Video retrieval method based on multi-core canonical correlation analysis

A correlation analysis and core typical technology, applied in image analysis, image data processing, special data processing applications, etc., can solve problems such as low efficiency, inability to meet the growing needs of users, and insufficient video information description capabilities

Active Publication Date: 2014-02-05
ZHEJIANG UNIV
View PDF5 Cites 34 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method of completely relying on manual labeling of video information is inefficient, and the ability to describe video information is insufficient and requires a certain amount of experience.
Therefore, text-based retrieval methods can no longer meet the growing needs of users

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 multi-core canonical correlation analysis
  • Video retrieval method based on multi-core canonical correlation analysis
  • Video retrieval method based on multi-core canonical correlation analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] With reference to accompanying drawing, further illustrate the present invention:

[0037] A video retrieval method based on multi-core canonical correlation analysis, the method comprises the following steps:

[0038] 1. After grabbing videos from the Internet, perform the following operations for each video and its text description:

[0039] 1) Segment the video according to whether the shot has a sudden change, extract its key frame, and extract the visual features in the key frame and the motion feature of the shot to form a video feature vector, and extract the word frequency feature for the text description of each video;

[0040]2) Use the multi-core canonical correlation analysis method to obtain the mapping matrix of video features and word frequency features respectively, so as to obtain the corresponding low-dimensional representations of the two, so that their correlation in the low-dimensional data space is maximized;

[0041] 3) When the user enters a key...

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

Disclosed is a video retrieval method based on multi-core canonical correlation analysis. The method includes grasping text descriptions corresponding to the video on internet, and then operating on the video: firstly dividing the video according to whether a shot is mutated or not, extracting key frames, extracting vision features of the key frames and moving features of the shot to form video feature vectors, and extracting word-frequency features from the text descriptions of each video; then utilizing the method of the multi-core canonical correlation analysis to obtain mapping matrixes and low-dimensional representation of the video features and the word-frequency features, and allowing the mapping matrixes and the low-dimensional representation to have the maximum correlation in low-dimensional space; finally, when a user inputs key words to perform video retrieval, acquiring the low-dimensional representation of the word-frequency features of the key words according to the mapping matrixes of the word-frequency features, and returning video retrieval results sequentially from large to small of the degrees of cosine similarity with the low-dimensional representation of the video features. The method has the advantages that the correlation of video content and the retrieval key words is enhanced, and the accuracy of retrieval by the user is improved.

Description

technical field [0001] The invention relates to the technical field of video retrieval, in particular to a video retrieval method based on multi-core canonical correlation analysis. Background technique [0002] With the rapid development of computer network multimedia technology and communication technology in recent years, people can upload, watch and download various video information through the Internet. The Internet has gradually become a huge video warehouse. How to retrieve the video information needed by users more quickly and effectively has increasingly become a hot issue in information retrieval. [0003] The traditional video retrieval method is based on text, which uses video tag information as keywords to form a one-to-one matching relationship with videos, and then performs clustering and classification by performing feature extraction and preprocessing on keywords. This method of completely relying on manual labeling of video information is inefficient, lac...

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): G06F17/30G06T7/00
CPCG06F16/7328G06F16/7847G06F16/786
Inventor 卜佳俊高珊李平陈纯何占盈宋明黎
Owner ZHEJIANG 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