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

Pre-sleep activity recognition method based on deep learning and sleep detection device

A technology of activity recognition and deep learning, applied in the field of bedtime activity recognition based on deep learning, can solve problems such as staying up late and poor self-control ability of teenagers, and achieve the effect of reducing the processing process, improving the effect, and correcting the bad habit of staying up late

Pending Publication Date: 2021-03-26
上海悠络客电子科技股份有限公司
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a method for identifying activities before going to bed based on deep learning, so as to solve the problem of poor self-control ability of teenagers and excessively long activities before going to bed, which lead to serious problems of staying up late

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
  • Pre-sleep activity recognition method based on deep learning and sleep detection device
  • Pre-sleep activity recognition method based on deep learning and sleep detection device
  • Pre-sleep activity recognition method based on deep learning and sleep detection device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 2

[0058] A sleep detection device, comprising the following modules:

[0059] The image acquisition module is used to receive each frame source image intercepted from the infrared night vision camera, and record the corresponding system time of each frame source image.

[0060] The human eye key point detection module is used to input the preprocessed image into the human eye key point detection model to obtain the human eye key point and its position coordinates. Figure 4 It is the facial feature point distribution before and after falling asleep provided by the present invention.

[0061] The EAR numerical calculation module is used to calculate the EAR numerical value.

[0062] The sleep state judgment module is used to judge whether to be in a sleep state based on the EAR value, if it is in a non-sleep state, then enters the activity recognition module before going to bed, and if it is in a sleep state, then stops detection;

[0063] The pre-sleep activity recognition mod...

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 provides a pre-sleep activity recognition method based on deep learning and a sleep detection device. The method comprises the steps of receiving each frame of source image captured froman infrared night vision camera, recording system time corresponding to each frame of source image, and preprocessing the images; inputting the preprocessed images into a human eye key point detection model to obtain human eye key points and position coordinates thereof; calculating an EAR value based on the human eye key points; judging whether a person is in a sleep state or not, if the personis in a non-sleep state, executing the following steps, and if the person is in the sleep state, stopping detection and recording sleep time; inputting the preprocessed images into a pre-sleep activity recognition model, and outputting activities recognized in each frame of image through calculation of the pre-sleep activity recognition model; recording the pre-sleep activities recognized in eachframe of image and the system time corresponding to the images from beginning to end; and finally, counting obtained pre-sleep activity data to generate a complete daily pre-sleep activity report.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a method for recognizing activities before going to bed based on deep learning. Background technique [0002] The phenomenon of staying up late is especially common among teenagers. Frequent staying up late has a great health impact on the body. Common hazards include decreased immunity, mental disorders, slowed brain and physical development, and so on. Teenagers often stay up late because they lack self-control and spend too much time before going to bed. Especially with the popularity of mobile phones and tablet computers and the rapid development of entertainment industries such as mobile games and social software, the phenomenon of teenagers playing mobile phones for a long time before going to bed is becoming more and more serious. It's getting serious. The present invention aims at the phenomenon and reason why teenagers generally stay up late, and p...

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): A61B5/00
CPCA61B5/4809A61B5/7264
Inventor 陶宇翎刘东海沈修平
Owner 上海悠络客电子科技股份有限公司
Features
  • Generate Ideas
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com