Efficient Mechanism for Discontinuity Preserving in Optical Flow Methods

We propose an efficient solution for preserving the motion boundaries in variational optical flow methods. This is a key problem of recent TV-L methods, which typically create rounded effects at flow edges. A simple strategy to overcome this problem consists in inhibiting the smoothing at high image gradients. However, depending on the strength of the mitigating function, this solution may derive in an illposed formulation. Therefore, this type of approaches is prone to produce instabilities in the estimation of the flow fields. In this work, we modify this strategy to avoid this inconvenience. Then, we show that it provides very good results with the advantage that it yields an unconditionally stable scheme. In the experimental results, we present a detailed study and comparison between the different alternatives.

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

[2]  Daniel Cremers,et al.  Structure- and motion-adaptive regularization for high accuracy optic flow , 2009, 2009 IEEE 12th International Conference on Computer Vision.

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

[4]  I. Cohen Nonlinear Variational Method for Optical Flow Computation , 2006 .

[5]  Julio Esclarín Monreal,et al.  A PDE model for computing the optimal flow , 1999 .

[6]  Yasuyuki Matsushita,et al.  Motion detail preserving optical flow estimation , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[7]  Hans-Hellmut Nagel,et al.  An Investigation of Smoothness Constraints for the Estimation of Displacement Vector Fields from Image Sequences , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Nelson Monzón,et al.  Optic Flow: Improving Discontinuity Preserving , 2013 .

[9]  Horst Bischof,et al.  A Duality Based Approach for Realtime TV-L1 Optical Flow , 2007, DAGM-Symposium.

[10]  Thomas Brox,et al.  High Accuracy Optical Flow Estimation Based on a Theory for Warping , 2004, ECCV.

[11]  Javier Sánchez Pérez,et al.  Horn-Schunck Optical Flow with a Multi-Scale Strategy , 2013, Image Process. Line.

[12]  Javier Sánchez Pérez,et al.  TV-L1 Optical Flow Estimation , 2013, Image Process. Line.

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

[14]  Stefano Soatto,et al.  Sparse Occlusion Detection with Optical Flow , 2012, International Journal of Computer Vision.