Method for converting flat video to tridimensional video based on bidirectional tracing and characteristic points correction

Abstract

The invention relates to a method for converting a plane video to a stereoscopic video, based on bidirectional tracking and characteristic dot correction, which pertains to the multimedia technical filed of computers. The method comprises the steps as follows: a whole plane video sequence is divided into subsequences which have relevant contents; a frame is appointed as a key frame; foreground object segmentation is carried out to the key frame, and corresponding depth maps and profile feature points are extracted; bidirectional tracking is carried out to obtain the profile feature points of a non-key frame; the profile feature points that do not meet the motion consistency rules is eliminated; the position of each profile feature point in the collection of the profile feature points of the non-key frame is adjusted to be on the profile of a corresponding foreground object so as to obtain the collection of the profile feature points corresponding to each non-key frame of the video subsequences and recover the foreground object profile of the non-key frame, thus the depth map sequence of an original plane video sequence is obtained; finally, a stereoscopic video sequence corresponding to the original plane video sequence is obtained. Based on the key frame, the method obtains the high-precision depth map of the video sequence, thus well realizing the conversion from the plane video to the stereoscopic video.

Description

technical field [0001] The invention belongs to the technical field of computer multimedia, and is a technology for converting common plane video into stereoscopic video. technical background [0002] Through the research on the elements of human physiological stereo vision, it is found that when human beings see the same scene with left and right eyes, they will have a three-dimensional sense due to the existence of "parallax". Traditional video sequences are single-channel planar video sequences, while stereoscopic video sequences include multiple (two or more) planar video sequences, and the views of each planar video sequence at the same time have "parallax" Information can provide the corresponding left-eye view sequence and right-eye view sequence for the viewer, which is also the reason why an immersive stereoscopic effect can be produced when watching a stereoscopic video. [0003] For a long time, realistic stereoscopic video has been loved by the public because of...

AI Technical Summary

Problems solved by technology

The key to converting planar video to stereoscopic video is to extract the depth information from the planar video sequence. At present, the user manually outlines the outline of the foreground object in the video frame and assigns the depth information to ensure the accuracy of the conversion, but the conversion workload is relatively large. , long conversion cycle and high commercial cost

In addition, computer algorithms are used to assist, such as outlining the outline of the foreground object in the key frame of the video sequence, giving depth information, and completing the automatic conversion of other non-key frames through the tracking algorithm, which can improve the efficiency of manual conversion, but the effect is limited by the robustness of the algorithm. Sexuality, according to the short distance, the accuracy of automatic conversion is not high

Images