Combined motion and edge analysis for a layer-based representation of image sequences

Author

Pedersini, Federico ; Sarti, Augusto ; Tubaro, Stefano

Author_Institution

Dipt. di Elettronica e Inf., Politecnico di Milano, Italy

Volume

1

fYear

1996

fDate

16-19 Sep 1996

Firstpage

921

Abstract

We propose a method for the motion-congruent segmentation of image sequences based on both motion field and luminance information. In order to do so, the affine motion models are determined by analyzing the motion field through a clustering procedure, while their regions of validity are determined by an MRF-based region estimator. This last block performs a pixel-wise re-assignment of a limited number of affine models (those determined via clustering)

Keywords

Markov processes; brightness; edge detection; image representation; image segmentation; image sequences; motion estimation; random processes; MRF based region estimator; affine motion models; clustering procedure; edge analysis; image representation; image sequences; layer based representation; luminance information; motion analysis; motion congruent segmentation; motion field analysis; motion field information; pixel-wise reassignment; Image analysis; Image motion analysis; Image segmentation; Image sequence analysis; Image sequences; Layout; Motion analysis; Motion compensation; Motion estimation; Parametric statistics;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 1996. Proceedings., International Conference on

Conference_Location

Lausanne

Print_ISBN

0-7803-3259-8

Type

conf

DOI

10.1109/ICIP.1996.559650

Filename

559650