Supercharge Your Innovation With Domain-Expert AI Agents!

Method for extracting compressed domain key frame based on similarity of adjacent I frame DC image

A technology of image similarity and extraction method, which is applied in the field of network video content analysis to achieve the effect of ensuring effectiveness and accuracy and improving speed

Inactive Publication Date: 2011-01-19
西安博易智能科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a compression domain key frame extraction method based on the similarity of adjacent I frame DC images, which can quickly and accurately complete the network video key frame extraction process, and solve the existing key frame extraction method that can only process a single Shortcomings of the video standard, which simplifies the video keyframe extraction process

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 extracting compressed domain key frame based on similarity of adjacent I frame DC image
  • Method for extracting compressed domain key frame based on similarity of adjacent I frame DC image
  • Method for extracting compressed domain key frame based on similarity of adjacent I frame DC image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0028] The method of the invention takes into account factors such as the existence of multiple video compression standards and the real-time nature of network video content auditing, and uses the DC image characteristics of the I frame in the compressed domain to provide a method for quickly extracting key frames in the compressed domain. Suppose VS is the original video stream to be processed, DC i is the DC image corresponding to the ith I frame in the VS, i=1, 2, 3, . . . , n. n is the total number of I frames, then the similarity d of adjacent I frame DC images j defined as: d j = dist ( j , j + 1 ) = Σ l = 0 L ...

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 for extracting a compressed domain key frame based on the similarity of adjacent I frame DC image. The method comprises the following steps: firstly, calculating the similarity of an adjacent I frame DC image in original video to form a similarity set; secondly, carrying out clustering of the similarity set of the adjacent I frame DC image by means of a clusteringalgorithm Kmeans; and finally, extracting the key frame according to the similarity value of each I frame in the clustering result. The method makes full use of the characteristic that adjacent I frames have greater similarity to reduce calculation times, thereby avoiding a great deal of unnecessary calculation and making use of the clustering algorithm Kmeans to complete clustering of the similarity set S dist within shorter time; and thus the extraction method changes the conception of dividing lens first and then extracting key frame, simplifies the extraction process of video key frame andensures result validity; moreover, the extraction method can process key frame extraction of different types of video files.

Description

technical field [0001] The invention belongs to the technical field of network video content analysis, and relates to a compression domain key frame extraction method based on the similarity of adjacent I-frame DC images. Background technique [0002] With the in-depth development of network multimedia technology, network video has gradually become a mainstream way of information expression. In network video content analysis, due to the large amount of data in the video itself, it takes a lot of time and space to analyze all video frames, which cannot meet the requirements for real-time performance. Because the video content has a certain correlation in time and space, the key frame can usually reflect the main content of the video. Therefore, by extracting and analyzing key frames, the amount of video processing data can be effectively reduced, the time and space complexity of calculation can be reduced, and the efficiency of network video content analysis can be improved....

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): H04N7/26G06F17/30H04N19/159
Inventor 孙钦东王倩郭晓军胡敏
Owner 西安博易智能科技有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com