Sparsity model for robust optical flow estimation at motion discontinuities

This paper introduces a new sparsity prior to the estimation of dense flow fields. Based on this new prior, a complex flow field with motion discontinuities can be accurately estimated by finding the sparsest representation of the flow field in certain domains. In addition, a stronger additional spar-sity constraint on the flow gradients is incorporated into the model to cope with the measurement noises. Robust estimation techniques are also employed to identify the outliers and to refine the results. This new sparsity model can accurately and reliably estimate the entire dense flow field from a small portion of measurements when other measurements are corrupted by noise. Experiments show that our method significantly outperforms traditional methods that are based on global or piecewise smoothness priors.

[1]  Emmanuel J. Candès,et al.  Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information , 2004, IEEE Transactions on Information Theory.

[2]  Hans-Peter Seidel,et al.  Complementary Optic Flow , 2009, EMMCVPR.

[3]  Joachim Weickert,et al.  A Theoretical Framework for Convex Regularizers in PDE-Based Computation of Image Motion , 2001, International Journal of Computer Vision.

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

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

[6]  Edward H. Adelson,et al.  Representing moving images with layers , 1994, IEEE Trans. Image Process..

[7]  David J. Field,et al.  Emergence of simple-cell receptive field properties by learning a sparse code for natural images , 1996, Nature.

[8]  David L Donoho,et al.  Compressed sensing , 2006, IEEE Transactions on Information Theory.

[9]  E.J. Candes,et al.  An Introduction To Compressive Sampling , 2008, IEEE Signal Processing Magazine.

[10]  E. Candès,et al.  Stable signal recovery from incomplete and inaccurate measurements , 2005, math/0503066.

[11]  Azriel Rosenfeld,et al.  Accurate dense optical flow estimation using adaptive structure tensors and a parametric model , 2002, Object recognition supported by user interaction for service robots.

[12]  Michael J. Black,et al.  On the Spatial Statistics of Optical Flow , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[13]  Allen Y. Yang,et al.  Robust Face Recognition via Sparse Representation , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Carsten Rother,et al.  Discrete-Continuous Optimization for Optical Flow Estimation , 2009, Statistical and Geometrical Approaches to Visual Motion Analysis.

[15]  Thomas S. Huang,et al.  Image super-resolution as sparse representation of raw image patches , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  Li Xu,et al.  A Segmentation Based Variational Model for Accurate Optical Flow Estimation , 2008, ECCV.

[17]  Patrick Bouthemy,et al.  Multimodal Estimation of Discontinuous Optical Flow using Markov Random Fields , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  Carsten Rother,et al.  FusionFlow: Discrete-continuous optimization for optical flow estimation , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

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

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

[21]  A. Pentland,et al.  Robust estimation of a multi-layered motion representation , 1991, Proceedings of the IEEE Workshop on Visual Motion.

[22]  Patrick Pérez,et al.  Hierarchical Estimation and Segmentation of Dense Motion Fields , 2002, International Journal of Computer Vision.

[23]  Haibin Ling,et al.  Robust Visual Tracking using 1 Minimization , 2009 .

[24]  Michael J. Black,et al.  Learning Optical Flow , 2008, ECCV.

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

[26]  Haibin Ling,et al.  Robust visual tracking using ℓ1 minimization , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[27]  Cheng Lei,et al.  Optical flow estimation on coarse-to-fine region-trees using discrete optimization , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[28]  Volkan Cevher,et al.  Compressive Sensing for Background Subtraction , 2008, ECCV.