Summary: IEEE TRANSACTIONS ON IMAGE PROCESSING 1
FigureGround Segmentation from Occlusion
Pedro M. Q. Aguiar, Member, IEEE, and Jos´e M. F. Moura, Fellow, IEEE
Layered video representations are increasingly popular, see  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.
EDICS: 2-SEGM (Image and Video Processing--Segmentation), 2-ANAL (Analysis).
Permission to publish this abstract separately is granted.
Contact author: Jos´e M. F. Moura, Carnegie Mellon University, ECE Dep., 5000 Forbes Ave, Pittsburgh, PA 15213-3890. E-mail: