Manufacture method and manufacture device for interactive three-dimensional video key frame

Abstract

The invention discloses a manufacture method and a manufacture device for an interactive three-dimensional video key frame. The manufacture method comprises the following steps that an image sequence is obtained, in addition, a key frame in the image sequence is selected, and after the key frame is subjected to the image denoising, the K-means clustering algorithm is invoked for merging similar pixel points in the key frame into a region, and region information is recorded; each region assigned weight is calculated, a GrpahCut algorithm is invoked according to the region assigned weight for carrying out region division on the key frame for obtaining the region division results; and the image expansion and corrosion operation is carried out according to the image division results for constructing a trisection image of the key frame, and in addition, a Bayesian cutout algorithm is invoked for obtaining the refined division results; the image foreground and background regions are constructed according to the refined division results, in addition, the depth assignment is respectively carried out, and the foreground and background depth images are merged for obtaining a key frame depth image to be output. The manufacture method has the advantages that the manufacture cost of the key frame is reduced, and in addition, the manufacture speed and the precision are high.

Description

technical field [0001] The invention relates to the technical field of computer image processing, in particular to a method for making an interactive stereoscopic video key frame and a device for making an interactive stereoscopic video key frame. Background technique [0002] Stereoscopic video, as an important form of expression of current film and television works, is widely considered to be the main development direction of the film and television industry in the future. The display effect of stereoscopic video is clear in layers, bright in color, has a strong visual impact, and leaves a deep impression on the audience. In addition, the display effect of stereoscopic video is more realistic, and the scenes and characters are lifelike, which gives the audience a strong immersive feeling and has high artistic appreciation value. Because stereoscopic video has the characteristics that these flat videos do not have, it has broad market prospects and commercial value in fiel...

AI Technical Summary

Problems solved by technology

This method requires the use of professional stereoscopic video shooting equipment and a complete post-processing pipeline, which is expensive

At the same time, stereo cameras need to be matched and calibrated between different viewing angles when shooting, which has certain restrictions on the shooting environment and camera movement, which to a large extent restrict the popularity of direct shooting with stereo cameras

The second way is to use 3D modeling software to make stereoscopic videos. This method can generate stereoscopic videos based on any scene, but it requires professionals to spend a lot of energy on modeling scenes and objects, and the economic and time costs are prohibitive.

However, the edges of the segmentation results obtained by this type of method are relatively blunt, especially when there are objects in the image that are occluded from front and back or have small hair edges, etc., the phenomenon of segmentation edge errors is more obvious

The inaccuracy of the segmentation results directly leads to the inaccuracy of the depth assignment, which affects the quality of the key frame depth map, and eventually leads to obvious defects such as object edge jitter in the generated stereoscopic video

These flaws will cause discomfort to stereoscopic video viewers, and to a certain extent limit the popularization of flat video stereoscopic technology

Images