Method for converting plane video into stereoscopic video based on human-machine interaction

Abstract

The present invention relates to a human-machine interaction based method for converting plane video to stereo video, which belongs to the computer multimedia technology field. The method comprises that: performing object partition to foreground object of first frame of plane video sequence and designating the deepness value, giving a deepness value for the background region, generating a deepness map of the first frame; selecting a plurality of characteristic points using KLT method on the profile of foreground object partitioned from the first frame, and performing track, obtaining positions of a plurality of characteristic points in the subsequent frame; generating closed profile curve of a plurality of objects in the frame using profile recovery method; generating deepness map; synthesizing a left view of original sequence and a right view synthesized by a left view and corresponding deepness map to obtain the stereo video frame; consisting stereo video sequence with all stereo video frame.The advantage of the invention is that accurate deepness map of each frame is obtained, thereby implementing conversion from plane video to stereo video, and the method simplifies working amount of users in the maximal degree.

Description

technical field [0001] The invention belongs to the technical field of computer multimedia, and in particular relates to a technology for converting common plane video into stereoscopic video. technical background [0002] Anyone who has seen a 3D movie will be deeply impressed by its realism, and the feeling of being there is unforgettable, but now, stereoscopic video is gaining more and more popularity worldwide and in many industries. For example, large-scale shopping and entertainment venues in some central cities in China have begun to arrange three-dimensional players, using these three-dimensional players to play pre-made advertisements or other promotional videos, giving people a strong visual impact Powerful, very able to attract the audience's attention. [0003] Planar video is a monocular video sequence, and the above-mentioned 3D movie belongs to stereoscopic video. The so-called stereoscopic video is a binocular video sequence, which includes two video sequenc...

AI Technical Summary

Problems solved by technology

[0009] 1. The depth information obtained by analyzing the image motion between frames can only be regarded as "false information" instead of real depth information, so the obtained depth map often does not match the actual situation

[0010] 2. Since the depth information is obtained based on inter-frame motion, if there is no moving part in the image, no depth information can be obtained

[0011] Of course, there are also some automatic methods to obtain the depth information of still images based on depth cues such as occlusion, shadows, and textures, but generally speaking, these methods are not very versatile.

[0012] Therefore, the automatic planar video to stereoscopic video conversion method, whether it is based on the depth cues (occlusion, shadow, texture, etc.) of the static image, or based on the image motion between frames, the obtained depth information often does not match the actual situation.

Images