Title :
Using 3D Spline Differentiation to Compute Quantitative Optical Flow
Author :
Barron, John Leonard ; Daniel, Marc ; Mari, Jean-Luc
Author_Institution :
University of Western Ontario, Canada
Abstract :
We show that differentiation via fitting B-splines to the spatio-temporal intensity data comprising an image sequence provides at least the same and usually better 2D Lucas and Kanade optical flow than that computed via Simoncelli’s balanced/matched filters.
Keywords :
2D Optical Flow; B-Splines; Differentiation; Filters; Quantitative Error Analysis; Data flow computing; Equations; Image motion analysis; Image sequences; Matched filters; Optical computing; Optical devices; Optical filters; Spline; Surface fitting; 2D Optical Flow; B-Splines; Differentiation; Filters; Quantitative Error Analysis;
Conference_Titel :
Computer and Robot Vision, 2006. The 3rd Canadian Conference on
Print_ISBN :
0-7695-2542-3
DOI :
10.1109/CRV.2006.84
