Multi-video abstraction method based on hypergraph master-set clustering

A multi-video and summary technology, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve problems that need to be improved, and achieve the effect of low computing cost, good performance, simple and feasible practicability

Active Publication Date: 2017-09-26
TIANJIN UNIV
View PDF2 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, due to the complexity of multi-video data, the method of multi-video summarization technology still needs to be improved

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
  • Multi-video abstraction method based on hypergraph master-set clustering
  • Multi-video abstraction method based on hypergraph master-set clustering
  • Multi-video abstraction method based on hypergraph master-set clustering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] Aiming at the characteristics of redundant information and repeated information of multimedia video data, the present invention combines the visual information of video and prior information related to the theme, and utilizes the main set clustering idea and the maximum marginal correlation idea to improve the traditional multi-video summarization method. Improvements were made, and finally, the visual similarity was used for summary presentation, which achieved the purpose of effectively utilizing video topic-related information and improving the efficiency of users browsing videos.

[0038] The purpose of the present invention is to provide a multi-video summarization technology based on hypergraph principal set clustering. In view of the characteristics of high redundancy, strong crossover, and topic diversity of multiple video data sets, the present invention first constructs a video key frame content node hypergraph, and obtains candidate key frame sets with strong ...

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 video abstraction treatment and provides a multi-video abstraction method utilizing hypergraph master-set clustering thoughts and thoughts related to maximum boundary and capable of combining video visual information with theme-related prior information. According to the technical scheme, the multi-video abstraction method based on hypergraph master-set clustering includes: building video key frame content node hypergraphs, and using dichotomy master-set clustering to obtain candidate key frame sets high in coverage; using the universality relationship of webpage pictures and video sets under the same event theme to obtain key frame sets high in theme relevance degree and small in redundancy; sorting the key frame sets according to the visual coherence of video frames so as to achieve simple and meaningful multi-video abstraction. The method is mainly applicable to video treatment occasions.

Description

technical field [0001] The present invention relates to video summarization processing. Especially when it comes to multimedia video data with redundancy and crossover characteristics, the multi-video key shots are analyzed through the hypergraph main set clustering method, and then combined with the auxiliary information of the webpage pictures to extract the summary based on the hypergraph main set A multi-video summarization method for clustering. Specifically, it involves multi-video summarization methods based on hypergraph principal set clustering. Background technique [0002] With the development of technology, the number of online videos is increasing at a rapid rate, and users can also use their mobile devices to upload personal videos to sharing websites conveniently. There may be a lot of redundant information in videos recording the same event and scene, which makes it difficult for users to capture important information. Therefore, it is urgent to extract me...

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): G06F17/30G06K9/00
CPCG06F16/735G06F16/739G06F16/783G06V20/41
Inventor 冀中张媛媛
Owner TIANJIN UNIV
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap