Shot-based television advertisement recognition method

Abstract

The invention discloses a shot-based television advertisement recognition method. The method comprises the following steps: firstly, decomposing continuous video data into shots; then extracting the features of each shot by a convolution neural network; performing dimension reduction processing on feature vectors; classifying the shots into advertisements and non-advertisements by a trained classification model; and after advertisement shots are classified, recognizing the content of the advertisement shots by using image and audio features in the shots, that is, recognizing the shots are advertisements of which company or product. The aim of the invention is to monitor commercial advertisements broadcast in television broadcasting; the advertisements can be recognized in various programssuch as movies, TV shows, variety shows, news and sports, and among different programs; the calculation cost can be lowered; and the efficiency is increased.

Description

technical field

[0001] The invention relates to the technical field of advertisement identification, in particular to a lens-based television advertisement identification method. Background technique

[0002] Advertising is becoming more and more important to the development of today's business, but most of the current research is on Internet advertising, and there is little analysis and monitoring of TV advertising. Due to the high cost, TV advertisements are often more reflective of the development direction of a company or a product. Automatic advertisement recognition technology is the key technology to accurately and effectively monitor the amount of advertisement broadcast. For advertising customers, the effect of advertisement placement can be analyzed by monitoring the actual broadcast volume, combined with ratings data and sales conditions; for market analysis and consulting agencies , this measurement provides data reference for its analysis of enterprise developm...

Images