Award
Karel Zimmermann's PhD thesis Fast Learnable Methods for Object
Tracking , co-supervised by Jiri Matas and Tomas Svoboda, was awarded
the Antonin Svoboda prize for the best PhD dissertation in Czech
Republic in the fields of cybernetics and informatics in 2008. The
prize is awarded by the Czech Society for Cybernetics and Informatics
(CSKI).
Movies
Motion blur (images)
|
|
Download
Abstract
We propose a learnable tracking method, where the computational
complexity is explictly taken into account. The computational
complexity, defined as the total number of pixels used for linear
motion prediction, is minimized during an offline learning stage.
Learning algorithm, based on linear and dynamic programming, searches
for an optimal predictor, given a range of admissible motions, desired
accuracy and a set of training examples. As a result, the globally
optimal sequence of predictors covering the object is delivered. The
local motion is determined only by a few hundreds of multiplications
resulting in tracking with a fraction of the processing power of a
desktop PC. The global motion of the object is robustly estimated by
Ransac algorithm from some local motions. We also make explicit
the trade-off between the number of estimated local motions and the
number of Ransac iterations. The optimal predictor is applied
to real-time object tracking and its performance superiority and
robustness are experimentally demonstrated.
Support
Note that the videos are on-line and the pdf viewer downloads them if enabled.
References
[1] |
K. Zimmermann, J. Matas, and T. Svoboda. Tracking by an Optimal
Sequence of Linear Predictors. IEEE Transactions on Pattern
Analysis and Machine Intelligence. 31(4), 2009, [pdf]
|
[2] |
K. Zimmermann, T. Svoboda, J. Matas. Anytime learning for the NoSLLiP tracker. Image and Vision Computing. Accepted, pre-published on line doi:10.1016/j.physletb.2003.10.07, [pdf] |
[3] |
K. Zimmermann, T. Svoboda, J. Matas. Simultaneous learning of motion
and appearance. The 1st International Workshop on Machine Learning
for Vision-based Motion Analysis, In conjunction with the 10th
European Conference on Computer Vision 2008, [ paper | talk ].
|
[4] |
K. Zimmernann, T. Svoboda, J. Matas. Adaptive Parameter
Optimization for Real-time Tracking. In Proceedings of the
Workshop on Non-rigid Registration and Tracking through Learning - NRTL
2007 (joint workshop with the ICCV 2007). [ paper
]
|
[5] |
J.Matas, K.Zimmermann, T. Svoboda, A. Hilton, Learning Efficient Linear Predictors for Motion Estimation, Proceedings of 5th Indian Conference on Computer Vision, Graphics and Image Processing,
issn 0302-9743, isbn 978-3-540-68301-8, India, 2006
|
[6] |
K. Zimmermann. Fast Learnabe Methods for Object Tracking. PhD Thesis, Czech Technical Univeristy in Prague. [PDF]. Defended 7 Nov 2008.
|
|