Unlock instant, AI-driven research and patent intelligence for your innovation.

Method and system for automatically identifying shaking video

An automatic identification and video technology, applied in the field of video processing, can solve problems such as low detection accuracy, lack of video analysis, and easy judgment errors

Active Publication Date: 2022-02-01
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the above-mentioned technical problems, the purpose of the present invention is to overcome the video shake detection method in the prior art, which can only judge whether the video shakes by the displacement between local adjacent frames. It is easy to make mistakes in judgment, and lacks the analysis of the whole video, resulting in the problem of low detection accuracy, so as to provide a way to use the convolutional neural network to learn the relationship between consecutive frames in the video during use, so as to adjust the degree of jitter in the video A method and system for automatically identifying and judging shaking videos to effectively improve detection accuracy

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
  • Method and system for automatically identifying shaking video
  • Method and system for automatically identifying shaking video
  • Method and system for automatically identifying shaking video

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with aspects of the invention as recited in the appended claims.

[0042] figure 1 is a flow chart of a method for automatically identifying shaking videos according to an exemplary embodiment, as shown in figure 1 As shown, the method for automatically identifying shaking video includes the following steps:

[0043] In step S11, an input video is received; and

[0044] In step S12, the input video is classified using a classification model; wherein,

[004...

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 present invention discloses a method and system for automatically identifying shaking videos, wherein the method includes: receiving an input video; and classifying the input video by using a classification model; The model is trained as the basic network structure. This method overcomes the video jitter detection method in the prior art and can only judge whether the video is jittered by the displacement between local adjacent frames. The overall analysis causes the problem of low detection accuracy.

Description

technical field [0001] The present invention relates to the technical field of video processing, in particular to a method and system for automatically identifying shaking videos. Background technique [0002] With the vigorous development of the Internet content ecology, there are more and more types of information with video as the carrier, such as Baidu Feed graphic information, full-name short videos and other resources. The low-quality problem of the search results of small videos is also gradually exposed. Therefore, it is very important to identify low-quality videos as a basis for suppressing online data or lowering the ranking of rankings. Among them, small videos with violent camera shake are very unfriendly to users and belong to the category of low-quality videos. Therefore, features are required to describe this dimension to meet online needs. [0003] The most notable feature when the video shakes is the overall displacement between frames. Therefore, most cur...

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 Patents(China)
IPC IPC(8): G06V20/40G06V10/82G06N3/04G06N3/08
CPCG06N3/08G06V20/41G06N3/045
Inventor 左斌华李鑫刘霄孙昊文石磊丁二锐
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD