Unlock instant, AI-driven research and patent intelligence for your innovation.

Human body action scoring method based on machine vision

A technology of human body movement and machine vision, applied to instruments, computer components, character and pattern recognition, etc., can solve the problems of narrow application, potential safety hazards, low reliability, etc., achieve visual scoring and improve usability , the effect of broadening the scope of application

Pending Publication Date: 2020-09-08
影子江湖文化(北京)有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the problems of narrow applicability, low reliability, and potential safety hazards of existing human action evaluation methods, an embodiment of the present invention provides a machine vision-based human action scoring method, including:

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
  • Human body action scoring method based on machine vision
  • Human body action scoring method based on machine vision

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0037] Please refer to figure 1 As shown, the embodiment of the present invention discloses a human action scoring method based on machine vision, including S101-S104, wherein,

[0038] S101. Acquire an action feature scheme according to the action category selected by the user, and initially correct the image acquisition angle and position.

[0039] In this embodiment, the user needs to select an action category, and the action category includes but not limited to martial arts action, dance action, sports event action and fitness action. Sports activities may include running, long jump, and high jump. After the action category is selected, an action feature scheme corresponding to the action category is generated. In the embodiment of the present invention, the same action can have action feature schemes from multiple perspectives. Taking the barbell bench press as an example, there are action feature schemes in total of three perspectives, including two mutually perpendicu...

no. 2 example

[0053] Please refer to figure 2 As shown, the embodiment of the present invention discloses a human action scoring method based on machine vision, including S201-S215, wherein,

[0054] S201. Generate an action feature scheme corresponding to the action category according to the action category selected by the user.

[0055] Likewise, the same action category in this embodiment may correspond to multiple action feature schemes.

[0056] S202. Obtain a shooting specification and an action specification corresponding to the action feature scheme.

[0057] In this embodiment, the shooting specification includes camera angle, horizontal position, height, etc., and the action specification is used to guide the user's standard initial actions to improve the accuracy of scoring.

[0058] S203. Send a first prompt message when the camera angle and position meet the shooting specification.

[0059] S204. When the user's initial action conforms to the action specification, send out ...

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 human body action scoring method based on machine vision, which comprises the following steps: acquiring an action feature scheme according to an action category selected bya user, and initially correcting an image collection angle and position; acquiring an actual image of a user action, and extracting corresponding key feature points in the actual image according to the action feature scheme, the key feature points which comprises feature points of a head, a neck, shoulders, a chest, an abdomen, elbows, wrists, hands, buttocks, knees, ankles, feet or props; connecting corresponding key feature points according to the action feature scheme to generate feature connecting lines, wherein the feature connecting lines comprise feature connecting lines of the head, the neck, the shoulders, the chest, the abdomen, the upper arms, the lower arms, the thighs, the shanks, the feet or the hands and props; and determining a human body action score according to the matching degree of the corresponding feature connecting lines in the actual image and the standard image. The method has high reliability and usability, and the use experience of a user is improved.

Description

technical field [0001] The invention relates to the field of automatic detection devices, in particular to a machine vision-based human action scoring method. Background technique [0002] With the improvement of people's living standards, sports activities such as dance, martial arts or fitness have gradually become a choice for people to strengthen their bodies and enrich their leisure life. However, due to the aesthetics, efficiency and safety of movements, human movements The standardization of human body movements is particularly important. The current evaluation methods of human body movements have a single application and cannot meet the guidance needs of different groups of people for different sports activities. [0003] At the same time, since the current evaluation methods of human body movements are usually based on two-dimensional pictures, they cannot objectively and accurately reflect the standard degree of human activities in three-dimensional space. Taking t...

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
CPCG06V40/23G06V10/751
Inventor 石晓冬张红旗杨德战
Owner 影子江湖文化(北京)有限公司