DMCA
Figure–Ground Segmentation from Occlusion (2004)
Cached
Download Links
| Venue: | IEEE TRANSACTIONS ON IMAGE PROCESSING |
| Citations: | 7 - 2 self |
BibTeX
@MISC{Aguiar04figure–groundsegmentation,
author = {Pedro M. Q. Aguiar and José M. F. Moura},
title = { Figure–Ground Segmentation from Occlusion},
year = {2004}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Layered video representations are increasingly popular, see [2] for a recent review. Segmentation of moving objects is a key step for automating such representations. Current motion segmentation methods either fail to segment moving objects in low textured regions or are computationally very expensive. This paper presents a computationally simple algorithm that segments moving objects even in low texture/low contrast scenes. Our method infers the moving object templates directly from the image intensity values, rather than computing the motion field as an intermediate step. Our model takes into account the rigidity of the moving object and the occlusion of the background by the moving object. We formulate the segmentation problem as the minimization of a penalized likelihood cost-function and present an algorithm to estimate all the unknown parameters: the motions, the template of the moving object, and the intensity levels of the object and of the background pixels. The cost function combines a maximum likelihood estimation term with a term that penalizes large templates. The minimization algorithm performs two alternate steps for which we derive closed-form solutions. Relaxation improves the convergence even when low texture makes it very challenging to segment the moving object from the background. Experiments demonstrate the good performance of our method.
Keyphrases
figure ground segmentation current motion segmentation method penalized likelihood cost-function maximum likelihood estimation term good performance key step intermediate step minimization algorithm performs unknown parameter closed-form solution object template background pixel intensity level recent review segmentation problem low texture low contrast scene low texture video representation low textured region motion field image intensity value cost function simple algorithm large template
