Improved Chinese opera video fusion method based on Background Matting

A technology of video fusion and opera, applied in the direction of editing/combining graphics or text, image data processing, instruments, etc., can solve the problems of difficult to achieve the expected effect, cumbersome processing process, long processing time, etc., to improve the rough edges of characters, Simplified steps, fast fusion effect

Pending Publication Date: 2021-11-02
NORTHWEST UNIV(CN)
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] At present, most of the existing video fusion methods need to create a three-part map in a specific environment or manually to produce better results, which require high material requirements, cumbersome processing, and long processing time
There are also some methods that do not require a three-point map, but the effect is not good, and it is difficult to achieve the expected effect

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
  • Improved Chinese opera video fusion method based on Background Matting
  • Improved Chinese opera video fusion method based on Background Matting
  • Improved Chinese opera video fusion method based on Background Matting

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The specific content of the present invention will be further explained in detail below in conjunction with the examples.

[0039] Such as Figure 1-Figure 3 Shown, the present invention provides a kind of method based on the opera video fusion of Background Matting improvement, specifically comprises the following steps:

[0040] Step 1: Enter the Xiqu video with characters to be replaced (a), the background image (b) without characters in the Xiqu video (a), and the background video to be replaced (c), see Figure 4 shown;

[0041] Step 2: Carry out frame extraction to opera video (a) and background video (c) input in step 1, get as follows Figure 5 The video frame diagram shown;

[0042] Step 3: Normalize the video frames extracted in step 2, and set the pixel value of each frame to

[0043] Step 4: Use homography to align the background image (b) with the video frame image extracted from the opera video (a), and at the same time, convert the video frame image e...

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 an improved Chinese opera video fusion method based on Background Matting, which comprises the steps of firstly, respectively carrying out frame extraction on an input original traditional opera video and a new background video, and then resetting the sizes of video frames of the original traditional opera video and the new background video; secondly, using an AKAZE feature extraction and matching method for carrying out alignment processing on a background and an original image, wherein an experimental result shows that the matching speed is greatly improved, meanwhile, a mode of converting an image in Background Matting into a gray scale is modified, so that the video under a green screen background can be segmented, and the accuracy of video segmentation is improved; and finally, fusing the figures extracted from the video frames to the corresponding positions in the new background video frames, and synthesizing the fused video frames into a new opera video according to the original resolution, thereby effectively improving the problem of rough edges of the fused figures, and greatly improving the opera video fusion speed.

Description

technical field [0001] The invention belongs to the technical field of computer graphics processing, and in particular relates to an improved opera video fusion method based on Background Matting. Background technique [0002] Chinese opera is mainly composed of three different art forms: folk song and dance, rap and burlesque. It originated from primitive singing and dancing, and is a comprehensive stage art style with a long history. It is characterized by the aggregation of many art forms under one standard, and embodies their respective personalities in the common nature. [0003] Opera is one of the traditional Chinese arts. There are various and interesting operas. The performances include singing, dancing, speaking, singing, writing and martial arts. It combines "singing, doing, reciting, and fighting" in one. It is unique in the history of world drama. Comprehensiveness, fictitiousness, and procedurality are the main artistic characteristics of Chinese opera. Thes...

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): G06T11/60G06T7/194G06T9/00
CPCG06T11/60G06T7/194G06T9/00G06T2207/10016
Inventor 周明全白涛冯龙耿国华李蕊李启航杨雪刘阳洋周蓬勃
Owner NORTHWEST UNIV(CN)
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