Empirical choice of smoothing parameters in optical flow with correlated errors

Optical flow estimation algorithms such as the Lukas-Kanade (1981) method and Horn and Schunk (1981) method require selection of a tuning parameter. In the former case a neighbourhood size, in the latter, a penalty parameter. Selection of these tuning parameters is difficult in general but has a profound effect on the results. So automatic methods of selection are of great interest. In previous work we have developed such methods based on white noise assumptions and here we show how to adjust for the effect of spatially correlated errors. These always occur in practice and can degrade the performance of white noise based procedures.

[1]  Jitendra Malik,et al.  Robust computation of optical flow in a multi-scale differential framework , 2005, International Journal of Computer Vision.

[2]  David J. Fleet,et al.  Performance of optical flow techniques , 1994, International Journal of Computer Vision.

[3]  Linda G. Shapiro,et al.  Computer and Robot Vision (Volume II) , 2002 .

[4]  N.P. Galatsanos,et al.  Spatially-adaptive regularized pel-recursive motion estimation based on cross-validation , 1998, Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269).

[5]  Aggelos K. Katsaggelos,et al.  General choice of the regularization functional in regularized image restoration , 1995, IEEE Trans. Image Process..

[6]  Victor Solo A sure-fired way to choose smoothing parameters in ill-conditioned inverse problems , 1996, Proceedings of 3rd IEEE International Conference on Image Processing.

[7]  A. N. Tikhonov,et al.  Solutions of ill-posed problems , 1977 .

[8]  Victor Solo Total variation denoising in coloured noise , 2000, 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).

[9]  Naoya Ohta Optical Flow Detection Using a General Noise Model for Gradient Constraint , 1997, CAIP.

[10]  Y. J. Tejwani,et al.  Robot vision , 1989, IEEE International Symposium on Circuits and Systems,.

[11]  Michael J. Black,et al.  The Robust Estimation of Multiple Motions: Parametric and Piecewise-Smooth Flow Fields , 1996, Comput. Vis. Image Underst..

[12]  Takeo Kanade,et al.  An Iterative Image Registration Technique with an Application to Stereo Vision , 1981, IJCAI.

[13]  Victor Solo,et al.  A data-driven method for choosing smoothing parameters in optical flow problems , 1997, Proceedings of International Conference on Image Processing.

[14]  Naomi Altman,et al.  Kernel Smoothing of Data with Correlated Errors , 1990 .

[15]  A. M. Thompson,et al.  On some Bayesian choices of regularization parameter in image restoration , 1993 .

[16]  Richard Szeliski,et al.  Bayesian modeling of uncertainty in low-level vision , 2011, International Journal of Computer Vision.

[17]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[18]  Linda G. Shapiro,et al.  Computer and Robot Vision , 1991 .

[19]  Zhenyu Zhou,et al.  Approximate maximum likelihood hyperparameter estimation for Gibbs priors , 1997, IEEE Trans. Image Process..