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

Learning environment action behavior recognition method based on learning table

A technology of learning environment and identification method, applied in the field of action behavior identification of learning environment based on study table, can solve problems such as being unsuitable for children, and achieve the effects of improving learning concentration, improving reliability and improving identification efficiency

Pending Publication Date: 2022-05-31
杭州好学童科技有限公司
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The present invention mainly solves the problem that the algorithm and device for recognizing motions in the prior art are not suitable for children's motion behavior recognition during learning; it provides a learning environment motion behavior recognition method based on a learning table, through a device integrated on the learning table Action recognition for children in the learning state, so as to judge small movements during learning, and help parents improve children's learning concentration

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
  • Learning environment action behavior recognition method based on learning table

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0049] A method for recognizing actions and behaviors in a learning environment based on a study table in this embodiment, such as figure 1 shown, including the following steps:

[0050] S1: Determine whether there are children in front of the learning table through the human body detection algorithm, so as to determine whether to enable the action recognition algorithm.

[0051] S101: The camera set on the study desk acquires pictures or video streams in front of the study desk.

[0052] S102: Determine whether there is a child in front of the study table according to the trained human detection algorithm model, if yes, go to step S103; if not, go back to step S101.

[0053] The human detection algorithm is yolov3 algorithm, faster RCNN algorithm or SSD algorithm. In this embodiment, the human body detection algorithm is yolov3.

[0054] The model building process of the human detection algorithm model is as follows:

[0055] A1: Collecting image sample data; image sample...

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 learning environment action behavior recognition method based on a learning table. The problem that in the prior art, an action recognition algorithm and device are not suitable for action behavior recognition during learning of children is solved. The method comprises the following steps of S1, judging whether a child exists in front of a learning desk or not through a human body detection algorithm so as to judge whether to start an action recognition algorithm or not; s2, starting an action recognition algorithm, collecting pictures in front of the learning desk within a certain time, and arranging and integrating the pictures into a plurality of combined pictures according to a time sequence; and S3, judging the category of the composite image according to the change of the action feature points of the composite image in the spatial position, and judging the action of the child in front of the learning desk within the time period. Through the camera integrated on the intelligent learning desk, actions of a child in front of the desk are recognized, small actions of the child in a learning environment are judged, and parents are helped to improve learning concentration of the child.

Description

technical field [0001] The invention relates to the field of learning action recognition, in particular to a learning table-based learning environment action behavior recognition method. Background technique [0002] There are many algorithms and devices for recognizing actions on the market, but none of them are suitable for children's action and behavior recognition during learning. At the same time, most study desks at this stage are not equipped with corresponding functions. [0003] When children are learning, I hope to use certain methods to judge the children's current learning behaviors and actions, understand the actions that children appear in learning and the possible meanings of children's actions, and hope to use the recognition results to judge the current situation. Children's learning situation, help parents to scientifically standardize children's learning behavior, help children correct bad little movements, so as to improve children's concentration in lear...

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): G06V40/20G06V40/10G06V10/774G06K9/62
CPCG06F18/214
Inventor 胡东明
Owner 杭州好学童科技有限公司
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