; the front-end device 10 is also used to realize remote video calls with the back-end device 12; the front-end device 10 It is also used to query the data information stored in the small server 11;

[0070] The small server 11 is used to receive and store image...

Embodiment 2

[0082] On the basis of Embodiment 1, this embodiment provides a sleep state monitoring method for deep learning image recognition, please refer to the attached figure 2 shown, including:

[0083] S1. Collect image information of the human body, upload the collected image information to a small server, and the small server recognizes and analyzes the image information;

[0084] S2. The small server analyzes and judges the image information through the image processing system. The image processing system analyzes and judges the image information, including detecting human body movement through optical flow contour feature points and body pixel point recognition methods, and recognizing human body movement through human eye recognition. The detection method judges the face information to obtain the open and closed state of the user's eyes;

[0085] S3. Determine whether the user is in a sleep state according to the judgment of human body movement and face information, and outpu...

Embodiment 3

[0132] On the basis of Embodiment 1 and Embodiment 2, this embodiment also includes a login management method, specifically including:

[0133] Before entering the main interface to operate, the user needs to perform identity verification, and can only operate after logging in to the system. The login interface is planned to be a Gridlayout layout, pursuing a simple UI design. After running, the login system interface will pop up automatically. Just enter the correct account number and corresponding password. If you do not have an account number, you can click the registration button at the bottom of the screen to register. The login function is implemented based on the SQlite portability database owned by the background.

[0134]After entering the correct account number and password, the user can enter the main interface. In the main interface, there are different options in units of days, which classify the guardianship situation. Users can choose daily guardianship reports ...

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 sleep state monitoring energy-saving elderly-assisting system based on deep learning image recognition, and the system consists of front-end equipment, a small-size server, apower control module and rear-end equipment, and can collect an image and upload the image to the small-size server through a network. An image processing system in the small server analyzes the image by using a human eye state recognition detection technology and a limb recognition detection technology, and sends a control signal to a power supply control module after judging that the old peoplefall asleep; a Bluetooth communication device in the power supply control module receives a control signal of the small server and generates a corresponding infrared control signal, and an infrared transmitting device in the module controls the volume, brightness and power supply of the television, so that the aim of saving energy is fulfilled; and the small server also regularly sends a report to the rear-end children mobile phone and receives a network query request of the front-end equipment or the rear-end equipment, so that the purpose of helping the aged is achieved.

Description

technical field [0001] The invention relates to the technical field of image processing and analysis, in particular to a sleep state monitoring system based on deep learning image recognition. Background technique [0002] At present, population aging has become an extremely serious social problem in our country. There are three reasons for this: the implementation of the family planning policy has gradually reduced the number of newborns in our country; Progress has greatly increased the average life expectancy of the elderly. At the same time, children are unable to go home often due to busy work, and it is common for empty-nest elderly to live alone. If the elderly do not know how to use smartphones, their loneliness will become more severe and family ties will become weaker. The application of the assistance system for the elderly enables children to work with more peace of mind and reduces accidents. [0003] Elderly people often fall asleep while watching TV, and tur...

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 Applications(China)
IPC IPC(8): G06K9/00G06N3/04G08B21/04G08B21/06H04L29/08
CPCG08B21/0407G08B21/06H04L67/025G06V40/171G06V40/174G06V40/20G06N3/045
Inventor 娄娟石画王佳兴王日舟万兆嬴赵牧驰赵佳慧刘丰瑞刘佳霖庄可好王梓丞
Owner NORTHEAST DIANLI UNIVERSITY
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