Method for splitting news video program, and method and system for cataloging news videos

Abstract

The invention discloses a method for splitting a news video program and a method and a system for cataloging news videos. The method for splitting the news video program comprises the following steps of: sequencing detection results according to a time sequence to obtain an event sequence by detecting characteristic information of titles of the news video, a headline, characteristic information of comperes, lens transformation, a mute point of an audio, a switching point, a keynote period sudden change point and the like; briefing the event sequence by adopting a preset symbol set and a production rule, and judging rough positions of start points and end points of news sections in the event sequence; calculating a union posterior probability of a start position of each news section near the rough start position according to the event sequence, selecting the moment with the maximum posterior probability as the accurate start position of each news section, splitting the news video, and thus obtaining the news video sections. According to the method, the adopted algorithm is stable and effective; the structural information in the news video can be summarized effectively; the accurate positions of splitting points of the news sections can be determined; and the news video can be split stably and accurately.

Description

technical field [0001] The invention relates to the technical field of video processing, in particular to a news video program segmentation method, a news video cataloging method and a system. Background technique [0002] News video is an important processing object of media units such as TV stations and video websites. On the one hand, after years of accumulation, a large number of news videos covering all aspects of life have become valuable assets of these media units; on the other hand, new video data needs to be processed in a timely manner every day. At the same time, news video is also a video type that is more suitable for processing. People can obtain relevant semantic information from videos. These semantic information have a unified structure in content organization, which is easy to extract, think and process these semantic information, so as to understand the video content. [0003] However, unlike traditional text news programs, video news programs cannot di...

AI Technical Summary

Problems solved by technology

The main problems are: (1) The assumption is unreasonable. In practical applications, for a 30-minute news program, the host usually only appears for less than 5 minutes, and a large number of other faces will generate many false alarms. Affect the performance of the algorithm; (2) The time domain information is not fully utilized, and the candidate frame group generated based on voting does not make full use of the time domain information, and cannot adapt to the situation where the video content changes gradually. At the same time, the distribution of the candidate frames in the time domain is compared messy, making post-processing more difficult

[0011] There are more deviations between the cutting point of the news segment in the segmentation result and the real cutting point

Images