Action feature validity judgment method, computer storage medium and electronic device

A judging method and effectiveness technology, which is applied in computer parts, computing, character and pattern recognition, etc., can solve problems such as inaccurate judgment results, and achieve the effect of improving stability and effectiveness, reducing deviation, and reducing interference

Active Publication Date: 2020-03-24
爱菲力斯(深圳)科技有限公司
View PDF3 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is to provide a method for judging the validity of action features, a computer storage medium and an electronic device to solve the problem of inaccurate judgment results caused by data jitter in the prior art when judging human body motion trends

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
  • Action feature validity judgment method, computer storage medium and electronic device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the embodiments and accompanying drawings.

[0020] The action feature validity determination method provided by the embodiment of the present invention can be applied to action recognition. Action recognition in this article mainly refers to human action recognition, that is, to collect human action images or videos through image acquisition equipment, and identify human action postures or action trends from human action images or videos. Human action recognition can be widely used in somatosensory games, sports and fitness guidance and other fields. Action feature validity is used to indicate whether the action features in the image frame are valid for action recognition during the action recognition process, that is, whether the action features in the image frame can be used for action rec...

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 an action feature validity judgment method, a computer storage medium and an electronic device. The action feature validity judgment method includes the steps: judging whethercontinuous action and data jitter occur between adjacent image frames or not according to the length of the generation timestamp interval between the adjacent image frames and the consistency of the action features, and presetting a cache queue to cache the action features and the generation timestamp information of the continuous image frames without data jitter; and presetting the length of a cache queue (i.e., the number of continuous image frames without data jitter), and when the cache reaches the preset number of image frame information, judging the action feature in each image frame cached in the cache queue to be an effective feature. According to the action feature validity judgment method, data jitter caused by factors such as environmental influence, insufficient equipment precision, errors of a bottom-layer algorithm and abrupt change of an object motion track is reduced, and interference to judgment of the motion trend of the object is reduced, and deviation of a judgmentresult is effectively reduced, and stability and effectiveness of motion tracking are improved.

Description

technical field [0001] The invention relates to machine vision recognition technology, in particular to a method for judging the validity of action features, a computer storage medium and an electronic device. Background technique [0002] In the field of visual recognition of human motion and posture, for dynamic recognition processes such as motion trend prediction and motion tracking, it is necessary to perform correlation calculations on continuous motions, and deviations in each frame of data will affect the final recognition results. Factors such as environmental influences, lack of equipment accuracy, and sudden changes in the trajectory of objects will all lead to data jitter. These jittery data will interfere with the judgment of the actual movement trend, resulting in deviations in the judgment results, or even complete errors. Contents of the invention [0003] The technical problem to be solved by the present invention is to provide a method for judging the val...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00
CPCG06V40/20G06V20/46
Inventor 胡佳文
Owner 爱菲力斯(深圳)科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap