| | |
Summary: Presented at: IEEE Conference on Computer Vision and Pattern Recognition, Mauii, Hawaii. June, 1991.
Probability Distributions of Optical Flow
Eero P. Simoncelli y
Edward H. Adelson z
David J. Heeger x
Abstract
Gradient methods are widely used in the com-
putation of optical
ow. We discuss extensions
of these methods which compute probability dis-
tributions of optical
ow. The use of distribu-
tions allows representation of the uncertainties
inherent in the optical
ow computation, facil-
itating the combination with information from
other sources. We compute distributed optical
ow for a synthetic image sequence and demon-
strate that the probabilistic model accounts for
the errors in the
ow estimates. We also compute
distributed optical
ow for a real image sequence.
1 Introduction
The recovery of motion information from visual input is
|
