Non-Gaussian velocity distributions integrated over space, time, and scales

Velocity distributions are an enhanced representation of image velocity containing more velocity information than velocity vectors. In particular, non-Gaussian velocity distributions allow for the representation of ambiguous motion information caused by the aperture problem or multiple motions at motion boundaries. To resolve motion ambiguities, discrete non-Gaussian velocity distributions are suggested, which are integrated over space, time, and scales using a joint Bayesian prediction and refinement approach. This leads to a hierarchical velocity-distribution representation from which robust velocity estimates for both slow and high speeds as well as statistical confidence measures rating the velocity estimates can be computed.

[1]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.

[2]  Edward H. Adelson,et al.  Probability distributions of optical flow , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[3]  Volker Willert,et al.  Building a Motion Resolution Pyramid by Combining Velocity Distributions , 2004, DAGM-Symposium.

[4]  Rajesh P. N. Rao,et al.  Probabilistic Models of the Brain: Perception and Neural Function , 2002 .

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

[6]  Yair Weiss.  Bayesian motion estimation and segmentation , 1998 .

[7]  P. Anandan,et al.  Hierarchical Model-Based Motion Estimation , 1992, ECCV.

[8]  Gerhard Krieger,et al.  Nonlinear mechanisms and higher-order statistics in biological vision and electronic image processing: review and perspectives , 2001, J. Electronic Imaging.

[9]  David J. Fleet,et al.  Likelihood functions and confidence bounds for total-least-squares problems , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[10]  Michael Werman,et al.  A general filter for measurements with any probability distribution , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[11]  Eero P. Simoncelli.  Bayesian multi-scale differential optical flow , 1999 .

[12]  John Zelek,et al.  Bayesian Real-time Optical Flow , 2002 .

[13]  Ajit Singh,et al.  Incremental estimation of image flow using a Kalman filter , 1992, J. Vis. Commun. Image Represent..

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

[15]  John S. Zelek,et al.  Towards Bayesian real-time optical flow , 2004, Image Vis. Comput..

[16]  P. Anandan,et al.  A computational framework and an algorithm for the measurement of visual motion , 1987, International Journal of Computer Vision.

[17]  Neil J. Gordon,et al.  A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking , 2002, IEEE Trans. Signal Process..

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

[19]  Q.X. Wu,et al.  A Correlation-Relaxation-Labeling Framework for Computing Optical Flow - Template Matching from a New Perspective , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[20]  David J. Fleet,et al.  Computing Optical Flow with Physical Models of Brightness Variation , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[21]  Alan L. Yuille,et al.  Probabilistic Motion Estimation Based on Temporal Coherence , 2000, Neural Computation.

[22]  David G. Stork,et al.  Pattern Classification (2nd ed.) , 1999 .

[23]  David J. Fleet,et al.  Velocity Likelihoods in Biological and Machine Vision , 2001 .

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

[25]  Ajit Singh,et al.  An estimation-theoretic framework for image-flow computation , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[26]  Steven S. Beauchemin,et al.  The computation of optical flow , 1995, CSUR.

[27]  Neil J. Gordon,et al.  A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking , 2002, IEEE Trans. Signal Process..

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

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

[30]  Michael Isard,et al.  CONDENSATION—Conditional Density Propagation for Visual Tracking , 1998, International Journal of Computer Vision.

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

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

[33]  Shahriar Negahdaripour,et al.  Revised Definition of Optical Flow: Integration of Radiometric and Geometric Cues for Dynamic Scene Analysis , 1998, IEEE Trans. Pattern Anal. Mach. Intell..