An appearance based approach for video object extraction and representation

Author

Garg, Gaurav ; Sharma, Pramod K. ; Chaudhury, Santanu ; Chowdhury, Ragini

Author_Institution

Dept. of Electr. Eng., Indian Inst. of Technol., New Delhi, India

Volume

2

fYear

2002

fDate

2002

Firstpage

536

Abstract

We describe a novel appearance based scheme for extraction and representation of video objects. The tracking algorithm used for video object extraction is based upon a new eigen-space update scheme. We propose a scheme for organisation of video objects in an appearance based hierarchy. The appearance based hierarchy is constructed using a new SVD based eigen-space merging algorithm. The hierarchy enables approximate query resolution. Experiments performed on a large number of video sequences have yielded promising results.

Keywords

eigenvalues and eigenfunctions; feature extraction; image sequences; merging; object recognition; singular value decomposition; video databases; SVD; appearance based approach; appearance based hierarchy; approximate query resolution; eigen-space merging algorithm; eigen-space update scheme; experiments; singular value decomposition; tracking algorithm; video object extraction; video object representation; video sequences; Content based retrieval; Data mining; Eigenvalues and eigenfunctions; Histograms; Matrix decomposition; Merging; Robustness; Tracking; Video coding; Video sequences;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 2002. Proceedings. 16th International Conference on

ISSN

1051-4651

Print_ISBN

0-7695-1695-X

Type

conf

DOI

10.1109/ICPR.2002.1048358

Filename

1048358