Title :
Adaptive Multiscale Optical Flowestimation
Author :
Li, Jian ; Benton, Christopher P. ; Nikolov, Stavri G. ; Scott-Samuel, Nicholas E.
Author_Institution :
Univ. of Bristol, Bristol
fDate :
Sept. 16 2007-Oct. 19 2007
Abstract :
The current paper presents a novel adaptive multiscale scheme to estimate optical flow from image sequences. The scheme models estimation uncertainties which are used to reduce the influence of unreliable intermediate estimates on accuracy. The experimental results show that the proposed method provides more accurate estimates for both small and large motions than a standard multiscale scheme in which an increment is added to an intermediate estimate regardless of estimation certainty.
Keywords :
estimation theory; image sequences; matrix algebra; adaptive multiscale optical flow estimation; estimation uncertainty; image sequences; matrix algebra; Adaptive optics; Computer errors; Image motion analysis; Image sequences; Least squares approximation; Motion estimation; Optical filters; Psychology; Stochastic processes; Uncertainty; Optical flow; least squares; multiscale; pyramid; uncertainty;
Conference_Titel :
Image Processing, 2007. ICIP 2007. IEEE International Conference on
Conference_Location :
San Antonio, TX
Print_ISBN :
978-1-4244-1437-6
Electronic_ISBN :
1522-4880
DOI :
10.1109/ICIP.2007.4379204