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

Sit-up counting method based on image vision technology

A counting method and image vision technology, applied in computing, computer components, biological neural network models, etc., can solve the problems of inability to judge whether the action is standard, high cost, and affecting the accuracy and real-time performance of sit-up counting

Pending Publication Date: 2022-06-03
苏州清研军正电子科技有限公司
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

(1) High cost;
(2) Unable to judge whether the action is standard;
(3) Manual counting is required;
The above deficiencies will affect the accuracy and real-time performance of counting sit-ups

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
  • Sit-up counting method based on image vision technology
  • Sit-up counting method based on image vision technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0009] like figure 1 Show, the present invention based on image vision technology, including the method of sitting up, including steps:

S101, start the timing;

S102, input a single frame image;

S103. Use the trained convolutional neural network to detect and position the human joint nodes. Positioning the human joint node includes: head A, shoulder B, clock C, knee D, ankle E, such as such as ankle, such as ankle, such as ankle, such as ankle, such as ankle E, such as such as ankle, such as ankle E, such as such as ankle, such as ankle E, such as such as ankle, such as ankle E, such as an ankle E, such as such as ankle, such as ankle E, such as such as ankle, such as ankle E, such as such as ankle, such as ankle E, such as such as ankle, such as ankle E, such as such as ankle, such as ankle E, such as such as ankle, such as ankle E, such as such as ankle, such as ankle E, such as such as ankle. figure 2 Show;

S104, input E -point vertical coordinate threshold EY thres If e -po...

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 sit-up counting method based on an image vision technology, and the method comprises the steps: detecting and positioning human joints based on a convolutional neural network, judging whether a sit-up action is standard or not through a joint angle, judging the number of actions through an extreme point, and judging whether the sit-up action is standard or not according to an ankle position and a straight slope. After timing is finished, the number of actions meeting the standard is judged according to all recording results, counting can be effectively conducted on the sit-up test, and the accuracy and real-time performance of sit-up counting are improved.

Description

Technical field [0001] The invention involves the field of physical fitness testing, especially a method of sit -ups based on image vision technology. Background technique [0002] Based on deep learning technology and image vision technology, the technical method of sitting on the subject is to determine whether the action is standardized by modeling the subject to calculate the standard of the standard. [0003] The current method of sitting on the sit -ups mainly exists in the following shortcomings: (1) High cost; (2) Unable to judge whether the action is standard; (3) Artificial operation count; The above shortcomings will affect the accuracy and real -time of the sits. Invention content [0004] The purpose of the present invention is to provide a method of sit -ups based on image vision technology. Based on the convolutional neural network, the joint detection and positioning of the human body is determined by the ankle position and joint angle. The number of action, ...

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): G06V40/20G06N3/04A63B71/06
CPCA63B71/06G06N3/045
Inventor 张伟
Owner 苏州清研军正电子科技有限公司