Supercharge Your Innovation With Domain-Expert AI Agents!

Method and system for improving speaker posture based on human body key point detection

A key point and speaker technology, applied in the field of education, can solve the problems of low efficiency and high price in speech posture improvement, and achieve the effect of high efficiency and low cost

Active Publication Date: 2022-02-11
湖南视觉伟业智能科技有限公司
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The present invention provides a method and system for improving a speaker's posture based on human body key point detection, which is used to solve the technical problems of low efficiency and high price in the existing speech posture improvement

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
  • Method and system for improving speaker posture based on human body key point detection
  • Method and system for improving speaker posture based on human body key point detection
  • Method and system for improving speaker posture based on human body key point detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] see figure 1 , the present invention's method for improving the speaker's gesture based on human body key point detection, comprises the following steps:

[0044] Store standard preset human body key point data and descriptors corresponding to each set of preset human body key point data in the database;

[0045] Obtain a video stream with depth information through the camera device;

[0046] Extract human body key point signals from the video stream with depth information, and compare the human body key point signals with the preset human body key point data in the database one by one:

[0047] If the difference between the human body key point signal and the preset human body key point data in the database is less than the threshold, it is judged that the comparison is successful, and the descriptor corresponding to the preset human body key point data is obtained; the descriptor voice is broadcast to the user;

[0048] If the difference between the human body key p...

Embodiment 2

[0056] This embodiment is an application example of Embodiment 1, and the steps of this embodiment are basically the same as those of Embodiment 1, and will not be repeated here. The difference between the two is that the key point signal of the human body is a combination of 2D key point positions of the human body, such as image 3 As shown, it includes: Combination 1 consisting of 4 key points of the right eye, 37 (outer eyelid point), 38 (inner eyelid point), 40 (inner eyelid point), and 41 (outer eyelid point), Combination 2 consisting of 4 key points 43 (inner point of upper eyelid), 44 (outer point of upper eyelid), 46 (outer point of lower eyelid) and 47 (inner point of lower eyelid) of the left eye, 21 ( Combination three consisting of the key point No. 22 (inside point) of the left eyebrow and the position of the key point No. 22 (inside point) of the left eyebrow.

[0057] Obtain multiple frontal images of human faces including staring eyes, normal eyes open, half-...

Embodiment 3

[0061] This embodiment is an application example of Embodiment 1, and the steps of this embodiment are basically the same as those of Embodiment 1, and will not be repeated here. The difference between the two lies in: the position combination of 3D key points of the human body, such as Figure 4 As shown, including: the point cloud coordinates of 21 key points for the left and right hands.

[0062] Obtain multiple hand detection images of the user in the state of open, slightly open, and clenched fists, obtain their 3D point cloud coordinates, and calculate the variance values ​​of all key points of the left and right hands in each state, and use them as their states threshold.

[0063] Judgment process, through real-time detection and calculation of the variance value of all key points of both hands and comparison with the threshold value of each state, if it is less than the threshold value in the slightly open state, and the threshold difference with the clench state is l...

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 method and system for improving a speaker's posture and body movement based on human body key point detection. The method includes: storing standard preset human body key point data and each group of preset human body key point data corresponding Descriptor: Obtain the video stream with depth information through the camera device; extract the key point signal of the human body from the video stream with depth information, and compare the key point signal of the human body with the preset key point data of the human body in the database one by one , if the difference between the human body key point signal and the preset human body key point data in the database is less than the threshold, it is determined that the comparison is successful, and the descriptor corresponding to the preset human body key point data is obtained; the description language is broadcast to the user. Compared with the traditional training method, the present invention has the advantages of real-time performance, high efficiency and low cost.

Description

technical field [0001] The invention relates to the fields of education and computer vision, and in particular to a method and system for improving a speaker's posture and movement based on human body key point detection. Background technique [0002] At present, when most individuals are speaking in public, they will have subtle body movements that are more or less imperceptible to them. These redundant small movements sometimes greatly affect the overall speech effect. In order to overcome these adverse effects, people usually watch the video repeatedly. Train or ask a professional instructor to supervise the training. The efficiency of the former self-study based on videos is too low, while the latter is difficult to popularize due to the high cost and the uneven level of instructors. Contents of the invention [0003] The present invention provides a method and system for improving a speaker's posture based on human body key point detection, which is used to solve 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): G06V40/20G06V40/16
CPCG06V40/165G06V40/20G06V40/28
Inventor 夏东佐凯张翀
Owner 湖南视觉伟业智能科技有限公司
Features
  • R&D
  • 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