Title :
Video classification using spatial-temporal features and PCA
Author :
Xu, Li-Qun ; Li, Yongmin
Author_Institution :
BTexact Technol., Ipswich, UK
Abstract :
We investigate the problem of automated video classification by analysing the low-level audio-visual signal patterns along the time course in a holistic manner. Five popular TV broadcast genre are studied including sports, cartoon, news, commercial and music. A novel statistically based approach is proposed comprising two important ingredients designed for implicit semantic content characterisation and class identities modelling. First, a spatial-temporal audio-visual "concatenated" feature vector is composed, aiming to capture crucial clip-level video structure information inherent in a video genre. Second, the feature vector is further processed using principal component analysis to reduce the spatial-temporal redundancy while exploiting the correlations between feature elements. This gives rise to a compact representation fro effective probabilistic modelling of each video genre. Extensive experiments are conducted assessing various aspects of the approach and their influence on the overall system performance.
Keywords :
audio-visual systems; correlation methods; feature extraction; image classification; image representation; principal component analysis; television broadcasting; video signal processing; PCA; TV broadcast genre; automated video classification; cartoon; clip-level video structure information; commercial; feature vector; low-level audio-visual signal patterns; music; news; principal component analysis; semantic content characterisation; spatial-temporal features; sports; system performance; Content based retrieval; Face; Humans; Indexing; Information retrieval; Principal component analysis; Signal analysis; Streaming media; TV broadcasting; Video sequences;
Conference_Titel :
Multimedia and Expo, 2003. ICME '03. Proceedings. 2003 International Conference on
Print_ISBN :
0-7803-7965-9
DOI :
10.1109/ICME.2003.1221354