Video structure alignment method and system

A technology of video structure and video, applied in the field of image processing, to achieve the effect of avoiding computational cost

Active Publication Date: 2020-08-21
TSINGHUA UNIV
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there is little research on how to extract salient edges from videos to achieve video structure alignment between different scenes

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 structure alignment method and system
  • Video structure alignment method and system
  • Video structure alignment method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0014] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0015] figure 1 It is a flowchart of an embodiment of the video structure alignment method of the present invention, such as figure 1 As shown, it includes: S101, merging the structural edge information map of any input video in the two input videos with the gradient information map of any input video, and obtaining the saliency edge feature map ...

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

Embodiments of the present invention provide a video structure alignment method and system. The alignment method includes: fusing the structure edge information map of any input video and the gradient information map of any input video in the two input videos, and obtaining the structure edge information map of any input video Salient edge feature map; down-sampling the salient edge feature map of any input video in time and space dimensions, and constructing a salient edge feature layer of any input video, wherein the salient edge feature layer starts from the top layer The underlying resolution is increased layer by layer; the correlation-based matching measure matches the salient edge feature layers of the two input videos, obtains a preset number of alignment results, and selects the preset number of alignment results Alignment of any alignment results to the video structure. The embodiment of the present invention avoids complex calculation costs brought about by edge calculation detection, etc., and can efficiently and quickly acquire alignment results and then align videos.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of image processing, and more specifically, to a video structure alignment method and system. Background technique [0002] Video matching technology is a very important tool in the field of computer graphics, which can help users quickly retrieve video content that meets their needs. Since video spatio-temporal alignment was proposed in 2002, video matching technology has been widely studied, but existing technologies are based on local feature matching or color matching, which are used to quickly retrieve video content of identical or visually similar scenes, such as the VideoSnapping system, which can be based on The time interval in which some scenes on the timeline match, and the alignment in the time interval of unmatched scenes is predicted. However, video alignment between different scenes is a challenge because: first, there are no robust local features for matching video cont...

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): G06K9/46G06T5/00
CPCG06T5/00G06V10/462
Inventor 胡事民汪淼方晓楠杨国炜
Owner TSINGHUA 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