Probabilistic tracking of motion boundaries with spatiotemporal predictions

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

Volumn 2, Issue , 2001, Pages

  Nestares, Oscar ^a   Fleet, David J ^a  

^a PALO ALTO RESEARCH CENTER   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

APPROXIMATION THEORY; COMPUTATIONAL METHODS; ELECTRIC FILTERS; IMAGE ANALYSIS; PROBABILITY DISTRIBUTIONS; TRACKING (POSITION);

PARTICLE FILTERS;

MOTION ESTIMATION;

EID: 0035680943     PISSN: 10636919     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (31)

1. Layered representation of motion video using robust maximum-likelihood estimation of mixture models and MDL encoding
2. The local frequency structure of 1d occluding image signals
3. The robust estimation of multiple motions: Parametric and piecewise-smooth flow fields
4. Probabilistic detection and tracking of motion discontinuities
5. People tracking with hybrid Monte Carlo
6. Adapting optical flow to measure object motion in reflectance and X-ray image sequences
7. Articulated body motion capture by annealled particle filtering
8. Stability of phase information
9. The design and use of steerable filters
10. Novel approach to nonlinear/non-Gaussian Bayesian state estimation
11. Analog hardware for detecting discontinuities in early vision
12. Multimodal motion estimation of discontinuous optical flow using Markov random fields
13. Condensation - Conditional density propagation for visual tracking
14. Mixture models for optical flow computation
15. Non-gaussian state-space modelling of nonstationary time series (with discussion)
16. Multigrid Bayesian estimation of image motion fields using stochastic relaxation
17. Sequential monte carlo methods for dynamics systems
18. Partitioned sampling, articulated objects, and interface-quality hand tracking
19. The factored frontier algorithm for approximate inference in DBNs
20. Analysis of accretion and deletion at boundaries in dynamic scenes
21. An investigation of smoothness constraints for the estimation of displacement vector fields from image sequences
22. Detecting kinetic occlusion
23. Compact representations of videos through dominant and multiple motion estimation
24. Image flow segmentation and estimation by constraint line clustering
25. Regularization of discontinuous flow fields
26. Learning image statistics for Bayesian tracking
27. The early detection of motion boundaries
28. Dynamic occlusion analysis in optical flow fields
29. Correctness of local probability propagation in graphical models with loops
30. Unified mixture framework for motion segmentation: Incorporating spatial coherence and estimating the number of models
31. Mixture models, Monte Carlo, Bayesian updating and dynamic models