Method and system for detecting advertisement in audio/video

Abstract

The invention relates to a method and a system for detecting advertisement in an audio / video. The method comprises the following steps of: step 1, extracting audio frequency from the audio / video to be detected, and extracting short-time energy of frames and Mel frequency cepstrum coefficient characteristic; and step 2, searching and finding two groups of frames, which have mutual similarity meeting a predetermined condition, from the audio frequency according to the short-time energy of the frames and the Mel frequency cepstrum coefficient characteristic, the positions of the frames in each group are continuous in the audio frequency, and a corresponding audio / video segment of each group of frames in the audio / video to be detected is the advertisement. Compared with the prior art, the method and the system can more accurately and efficiently detect an advertisement segment in the audio / video.

Description

technical field [0001] The invention relates to the field of audio and video detection, in particular to a method and system for detecting advertisements from audio and video. Background technique [0002] Advertisement detection refers to locating and marking where advertisements appear in video and audio programs. Automatic advertisement detection is to use the computer to automatically detect the advertisement segment from the video and audio stream and precisely locate the position of the advertisement segment. [0003] Currently common automatic advertisement detection methods include rule-based methods, identification-based methods, shot classification-based methods, and recognition-based methods. [0004] The rule-based approach uses a set of features and rules to distinguish commercials from regular broadcast TV programming, which is non-commercial. Advertisements usually appear in groups, and each group of advertisements is called an ad group. Advertisements and ...

AI Technical Summary

Problems solved by technology

Problems with the rule-based approach include: difficulty in finding uniform rules for all kinds of programs; features selected to represent advertisements are sometimes not stable and reliable; and it is difficult to build a uniform detection system through these features

However, the disadvantage of this method is that it is difficult to obtain a database containing a large number of advertisements. If it is manually intercepted and marked from the program, it will consume huge manpower and material resources

Moreover, this method cannot detect ad segments that do not exist in the database

In addition, as the database size increases, the detection efficiency will decrease.

[0008] The data processed by the above various methods is video data. Due to the characteristics of the video itself, the above various methods need to process a large amount of data and high feature complexity, so the calculation speed is slow.

Images