Method for obtaining compressed video caption based on H.264/AVC

Abstract

The invention discloses a method for obtaining compressed video caption based on H.264 / AVC, which comprises the following steps: firstly, executing the H.264 / AVC code flow analysis in the step 10, decoding the luminance component image section of a frame I from an H.264 / AVC compressed video data flow and decoding the AC coefficient; secondly, executing the entropy decoding and the inverse quantization in the step 20, performing the entropy decoding and the inverse quantization to the AC coefficient obtained in the step 10 so as to obtain the AC coefficient of DCT transform of each 4*4 and 8*8block; thirdly, executing the texture description based on the block in the step 30 and respectively performing the texture description to the AC coefficients obtained in the step 20; fourthly, executing the caption block crude detection in the step 40 and primarily determining that each block belongs to the caption block or the background block on the basis of performing the texture description to all blocks in the frame I; fifthly, executing the caption strip positioning in the step 50 and positioning a caption strip on the basis of obtaining the template TMAP acquired by the caption block crude detection: repeating the steps 10-50 until the video flow ending position and executing the caption detection ending in the step 60.

Description

A method of obtaining video subtitles based on H.264 / AVC compression technical field The invention relates to the field of applied electronic technology, in particular to a method for acquiring video subtitles based on H.264 / AVC compression. Background technique Video subtitles are closely related to the content of video programs, and can effectively assist people to grasp the theme of the program in video appreciation, and then understand the content of the video. The detection and recognition of video subtitle information can enrich text-based video content queries. Therefore, effective acquisition of video subtitle information is a necessary link. Due to the huge amount of video, it is generally necessary to compress the video during storage and transmission. H.264 / AVC is by far the most effective video compression method. There are important applications in many occasions. In the prior art, Chinese patent ZL02801652.1 discloses a technical solution of "detecting su...

AI Technical Summary

Problems solved by technology

In the prior art, Chinese patent ZL02801652.1 discloses a technical solution of "detecting subtitles in video signals". The advantage of this solution is that the calculation complexity is not very high, but its technical implementation assumes that the position of subtitles is It is fixed in the middle and lower part of the image. Therefore, this technology cannot effectively detect and acquire subtitle information when there are full-screen subtitles in the video program and the position is not fixed; if the subtitle information is not in the specified detection Within the range, the subtitle information cannot be well obtained and applied

In the process of implementing the present invention, the inventor found that there is still a technical solution in the prior art, that is, the detection of subtitles is based on the information in the pixel domain, but for H.264 / AVC compressed video, it first needs to be decoding, and then detection, so the computational complexity is high

Images