Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Rope skipping posture and number recognition method based on computer vision

A technology of computer vision and recognition methods, applied in computer components, computing, neural learning methods, etc., can solve problems such as strong dependence on counters and limited artificial concentration

Active Publication Date: 2021-03-09
CHENGDU REMARK TECH CO LTD +1
View PDF14 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Eliminate the disadvantages of limited artificial concentration, strong reliance on skipping ropes for counters, and high requirements for audio frequency on the surrounding environment

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 posture and number recognition method based on computer vision
  • Rope skipping posture and number recognition method based on computer vision
  • Rope skipping posture and number recognition method based on computer vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] A computer vision-based rope skipping posture and number recognition method, such as image 3 , including the following steps, in order:

[0052] Step S1: collecting video of human jumping rope;

[0053] Step S2: Perform human key point detection on each frame of the video to obtain the coordinate positions and coordinate confidence of the 18 key points of the human body in each frame, and sequentially number them as 0, 1, ..., 17;

[0054] Step S3: Process the coordinate data of the key points, and normalize the coordinates of the key points to -0.5~0.5;

[0055] Step S4: Utilize the selected T-frame keyframes and the coordinates of the key points in each frame keyframe and the confidence of the coordinates to construct a skeleton sequence graph structure, record the space-time graph of the skeleton sequence as G=(V, E), and the nodes V={Vti|t=1,...,T; i=0,...,n-1}, the eigenvector F(vti)={xti,yti,scoreti of the i-th node of frame t }, (xti, yti) is the processed coo...

Embodiment 2

[0074] Feature vector in the step S9 The specific set of eigenvector included angles is: S A ={An(0)(1)-(1)(5), An(0)(1)-(1)(2), An(1)(2)-(1)(5), An(1) )(2)-(2)(3), An(2)(3)-(3)(4), An(1)(5)-(5)(6), An(5)(6)- (6)(7), An(1)(2)-(1)(8), An(1)(5)-(1)(11), An(1)(8)-(8)(9 ), An(8)(9)-(9)(10), An(1)(11)-(11)(12), An(11)(12)-(12)(13), An(2 )(8)-(2)(3), An(5)(11)-(5)(6)}, where 18 key points are numbered nose 0, neck 1, right shoulder 2, right elbow 3, right Wrist 4, Left Shoulder 5, Left Elbow 6, Left Wrist 7, Right Hip 8, Right Knee 9, Right Ankle 10, Left Hip 11, Left Knee 12, Left Ankle 13, Right Eye 14, Left Eye 15, Right Ear 16, Left ear 17.

[0075] Further, the method of calculating the cosine similarity in step S10 is to calculate the cosine of the angle between the eigenvectors, and calculate the variance or standard deviation between the cosine and the cosine of the angle between the cosine and the preset eigenvector, and the preset threshold is generally Take 0.68. ...

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 rope skipping posture and number recognition method based on computer vision. An ST-CGN model is used for training a skeleton sequence topological graph structure of each frame of image with extracted features; softmax is carried out on the features extracted by the ST-CGN, action classification and confidence are output, and rope skipping action counting is carried out if action classification output is rope skipping; and cosine similarity between the standard action feature vector and the current action feature vector is calculated, and when the cosine similarity isgreater than a preset threshold, it is judged that the current action is a standard action. According to the method, whether the rope skipping posture is correct or not can be judged by using the GCNand cosine similarity algorithm, and the rope skipping number can be calculated by using a maximum value or minimum value method.

Description

technical field [0001] The invention relates to the field of human motion analysis, in particular to a computer vision-based recognition method for jumping rope gestures and numbers. Background technique [0002] Rope skipping can achieve aerobic and anaerobic exercise effects at the same time, exercise multiple muscles, exercise coordination and balance, and enhance cardiopulmonary function. Long-term pattern skipping training can effectively improve the bone density of teenagers, and significantly enhance physical fitness such as strength and explosive power. The recognition of the skipping posture refers to the recognition of the skipping posture and comparison with the standard posture to correct the wrong skipping posture. Counting the number of rope skipping refers to counting the number of different rope skipping methods. [0003] The method adopted in the prior art is to use the human body key point recognition algorithm to identify the key points of the human body...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V40/23G06V20/42G06N3/045G06F18/22G06F18/2415
Inventor 杨婷肖利
Owner CHENGDU REMARK TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com