Video matting method aiming at depth information

A technology of depth information and keying, applied in the field of image processing, to achieve the effect of maintaining spatial and temporal consistency, reducing flicker and visual abrupt change, and improving the efficiency of keying calculation

Active Publication Date: 2015-09-23
ZHEJIANG GONGSHANG UNIVERSITY
View PDF2 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The object of the present invention is to solve the above-mentioned problem in existing this field, provide a kind of video image sequence matting method fast, be suitable for carrying out fast and efficient foreground object extraction to the video sequence with coherence between frames, comprise the following steps:

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 matting method aiming at depth information
  • Video matting method aiming at depth information
  • Video matting method aiming at depth information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] Embodiment 1: Use a depth camera (such as Microsoft's Kinect) to shoot a video to obtain an image sequence with depth information, that is, the image also has a Depth value in addition to the Color value.

[0048] Analyze and obtain the image sequence, apply the matting method of the present invention to the image sequence, and carry out according to the following steps:

[0049] (1) Calculate the tripartite map of each frame image in the image sequence;

[0050] (2) Key frame selection and video segmentation; according to the overlapping area ratio P between unknown regions between adjacent frames U Frames key . Set a keyframe Fr key,i with the next keyframe Fr key,i+1 The image sequences between are classified into the same segment Seg[Fr key,i ];

[0051] (3) Calculate the unknown region R of each frame in the video segment frame by frame U Pixel foreground, background, and transparency (F, B, α) values ​​within . The simulated annealing optimization algorithm...

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 present invention discloses a video matting method aiming at depth information. The method comprises the steps of calculating the three-parted graph of each frame image; segmenting a video to keep the frame-to-frame consistency in each video segment; obtaining the optimal foreground and transparency estimation values of each pixel in an unknown area of each frame; obtaining a global optimal solution of the pixels in all unknown areas in the video segments; finishing the matting processing of a whole segment of video. The method of the present invention is suitable for carrying out the rapid and efficient foreground object extraction on a video sequence having the frame-to-frame consistency, can keep the space-time consistency of the video matting, and enables the flicker and visual mutation to be reduced and the matting calculation efficiency to be improved.

Description

technical field [0001] The invention belongs to the field of image processing, in particular to a video matting method with depth information. Background technique [0002] As a technology with many uses in the field of computer vision, image extraction has always attracted the attention of scholars and enterprises, and has a large number of successful practical applications in many fields. The technology of extracting objects of interest from video image sequences is a deeper research on single image matting. Although it is in its infancy, more and more scholars have begun to devote themselves to it because of its wide application prospects. field of research. [0003] The matting process of a single frame image is to calculate the foreground pixel value F, background pixel value B and alpha transparency value of each pixel in the image, which is an under-constrained problem and the calculation is complicated. However, video keying is the keying of image sequences, and th...

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): H04N5/272
Inventor 彭浩宇王勋刘春晓孔丁科
Owner ZHEJIANG GONGSHANG UNIVERSITY
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