Optimal dominant motion estimation using adaptive search of transformation space

A. Ulges, C. Lampert, D. Keysers, T. Breuel, in:, Springer, 2007, pp. 204–213.

Download
No fulltext has been uploaded. References only!

Conference Paper | Published
Author
; ; ;
Series Title
LCNS
Abstract
The extraction of a parametric global motion from a motion field is a task with several applications in video processing. We present two probabilistic formulations of the problem and carry out optimization using the RAST algorithm, a geometric matching method novel to motion estimation in video. RAST uses an exhaustive and adaptive search of transformation space and thus gives – in contrast to local sampling optimization techniques used in the past – a globally optimal solution. Among other applications, our framework can thus be used as a source of ground truth for benchmarking motion estimation algorithms. Our main contributions are: first, the novel combination of a state-of-the-art MAP criterion for dominant motion estimation with a search procedure that guarantees global optimality. Second, experimental results that illustrate the superior performance of our approach on synthetic flow fields as well as real-world video streams. Third, a significant speedup of the search achieved by extending the model with an additional smoothness prior.
Publishing Year
Date Published
2007-11-09
Volume
4713
Page
204 - 213
Conference
DAGM: German Association For Pattern Recognition
IST-REx-ID

Cite this

Ulges A, Lampert C, Keysers D, Breuel T. Optimal dominant motion estimation using adaptive search of transformation space. In: Vol 4713. Springer; 2007:204-213. doi:10.1007/978-3-540-74936-3_21
Ulges, A., Lampert, C., Keysers, D., & Breuel, T. (2007). Optimal dominant motion estimation using adaptive search of transformation space (Vol. 4713, pp. 204–213). Presented at the DAGM: German Association For Pattern Recognition, Springer. https://doi.org/10.1007/978-3-540-74936-3_21
Ulges, Adrian, Christoph Lampert, Daniel Keysers, and Thomas Breuel. “Optimal Dominant Motion Estimation Using Adaptive Search of Transformation Space,” 4713:204–13. Springer, 2007. https://doi.org/10.1007/978-3-540-74936-3_21.
A. Ulges, C. Lampert, D. Keysers, and T. Breuel, “Optimal dominant motion estimation using adaptive search of transformation space,” presented at the DAGM: German Association For Pattern Recognition, 2007, vol. 4713, pp. 204–213.
Ulges A, Lampert C, Keysers D, Breuel T. 2007. Optimal dominant motion estimation using adaptive search of transformation space. DAGM: German Association For Pattern Recognition, LCNS, vol. 4713. 204–213.
Ulges, Adrian, et al. Optimal Dominant Motion Estimation Using Adaptive Search of Transformation Space. Vol. 4713, Springer, 2007, pp. 204–13, doi:10.1007/978-3-540-74936-3_21.

Export

Marked Publications

Open Data IST Research Explorer

Search this title in

Google Scholar