Real-time detection of sport in MPEG-2 sequences using high-level AV-descriptors and SVM

Author

Glasberg, Ronald ; Schmiedeke, Sebastian ; Oguz, Hüseyin ; Kelm, Pascal ; Sikora, Thomas

Author_Institution

Commun. Syst. Group, Tech. Univ. Berlin, Berlin

fYear

2008

fDate

13-16 Nov. 2008

Firstpage

727

Lastpage

732

Abstract

We present a new approach for classifying MPEG-2 video sequences as dasiasportpsila or dasianon-sportpsila by analyzing new high-level audiovisual features of consecutive frames in real-time. This is part of the well-known video-genre-classification problem, where popular TV-broadcast genres like cartoon, commercial, music video, news and sports are studied. Such applications have also been discussed in the context of MPEG-7. In our method the extracted features are logically combined by a support vector machine to produce a reliable detection. The results demonstrate a high identification rate of 98.5% based on a large balanced database of 100 representative video sequences gathered from free digital TV-broadcasting and world wide web.

Keywords

image classification; image sequences; support vector machines; video signal processing; MPEG-2 video sequence classification; MPEG-7; SVM; TV-broadcast genres; World Wide Web; free digital TV-broadcasting; high-level AV-descriptors; high-level audiovisual features; real-time sport detection; support vector machine; video-genre-classification problem; Cameras; Color; Event detection; Feature extraction; Principal component analysis; Real time systems; Spatial databases; Support vector machine classification; Support vector machines; Video sequences;

fLanguage

English

Publisher

ieee

Conference_Titel

Digital Information Management, 2008. ICDIM 2008. Third International Conference on

Conference_Location

London

Print_ISBN

978-1-4244-2916-5

Electronic_ISBN

978-1-4244-2917-2

Type

conf

DOI

10.1109/ICDIM.2008.4746790

Filename

4746790