Better proposal distributions: object tracking using unscented particle filter

Tracking objects involves the modeling of non-linear non-Gaussian systems. On one hand, variants of Kalman filters are limited by their Gaussian assumptions. On the other hand, conventional particle filter, e.g., CONDENSATION, uses transition prior as the proposal distribution. The transition prior does not take into account current observation data, and many particles can therefore be wasted in low likelihood area. To overcome these difficulties, unscented particle filter (UPF) has recently been proposed in the field of filtering theory. In this paper, we introduce the UPF framework into audio and visual tracking. The UPF uses the unscented Kalman filter to generate sophisticated proposal distributions that seamlessly integrate the current observation, thus greatly improving the tracking performance. To evaluate the efficacy of the UPF framework, we apply it in two real-world tracking applications. One is the audio-based speaker localization, and the other is the vision-based human tracking. The experimental results are compared against those of the widely used CONDENSATION approach and have demonstrated superior tracking performance.

[1]  Michael Isard,et al.  Partitioned Sampling, Articulated Objects, and Interface-Quality Hand Tracking , 2000, ECCV.

[2]  Rama Chellappa,et al.  Simultaneous tracking and verification via sequential posterior estimation , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[3]  B. Anderson,et al.  Optimal Filtering , 1979, IEEE Transactions on Systems, Man, and Cybernetics.

[4]  Nando de Freitas,et al.  The Unscented Particle Filter , 2000, NIPS.

[5]  Andrew Blake,et al.  Nonlinear filtering for speaker tracking in noisy and reverberant environments , 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

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

[7]  Michael Isard,et al.  Learning to Track the Visual Motion of Contours , 1995, Artif. Intell..

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

[9]  Jun S. Liu,et al.  Sequential Imputations and Bayesian Missing Data Problems , 1994 .

[10]  David A. Forsyth,et al.  How Does CONDENSATION Behave with a Finite Number of Samples? , 2000, ECCV.

[11]  Anoop Gupta,et al.  Automating camera management for lecture room environments , 2001, CHI.

[12]  J. Hammersley,et al.  Poor Man's Monte Carlo , 1954 .

[13]  Jun S. Liu,et al.  Sequential Monte Carlo methods for dynamic systems , 1997 .

[14]  S. Julier,et al.  A General Method for Approximating Nonlinear Transformations of Probability Distributions , 1996 .

[15]  Michael J. Black,et al.  A Probabilistic Framework for Matching Temporal Trajectories: CONDENSATION-Based Recognition of Gestures and Expressions , 1998, ECCV.

[16]  Simon J. Godsill,et al.  On sequential simulation-based methods for Bayesian filtering , 1998 .

[17]  Hong Wang,et al.  Voice source localization for automatic camera pointing system in videoconferencing , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[18]  Christophe Andrieu,et al.  Particle filtering for non-stationary speech modelling and enhancement , 2000, INTERSPEECH.

[19]  Hong Wang,et al.  Voice source localization for automatic camera pointing system in videoconferencing , 1997, Proceedings of 1997 Workshop on Applications of Signal Processing to Audio and Acoustics.