Computing Optical Flow Distributions Using Spatio-temporal Filters
Eero P. Simoncelli and Edward H. Adelson
MIT Media Laboratory Vision and Modeling Technical Report #165 (1991).
We describe the relationship between gradient methods for computing optical flow and filter-based spatio-temporal
energy models of biological motion processing, revealing that these techniques are equivalent under certain
conditions. We discuss extensions of these techniques which compute probability distributions of optical flow. The
use of distributions allows proper handling of the uncertainties inherent in the optical flow computaion,
facilitating the combination with information from other sources. The probabilistic framework also leads to several
useful extensions of the standard quadratic gradient solution. We use these extensions to compute optical flow for
both synthetic and a real image sequence.