Detection of moving objects in facial image sequences

Author

Yahampath, P. ; Chen, H. ; Kinsner, W.

Author_Institution

Dept. of Electr. & Comput. Eng., Manitoba Univ., Winnipeg, Man., Canada

Volume

1

fYear

1998

fDate

24-28 May 1998

Firstpage

369

Abstract

An approach to detection of moving objects in facial image sequences, with application to very low bit rate video coding is presented. In this approach, a split-and-merge procedure is used. The basis of the approach is the segmentation of a given frame based on edge detection and subsequent merging of regions based on motion analysis. The edge detection has been achieved using the wavelet transform. The motion estimation is based on a geometric model for the objects to be detected. Preliminary results obtained with typical head and shoulder images are presented

Keywords

edge detection; image segmentation; image sequences; motion estimation; object detection; video coding; wavelet transforms; VLBR coding; edge detection; facial image sequences; frame segmentation; geometric model; head and shoulder images; motion analysis; motion estimation; moving objects detection; split-and-merge procedure; very low bit rate coding; video coding; wavelet transform; Bit rate; Face detection; Image edge detection; Image segmentation; Image sequences; Merging; Motion analysis; Object detection; Video coding; Wavelet transforms;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrical and Computer Engineering, 1998. IEEE Canadian Conference on

Conference_Location

Waterloo, Ont.

ISSN

0840-7789

Print_ISBN

0-7803-4314-X

Type

conf

DOI

10.1109/CCECE.1998.682761

Filename

682761