A method of natural background video matting

Abstract

The invention provides a natural background video sectional drawing method. The method comprises the steps that 1) the method automatically selects a key frame, specifically the method automatically selects the key frame in a video by calculating inter-frame difference; 2) a key frame Trimap map is generated, specifically a user us allowed to provide useful information through a small amount of manual interaction and a GrabCut segmentation algorithm and a Gaussian blur method are used to semi-automatically generate the Trimap map on the key frame; 3) a middle frame Trimap map is generated, specifically bidirectional optical flow propagation is used to generate the Trimap map of each middle frame, and color, gradient and other information are used to correct errors generated by optical flow propagation; and 4) according to the Trimap maps of all video frames and a Bayesian sectional drawing algorithm with added three-dimensional space-time optimization, the alpha mask map of each frame of the video is calculated, and the alpha mask map and a new background are synthesized to acquire a new synthesized video. According to the invention, the method has the advantages of fast speed and less user interaction, and the finally acquired new synthesized video has the advantages of good time coherence, high reality and the like.

Description

technical field [0001] The present invention relates to the technical field of video processing, in particular to a natural background video cutout method. Background technique [0002] Matting refers to the process of precisely separating the foreground object of interest from the background in a static image or a continuous video sequence. It has a wide range of applications in photo editing, film and television animation production, virtual reality and other fields. [0003] Specifically, foreground objects are extracted from the background by estimating the color and transparency information of each pixel in the image. The transparency value of a pixel is called an alpha value, and the image composed of all pixel transparency is called an alpha mask. The formal description of cutout is as follows: [0004] I z = α z f z +(1-α z )B z (1) [0005] Among them, I z , F z 、B z 、α z Respectively, the observed color, foreground color, background color, α value of ...

AI Technical Summary

Problems solved by technology

[0013] Most of the above methods rely too much on user interaction, which not only consumes more time, but also increases the uncertainty of the video matting results.

Moreover, some methods use the matting algorithm on a single frame separately, and do not make full use of the temporal and spatial correlation between video frames, which makes the matting results lack of coherence, and flicker and jitter appear in the new synthetic video

Images