Motion characterization from temporal cooccurrences of local motion-based measures for video indexing

Author

Bouthemy, Patrick ; Fablet, Ronan

Author_Institution

IRISA, Rennes, France

Volume

1

fYear

1998

fDate

16-20 Aug 1998

Firstpage

905

Abstract

This paper describes an original approach for motion interpretation with a view to content-based video indexing. We exploit a statistical analysis of the temporal distribution of appropriate local motion-based measures to perform a global motion characterization. We consider motion features extracted from temporal cooccurrence matrices, and related to properties of homogeneity, acceleration or complexity. Results on various real video sequences are reported and provide a first validation of the approach

Keywords

feature extraction; image sequences; indexing; motion estimation; multimedia databases; statistical analysis; video signal processing; content-based indexing; feature extraction; homogeneity; motion characterization; multimedia database; statistical analysis; temporal cooccurrences; temporal distribution; video indexing; video sequences; Content based retrieval; Fires; Indexing; Motion analysis; Motion measurement; Multimedia databases; Rivers; Statistical analysis; TV; Video sequences;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 1998. Proceedings. Fourteenth International Conference on

Conference_Location

Brisbane, Qld.

ISSN

1051-4651

Print_ISBN

0-8186-8512-3

Type

conf

DOI

10.1109/ICPR.1998.711298

Filename

711298