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

Action recognition method based on artificial intelligence and related device

An action recognition and action technology, applied in the field of image processing, can solve the problems of limited intelligent interactive configuration scenarios, high cost, and large volume of dedicated action recognition cameras.

Active Publication Date: 2020-02-07
TENCENT TECH (SHENZHEN) CO LTD
View PDF9 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, dedicated action recognition cameras are bulky and costly, resulting in the limitation of intelligent interactive configuration scenarios based on action recognition

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 recognition method based on artificial intelligence and related device
  • Action recognition method based on artificial intelligence and related device
  • Action recognition method based on artificial intelligence and related device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] Embodiments of the present application are described below in conjunction with the accompanying drawings.

[0036] Action recognition technology can help smart devices understand the interactive actions made by interactive objects and respond accordingly. The interactive objects can be users, other objects that can make actions, or even robots.

[0037] Accurate recognition of interactive actions made by interactive objects is the key to realizing intelligent interaction. In some related technologies, a dedicated camera is often used to collect interactive objects. Due to the powerful functions of the dedicated camera, it can collect detailed information related to interactive actions, thereby realizing accurate action recognition. However, special equipment also brings the problems of large size and high cost, which hinders the development of intelligent interaction.

[0038] To this end, the embodiment of the present application provides an action recognition method....

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 action recognition method based on artificial intelligence and a related device. The method comprises steps of determining node sequence information corresponding to the video frames in the to-be-identified video data, determining action types corresponding to the video frames according to the node sequence information corresponding to the N continuousvideo frames in the to-be-identified video data, and determining which interaction action the interaction object makes according to the action types. When determining an action category correspondingto a video frame, information carried by N continuous video frames where the video frame is located is referred to, or related information of the video frame in past and / or future time is referred to;therefore, more effective information is introduced; even if the to-be-identified video data is acquired by adopting a non-special action identification acquisition device, relatively high action identification precision can also be realized in a mode of determining the action type corresponding to each video frame through a group of continuous video frames, so that the application range and theimplementation cost of an intelligent interaction scene are reduced.

Description

technical field [0001] The present application relates to the field of image processing, in particular to an artificial intelligence-based action recognition method and related devices. Background technique [0002] Action recognition technology can help smart devices understand the actions of interactive objects and make corresponding responses. For example, users can trigger certain functions of smart devices through gestures. Action recognition technology is the key technology to realize intelligent interaction. [0003] In a related technology for motion recognition, a dedicated motion recognition camera such as a Kinect camera is used to collect motions made by an interactive object, and motion recognition is performed based on the collected data. [0004] However, dedicated action recognition cameras are bulky and costly, resulting in limitations in intelligent interactive configuration scenarios based on action recognition. Contents of the invention [0005] In ord...

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): G06K9/00G06K9/68G06N3/04G06N3/08
CPCG06N3/08G06V40/20G06V30/242G06N3/045G06N3/084G06V10/82G06V10/764G06N3/044
Inventor 迟万超张冲凌永根刘威张正友袁泽剑宋子扬殷梓译
Owner TENCENT TECH (SHENZHEN) 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