Efficient image segmentation for region-based motion estimation and compensation

Author

Salgado, Luis ; García, Narciso ; Menéndez, José M. ; Rendón, Enrique

Author_Institution

Image Process. Group, Univ. Politecnica de Madrid, Spain

Volume

10

Issue

7

fYear

2000

fDate

10/1/2000 12:00:00 AM

Firstpage

1029

Lastpage

1039

Abstract

An intra-frame segmentation strategy to assist region-based motion estimation and compensation is presented. It is based on the multiresolution application of a histogram clustering and a probabilistic relaxation-labeling algorithm, followed by a local gradient-based bottom-up merging procedure. Specially suited for region-based video coding, it strongly differs from other proposals in that it generates arbitrary shaped image regions with pixel accuracy at a low computational cost, while allowing full reconstruction of the segmentation at the decoder without the transmission of any region description information

Keywords

computational complexity; gradient methods; image resolution; image segmentation; motion compensation; motion estimation; video coding; arbitrary shaped image region; computational cost; decoder; histogram clustering; image segmentation; intra-frame segmentation strategy; local gradient-based bottom-up merging procedure; multiresolution application; pixel accuracy; probabilistic relaxation-labeling algorithm; reconstruction; region-based motion estimation; region-based video coding; Clustering algorithms; Computational efficiency; Histograms; Image generation; Image segmentation; Merging; Motion estimation; Pixel; Proposals; Video coding;

fLanguage

English

Journal_Title

Circuits and Systems for Video Technology, IEEE Transactions on

Publisher

ieee

ISSN

1051-8215

Type

jour

DOI

10.1109/76.875507

Filename

875507