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

Cutting frame determination method, network training method, device, equipment and storage medium

A network and classification network technology, applied in the field of cloud computing, can solve problems such as slow processing speed, and achieve the effect of reducing the amount of data processing, reducing missed detection, and improving the content of the picture.

Pending Publication Date: 2020-07-24
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF11 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, when determining the similarity, it is necessary to compare the video frames two by two, which causes the problem of slow processing speed

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
  • Cutting frame determination method, network training method, device, equipment and storage medium
  • Cutting frame determination method, network training method, device, equipment and storage medium
  • Cutting frame determination method, network training method, device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0066] 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.

[0067] Shot segmentation of video sequences, also known as shot change detection, is one of the key technologies in video database technology. The video shot boundary detection technology is to divide the complete video into a series of shot segments according to the shot boundaries. The current shot segmentation refers to cutting when there is a sudden change in th...

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 provides a cut frame determination method, a network training method, a device, equipment and a storage medium, and relates to the field of cloud computing, the cut frame determination method comprises steps of dividing a video to be processed into a plurality of video units; inputting the first frame of picture and the tail frame of picture of the video unit into a preset classification network, and determining the similarity of the first frame of picture and the tail frame of picture through the classification network; and determining a cutting frame picture in the target videounit of which the similarity meets a preset condition. In the scheme provided by the invention, through a mode of segmenting the video into the video units, a part of the video units without the cutting frame pictures can be filtered, so that only the video units comprising the cutting frame pictures are further processed, and the data processing amount can be reduced. Furthermore, according to the scheme provided by the invention, the similarity between the picture frames is determined by utilizing the preset classification network, and the situation that the similarity between the picture frames is identified only by utilizing low-level features in the prior art is avoided, so that the picture content can be better understood, and the missing detection situation is reduced.

Description

technical field [0001] The present disclosure relates to artificial intelligence technology, and in particular to the field of cloud computing. Background technique [0002] Shot segmentation of video sequences, also known as shot change detection, is one of the key technologies in video database technology. The video shot boundary detection technology is to divide the complete video into a series of shot segments according to the shot boundaries. [0003] The existing video segmentation methods first extract the features of video frames, such as color, texture, shape, motion, etc., and then find the shot boundaries of the video by judging the similarity relationship between video frames. [0004] However, when determining the similarity, it is necessary to perform a pairwise comparison of video frames, which causes a problem of slow processing speed. Contents of the invention [0005] The present disclosure provides a cutting frame determination method, a network traini...

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): G06K9/00G06K9/62
CPCG06V20/49G06F18/22G06F18/24143
Inventor 张沁怡
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD