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

Motion recognition method and device, electronic equipment and storage medium

An action recognition and action technology, applied in the field of computer vision, can solve the problems of unstable image quality, affect the accuracy of action recognition, low image quality, etc., to reduce the requirements of use scenarios, simplify the processing of action recognition, and improve the accuracy of action recognition. Effect

Pending Publication Date: 2020-10-09
BEIJING IQIYI TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, since visible light images are greatly affected by the environment, the image quality is unstable, which easily affects the accuracy of action recognition.
For example, the action recognition of the target object contained in the visible light image with strong exposure will reduce the accuracy of the recognition result due to the low image quality

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
  • Motion recognition method and device, electronic equipment and storage medium
  • Motion recognition method and device, electronic equipment and storage medium
  • Motion recognition method and device, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0073] The technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention.

[0074] Due to the complex algorithm of the existing action recognition method, it is difficult to apply it to other fields. In order to simplify the processing of action recognition and expand the application scenarios of action recognition, the embodiment of the present invention provides an action recognition method, such as figure 2 shown, including:

[0075] Step 201, acquiring multiple frames of continuous infrared images; the infrared image is an image of a designated part of a target object captured by an infrared camera, and the target object is deployed with multiple photocapturing balls, wherein each photocapturing ball corresponds to the target object a designated part of . Wherein, the target objects may be: people, animals and so on. The phototrap deployed against the target object may b...

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 provides an action recognition method and device, electronic equipment and a storage medium. The method comprises the steps that multiple frames of continuous infraredimages are acquired; wherein the infrared image is an image which is shot by one infrared camera and contains a specified part of a target object, the target object is deployed with a plurality of light capturing balls, and each light capturing ball corresponds to one specified part of the target object; determining a target image group containing multiple frames of target images from the multipleframes of continuous infrared images; and inputting multiple frames of target images in the target image group into a pre-trained action recognition model to obtain an action type of the target object corresponding to the target image group. By adopting the method provided by the embodiment of the invention, the processing of the action recognition of the target object is simplified, the requirement of a use scene of the action recognition is reduced, and meanwhile, higher action recognition precision can be achieved under the use scene with lower requirement.

Description

technical field [0001] The present invention relates to the technical field of computer vision, in particular to an action recognition method, device, electronic equipment and storage medium. Background technique [0002] At present, there are many technologies for recognizing human actions. For example: only through image processing technology, the movement of the target object in the video screen is recognized, or the movement of the target object is recognized through light capture technology. [0003] At present, the method of recognizing the action of the target object through light capture technology is mainly used in film and television production. The identification process needs to be completed in a professional studio, such as figure 1 Shown: [0004] Multiple infrared cameras 103 are installed at different positions in the studio, and actors wear special light-trapping clothes 101 on which are deployed multiple light-trapping balls 102 with strong reflection ca...

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): G06K9/00G06K9/62G06N3/04
CPCG06V40/23G06N3/045G06F18/2415G06F18/214
Inventor 刘思阳
Owner BEIJING IQIYI 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