Method for searching visual lens based on contents

A lens and content technology, applied in the field of video retrieval, can solve the problems of high manpower consumption, inability to make full use of rich information content of video, hinder effective acquisition and use of information, etc., and achieve the effect of high retrieval accuracy

Inactive Publication Date: 2008-06-18
NANJING UNIV OF SCI & TECH
View PDF1 Cites 29 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Digitized media information, especially digitized video and audio information has massive data, which causes great difficulties to the management, storage and transmission of information, and becomes the main bottleneck that hinders the effective acquisition and use of information by human beings.
According to the traditional text data analysis, manage

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 searching visual lens based on contents
  • Method for searching visual lens based on contents
  • Method for searching visual lens based on contents

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The present invention will be described in further detail below in conjunction with the accompanying drawings.

[0030] to combine figure 1 and figure 2 , the content-based lens retrieval method of the present invention comprises the following steps:

[0031] In the first step, the video database is first segmented by shot, and the shot is used as the basic structural unit and retrieval unit of the video content. The method of segmenting the video database is the gradual shot segmentation method based on statistical distribution.

[0032] The second step is to use the key frame strategy of the key frame number and the spatial-temporal attention selection model to select the attention area to characterize the content of the video lens, that is, to characterize the content of the lens, including the following steps:

[0033] (1) Let the total length of the shot be L, and the number of key frames be n, then select n key frames with a step length of L / (n-1); the extracte...

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 of retrieval of a lens based on the content. Firstly, video database is splitted by the lens and the lens is taken as a basic structure unit and a retrieval unit; care areas are selected to represent the content of the video lens by a key frame strategy of the number of the key frame and a selective model of space-time attention; a lens A and a lens B are designed as significant areas and the matching of the two corresponding key frames is calculated; the matching of the lens space-time content is calculated. The representation mode of the lens content of the invention keeps the converted information with associated semanteme and context to be on a time line; then the video content is retrieved on the content representation, good retrieval effect is obtained and higher accuracy can be obtained.

Description

a technical field [0001] The invention belongs to the technical field of video retrieval, in particular to a content-based video retrieval method. Two background technology [0002] With the continuous development of computer technology, computer processing power has been significantly improved. The advanced integrated manufacturing process has continuously improved the hardware performance, and the innovation of network technology and communication technology has effectively promoted the development of information technology. The amount of media information processed by people's applications is increasing exponentially every day, and the development of information technology has brought massive video data. New forms of media information exchange and application such as video on demand, digital interactive TV, and video conferencing have been fully integrated into people's daily study, work, life, and entertainment. Digitized media information, especially digitized video a...

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
IPC IPC(8): G06F17/30G06T7/00
Inventor 许满武杨献春朱光蔚杨群柏文阳陈红兵
Owner NANJING UNIV OF SCI & TECH
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