Video clip searching and positioning method based on content

A technology for video clips and positioning methods, which is applied in the field of video processing and can solve the problems of single video features, large computational complexity and storage space requirements.

Active Publication Date: 2017-05-31
XI AN JIAOTONG UNIV
View PDF4 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The above methods are all very robust, but have the following two disadvantages: 1. The video features are relatively single, and can only describe the video content in a limited way; and storage space requirements are large

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 clip searching and positioning method based on content
  • Video clip searching and positioning method based on content
  • Video clip searching and positioning method based on content

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0084] The implementation of the method of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0085] Such as figure 1 As shown, the present invention provides a content-based video segment retrieval method, which first divides the library video and query video into video segments of the same length, extracts the feature information in the video segment H.264 compressed code stream, and It is processed to generate six feature vectors and stored in the video library. The similarity between videos is judged by measuring the distance between the library video and the feature vector of the query video segment, so as to realize the video retrieval of similar content and select candidate videos. Such as figure 2 As shown, the present invention proposes a positioning algorithm based on a sliding window, uses the selected candidate video as the target video, takes the length of the query video as the window length, re-extracts th...

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 video clip searching and positioning method based on content. In order to solve the problems that in an existing video searching and positioning field, the feature extraction calculation amount is large, the feature is simplex, and the positioning accuracy rate is low, the invention provides a video clip searching and positioning method based on content, and belongs to the field of video processing. The method comprises the following steps of firstly partially decoding an H.264 compressed video to extract motion information and static information of videos, and generating a plurality of feature vectors; judging similarity between videos by measuring the distances between the feature vectors, thus achieving searching of the videos with similar content; and at last providing a positioning algorithm based on a sliding window, further using feature screening and positioning cut-off algorithms to accurately and effectively position the queried video in candidate videos screened according to the similarity based on the distances between the window measure feature vectors.

Description

technical field [0001] The invention belongs to the field of video processing, and relates to a content-based video segment retrieval and positioning method, and relates to a video retrieval method combining multiple features and a sliding window-based video positioning algorithm. Background technique [0002] With the rapid development of computer, multimedia and network technology, the production and dissemination of network video is becoming more and more convenient, which leads to the explosive growth of digital multimedia video information. Traditional video processing methods have been unable to satisfy people's rapid browsing, retrieval and query of massive video content. In order to effectively process a large number of video resources, intelligent analysis technology based on video content came into being. Content-based video segment retrieval technology can assist people to complete tasks such as video retrieval, location, and mining, so as to better manage and ef...

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): G06F17/30H04N21/845
CPCH04N21/8456G06F16/73G06F16/7837
Inventor 王萍张童宇
Owner XI AN JIAOTONG 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