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

Video consistent fusion processing method

A processing method and consistent technology, applied in the direction of TV, color TV, color TV parts, etc., to achieve simple user interaction and improve efficiency

Active Publication Date: 2012-04-04
ZHEJIANG UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the shortcomings of the existing video fusion technology, the present invention proposes a new video consistency fusion technology, which improves the efficiency of the existing video object extraction method, and focuses on solving the problem of inconsistency between the source and target scene lighting conditions. The fusion problem makes the fused object and the target scene highly harmonious and natural

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 consistent fusion processing method
  • Video consistent fusion processing method
  • Video consistent fusion processing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] Each part is described in detail below according to the flowchart of the present invention:

[0031] 1. Interactive selection and automatic extraction of video objects

[0032] In order to improve the accuracy of video object extraction in complex scenes, it is necessary to comprehensively consider multiple features to guide the extraction of video objects: (1) Foreground extraction should comprehensively consider multiple features, such as color, texture, shape and motion features. Among them, shape, as an important feature of object recognition, plays a greater role in object extraction. (2) These features should be evaluated both locally and globally to improve the accuracy of object extraction. In the process of video object extraction, the system first extracts the foreground contours of the key frames through manual interaction, and then automatically generates the foreground contours of the remaining frames by means of forward propagation based on key frames. 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 relates to a processing method for carrying out consistent fusion on video images from different sources. The method is mainly characterized by not only ensuring no seam and nature near the boundary in the video fusion process, but also comprehensively considering the global illumination and hue information of a target scene, wherein the information can be extracted from the target scene by the simple manual interactions and expressed by generating a corresponding reference image so as to diffuse into an object to be fused in an image fusion mode, thereby finally generating a new video with high reality. The invention can be used in the fields of post production of film and television programs, design of special effects of game scenes, manufacture of advertisements, news media, multimedia educational technologies and the like, provides powerful theoretical and technical support for fast development, and can reduce the manufacturing cost, thereby obtaining great economic benefit.

Description

Technical field: [0001] The invention relates to a method for consistent fusion of video images, specifically, interactive selection and automatic extraction of video foreground objects, seamless fusion between different source videos, and consistency of lighting and color tones in different video scenes processing techniques and methods. Background technique: [0002] Extracting foreground objects from still images or video sequences is a very important application of video image editing. The extraction of static images is the basis of video object extraction. Generally speaking, the user needs to interactively specify some foreground and background areas, and then use statistical methods to estimate the classification of the unknown area foreground and background from known information. Or adopt a simple boundary tracking method, and then use a statistical method to optimize the alpha matte of the transparent value matting result. At present, the research on alpha mattin...

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): H04N5/262
Inventor 张赟童若锋唐敏
Owner ZHEJIANG 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