Scalable indexing of HD Video

Author

Morand, C. ; Benois-Pineau, J. ; Domenger, J-Ph

Author_Institution

LaBRI, Univ. Bordeaux, Talence

fYear

2008

fDate

18-20 June 2008

Firstpage

417

Lastpage

424

Abstract

Video indexing technique is crucial in multimedia applications. In the case of HD (high definition) video, the principle of scalability is of great importance. The wavelet decomposition used in the MJPEG2000 provides this property. In this paper, two descriptors for indexing of HD video are presented. The first one is based on the GM (global motion) of the video and the correlation matrix is used as similarity measure for matching. The second one is object-oriented and uses histograms in the wavelet domain as indexes ; similarity measure is then based on histogram intersection. The complete process of extraction of objects of interest and to determine GM are also detailed.

Keywords

indexing; matrix algebra; video retrieval; wavelet transforms; HD video; MJPEG2000; correlation matrix; global video motion; high definition video; histogram intersection; multimedia applications; scalable indexing; video indexing technique; wavelet decomposition; Discrete wavelet transforms; High definition video; Histograms; Image segmentation; Indexing; Motion estimation; Multimedia databases; Scalability; Video compression; Wavelet domain;

fLanguage

English

Publisher

ieee

Conference_Titel

Content-Based Multimedia Indexing, 2008. CBMI 2008. International Workshop on

Conference_Location

London

Print_ISBN

978-1-4244-2043-8

Electronic_ISBN

978-1-4244-2044-5

Type

conf

DOI

10.1109/CBMI.2008.4564977

Filename

4564977