Motion recognition method and device, computer storage medium and computer device

An action recognition and action type technology, applied in the field of image processing, can solve the problem of low accuracy of action recognition

Active Publication Date: 2020-03-06
TENCENT TECH (SHENZHEN) CO LTD
View PDF9 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Based on this, it is necessary to provide an action recognition method, device, computer-readable storage medium and computer equipment for the technical problem of low accuracy of action recognition by traditional two-dimensional convolutional neural networks

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, computer storage medium and computer device
  • Motion recognition method and device, computer storage medium and computer device
  • Motion recognition method and device, computer storage medium and computer device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, and are not intended to limit the present application.

[0054] Artificial Intelligence (AI) is a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technique of computer science that attempts to understand the nature of intelligence and produce a new kind of intelligent machine that can respond in a similar way to human intelligence. Artificial intelligence is t...

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 relates to a motion recognition method and device, a computer readable storage medium and a computer device. The method comprises the steps of obtaining original sub-feature maps of image data of each time sequence frame on different convolution channels through a multi-channel convolution layer; taking each time sequence frame as a target time sequence frame; calculating the motioninformation weight of the target time sequence frame on each convolution channel according to the original sub-feature map of the target time sequence frame on each convolution channel and the original sub-feature map of the next time sequence frame on each convolution channel, and obtaining the motion information feature map of the target time sequence frame on each convolution channel accordingto the motion information weight; performing time sequence convolution on the motion information feature map of the target time sequence frame on each convolution channel to obtain a time sequence motion feature map of the target time sequence frame on each convolution channel; and obtaining the action type of the moving object in the image data of the target time sequence frame according to the time sequence motion feature map of the target time sequence frame in each convolution channel. According to the scheme provided by the invention, the action recognition precision can be effectively improved.

Description

technical field [0001] The present application relates to the technical field of image processing, and in particular to an action recognition method, device, computer-readable storage medium and computer equipment. Background technique [0002] With the development of computer technology, action recognition technology has expanded from the field of images to the field of video. In the prior art, the action recognition of video data generally uses a two-dimensional convolutional network neural network to identify each frame of image in the video data, and finally performs a fusion of the action recognition results of all frames of the video data to obtain Action recognition results for video data, but in scenes that emphasize changes in the motion of moving objects, even if the order of each frame image in the video data is disrupted, it will not affect the recognition of the action type in the video data by the two-dimensional convolutional network neural network As a resul...

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): G06K9/00G06N3/04
CPCG06V40/20G06N3/045G08B21/0407G08B21/0261G06N3/08G06V10/62G06V10/454G06V10/82G06V40/28G06V10/40G06T7/246G06N3/02G06T2207/20081G06F18/213
Inventor 罗栋豪王亚彪郭晨阳邓博元汪铖杰李季檩黄飞跃吴永坚
Owner TENCENT TECH (SHENZHEN) CO LTD
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