Video retrieval method based on novel semantic space

A semantic and spatial technology, applied in special data processing applications, instruments, electronic digital data processing, etc., to achieve the effect of improving retrieval accuracy

Active Publication Date: 2013-09-04
魏骁勇
View PDF5 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The present invention makes full use of the affiliation and derivation relations between the semantics of multiple concepts to construct a globally unified semantic space, and perform semantic-based retrieval on this space, which solves the deficiency of video retrieval based on the semantic method of a single concept , so as to improve the retrieval 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
  • Video retrieval method based on novel semantic space
  • Video retrieval method based on novel semantic space
  • Video retrieval method based on novel semantic space

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] A video retrieval method based on a novel semantic space, characterized in that:

[0020] Given a set of basic concept semantics, the traditional concept semantic space C=[C 1 , C 2 ,......C N ], where each C i For the semantics of a concept, each concept C i corresponds to a detector d i , to map the low-level features of the video into the concept space.

[0021] The process of constructing a new semantic space B is as follows:

[0022] Step A1: Transform the semantic space to obtain a new complete and compact semantic space P. The method can be selected according to the situation of the C space. The linear space can use PCA, SVD, non-negative matrix decomposition, etc., and the nonlinear space can use The manifold method.

[0023] Step A2: Map the semantics in C space to P space, and then perform hierarchical clustering, using Brown Cluster or other algorithms. The result of the clustering can construct a tree structure to express the affiliation and generali...

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 retrieval method based on a novel semantic space. The video retrieval method based on the novel semantic space comprises the steps of firstly creating a concept space for all of concepts and creating a detector for each concept and used for mapping low-level features in videos into the concept space; performing spectral factorization to the created concept space to obtain the semantic space formed by multiple 'key concepts'; and creating an overall body semantic space for evaluating similarity of different concepts according to the semantic space. By means of the method, the problem that different concepts cannot be directly compared uniformly and overall in the retrieval process is solved, and accordingly the video retrieval accuracy is improved.

Description

technical field [0001] The invention relates to the field of multimedia retrieval, and proposes a video retrieval method based on a novel semantic space. Background technique [0002] Traditional video retrieval is based on video text tags, and the correlation between video features and text features is not combined, resulting in poor retrieval results. Video retrieval based on concept semantics has become the mainstream trend. However, the current technology is mainly based on the semantics of a single concept for video retrieval, ignoring the affiliation between concepts, deriving the relationship, and not giving full play to the relationship between concept semantics. ability. For example, concepts such as "tank", "mortar", and "bomber" are subordinate to the concept of "weapon", and the concept of "weapon" has a certain derivation ability for the concept of "war". When retrieving videos related to "war", when "tanks" and "mortars" appear in the video, then there is a 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): G06F17/30
Inventor 魏骁勇杨震群黄劲徐浩然孙洋
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