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

Rope skipping counting method based on deep learning

A counting method and deep learning technology, which is applied in the field of rope skipping counting based on deep learning, can solve problems such as counting accuracy errors of skipping ropes, and achieve the effects of fast counting speed, high application value, and high accuracy

Active Publication Date: 2020-12-08
ZHEJIANG UNIV
View PDF8 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The above methods all use intelligent methods based on vision and hearing to count rope skipping, but these methods have certain errors in the accuracy of rope skipping counting

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
  • Rope skipping counting method based on deep learning
  • Rope skipping counting method based on deep learning
  • Rope skipping counting method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0043] see Figure 1 to Figure 9 , the rope skipping counting method based on deep learning of the present embodiment comprises the following steps:

[0044] In the preparatory step, the original video data of the rope skipping action is obtained, and the image data is extracted from the original video data.

[0045] Step S100, read the image, and compress the video size frame by frame.

[0046] Step S200, process the compressed video with the Farneback dense optical flow algorithm, and output a new BGR video. In this embodiment, the frame features during the rising and falling processes are obvious and arranged in time sequence, and the output images are divided into three categories, which are respectively "rising frames" (such as image 3 shown), "still frame" (such as Figure 4 ) and "drop frame" (as in Figure 5 shown).

[0047] Step S300, image classification: use the trained neural network model to classify. Specifically include:

[0048] Step S301, video image p...

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 rope skipping counting method based on deep learning, and belongs to the technical field of intelligent fitness sports equipment. The method comprises the following steps of: 1) acquiring original video data of rope skipping actions, and extracting image data from the original video data; 2) reading video images, and compressing the video size frame by frame; 3) processing the compressed video by using a Farneback dense optical flow algorithm, and outputting a new BGR video; 4) classifying each frame of image in the BGR video by using a trained classification model;5) judging the rope skipping state according to the classification result; 6) counting the skipping ropes according to the change of the rope skipping state; and 7) outputting and displaying the result. The obtained image data is preprocessed, then classification is carried out by using the trained model, the current motion state is judged according to the classification result, and finally the change frequency of the rope skipping state is counted. The method is high in accuracy and high in counting speed, and has very high application value.

Description

technical field [0001] The invention relates to the technical field of intelligent fitness equipment, in particular to a method for counting rope skipping based on deep learning. Background technique [0002] Rope skipping has been used as an important sport for entertainment or competition on many occasions. At the same time, it is also a compulsory subject for the physical examination of elementary and middle school students. However, counting is required in the process of skipping rope. When there are many people, counting each person will greatly delay the precious time of the referee, and sometimes when the rope skipping speed is fast or the referee is inattentive, counting errors are prone to occur. Existing skipping ropes that can count automatically often adopt traditional methods such as machinery, and there are problems such as the ubiquity of counting not being accurate enough, or not being able to count backwards, or not being able to use for a long time. There...

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): A63B71/06G06N3/08G06N3/04G06K9/62G06K9/00
CPCA63B71/0619G06N3/08A63B2220/17A63B2220/806G06V20/41G06N3/045G06F18/214
Inventor 林峰鲁昱舟
Owner ZHEJIANG UNIV