Supercharge Your Innovation With Domain-Expert AI Agents!

Posture recognition method and somatosensory game action guidance system

A recognition method and action guidance technology, applied in the field of biometrics, can solve problems such as the decline in recognition accuracy

Pending Publication Date: 2020-07-07
西安思博探声生物科技有限公司
View PDF7 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The posture recognition technology in the prior art is based on the research of vision-based posture recognition. It usually needs to obtain human body images through cameras or cameras, and then process the human body posture in the image. However, the method of obtaining human body posture by this image processing method is often affected by A series of problems such as pixel quality and whether the image is occluded lead to a decline in recognition accuracy, and usually such devices are limited by application scenarios because they require video or camera equipment

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
  • Posture recognition method and somatosensory game action guidance system
  • Posture recognition method and somatosensory game action guidance system
  • Posture recognition method and somatosensory game action guidance system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] See figure 1 , figure 1 It is a schematic flow chart of a posture recognition method provided by an embodiment of the present invention; wherein, the posture recognition method includes:

[0039] Step 102, collecting joint motion signals of different joint parts of the human body;

[0040] It should be noted that joint motion signals include joint vibration signals and joint sound signals; the vibration signals generated by the movement of joints are generated between the bones and soft tissues inside the joints, and the vibration signals generated by damaged joints can be distinguished from those of undamaged joints. The vibration signal generated by the joint. In addition, the bones and soft tissues inside the joint produce sound due to the movement of the joint, that is, the sound signal of the joint.

[0041] When the human body is in motion, the joints of the limbs of the human body are also in a moving posture. With the different postures and movement speeds of...

Embodiment 2

[0056] In this embodiment, on the basis of the foregoing embodiments, when the classification model is a machine learning algorithm model such as a neural network algorithm model, the embodiment of the present invention provides a classification model training method. Please refer to figure 2 , figure 2 A schematic flow chart of a training method for a classification model provided by an embodiment of the present invention; figure 2 As shown, the training method of the classification model is as follows:

[0057] Step 202, according to the joint motion signal, obtain a preset number of characteristic values ​​of the human body motion posture corresponding to different human motion postures;

[0058] In this step, a preset number of joint motion signals can be obtained for training the classification model, and the obtained joint motion signals are processed to form the joint motion signal feature value to obtain the human body motion posture feature value; wherein, the jo...

Embodiment 3

[0069] See image 3 , image 3 It is a schematic structural diagram of a collection device of a somatosensory game action guidance system provided by an embodiment of the present invention;

[0070] The somatosensory game action guidance system includes: a plurality of acquisition devices 10 and a server 20, wherein,

[0071] The plurality of acquisition devices 10 are used to obtain the characteristic value of the human body movement posture;

[0072] The server 20 is configured to obtain a classification result according to a pre-trained classification model and the feature value of the human body motion posture, and obtain human body motion posture information according to the classification result.

[0073] The plurality of collection devices 10 are respectively arranged on different joints of the human body, wherein the collection devices 10 include:

[0074] An acquisition module 101, configured to acquire joint motion signals of joint parts of the human body under th...

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 relates to a posture recognition method and a somatosensory game action guidance system. The posture recognition method comprises the steps of: acquiring joint movement signals of different joint parts of a human body; forming human body motion posture feature values according to the joint motion signals; classifying the human body motion posture feature values according to a pre-trained classification model to obtain a classification result; and judging motion posture information of the human body according to the classification result. The somatosensory game action guidance system comprises a plurality of acquisition devices (10) and a server (20), the human body posture feature values are generated by acquiring joint motion signals of the human body, the pre-trained classification model is used for judging human body postures, and the somatosensory game action guidance system is accurate in recognition and is not limited by recognition scenes.

Description

technical field [0001] The invention belongs to the technical field of biological identification, and in particular relates to a body posture identification method and a somatosensory game action guidance system. Background technique [0002] As a form of intelligent human-computer interaction, body recognition technology has become more and more known, and its application in daily life is becoming more and more extensive. At present, the research on human body recognition has become a research hotspot in artificial intelligence technology. . [0003] The posture recognition technology in the prior art is based on the research of vision-based posture recognition. It usually needs to obtain human body images through cameras or cameras, and then process the human body posture in the image. However, the method of obtaining human body posture by this image processing method is often affected by A series of problems such as pixel quality and whether the image is occluded lead to...

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): G06K9/00G06K9/62
CPCG06V40/23G06F18/241
Inventor 丁坦李东韬卞鸿鹄王漪
Owner 西安思博探声生物科技有限公司
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