Title :
A General Framework and New Alignment Criterion for Dense Optical Flow
Author :
Ben-Ari, Rami ; Sochen, Nir
Author_Institution :
Tel Aviv University
Abstract :
The problem of dense optical flow computation is addressed from a variational viewpoint. A new geometric framework is introduced. It unifies previous art and yields new efficient methods. Along with the framework a new alignment criterion suggests itself. It is shown that the alignment between the gradients of the optical flow components and between the latter and the intensity gradients is an important measure of the flow’s quality. Adding this criterion as a requirement in the optimization process improves the resulting flow. This is demonstrated in synthetic and real sequences.
Keywords :
Anisotropic magnetoresistance; Art; Computer vision; Geometrical optics; Image motion analysis; Image processing; Mathematics; Optical computing; Optical devices; Smoothing methods;
Conference_Titel :
Computer Vision and Pattern Recognition, 2006 IEEE Computer Society Conference on
Print_ISBN :
0-7695-2597-0
DOI :
10.1109/CVPR.2006.25