Optimal Dominant Motion Estimation using Adaptive Search of Transformation Space

Adrian Ulges, Christoph Lampert, Daniel Keysers, Thomas Breuel
Pattern Recognition, 29th Annual DAGM Symposium volume 4713, Lecture Notes in Computer Science, Pages 204-213, Heidelberg, Germany, Springer, 9/2007

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.

Files:

  dagm-motionrast.pdf

BibTex:

@inproceedings{ ULGE2007,
	Title = {Optimal Dominant Motion Estimation using Adaptive Search of Transformation Space},
	Author = {Adrian Ulges and Christoph Lampert and Daniel Keysers and Thomas Breuel},
	BookTitle = {Pattern Recognition, 29th Annual DAGM Symposium},
	Month = {9},
	Year = {2007},
	Series = {Lecture Notes in Computer Science},
	Publisher = {Springer},
	Publisher = {4713},
	Pages = {204-213}
}

     
Last modified:: 30.08.2016