Video-based human body behavior recognition method, device and equipment and storage medium

A recognition method and human body technology, applied in the field of human body recognition, can solve problems such as inaccurate methods and inaccurate identification of human behavior types, etc., to achieve the effects of reducing the number of frames, ensuring accuracy, and ensuring correctness and accuracy

Active Publication Date: 2020-06-09
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF7 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, in the prior art, the behavior of the human object in the video is only confirmed based on the characteristics of the human object on one frame, and then the behavior type of the human object in the video is obtained; The semantics are different, the existing methods are not accurate, and cannot accurately identify the behavior type of the human body in a video

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
  • Video-based human body behavior recognition method, device and equipment and storage medium
  • Video-based human body behavior recognition method, device and equipment and storage medium
  • Video-based human body behavior recognition method, device and equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0089] Exemplary embodiments of the present application are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present application to facilitate understanding, and they should be regarded as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

[0090] With the development of video and image technology, human objects in the video can be detected, and then the behavior type of the human objects can be determined, so as to determine whether unsafe behaviors are being carried out. In various public places, such as schools, prisons, railway stations, subways, etc., for the sake of social stability and personnel ...

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 a video-based human body behavior recognition method, apparatus and device, and a storage medium, and relates to the technical field of human body recognition. According to thespecific implementation scheme, a human body frame of each video frame of a to-be-identified video is acquired, each human body frame comprises a plurality of human body key points, and each human body key point has a key point feature; constructing a feature matrix according to the human body frame of each video frame; convolution is carried out on the feature matrix in the dimension of the number of video frames to obtain a first convolution result, and convolution is carried out on the feature matrix in the dimension of the number of key points to obtain a second convolution result; and inputting the first convolution result and the second convolution result into a preset classification model to obtain a human body behavior category of the to-be-identified video. The relation between the video frames of the front and rear frames is considered, the understanding deviation of the video can be reduced, and the accuracy and recall rate of the human body behavior category of the video are improved.

Description

technical field [0001] The present application relates to human body recognition technology in the field of image processing technology, and in particular to a video-based human body behavior recognition method, device, equipment and storage medium. Background technique [0002] With the development of video and image technology, human objects in the video can be detected, and then the behavior type of the human objects can be determined, so as to determine whether unsafe behaviors are being carried out. [0003] In the prior art, when the video technology is used to analyze the behavior type of the human object, the behavior of the human object in the video can be determined based on the characteristics of the human object in a certain frame. [0004] However, in the prior art, the behavior of the human object in the video is only confirmed based on the characteristics of the human object on one frame, and then the behavior type of the human object in the video is obtained;...

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): G06K9/00G06V10/44
CPCG06V40/20G06V20/41G08B13/19613G06V10/44G06N3/045G06F3/011G06F3/017G06N3/02G06V20/46
Inventor 迟至真李甫孙昊何栋梁龙翔周志超王平文石磊丁二锐
Owner BEIJING BAIDU NETCOM SCI & TECH 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