Two-Frame Optical Flow Formulation in an Unwarping Multiresolution Scheme

In this paper, we propose a new formulation of the Differential Optical Flow Equation (DOFE) between two consecutive images considering spatial and temporal information from both. The displacement field is computed in a Markov Random Field (MRF) framework. The solution is done by minimization of the Gibbs energy using a Direct Descent Energy (DDE) algorithm. A hybrid multiresolution approach, combining pyramidal decomposition and two-step multigrid techniques, is used to estimate small and large displacements. A new pyramidal decomposition method without warping process between pyramid levels is introduced. The experiments carried out on benchmark dataset sequences show the effectiveness of the new optical flow formulation using the proposed unwarped pyramid decomposition schema.

[1]  Edward H. Adelson,et al.  The Laplacian Pyramid as a Compact Image Code , 1983, IEEE Trans. Commun..

[2]  R. M. Díaz,et al.  On first-passage problems for asymmetric one-dimensional diffusions , 2007 .

[3]  Azriel Rosenfeld,et al.  Two-frame multi-scale optical flow estimation using wavelet decomposition , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

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

[5]  Joachim Weickert,et al.  Reliable Estimation of Dense Optical Flow Fields with Large Displacements , 2000, International Journal of Computer Vision.

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

[7]  T. Brox,et al.  Numerical Justification for Multiresolution Optical Flow Computation , 2022 .

[8]  Thomas Brox,et al.  Universität Des Saarlandes Fachrichtung 6.1 – Mathematik Highly Accurate Optic Flow Computation with Theoretically Justified Warping Highly Accurate Optic Flow Computation with Theoretically Justified Warping , 2022 .

[9]  Patrick Pérez,et al.  Dense Estimation of Fluid Flows , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Patrick Pérez,et al.  A multigrid approach for hierarchical motion estimation , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

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

[12]  Véronique Prinet,et al.  Optical flow robust estimation in a hybrid multi-resolution MRF framework , 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

[13]  William T. Freeman,et al.  Presented at: 2nd Annual IEEE International Conference on Image , 1995 .

[14]  Patrick Pérez,et al.  Dense estimation and object-based segmentation of the optical flow with robust techniques , 1998, IEEE Trans. Image Process..

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

[16]  Richard Szeliski,et al.  A Database and Evaluation Methodology for Optical Flow , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[17]  Karl Krissian,et al.  Symmetric Optical Flow , 2007, EUROCAST.