Infant sleeping posture detection method and device and computer readable storage medium

A sleeping position detection, infant technology, applied in computer parts, computing, instruments, etc., can solve the problems of inaccurate monitoring, prone to misjudgment, inconvenient to use, etc., to achieve good user experience, accurate monitoring, and accurate identification. Effect

Pending Publication Date: 2019-06-14
武汉星巡智能科技有限公司
View PDF3 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The sensor used in the first device is usually one of light sensor, infrared sensor, and temperature sensor. When detecting through these sensors, the sensor usually needs to be placed inside the quilt, which is inconvenient to use, and the monitoring is not accurate, and misjudgment is easy to occur In this case, it will increase the burden on parents
Another monitoring method is not only costly, but also does not have an interactive module or an alarm device, and parents may not be informed of dangerous or critical situations in time

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
  • Infant sleeping posture detection method and device and computer readable storage medium
  • Infant sleeping posture detection method and device and computer readable storage medium
  • Infant sleeping posture detection method and device and computer readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] see figure 1 , the invention provides a kind of infant sleeping posture detection method, it comprises the steps:

[0047] S100, acquiring video images based on visible light of the infant's sleeping state;

[0048] The preset area where the baby's head is located is photographed by a camera device based on visible light such as a CCD camera to obtain the sleep state of the infant.

[0049] S200, quickly generate a candidate form by processing the video image through the first convolutional neural network;

[0050] In a preferred embodiment of the present invention, the rapid generation of candidate frames through the first convolutional neural network includes: processing the video image using a full convolutional neural network to obtain candidate frames and boundary regression vectors, and at the same time, Candidate windows are calibrated against bounding boxes, and then non-maximum suppression is used to remove overlapping windows.

[0051] S300. Refining the ca...

Embodiment 2

[0100] see figure 2 On the other hand, the present invention also provides a device for detecting sleeping positions of infants, comprising:

[0101] Image acquisition module 1, used to acquire video images based on visible light of infant sleep state;

[0102] The first processing module 2 is used to process the video image through the first convolutional neural network to quickly generate a candidate form;

[0103] The second processing module 3 is configured to refine the candidate frames through a second convolutional neural network and discard at least partially overlapping frames, wherein the number of convolutional layers of the second convolutional neural network is greater than that of the first volume The number of convolutional layers of the product neural network;

[0104] The third processing module 4 is used to refine the candidate form through the third convolutional neural network, and simultaneously display the preset number of facial feature point position...

Embodiment 3

[0109] Another aspect of the present invention also provides a computer-readable storage medium, the computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to achieve the following step:

[0110] Obtain video images based on visible light of the sleep state of infants;

[0111] Processing the video image through the first convolutional neural network to quickly generate a candidate form;

[0112] Refining the candidate frames by a second convolutional neural network, discarding at least partially overlapping frames, wherein the number of convolutional layers of the second convolutional neural network is greater than the number of convolutional layers of the first convolutional neural network ;

[0113] Refining the candidate form through a third convolutional neural network, while displaying a preset number of facial feature point positions, wherein the number of convolutional layers of the third c...

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 an infant sleeping posture detection method and device and a computer readable storage medium. The method comprises the steps of obtaining a visible light-based video image ofan infant sleeping state; processing the video image through a first convolutional neural network to quickly generate a candidate window; refining the candidate forms through a second convolutional neural network, and abandoning at least a part of overlapped forms, the number of convolutional layers of the second convolutional neural network being greater than the number of convolutional layers ofthe first convolutional neural network; refining the candidate form through a third convolutional neural network, and displaying a preset number of facial feature point positions at the same time, the number of convolutional layers of the third convolutional neural network being greater than the number of convolutional layers of the second convolutional neural network; judging whether a face target exists in the video image or not; and if the human face target does not exist, sending the abnormal information to the mobile terminal. The method has the advantages of being accurate in monitoring, convenient to use and high in safety.

Description

technical field [0001] The invention relates to the technical field of infant monitoring, in particular to a face detector-based infant sleeping posture detection method, device and computer-readable storage medium. Background technique [0002] Infants and young children often turn over, kick the quilt, etc. during sleep, which may cause clothing to compress the mouth and nose, not cover the quilt, cross the safe area and fall out of bed, etc., affecting the sleep quality of infants and even endangering the safety of infants and young children. The body is healthy, and the baby spends a lot of time sleeping, so a device for detecting the baby's sleeping position came into being. [0003] Existing detection methods for detecting the baby's sleeping position generally include two types: one is to monitor the state of the baby with a device with a single sensor; the other is to use a camera to monitor. The sensor used in the first device is usually one of light sensor, infrar...

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): G06K9/00G06N3/04
Inventor 陈辉张晓亮
Owner 武汉星巡智能科技有限公司
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