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

Identification method and system for heel key point of standing long jump and test method

An identification method and key point technology, which is applied in the field of identification of key points of the heel of the standing long jump, can solve the problems that the validity and reliability of the distance measurement of the standing long jump result cannot be effectively guaranteed, and the accuracy of heel recognition is not high, so as to improve the accuracy and performance, The effect of heel recognition stabilization

Pending Publication Date: 2021-07-27
广州深灵科技有限公司
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Therefore, the prior art does not have a fast and accurate identification method for the key points of the heel in the standing long jump scene. The current heel recognition accuracy is not high, and the validity and reliability of the distance measurement of the standing long jump result cannot be effectively guaranteed.

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
  • Identification method and system for heel key point of standing long jump and test method
  • Identification method and system for heel key point of standing long jump and test method
  • Identification method and system for heel key point of standing long jump and test method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0064] A kind of identification method of standing long jump heel key point of the embodiment of the present invention, comprises the following steps:

[0065] Step 101: the step of acquiring images, in the scene of standing long jump, collecting images containing people and background images in the test area;

[0066] Specifically, the camera captures the video of the whole process of the standing long jump test of Mr. Hu's worsening training, and obtains images containing people and background images. It is also possible to first shoot background images without people and background images containing people.

[0067] Step 102: an image input step, inputting the acquired image containing people and the background image;

[0068] Specifically, the acquired image containing people and the background image are input.

[0069] Step 103: the step of quickly identifying the human body frame, using the human-containing image and the background image, estimating the human body frame...

Embodiment 2

[0104] A recognition system for a method for recognizing key points of the heel of a standing long jump, comprising:

[0105] Obtaining an image device 1, used to collect images containing people and background images in the test area in the scene of standing long jump;

[0106]Image input device 2, used for inputting the acquired images containing people and background images;

[0107] The device 3 for quickly identifying the human body frame is used to use the human-containing image and the background image to estimate the human body frame through the optical flow algorithm, identify the portrait and cut out the human body frame and the corresponding background frame;

[0108] The frame recognition device 4 of the foot is used to input the human body frame and the background frame output in the step of quickly identifying the human body frame, use the feature extraction neural network to extract the difference object segmentation features, estimate the frame of the foot, and...

Embodiment 3

[0111] Based on the heel key point recognition method proposed above, it is applied to the image-based standing long jump self-service test and score collection to improve the accuracy of test scores.

[0112] A standing long jump self-test method, comprising the steps of:

[0113] Step 301: Set a test area according to the acquisition range of the image acquisition device;

[0114] Specifically, install the camera: select a designated standing long jump site, install a fixed camera, and combine the standing long jump test area marking device. The test area marking device is a stretching marking device that supports activities, and the test area is set according to the image range of the camera.

[0115] Step 302: Automatically detect whether a person enters the testing area;

[0116] Specifically, enable the self-service test mode: for example, in human-computer interaction modules such as teachers or staff terminals. Personnel entering the test area: the system can automat...

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 embodiment of the invention discloses an identification method and system for heel key points of standing long jump and a test method. According to the method, a human-containing image and a background image are taken as input, and the problem of identification of the heel key points is decomposed into three steps: human body identification, foot frame identification and heel key point identification through an algorithm; in each step, the output of the previous step is used as the input, the complexity of the problem is gradually reduced, the algorithm utilizes the information that the key points of the heel is a certain point on the human body contour, the feature information of human body segmentation is introduced in the middle, and the features of human body segmentation and key point identification are fused for multiple times in the algorithm; the method assists in the identification of the key points of the heel, directly outputs the key points of the heel after analysis, improves the recognition precision of the heel of the standing long jump, and guarantees the effectiveness and reliability of the distance measurement of a standing long jump result.

Description

technical field [0001] The invention relates to the technical fields of image segmentation and IT application, in particular to a method, system and test method for identifying key points of the heel of a standing long jump. Background technique [0002] In the field of human key point recognition and human body contour recognition, including the recognition of human skeleton key points and human body contour recognition, the basic framework of the algorithm is to describe the problem as a regression problem of key points or a classification problem of pixel points. The determination of the parameters of the algorithm model is based on supervised learning. By learning a large number of pictures marked with key points, the optimal or better value of the parameters is found. The key point identification algorithm described above is a general-purpose algorithm. Key point recognition in special fields can be combined with application scenarios to improve the accuracy of key poi...

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): G06K9/00G06K9/34G06N3/04G06N3/08
CPCG06N3/08G06V40/10G06V10/267G06N3/045
Inventor 不公告发明人
Owner 广州深灵科技有限公司
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