An object-based segmentation approach for very low bit rate video sequence

Author

Yong, Yang ; Bo, Huang ; Qiao, Wang ; Lenan, Wu

Author_Institution

Dept. of Radio Eng., Southeast Univ., Nanjing, China

fYear

2001

fDate

2001

Firstpage

205

Lastpage

208

Abstract

An object based spatial-temporal segmentation approach for very low bit rate video sequences is proposed. Temporal segmentation is processed by the absolute displaced frame difference instead of the change detection mask. A fast rain-falling watershed algorithm is used for the spatial segmentation. The final result is obtained by the combination of the temporal segmentation and the spatial segmentation. The proposed method achieves excellent performance with MPEG-4 test sequences of videoconferencing

Keywords

image segmentation; image sequences; motion estimation; teleconferencing; video coding; MPEG-4 test sequences; absolute displaced frame difference; fast rain-falling watershed algorithm; object based segmentation approach; object based spatial-temporal segmentation approach; spatial segmentation; temporal segmentation; very low bit rate video sequence; videoconferencing; Bit rate; Change detection algorithms; Light sources; MPEG 4 Standard; Motion segmentation; Object detection; Partial response channels; Testing; Video sequences; Videoconference;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Multimedia, Video and Speech Processing, 2001. Proceedings of 2001 International Symposium on

Conference_Location

Hong Kong

Print_ISBN

962-85766-2-3

Type

conf

DOI

10.1109/ISIMP.2001.925368

Filename

925368