Title :
An automatic system for real-time video-genres detection using high-level-descriptors and a set of classifiers
Author :
Glasberg, Ronald ; Schmiedeke, Sebastian ; Kelm, Pascal ; Sikora, Thomas
Author_Institution :
Commun. Syst. Group, Tech. Univ. Berlin, Berlin
Abstract :
We present a new approach for classifying MPEG-2 video sequences as dasiacartoonpsila, dasiacommercialpsila, dasiamusicpsila, dasianewspsila or dasiasportpsila by analyzing specific, high-level audio-visual features of consecutive frames in real-time. This is part of the well-known video-genre-classification problem, where popular TV-broadcast genres are studied. Such applications have also been discussed in the context of MPEG-7 [1]. In our method the extracted features are logically combined using a set of classifiers to produce a reliable recognition. The results demonstrate a high identification rate based on a large representative collection of 100 video sequences (20 sequences per genre) gathered from free digital TV-broadcasting in Europe.
Keywords :
feature extraction; image classification; image sequences; real-time systems; video signal processing; Europe; MPEG-2 video sequence classification; digital TV-broadcasting; feature extraction; high-level audio-visual features; high-level-descriptors; real-time video-genres detection; reliable recognition; Classification tree analysis; Detectors; Europe; Feature extraction; Hidden Markov models; MPEG 7 Standard; Real time systems; Support vector machine classification; Support vector machines; Video sequences; Classifier Combination; Genre-Detection; High-Level Descriptors;
Conference_Titel :
Consumer Electronics, 2008. ISCE 2008. IEEE International Symposium on
Conference_Location :
Vilamoura
Print_ISBN :
978-1-4244-2422-1
Electronic_ISBN :
978-1-4244-2422-1
DOI :
10.1109/ISCE.2008.4559449
