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.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Black, M.J., Anandan, P.: The Robust Estimation of Multiple Motions: Parametric and Piecewise-Smooth Flow Fields. CVIU, 63(1), 75–104 (1996)
Breuel, T.M.: On the Use of Interval Arithmetic in Geometric Branch-and-Bound Algorithms. Pattern Recogn. Lett. 24(9-10), 1375–1384 (2003)
Breuel, T.M.: Fast Recognition using Adaptive Subdivisions of Transformation Space. In: CVPR 1992, pp. 445–451 (1992)
Cremers, D., Soatto, S.: Motion Competition: A Variational Approach to Piecewise Parametric Motion Segmentation. Int. J. Comput. Vision 62(3), 249–265 (2005)
Fischler, M.A., Bolles, R.C.: Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography. Communications of the ACM 24(6), 381–395 (1981)
Geman, D.: Stochastic Model for Boundary Detection. Image Vision Comput. 5(2), 61–65 (1987)
Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, New York (2003)
Irani, M., Anandan, P.: About Direct Methods. In: ICCV 1999: Intern. Workshop on Vision Algorithms, London, UK, pp. 267–277 (2000)
Jepson, A., Black, M.J.: Mixture Models for Optical Flow Computation. In: CVPR 1993, pp. 760–761 (1993)
Kühne, G.: Motion-based Segmentation and Classification of Video Objects. PhD thesis, University of Mannheim (2002)
Lepetit, V., Fua, P.: Monocular Model-Based 3D Tracking of Rigid Objects: A Survey. Foundations and Trends in Computer Graphics and Vision 1(1) (2005)
Murray, D.W., Buxton, B.F.: Scene Segmentation from Visual Motion using Global Optimization. IEEE Trans. Pattern Anal. Mach. Intell. 9(2), 220–228 (1987)
Smolic, A.: Globale Bewegungsbeschreibung und Video Mosaiking unter Verwendung parametrischer 2-D Modelle. PhD thesis, RWTH Aachen (2001)
Tomasi, C., Kanade, T.: Detection and Tracking of Point Features. Technical Report CMU-CS-91-132, CMU (1991)
Tourapis, A.M.: Enhanced Predictive Zonal Search for Single and Multiple Frame Motion Estimation. In: Proc. SPIE Conf. Visual Communications and Image Processing, Lugano, Switzerland, pp. 1069–1079 (2002)
Wang, J.Y.A., Adelson, E.H.: Layered Representation for Motion Analysis. In: CVPR 1993, pp. 361–366 (1993)
Weiss, Y.: Smoothness in Layers: Motion Segmentation using Nonparametric Mixture Estimation. In: CVPR 1997, pp. 520–526 (1997)
Ulges, A.: Motion Interpretation using Adaptive Search of Transformation Space. Technical Report, IUPR Research Group, TU Kaiserslautern (2007)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ulges, A., Lampert, C.H., Keysers, D., Breuel, T.M. (2007). Optimal Dominant Motion Estimation Using Adaptive Search of Transformation Space. In: Hamprecht, F.A., Schnörr, C., Jähne, B. (eds) Pattern Recognition. DAGM 2007. Lecture Notes in Computer Science, vol 4713. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74936-3_21
Download citation
DOI: https://doi.org/10.1007/978-3-540-74936-3_21
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-74933-2
Online ISBN: 978-3-540-74936-3
eBook Packages: Computer ScienceComputer Science (R0)