Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method and system for extracting, seeking and comparing visual patterns based on frame-to-frame variation characteristics

An extraction method and visual pattern technology, which is applied in the field of computer networks, can solve problems such as homology judgment between videos, and achieve the effects of avoiding disk storage space, good robustness, and ensuring query accuracy

Inactive Publication Date: 2011-05-11
PEKING UNIV
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0026] The technical problem to be solved by the present invention is: how to extract the video fingerprint that can uniquely identify the content from the video content, and further effectively solve the problem of homology judgment between videos in the massive video library

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 and system for extracting, seeking and comparing visual patterns based on frame-to-frame variation characteristics
  • Method and system for extracting, seeking and comparing visual patterns based on frame-to-frame variation characteristics
  • Method and system for extracting, seeking and comparing visual patterns based on frame-to-frame variation characteristics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0089] Below through embodiment and in conjunction with appendix Figure 4-7 The present invention is described in detail.

[0090] A visual pattern extraction, search and comparison method based on inter-frame variation features. The input video to be queried first passes through a preprocessing module. On the one hand, the preprocessing module is to unify various videos of different quality (maybe high-definition video or very blurry digital / analog, analog / digital converted video) to the same resolution and the same richness of detail as much as possible . The preprocessing should mainly include the functions of video denoising, removing high-frequency energy of video, and converting color frames into other visual signal frames.

[0091] After the input video is preprocessed, several adjacent frames are calculated, and the areas with the most abundant visual information changes between adjacent frames are estimated, and the positions of these areas are recorded, sorted, ad...

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 relates to a method and a system for extracting, looking up and comparing visual patterns based on frame-to-frame variation characteristics. The method comprises the following steps: performing effective video preprocessing, and unifying various videos with different qualities and resolution ratios to a level with accordant resolution ratios and video qualities as much as possible; performing calculation of relativity between a number of adjacent frames to find out a plurality of image blocks with obvious (such as the biggest difference) characteristics between a number of the adjacent frames, and coding the plurality of the blocks to form frame fingerprints; and combining the sequences of the frame fingerprint to form the visual patterns. Simultaneously, because the method for extracting the visual patterns has good robustness, a visual pattern comparison and lookup algorithm which is matched with the method for extracting the visual patterns and is based on matched inverted row query and window sliding is invented. Under the condition of ensuring the accuracy of the query, the retrieval rate is greatly improved. The method and the system can be applicable for real-time operations.

Description

technical field [0001] The invention relates to a method and system for visual pattern extraction, search and comparison based on inter-frame variation features, mainly a method and system for visual pattern extraction and fragment matching based on measurement of inter-frame variation characteristics, and belongs to the technical field of computer networks. Background technique [0002] With the rapid development of the Internet and digital multimedia technology, we are entering a new digital era. Digital image, video, audio and other digital media are becoming the main driving force of the information explosion. Media resources such as images, audio, and video (for convenience, hereinafter referred to as streaming media) and data resources such as data, documents, and codes (referred to as conventional data or data compared to streaming media) together constitute information resources, all of which have been edited by information sources. The decoding technique is represe...

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): H04N5/262H04N7/26H04N7/50G06K9/00
Inventor 黄铁军黄铮田永鸿高文
Owner PEKING UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com