News video scene generating method

Abstract

The invention discloses a news video scene generating method which comprises the following steps: firstly sampling a news video sequence according to a preset interval; calculating the similarity of color histograms of two adjacent video image frames according to the color histogram of a sampled video image; determining a shot boundary sequence according to interframe similarity, the preset high threshold value, the preset low threshold value and the preset lowest threshold value of length of a dissolve shot of the whole news video sequence; then judging with a flashlight; selecting a first frame of each shot as a shot key frame and outputting a boundary sequence of the scene according to the similarity among shot key frames and a corner distribution figure in a subtitle area. With the adoption of the technical scheme, the problem that partitioning algorithm of the double threshold value shot is higher in complexity and the partitioning result is affected by the flashlight can be solved, and continuous shots with same subtitle and the similar visions can be merged to a same video scene when the video scene is generated.

Description

technical field [0001] The invention relates to the field of multimedia technologies, in particular to a method for generating news video scenes. Background technique [0002] With the rapid popularization of multimedia technology, people need to contact and process a large amount of video information. The existing video organization methods are to manually edit video paragraphs, and then use text descriptions to summarize the content of the video. However, due to the rich content of images or videos, many features of images, such as irregular shapes and scattered textures, are difficult to express in text descriptions.” Moreover, text descriptions are highly subjective, and different observers or the same observer in different The description of the same thing will be different under different angles. If there is no uniform standard for the description of visual information, it will not be possible to organize and query this information well, and then use it effectively. In...

AI Technical Summary

Problems solved by technology

[0015] The purpose of the present invention is to propose a method for generating news video scenes, which can solve the problems of the high complexity of the double-threshold shot segmentation algorithm and the influence of flashlights on the segmentation results, and can combine consecutive shots with the same subtitle and Combine visually similar shots into the same video scene, thereby realizing news video shot segmentation and automatic scene generation, reducing the workload of news video editing

Images