Variational Inference for Visual Tracking

Jaco Vermaak; Neil D. Lawrence; Patrick Pérez

Back to publications

Variational Inference for Visual Tracking

Jaco Vermaak, Neil D. Lawrence, Patrick Pérez

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE Computer Society Press I:773-780, 2003.

Abstract

The likelihood models used in probabilistic visual tracking applications are often complex non-linear and/or non-Gaussian functions, leading to analytically intractable inference. Solutions then require numerical approximation techniques, of which the particle filter is a popular choice. Particle filters, however, degrade in performance as the dimensionality of the state space increases and the support of the likelihood decreases. As an alternative to particle filters this paper introduces a variational approximation to the tracking recursion. The variational inference is intractable in itself, and is combined with an efficient importance sampling procedure to obtain the required estimates. The algorithm is shown to compare favourably with particle filtering techniques on a synthetic example and two real tracking problems. The first involves the tracking of a designated object in a video sequence based on its colour properties, whereas the second involves contour extraction in a single image.

Links

Cite this Paper

BibTeX


@InProceedings{Vermaak:variational03,
  title = 	 {Variational Inference for Visual Tracking},
  author = 	 {Vermaak, Jaco and Lawrence, Neil D. and Pérez, Patrick},
  booktitle = 	 {Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition},
  pages = 	 {773--780},
  year = 	 {2003},
  volume = 	 {I},
  publisher =    {IEEE Computer Society Press},
  pdf = 	 {https://lawrennd.github.io/publications/files/variationalTracking.pdf},
  url = 	 {/publications/vermaak-variational03.html},
  abstract = 	 {The likelihood models used in probabilistic visual tracking applications are often complex non-linear and/or non-Gaussian functions, leading to analytically intractable inference. Solutions then require numerical approximation techniques, of which the particle filter is a popular choice. Particle filters, however, degrade in performance as the dimensionality of the state space increases and the support of the likelihood decreases. As an alternative to particle filters this paper introduces a variational approximation to the tracking recursion. The variational inference is intractable in itself, and is combined with an efficient importance sampling procedure to obtain the required estimates. The algorithm is shown to compare favourably with particle filtering techniques on a synthetic example and two real tracking problems. The first involves the tracking of a designated object in a video sequence based on its colour properties, whereas the second involves contour extraction in a single image.}
}

Endnote

%0 Conference Paper
%T Variational Inference for Visual Tracking
%A Jaco Vermaak
%A Neil D. Lawrence
%A Patrick Pérez
%B Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
%D 2003	
%F Vermaak:variational03
%I IEEE Computer Society Press
%P 773--780
%U /publications/vermaak-variational03.html
%V I
%X The likelihood models used in probabilistic visual tracking applications are often complex non-linear and/or non-Gaussian functions, leading to analytically intractable inference. Solutions then require numerical approximation techniques, of which the particle filter is a popular choice. Particle filters, however, degrade in performance as the dimensionality of the state space increases and the support of the likelihood decreases. As an alternative to particle filters this paper introduces a variational approximation to the tracking recursion. The variational inference is intractable in itself, and is combined with an efficient importance sampling procedure to obtain the required estimates. The algorithm is shown to compare favourably with particle filtering techniques on a synthetic example and two real tracking problems. The first involves the tracking of a designated object in a video sequence based on its colour properties, whereas the second involves contour extraction in a single image.

RIS


TY  - CPAPER
TI  - Variational Inference for Visual Tracking
AU  - Jaco Vermaak
AU  - Neil D. Lawrence
AU  - Patrick Pérez
BT  - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
DA  - 2003/01/01	
ID  - Vermaak:variational03
PB  - IEEE Computer Society Press
VL  - I
SP  - 773
EP  - 780
L1  - https://lawrennd.github.io/publications/files/variationalTracking.pdf
UR  - /publications/vermaak-variational03.html
AB  - The likelihood models used in probabilistic visual tracking applications are often complex non-linear and/or non-Gaussian functions, leading to analytically intractable inference. Solutions then require numerical approximation techniques, of which the particle filter is a popular choice. Particle filters, however, degrade in performance as the dimensionality of the state space increases and the support of the likelihood decreases. As an alternative to particle filters this paper introduces a variational approximation to the tracking recursion. The variational inference is intractable in itself, and is combined with an efficient importance sampling procedure to obtain the required estimates. The algorithm is shown to compare favourably with particle filtering techniques on a synthetic example and two real tracking problems. The first involves the tracking of a designated object in a video sequence based on its colour properties, whereas the second involves contour extraction in a single image.
ER  -

APA


Vermaak, J., Lawrence, N.D. & Pérez, P.. (2003). Variational Inference for Visual Tracking. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition I:773-780 Available from /publications/vermaak-variational03.html.