A method for automatic selection of stereoscopic subtitle adding position suitable for stereoscopic video

A stereoscopic video and automatic selection technology, applied in the field of video processing, can solve problems such as unfavorable development in the field of stereoscopic information, occlusion of subtitles and image content, and reduced viewing experience, so as to improve viewing experience, simple and effective algorithm, and reduce discomfort Effect

CN108712642BInactive Publication Date: 2020-07-10TIANJIN UNIV
4 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Publication Date
2020-07-10
Estimated Expiration
Not applicable · inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention relates to a three-dimensional (3D) subtitles adding location automatic selection method suitable for a three-dimensional video. The method comprises the following steps: 3D image parallax metering; 3D subtitles initial location judging; and optimal subtitles location and parallax selection, wherein the parallax video sets P are orderly from big to small in consideration that the smaller the parallax value is, the more the uncomfortable watching is, the small numerical value with high frequency is used as the final parallax value df in the 3D subtitles adding, multiple corresponding candidate regions are possibly existent under the parallax value condition, the coordinates corresponding to the regions form a set, and the final coordinate location of the 3D subtitles is determined by selecting the coordinate location closest to the coordinate point from the set.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the field of video processing and relates to the problem of automatically selecting the position of stereoscopic subtitles to improve viewing comfort. Background technique

[0002] With the rapid development of electronic technology and network technology, digital images are widely used in people's daily life. Stereoscopic images have developed rapidly in recent years, and have been successfully applied to various fields such as advertisements, television, dramas, and movies, and are closely related to people's lives. As a tool to assist picture content, subtitles are crucial to human understanding of video information. At this stage, video subtitles mainly rely on manual addition in the later stage. This method is time-consuming and labor-intensive, which is not conducive to the rapid development of the field of three-dimensional information. Moreover, adding subtitles based on experience often results in occlusion of subtit...

Examples

Embodiment Construction

[0030] In order to make the technical solution of the present invention clearer, the specific implementation manners of the present invention will be further described below.

[0031] 1. Stereo image parallax calculation

[0032] For the stereoscopic video V and its stereoscopic image pair I for each frame v (v=1, 2, 3, ..., K, K represents the number of stereoscopic video frames), firstly apply the optical flow method to calculate its disparity map D.

[0033] 2. Preliminary position determination of stereoscopic subtitles

[0034] The present invention has the explanation of the following points: 1, for the stereoscopic video frame, the present invention selects two regions (upper region and lower region) as the candidate regions added by subtitles, such as figure 1 As shown (the range of the upper area is Where W and H represent the width and height of the image respectively, and the range of the lower area is 2. Considering that the stereoscopic subtitles are often l...