Multiple-Motion-Estimation by Block-matching using MRF

This paper deals with the problem of estimating multiple motions at points where these motions are overlaid. We present a new approach that is based on block-matching and can deal with both transparent motions and occlusions. We derive a block-matching constraint for an arbitrary number of moving layers. We use this constraint to design a hierarchical algorithm that can distinguish between the occurrence of single, transparent, and occluded motions and can thus select the appropriate local motion model. The algorithm adapts to the amount of noise in the image sequence by use of a statistical confidence test. Robustness is further increased with a regularization scheme based on Markov Random Fields. Performance is demonstrated on image sequences synthesized from natural textures with high levels of additive dynamic noise and on real video sequences.

[1]  Eero P. Simoncelli,et al.  Separation of transparent motion into layers using velocity-tuned mechanisms , 1994 .

[2]  Erhardt Barth,et al.  Analytic solutions for multiple motions , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[3]  Weichuan Yu,et al.  Detection and characterization of multiple motion points , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[4]  M. Bertero,et al.  Ill-posed problems in early vision , 1988, Proc. IEEE.

[5]  Shmuel Peleg,et al.  A Three-Frame Algorithm for Estimating Two-Component Image Motion , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Eero P. Simoncelli.  Distributed representation and analysis of visual motion , 1993 .

[7]  Til Aach,et al.  Estimation of multiple motions: regularization and performance evaluation , 2003, IS&T/SPIE Electronic Imaging.

[8]  Keith Langley,et al.  PII: S0042-6989(98)00093-5 , 1998 .

[9]  Til Aach,et al.  Disparity-based segmentation of stereoscopic foreground/background image sequences , 1994, IEEE Trans. Commun..

[10]  Christoph Stiller,et al.  Object-based estimation of dense motion fields , 1997, IEEE Trans. Image Process..

[11]  Til Aach,et al.  BAYESIAN MOTION ESTIMATION FOR TEMPORALLY RECURSIVE NOISE REDUCTION IN X-RAY FLUOROSCOPY , 1998 .

[12]  Trevor Darrell,et al.  On the use of "nulling" filters to separate transparent motions , 1993, CVPR 1993.

[13]  Erhardt Barth,et al.  Analysis of motion and curvature in image sequences , 2002, Proceedings Fifth IEEE Southwest Symposium on Image Analysis and Interpretation.

[14]  Andrew B. Watson,et al.  A look at motion in the frequency domain , 1983 .

[15]  Richard Szeliski,et al.  Layer extraction from multiple images containing reflections and transparency , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[16]  David Vernon,et al.  Decoupling Fourir Components of Dynamic Image Sequences: A Theory of Signal Separation, Image Segmentation, and Optical Flow Estimation , 1998, ECCV.

[17]  Til Aach,et al.  Spatio-temporal motion estimation for transparency and occlusions , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[18]  J. Besag.  On the Statistical Analysis of Dirty Pictures , 1986 .

[19]  Til Aach,et al.  Bayesian algorithms for adaptive change detection in image sequences using Markov random fields , 1995, Signal Process. Image Commun..

[20]  Kenji Mase,et al.  Simultaneous multiple optical flow estimation , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[21]  Til Aach.  Bayes-Methoden zur Bildsegmentierung, Änderungsdetektion und Verschiebungsvektorschätzung , 1993 .

[22]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  Keith Langley,et al.  Computational analysis of non-Fourier motion , 1994, Vision Research.

[24]  Til Aach,et al.  Estimation of Multiple Motions by Block Matching , 2003, SNPD.

[25]  Eric Bruno,et al.  A robust multiscale B-spline function decomposition for estimating motion transparency , 2003, IEEE Trans. Image Process..

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