Research on TV advertisement detection base on video shot

Author

Xia, Qian ; Tang, Guoneng

Author_Institution

Coll. of Media & Commun., Guizhou MinZu Univ., Guiyang, China

Volume

2

fYear

2012

fDate

20-21 Oct. 2012

Firstpage

245

Lastpage

248

Abstract

Combined adaptive double threshold shot detection method with TV program Audio features, a robust TV commercial video detection method is proposed. Firstly, Commercial videos are separated from complete TV programs with adaptive double threshold shot detection method. At the same time the paper suggests that the audio cut information are combined with the shot boundary detection algorithm, to improve the shot boundary accuracy. Finally complete TV shows without commercial video can be got by asymmetric AdaBaost shot classification. The results on some TV programs show the effectiveness of the suggested method.

Keywords

advertising; image classification; image segmentation; image sensors; television standards; television stations; TV advertisement detection; TV media standard; TV program audio; adaptive double threshold shot detection method; asymmetric AdaBaost shot classification; audio cut information; domestic TV station; robust TV commercial video detection method; shot boundary detection algorithm; video shot; Accuracy; Advertising; Detection algorithms; Feature extraction; Histograms; Lenses; TV; commercial video; frame difference; shot boundary detection;

fLanguage

English

Publisher

ieee

Conference_Titel

System Science, Engineering Design and Manufacturing Informatization (ICSEM), 2012 3rd International Conference on

Conference_Location

Chengdu

Print_ISBN

978-1-4673-0914-1

Type

conf

DOI

10.1109/ICSSEM.2012.6340855

Filename

6340855