Probabilistic tracking in a metric space

A new exemplar-based, probabilistic paradigm for visual tracking is presented. Probabilistic mechanisms are attractive because they handle fusion of information, especially temporal fusion, in a principled manner. Exemplars are selected representatives of raw training data, used here to represent probabilistic mixture distributions of object configurations. Their use avoids tedious hand-construction of object models and problems with changes of topology. Using exemplars in place of a parameterized model poses several challenges, addressed here with what we call the "Metric Mixture" (M/sup 2/) approach. The M/sup 2/ model has several valuable properties. Principally, it provides alternatives to standard learning algorithms by allowing the use of metrics that are not embedded in a vector space. Secondly, it uses a noise model that is learned from training data. Lastly, it eliminates any need for an assumption of probabilistic pixelwise independence. Experiments demonstrate the effectiveness of the M/sup 2/ model in two domains tracking walking people using chamfer distances on binary edge images and tracking mouth movements by means of a shuffle distance.

[1]  J. Davenport.  Editor , 1960 .

[2]  A.H. Haddad,et al.  Applied optimal estimation , 1976, Proceedings of the IEEE.

[3]  D J Field,et al.  Relations between the statistics of natural images and the response properties of cortical cells. , 1987, Journal of the Optical Society of America. A, Optics and image science.

[4]  Terry E. Weymouth,et al.  Using Dynamic Programming For Minimizing The Energy Of Active Contours In The Presence Of Hard Constraints , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[5]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[6]  Daniel P. Huttenlocher,et al.  Tracking non-rigid objects in complex scenes , 1993, 1993 (4th) International Conference on Computer Vision.

[7]  N. Gordon,et al.  Novel approach to nonlinear/non-Gaussian Bayesian state estimation , 1993 .

[8]  Richard Szeliski,et al.  Tracking with Kalman snakes , 1993 .

[9]  Geir Storvik,et al.  A Bayesian Approach to Dynamic Contours Through Stochastic Sampling and Simulated Annealing , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Rachid Deriche,et al.  Region tracking through image sequences , 1995, Proceedings of IEEE International Conference on Computer Vision.

[11]  D. Mumford.  Perception as Bayesian Inference: Pattern theory: A unifying perspective , 1996 .

[12]  Tomaso A. Poggio,et al.  Image Synthesis from a Single Example Image , 1996, ECCV.

[13]  Michael Isard,et al.  Contour Tracking by Stochastic Propagation of Conditional Density , 1996, ECCV.

[14]  D. Mumford.  Pattern theory: a unifying perspective , 1996 .

[15]  Timothy F. Cootes,et al.  Active Appearance Models , 1998, ECCV.

[16]  Michael Isard,et al.  Active Contours , 2000, Springer London.

[17]  William T. Freeman,et al.  Learning to Estimate Scenes from Images , 1998, NIPS.

[18]  Matthew Brand,et al.  Shadow puppetry , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[19]  Dariu Gavrila,et al.  Real-time object detection for "smart" vehicles , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[20]  Alexei A. Efros,et al.  Texture synthesis by non-parametric sampling , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[21]  Kiriakos N. Kutulakos.  Approximate N-View Stereo , 2000, ECCV.

[22]  Marc Levoy,et al.  Fast texture synthesis using tree-structured vector quantization , 2000, SIGGRAPH.

[23]  Brendan J. Frey,et al.  Learning Graphical Models of Images, Videos and Their Spatial Transformations , 2000, UAI.