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

A method and system for intelligent learning to walk based on deep learning

A deep learning and intelligent technology, applied in the field of Internet education, can solve the problems of insufficient leg strength of children, danger of children with obstacles, and affecting the health of parents.

Active Publication Date: 2020-07-07
暗物智能科技(广州)有限公司
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But this is very unsafe, there will be a lot of sundries piled up in the room, obstacles will bring danger to children, and the baby walker slides very fast, on the sloped ground, for children, the strength of children's legs is insufficient, May cause inability to brake in time
[0003] When parents accompany their children to use the baby walker, the height of the baby walker is low, and parents often need to bend down or squat when pulling the baby walker, which will affect the health of the parents for a long 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
  • A method and system for intelligent learning to walk based on deep learning
  • A method and system for intelligent learning to walk based on deep learning
  • A method and system for intelligent learning to walk based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0063] Such as figure 1 As shown, a method of intelligent walking learning based on deep learning includes the following steps:

[0064] 101: Obtain an image ahead of the user's moving direction and store the image;

[0065] 102: Extract the obstacle area from the image, and mark the obstacle area with the first marker;

[0066] 103: Extract an open area from the image, and mark the open area with a second marker;

[0067] 104: Set several target points in the open area and store the target points, the target points are evenly spaced and gradually extend to the distance along the open area;

[0068] 105: Obtain the current location of the user, and generate a navigation route where the current location is in an open area. The navigation route connects the current location and the target point in series, and the navigation route is the shortest route;

[0069] 106: Projecting the navigation route in an open area;

[0070] 107: Obtain the location information of the user in ...

Embodiment 2

[0099] Obtaining the user's current location and generating a navigation route for the current location in an open area also includes;

[0100] The navigation route includes several branch lines, which respectively connect the user's current location with the target point and two adjacent target points, establish a third corresponding relationship between the branch line and the two connected position points and store the third corresponding relationship, the position point Including current position and target point.

[0101] Such as Figure 5 As shown, projecting the navigation route in the open area also includes:

[0102] Extract a target point closest to the user's current location;

[0103] Extract the first branch line corresponding to the target point and the current position;

[0104] Project the first branch line in the open area.

[0105] Such as Figure 6 As shown in , the distance between the user and the target point in the first branch line is calculated in...

Embodiment 3

[0112] Such as Figure 7 As shown, obtaining the user's location information in real time and storing the location information also includes:

[0113] Extract the user's real-time location information and the obstacle area around the location information;

[0114] Calculate the shortest distance between the location information and the obstacle area;

[0115] Determine whether the shortest distance is less than or equal to the preset distance;

[0116] If so, lock the user to stay at the location information;

[0117] Unlock the user when the user tends to move in other directions.

[0118] Such as Figure 8 As shown, when the shortest distance is less than or equal to the preset distance, it also includes:

[0119] Get obstacles in the obstacle area;

[0120] Calculate the hazard level of the obstacle;

[0121] Extract the warning information corresponding to the danger level;

[0122] Output warning messages to the user.

[0123] Specifically, in the process of free...

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 intelligent walking learning method based on deep learning and a system thereof. The method comprises the following steps: acquiring an image of the front of a moving direction of a user and storing the image; extracting an obstacle area and marking with a first mark; extracting an open area and marking with a second mark; setting a plurality of target points in the openarea with the target points evenly spaced and gradually extending far away along the open area; acquiring current position of the user, and generating a navigation route of the current position in the open area; projecting the navigation route into the open area; acquiring the user's position information in real time; generating the user's movement track, and establishing first correspondence between the movement track and the navigation route; calculating similarity between the movement track and the navigation route and establishing second correspondence between the similarity and the navigation route; and when the similarity is greater than or equal to the preset similarity, the navigation route corresponding to the similarity is deleted, indicating that the user has the walking ability in a corresponding area of the navigation route by the use of the method and the system.

Description

technical field [0001] The present invention relates to the field of Internet education, in particular to an intelligent learning-to-walk method and system based on deep learning. Background technique [0002] At present, the usage rate of baby walkers for children to learn to walk has become more and more widespread. Children riding on baby walkers can slide freely, walk in any place without falling, and learn to walk through children's independent learning. function. But this is very unsafe, there will be a lot of sundries piled up in the room, obstacles will bring danger to children, and the baby walker slides very fast, on the sloped ground, for children, the strength of children's legs is insufficient, It may result in failure to brake in time. [0003] When the parents accompany their children to use the baby walker, the height of the baby walker is low, and the parents often need to bend down or squat when pulling the baby walker, which will affect the health of the...

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): G01C21/34
CPCG01C21/3407
Inventor 顾健
Owner 暗物智能科技(广州)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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com