UNIGE document Scientific Article
previous document  unige:47480  next document
add to browser collection

A Robust Multiscale B-spline Function Decomposition Process to Motion Transparency Estimation

Pingault, M.
Pellerin, D.
Published in IEEE Transactions on Image Processing. 2003, vol. 12, no. 11, p. 1416-1426
Abstract Motion transparency phenomena in image sequences are frequent, but classical methods of motion estimation are unable to deal with them. This paper describes a method for estimating optical flow by a generalization of the brightness constancy assumption to additive transparencies. The brightness constancy assumption is obtained by setting constant velocity fields during three images of a sequence. Thus, by a Taylor development to its second order, we reach an extension of the optical flow constraint equation. Since the equation is nonlinear, the Levenberg-Marquardt algorithm is used. In order to suppress the unavoidable aperture problem, a global model based on B-spline basis functions is applied with the aim of constraining optical flows. This description of motion allows us to work on a coarse to fine estimation of artificial image sequences that shows good convergence properties. It is also applied to natural image sequences.
Keywords convergence of numerical methodsimage sequencesmotion estimationnonlinear equationssplines (mathematics)
Full text
Research groups Computer Vision and Multimedia Laboratory
Multimodal Interaction Group
(ISO format)
PINGAULT, M., BRUNO, Eric, PELLERIN, D. A Robust Multiscale B-spline Function Decomposition Process to Motion Transparency Estimation. In: IEEE Transactions on Image Processing, 2003, vol. 12, n° 11, p. 1416-1426. doi: 10.1109/TIP.2003.818357 https://archive-ouverte.unige.ch/unige:47480

365 hits

0 download


Deposited on : 2015-03-03

Export document
Format :
Citation style :