CONDENSATION—Conditional Density Propagation forVisual Tracking
International Journal of Computer Vision
BAYES AND EMPIRICAL BAYES METHODS FOR DATA ANALYSIS
Statistics and Computing
Stochastic simulation algorithms for dynamic probabilistic networks
UAI'95 Proceedings of the Eleventh conference on Uncertainty in artificial intelligence
Hyperdynamics Importance Sampling
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
Robust Multiple-People Tracking Using Colour-Based Particle Filters
IbPRIA '07 Proceedings of the 3rd Iberian conference on Pattern Recognition and Image Analysis, Part I
A color-based particle filter for multiple object tracking in an outdoor environment
Artificial Life and Robotics
Improving tracking by handling occlusions
ICAPR'05 Proceedings of the Third international conference on Pattern Recognition and Image Analysis - Volume Part II
Robust particle filtering for object tracking
ICIAP'05 Proceedings of the 13th international conference on Image Analysis and Processing
Monocular tracking of 3d human motion with a coordinated mixture of factor analyzers
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II
Probabilistic image-based tracking: improving particle filtering
IbPRIA'05 Proceedings of the Second Iberian conference on Pattern Recognition and Image Analysis - Volume Part I
A 3d dynamic model of human actions for probabilistic image tracking
IbPRIA'05 Proceedings of the Second Iberian conference on Pattern Recognition and Image Analysis - Volume Part I
Multiple objects tracking method based on particle filter
CSECS'11/MECHANICS'11 Proceedings of the 10th WSEAS international conference on Circuits, Systems, Electronics, Control & Signal Processing, and Proceedings of the 7th WSEAS international conference on Applied and Theoretical Mechanics
| Hi-index | 0.00 |
Condensation is a popular algorithm for sequential inference that resamples a sampled representation of the posterior. The algorithm is known to be asymptotically correct as the number of samples tends to infinity. However, the resampling phase involves a loss of information. The sequence of representations produced by the algorithm is a Markov chain, which is usually inhomogeneous. We show simple discrete examples where this chain is homogeneous and has absorbing states. In these examples, the representation moves to one of these states in time apparently linear in the number of samples and remains there. This phenomenon appears in the continuous case as well, where the algorithm tends to produce "clumpy" representations. In practice, this means that different runs of a tracker on the same data can give very different answers, while a particular run of the tracker will look stable. Furthermore, the state of the tracker can collapse to a single peak -- which has non-zero probability of being the wrong peak -- within time linear in the number of samples, and the tracker can appear to be following tight peaks in the posterior even in the absence of any meaningful measurement. This means that, if theoretical lower bounds on the number of samples are not available, experiments must be very carefully designed to avoid these effects.