Video retrieving method based on context space

A contextual and spatial technology, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve problems such as ignoring the co-occurrence of concept objects, and achieve the effect of promoting accuracy

Active Publication Date: 2013-09-04
魏骁勇
View PDF2 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] Semantic concept mining is gradually becoming the mainstream research direction to improve the accuracy of video retrieval, but traditional semantic concept mining mostly detects a single concept, ignoring the objective fact that most concept objects co-occur in videos

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 retrieving method based on context space
  • Video retrieving method based on context space
  • Video retrieving method based on context space

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The present invention provides a video retrieval method based on context space:

[0040] Given a set of basic concept vocabulary V=[C 1 ,C 2 ,C 3 …C n ].

[0041] The process of constructing the context space:

[0042] In step A1, Agglomerative hierarchical clustering is performed on the basic concept vocabulary set V to form a compact concept set V', which removes the redundancy of the original concept set and enhances the calculation stability of the matrix decomposition in the later stage. It is a refinement of the original concept set.

[0043] Step A2, using the Pearson product-moment as a measure of the correlation between any set of concept pairs in the V' concept set to construct a correlation matrix R. The Pearson product difference coefficient is described as follows:

[0044] PM ( C i , C j ) = ...

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 video retrieving method based on context space. The video retrieving method includes constructing a concept similarity matrix by analyzing basic concept space objects, then subjecting the concept similarity matrix to spectral factorization to obtain a group of basic concept sets, finally mapping known concepts to space spanned by the group of basic concept sets, and measuring similarity among the concept objects on the space. According to the video retrieving method based on the context space, by means of the way of constructing the concept space, problems of locality, inconsistency and the like caused by measurement standards under traditional ontology concept sets are avoided, so that the measurement standards among the concept objects mapped to the space are uniform and wholly consistent, an effective solution is provided for solving video retrieving problems, relationships of basic abstract conceptions are closer, and accuracy of video retrieval is effectively improved.

Description

technical field [0001] The invention relates to the field of multimedia semantic mining, and proposes a video retrieval method based on context space. Background technique [0002] Semantic concept mining is gradually becoming the mainstream research direction to improve the accuracy of video retrieval. However, traditional semantic concept mining mostly detects a single concept, ignoring the objective fact that most concept objects co-occur in videos. In short, concepts are not independent and unrelated to each other, and they are often closely related in video units. It is the objective fact that conceptual objects are interrelated that provides clues to further mine contextual information to enhance the accuracy of video retrieval. Especially on the premise that some known concept objects exist, under the guidance of context information (concept correlation), some conceptual knowledge that exists objectively but has not been found in traditional semantic concept mining c...

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): G06F17/30G06F17/27
Inventor 魏骁勇杨震群徐浩然孙洋黄劲
Owner 魏骁勇
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