Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/55296
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Journal article |
Title: | Parametric model-based motion segmentation using surface selection criterion |
Author: | Gheissan, N. Bab-Hadiashar, A. Suter, D. |
Citation: | Computer Vision and Image Understanding, 2006; 102(2):214-226 |
Publisher: | Academic Press Inc |
Issue Date: | 2006 |
ISSN: | 1077-3142 1090-235X |
Statement of Responsibility: | Niloofar Gheissari, Alireza Bab-Hadiashar and David Suter |
Abstract: | This paper presents a new framework for the motion segmentation task, which includes an algorithm capable of addressing the important issue of the inter-relationships between data segmentation, model selection, and noise scale estimation. In this algorithm, we have incorporated our newly proposed model selection criterion named Surface Selection Criterion. The presented algorithm simultaneously selects the correct motion model, while finding the scale of the noise and performing the segmentation task. As a result, the estimated motion parameters and the final segmentation results are accurate. The algorithm is tested for motion segmentation of synthetic and real video data containing multiple objects undergoing different types of motion. Our results also show that the proposed algorithm is capable of detecting occlusion and degeneracy. © 2006 Elsevier Inc. All rights reserved. |
Keywords: | Motion segmentation Model selection Optic flow Motion estimation |
Description: | Copyright © 2006 Elsevier Inc. All rights reserved. |
DOI: | 10.1016/j.cviu.2006.02.002 |
Published version: | http://dx.doi.org/10.1016/j.cviu.2006.02.002 |
Appears in Collections: | Aurora harvest 5 Computer Science publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.