Video thumbnail generation method and device

Abstract

The embodiment of the invention discloses a video thumbnail generation method and device. The method comprises the following steps: carrying out scene boundary detection on a video, and sectioning the video according to different scenes; from all sections of the video, selecting a section with the longest duration as a key section; from all video frames contained in the key section, selecting a video frame with the highest balance as a key video frame; and compressing an image of the key video frame so as to generate a thumbnail to be used as the thumbnail of the video. The video thumbnail generation method and device disclosed by the embodiment of the invention can solve the problems that in the prior art, by analyzing each video frame of the whole video to generate the thumbnail, the calculation amount is large, and the efficiency is low; the invention also solves the problem that in the prior art, a video frame having no reference value for the video content is used as the thumbnail of the video; and a video frame which represents the video content and has a reference value for users can be captured as the thumbnail of the video.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a video thumbnail generation method and device. Background technique [0002] In traditional media, text and pictures are the main information carriers. In order to facilitate people to quickly understand the content of text and pictures, abstracts and thumbnails are usually used to display some key information and attract users' attention. [0003] With the development of computer network technology, more and more people obtain information through video, but due to the particularity of video information, the content representation of space and time cannot be fully described by language alone. How to present the "summary" of the video to the user is an urgent problem to be solved. [0004] At present, the "summary" of the video is mainly to extract a certain frame of picture from the video to generate a thumbnail of the video, which is used as a content-based browsing and accessi...

AI Technical Summary

Problems solved by technology

[0007] The technical problem to be solved by the embodiments of the present invention is to provide a method and device for generating video thumbnails, which can avoid the problems in the prior art that generate thumbnails by analyzing each video frame of the entire video, which requires a large amount of calculation and low efficiency ; and solve the existing problem of using video frames that have no reference value for video content as video thumbnails, and can intercept video frames that represent video content and have reference value for users as video thumbnails

Images