Share Email Print
cover

Proceedings Paper

Multistage affine parameter clustering for improved motion segmentation
Author(s): Georgi D. Borshukov; Gozde Bozdagi; Yucel Altunbasak; A. Murat Tekalp
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

We propose two key modifications to a recent motion segmentation algorithm developed by Wang and Adelson, which greatly improve its performance. They are: (i) the adaptive k- means clustering step is replaced by a merging step, whereby the hypothesis (affine parameters of a block) which has the smallest representation error, rather than the respective cluster center is used to represent each layer, and (ii) we implement it in multiple stages, where pixels belonging to a single motion model are labeled at each stage. Performance improvement due to the proposed modifications is demonstrated on real video clips.

Paper Details

Date Published: 13 March 1996
PDF: 8 pages
Proc. SPIE 2666, Image and Video Processing IV, (13 March 1996); doi: 10.1117/12.234737
Show Author Affiliations
Georgi D. Borshukov, Univ. of Rochester (United States)
Gozde Bozdagi, Univ. of Rochester (United States)
Yucel Altunbasak, Univ. of Rochester (United States)
A. Murat Tekalp, Univ. of Rochester (United States)


Published in SPIE Proceedings Vol. 2666:
Image and Video Processing IV
Robert L. Stevenson; M. Ibrahim Sezan, Editor(s)

© SPIE. Terms of Use
Back to Top
PREMIUM CONTENT
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?
close_icon_gray