Title :
Displacement estimates through adaptive affinities
Author :
Werkhoven, P. ; Toet, A. ; Koenderink, J.J.
Author_Institution :
Buys Ballot Lab., Utrecht Univ., Netherlands
fDate :
7/1/1990 12:00:00 AM
Abstract :
A technique that is functionally equivalent to the oriented smoothing concept and reduces numerical complexity and computational costs by eliminating the smoothness requirement from the iteration process is introduced. Local affine transformations are applied to propagate uniquely computed flow vectors into homogeneous regions and along edges in a single step. The window within which the local affine transformation is performed can adapt to the local structure of the intensity pattern in accordance with the oriented smoothness concept as formulated by H. Nagel (1987)
Keywords :
filtering and prediction theory; pattern recognition; picture processing; adaptive affinities; displacement estimates; flow vectors; intensity pattern; local affine transformation; motion analysis; oriented smoothness concept; window; Computational efficiency; Equations; Image motion analysis; Image sequences; Image storage; Iterative algorithms; Layout; Motion analysis; Optical computing; Smoothing methods; Taylor series;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on