Summary: A unied mixture framework for motion segmentation:
incorporating spatial coherence and estimating the number of
models
Yair Weiss and Edward H. Adelson
Dept. of Brain and Cognitive Sciences
MIT E10-120, Cambridge, MA 02139, USA
fyweiss,adelsong@psyche.mit.edu
Abstract
Describing a video sequence in terms of a small
number of coherently moving segments is useful for
tasks ranging from video compression to event per-
ception. A promising approach is to view the motion
segmentation problem in a mixture estimation frame-
work. However, existing formulations generally use
only the motion data and thus fail to make use of static
cues when segmenting the sequence. Furthermore, the
number of models is either specied in advance or es-
timated outside the mixture model framework. In this
work we address both of these issues. We show how to
add spatial constraints to the mixture formulations and

Source: Adelson, Edward - Computer Science and Artificial Intelligence Laboratory, Department of Brain and Cognitive Science, Massachusetts Institute of Technology (MIT)

Collections: Biology and Medicine