Video content representation using optimal extraction of frames and scenes

Author

Doulamis, Nikolaos D. ; Doulamis, Anastasios D. ; Avrithis, Yannis S. ; Kollias, Stefanos D.

Author_Institution

Dept. of Electr. & Comput. Eng., Nat. Tech. Univ. of Athens, Greece

Volume

1

fYear

1998

fDate

4-7 Oct 1998

Firstpage

875

Abstract

An efficient video content representation is proposed using optimal extraction of characteristic frames and scenes. This representation, apart from providing browsing capabilities to digital video databases, also allows more efficient content-based queries and indexing. For performing the frame/scene extraction, a feature vector formulation of the images is proposed based on color and motion segmentation. Then, the scene selection is accomplished by clustering similar scenes based on a distortion criterion. Frame selection is performed using an optimization method for locating a set of minimally correlated feature vectors

Keywords

content-based retrieval; database indexing; feature extraction; image colour analysis; image motion analysis; image representation; image segmentation; optimisation; pattern clustering; video databases; video signal processing; browsing; content-based indexing; content-based queries; digital video databases; distortion criterion; feature vector formulation; minimally correlated feature vectors; motion segmentation; optimal frame extraction; optimal scene extraction; scene clustering; scene selection; video content representation; Computer vision; Content based retrieval; Feature extraction; Indexing; Layout; Motion segmentation; Multimedia databases; Optimization methods; Spatial databases; Video sequences;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 1998. ICIP 98. Proceedings. 1998 International Conference on

Conference_Location

Chicago, IL

Print_ISBN

0-8186-8821-1

Type

conf

DOI

10.1109/ICIP.1998.723660

Filename

723660