Stereo Based 3D Tracking and Scene Learning, Employing Particle Filtering within EM

We present a generative probabilistic model for 3D scenes with stereo views. With this model, we track an object in 3 dimensions while simultaneously learning its appearance and the appearance of the background. By using a generative model for the scene, we are able to aggregate evidence over time. In addition, the probabilistic model naturally handles sources of variability.

[1]  Nando de Freitas,et al.  Rao-Blackwellised Particle Filtering for Dynamic Bayesian Networks , 2000, UAI.

[2]  Takeo Kanade,et al.  Vision and control techniques for robotic visual tracking , 1991, Proceedings. 1991 IEEE International Conference on Robotics and Automation.

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

[4]  Brendan J. Frey,et al.  Transformation-Invariant Clustering and Dimensionality Reduction Using EM , 2001 .

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

[6]  P. K. Khosla,et al.  Adaptive Robotic Visual Tracking , 1991, 1991 American Control Conference.

[7]  Richard Szeliski,et al.  A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms , 2001, International Journal of Computer Vision.

[8]  Timothy F. Cootes,et al.  Active Appearance Models , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Marius Malciu,et al.  A robust model-based approach for 3D head tracking in video sequences , 2000, Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580).

[10]  Richard Szeliski,et al.  Stereo matching with non-linear diffusion , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[11]  Kentaro Toyama,et al.  Prolegomena for Robust Face Tracking , 1998 .

[12]  Michael Isard,et al.  ICONDENSATION: Unifying Low-Level and High-Level Tracking in a Stochastic Framework , 1998, ECCV.

[13]  Irfan Essa,et al.  Head Tracking Using a Textured Polygonal Model , 1998 .

[14]  R. Fildes.  Journal of the Royal Statistical Society (B): Gary K. Grunwald, Adrian E. Raftery and Peter Guttorp, 1993, “Time series of continuous proportions”, 55, 103–116.☆ , 1993 .

[15]  Brendan J. Frey,et al.  Keeping Flexible Active Contours on Track using Metropolis Updates , 2000, NIPS.

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

[17]  Nanning Zheng,et al.  Stereo Matching Using Belief Propagation , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

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

[19]  Alex Pentland,et al.  3D structure from 2D motion , 1999, IEEE Signal Process. Mag..

[20]  Mads Nielsen,et al.  Computer Vision — ECCV 2002 , 2002, Lecture Notes in Computer Science.

[21]  Takeo Kanade,et al.  A Stereo Matching Algorithm with an Adaptive Window: Theory and Experiment , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[22]  Frank Dellaert,et al.  Jacobian images of super-resolved texture maps for model-based motion estimation and tracking , 1998, Proceedings Fourth IEEE Workshop on Applications of Computer Vision. WACV'98 (Cat. No.98EX201).

[23]  Bernd Neumann,et al.  Computer Vision — ECCV’98 , 1998, Lecture Notes in Computer Science.

[24]  Nando de Freitas,et al.  Sequential Monte Carlo Methods in Practice , 2001, Statistics for Engineering and Information Science.