Title :
A data-driven method for choosing smoothing parameters in optical flow problems
Author :
Ng, Lydia ; Solo, Victor
Author_Institution :
Dept. of Electron., Macquarie Univ., North Ryde, NSW, Australia
Abstract :
In optical flow estimation, an additional constraint to the constant brightness assumption is required to uniquely determine both components of the flow. Typically, these constraints impose a smoothness requirement on the flow estimate. Since the smoothness constraint may be inconsistent with the brightness constraint, a smoothing parameter is introduced to control the tradeoff between satisfying the requirements of both constraints. Previously, there have only been heuristic discussions on how to choose the smoothing parameter. We show that the choice of the smoothing parameter can have a significant effect on the flow estimate and present a data-driven method based on estimated risk to select the smoothing parameter in the Horn and Schunck (1981) algorithm
Keywords :
brightness; image sequences; parameter estimation; smoothing methods; Horn and Schunck algorithm; brightness constraint; constant brightness; data-driven method; estimated risk; optical flow estimation; optical flow problems; smoothing parameters; smoothness constraint; stochastic model; Brightness; Equations; Image motion analysis; Image restoration; Image sequences; Inverse problems; Nonlinear optics; Optical devices; Smoothing methods; Uncertainty;
Conference_Titel :
Image Processing, 1997. Proceedings., International Conference on
Conference_Location :
Santa Barbara, CA
Print_ISBN :
0-8186-8183-7
DOI :
10.1109/ICIP.1997.632117
