A new framework dealing with motion estimation in transparent images is presented. It relies on a block-oriented estimation involving an efficient multiresolution minimization. A downhill simplex method provides an appropriate initialization to this scheme. The estimated velocity vectors are greatly improved by an original postprocessing stage which performs a single motion estimation on differences of warped images. Finally, a regularization step is carried out. It is demonstrated on a large set of simulations that a quarter-pixel accuracy can be attained on noise-free images. The case of noisy images is also addressed and provides satisfactory results, even in the case of low-contrasted medical images. An example on real clinical images is also reported with promising results.
Multiresolution parametric estimation of transparent motions
2005-01-01
232312 byte
Conference paper
Electronic Resource
English
Multiresolution Parametric Estimation of Transparent Motions
British Library Conference Proceedings | 2005
|Computing Occluding and Transparent Motions
British Library Online Contents | 1994
|Multiresolution motion estimation and target detection
Tema Archive | 1998
|Multiresolution-based motion estimation [3062-32]
British Library Conference Proceedings | 1997
|The Robust Estimation of Multiple Motions: Parametric and Piecewise-Smooth Flow Fields
British Library Online Contents | 1996
|