Scene content classification from MPEG coded bit streams

Author

Dawood, Ali M. ; Ghanbari, Mohammed

Author_Institution

Dept. of Electron. Syst. Eng., Essex Univ., Colchester, UK

fYear

1999

fDate

1999

Firstpage

253

Lastpage

258

Abstract

We propose a classification method of MPEG coded video based on the image texture and motion levels of the scene content. The texture and motion are divided into three levels each, low, medium and high, resulting into nine scene categories. Since in MPEG-1 (and MPEG-2) encoder the DCT coefficients of the I-frame are affected by the image texture, while the motion affects the macroblocks coding mode of P- and B-frames, hence, an automatic scene classification can be obtained from the coded bit stream based on the scene´s texture and motion levels. The method is useful for the content-based video analysis, such as video modeling and MPEG-7

Keywords

code standards; data compression; discrete cosine transforms; image classification; image motion analysis; image texture; telecommunication standards; transform coding; video coding; B-frames; DCT coefficients; I-frame; MPEG coded bit streams; MPEG coded video; MPEG-1 encoder; MPEG-2 encoder; MPEG-7 standard; P-frames; automatic scene classification; content-based video analysis; image texture; macroblocks coding mode; motion levels; scene content classification; video modeling; Data mining; Discrete cosine transforms; Image coding; Image databases; Image texture; Layout; MPEG 7 Standard; Multimedia databases; Streaming media; Videoconference;

fLanguage

English

Publisher

ieee

Conference_Titel

Multimedia Signal Processing, 1999 IEEE 3rd Workshop on

Conference_Location

Copenhagen

Print_ISBN

0-7803-5610-1

Type

conf

DOI

10.1109/MMSP.1999.793841

Filename

793841