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

A method for establishing a tree-shaped video semantic index based on context fusion

An index building and context technology, applied in the field of video retrieval, can solve the problem of not meeting user retrieval needs and other problems

Inactive Publication Date: 2017-05-10
FUZHOU UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, the traditional single-grained, non-hierarchical video semantic index can no longer meet the user's retrieval needs.

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
  • A method for establishing a tree-shaped video semantic index based on context fusion
  • A method for establishing a tree-shaped video semantic index based on context fusion
  • A method for establishing a tree-shaped video semantic index based on context fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0066] Please refer to figure 1 , a method for building a context-integrated tree-shaped video index, first extracts the semantic information of the shot in units of shots, then obtains the semantic context of the video shot in a supervised manner, and uses a tree structure to represent the context. Then combine the semantics of shots and their contexts to reason about scene semantics. Finally, the shot semantics and scene semantics are embedded into the tree structure and used as video indexes. details as follows:

[0067] 1. For n training video clips video j Perform shot segmentation to obtain r training video shots. Extract and quantify the visual features of the shot, and construct a visual feature vector v.

[0068] Set the annotation semantic set Semantic={Sem t |t=1,...,e}, artificially mark the semantic Sem appearing in r shots t , added to the lens semantic set of each lens, and then for each type of lens semantic Sem t Construct a shot semantic training set, ...

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 belongs to the field of technologies for retrieving video, and discloses a method for creating tree video semantic indexes. The video semantic indexes built by the aid of the method contain video semantics of various particle sizes, contexts among the video semantics are fused by the semantic indexes, and the video semantics of the different particle sizes are connected with one another according to the contexts, so that tree structures can be formed. The method is characterized by comprising steps of extracting lens semantic sets of various lenses one by one; acquiring contexts of video lens semantics under the monitoring condition and representing the contexts by context tag trees; combining the lens semantic sets and context information with one another to infer scene semantics; embedding the lens semantic sets and the scene semantics into the context tag trees to obtain the video indexes. The method has the advantages that after the semantic indexes are created for video by the aid of the method, users can input keywords of the different particle sizes to retrieve the video, search spaces can be diminished by the aid of context information in the indexes, and accordingly the efficiency of retrieval systems can be improved.

Description

technical field [0001] The invention belongs to the technical field of video retrieval, and is a method capable of constructing a video semantic index by using the shot semantics, scene semantics and semantic context of the video. Background technique [0002] Today video data has become one of the most important data on the Internet. However, with the explosive growth of video data, how to efficiently manage and retrieve videos has become a very difficult problem. Usually, a user inputs a keyword when retrieving a video, and then the video search engine needs to find relevant video data according to the keyword. This requires the establishment of a suitable semantic index for the video in order to improve the efficiency and hit rate of the user's video retrieval. The construction of video index based on video semantics is to automatically analyze the visual features of the video by computer to obtain the semantic information contained in the video, and then use the semant...

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 Patents(China)
IPC IPC(8): G06F17/30
CPCG06F16/71
Inventor 余春艳苏晨涵翁子林陈昭炯
Owner FUZHOU UNIV