Supercharge Your Innovation With Domain-Expert AI Agents!

Method for extracting key frames of video abstract

A technology of video summarization and extraction method, which is applied in special data processing applications, instruments, electrical digital data processing, etc. It can solve problems such as difficult to accurately express the inner semantics of video, inability to adapt, and insufficient comprehensive description of the dynamic characteristics of "objects".

Inactive Publication Date: 2020-05-01
杨晨曦
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to its expression form with static images as the result, it is difficult to accurately express the inner semantics of the video, and the description of the dynamic characteristics of the "object" is not comprehensive enough, so it is only suitable for the generation of wonderful moments of the video, and cannot meet the needs of "object" "In the case of feature analysis

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 for extracting key frames of video abstract
  • Method for extracting key frames of video abstract
  • Method for extracting key frames of video abstract

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] Considering that we want the selected keyframes to show the main content of the video as much as possible without information redundancy, we use the difference as a constraint to optimize the representativeness of the keyframe set.

[0026] (1) First we set the threshold δ of the representative ability of the key frame 1 , we are only interested in the representative capacity video frames for research. Next, we sort the video frames by representative size:

[0027]

[0028] Where k is the label of the video frame after sorting, and N is the representative capacity The number of video frames.

[0029] (2) We select key frames in order of frame representativeness from large to small. Frame 1 is the most representative and can obviously be used as a key frame. If the kth frame is selected into the keyframe set, then we define the candidate set for the next keyframe as {k+1,k+2,...,N}. The k+ith frame is selected into the key frame set, if it satisfies:

[0030]...

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 method for extracting key frames of a video abstract, which comprises the following steps of: extracting frames meeting representative and diversity conditions in the video abstract to serve as the key frames, in the formula, R (S) represents the representativeness of the key frames, D (S) represents the diversity of the key frames, and S represents the key frames. The invention provides a new representativeness and diversity definition method which is based on topological potential and norms respectively, and provides a mathematical model for key frame extraction.

Description

technical field [0001] This application relates to the field of machine learning and data analysis, and in particular refers to a method for extracting key frames of a video summary. Background technique [0002] Video summary: Video summary, also known as video enrichment, is a simple summary of the video content. In an automatic or semi-automatic manner, the moving target is first extracted through the analysis of the moving target, and then the trajectory of each target is analyzed to combine different targets. Stitching into a common background scene and combining them in some way. Video summarization plays an important role in video analysis and content-based video retrieval. In the field of social public security, the video surveillance system has become an important part of maintaining social order and strengthening social management. However, video recording has the characteristics of large amount of stored data and long storage time. The traditional method of find...

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): G06F16/738G06F16/732
Inventor 杨晨曦
Owner 杨晨曦
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com