Efficient image alignment using linear appearance models
People
Abstract
Visual tracking is a key component in many computer vision
applications. Linear subspace techniques (e.g. eigentracking)
are one of the most popular approaches to align
templates with appearance variations (e.g. illumination,
iconic changes). A number of well known tracking algorithms
have been proposed in the last years to accurately
fit these models to images. Computational efficiency is an
important limitation in object tracking algorithms and different
efficient techniques, such as the "projected-out" optimization,
have been proposed. They reduce the computational
cost using an efficient formulation in which many
of the involved operations can be precomputed. On the
other hand, alternative "simultaneous" algorithms jointly
optimize pose and appearance parameters, providing better
performance but increasing the computational cost.
In this paper, we propose an algorithm for efficient linear
appearance model fitting based on the inverse compositional
simultaneous optimization of pose and appearance.
We introduce a novel formulation which reduces
the required computational time while maintaining similar
convergence properties of previous "simultaneous" approaches.
Experimental results illustrate the capabilities of
this algorithm in face tracking.
Citation
|
Jose Gonzalez-Mora, Nicolas Guil, Emilio L. Zapata and Fernando de la Torre.
Efficient Image Alignment using Linear Appearance Models IEEE Conference on Computer Vision and Pattern Recognition, June, 2009. [PDF] [Bibtex] |
Acknowledgements and Funding
This work was partially supported by the Ministry of Education and Science (CICYT) of Spain under contract TIN2006-01078 and Junta de Andalucia under contract TIC-02800. Thanks to the Perception Lab at the University of Texas at Dallas and its supervisors A.J. O'Toole and H. Abdi for kindly providing their "Database of Moving Faces and People".
Copyright notice
| Component Analysis Lab |