Video image content editing and spreading method based on local feature structure keeping

一种内容编辑、视频图像的技术，应用在图像通信、图像增强、图像分析等方向，能够解决时间空间消耗率大、插入对象形状影响、不能很好的着色等问题，达到框架简单有效、节省计算时间、避免编辑异常的效果

Active Publication Date: 2013-01-30
BEIHANG UNIV
View PDF5 Cites 27 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method can better fuse the inserted objects, but the time and space consumption rate is too high
In 2009, Zeev Farbman et al. proposed a fast fusion method of video image scenes based on median coordinates, which greatly improved the space-time efficiency of the Poisson method, but this method is easily affected by the shape of the inserted object
However, this method cannot color the image reviewed by the scene very well, and the amount of interaction in the coloring process is too large

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 image content editing and spreading method based on local feature structure keeping
  • Video image content editing and spreading method based on local feature structure keeping
  • Video image content editing and spreading method based on local feature structure keeping

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0124] As an implementable manner, the seamless integration of the newly inserted object with the scene includes the following steps:

[0125] On the basis of the selected insertion object area, triangulate the area;

[0126] The inserted object can be selected by the user with a brush, or it can be selected according to the already made mask;

[0127] Then calculate the feature structure relationship between each pixel point on the edge of the insertion area and each triangle vertex in the area;

[0128] Then according to the color difference between each pixel on the edge of the inserted object area and the covered target scene pixel, the color modification value of each triangle vertex of the inserted object is obtained;

[0129] According to the color values ​​of the vertices of the triangles, the color values ​​of the pixels in each triangle are linearly interpolated to obtain the final generation effect.

[0130] refer to Figure 6 The flow chart of precise object ext...

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 video image content editing and spreading method based on local feature structure keeping. The method comprises the following steps of: mapping all pixel points in input image / video to a preset feature space; solving the nearest K neighbors of each pixel point in the feature space; constructing a local linear relation of all the pixel points by utilizing a local linear embedding dimension reducing method; matching the image / video editing requirements preset by a user with partial pixels of the image / video; and spreading the editing requirements preset by the user to all other pixels of the image / video by utilizing the correspondence of partial pixels in step S400 according to the structure relation of the pixels. The method can be used for preventing the editing and spreading of the image / video from being affected by object shape, and the editing and spreading of the image / video has certain adaptability and robustness.

Description

technical field [0001] The invention relates to the technical fields of image processing, computer vision and enhanced processing, in particular to a video image content editing and dissemination method based on local feature structure preservation. Background technique [0002] In the field of digital images, one of the most common image processing methods is to edit and process according to the video image content. For example, change the color of video images; blend objects from different video sources together to form a video without editing traces; accurately extract hair in images, etc. For art designers or staff engaged in film and television editing, in order to edit the color and content of a video, a large amount of manual editing will be carried out. In fact, video image content features usually have some kind of internal connection. The video image editing can be performed automatically according to these internal relations, which can improve the video image ed...

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): G06T7/40G06T5/00
CPCG06T11/001H04N1/56H04N1/60H04N1/6008H04N1/6083H04N1/62
Inventor 陈小武邹冬青赵沁平李健伟丁峰
Owner BEIHANG 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