Abstract
We introduce a novel perspective for viewing the “ego-motion reconstruction” problem as the estimation of the state of a dynamical system having an implicit measurement constraint and unknown inputs. Such a system happens to be “linear”, but it is defined on a space (the “Essential Manifold”) which is not a linear (vector) space.
We propose two recursive schemes for performing the estimation task: the first consists in “flattening the space” and solving a nonlinear estimation problem on the flat (euclidean) space. The second consists in viewing the system as embedded in a larger euclidean space, and solving at each step a linear estimation problem on a linear space, followed by a “projection” onto the Essential Manifold.
Both schemes output motion estimates together with the joint second order statistics of the estimation error, which can be used by any “structure from motion” module which incorporates motion error [18, 22] in order to estimate 3D scene structure.
Experiments are presented with real and synthetic image sequences.
Research funded by the California Institute of Technology, ONR grant N00014-93-1-0990, an AT&T Foundation Special Purpose grant and the ASI-RS-103 grant from the Italian Space Agency. P.P. gratefully acknowledges the Newton Institute for Mathematical Sciences of Cambridge, UK, where he conducted part of this research.
Chapter PDF
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Azarbayejani, A., Horowitz, B., and Pentland, A. Recursive estimation of structure and motion using relative orientation constraints. Proc. CVPR (New York, 1993).
Boothby, W. Introduction to Differentiable Manifolds and Riemannian Geometry. Academic Press, 1986.
Broida, T., and Chellappa, R. Estimating the kinematics and structure of a rigid object from a sequence of monocular frames. IEEE Trans. Pattern Anal. Mach. Intell. (1991).
Darmon. A recursive method to apply the hough transform to a set of moving objects. Proc. IEEE, CH 1746 7/82 (1982).
Di-Bernardo, E., Toniutti, L., Frezza, R., and Picci, G. Stima del moto dell'osservatore e della struttura della scena mediante visione monoculare. Tesi di Laurea-Università di Padova (1993).
Faugeras, O. Three dimensional vision, a geometric viewpoint. MIT Press, 1993.
Gennery, D. Tracking known 3-dimensional object. In Proc. AAAI 2nd Natl. Conf. Artif. Intell. (Pittsburg, PA, 1982), pp. 13–17.
Heel, J. Direct estimation of structure and motion from multiple frames. AI Memo 1190, MIT AI Lab (March 1990).
Isidori, A. Nonlinear Control Systems. Springer Verlag, 1989.
Jazwinski, A. Stochastic Processes and Filtering Theory. Academic Press, 1970.
Kalman, R. A new approach to linear filtering and prediction problems. Trans. of the ASME-Journal of basic engineering. 35–45 (1960).
Krener, A. J., and Respondek, W. Nonlinear observers with linearizable error dynamics. SIAM J. Control Optim. vol. 23 (2) (1985).
Longuet-Higgins, H. C. A computer algorithm for reconstructing a scene from two projections. Nature 293 (1981), 133–135.
Matthies, L., Szelisky, R., and Kanade, T. Kalman filter-based algorithms for estimating depth from image sequences. Int. J. of computer vision (1989).
Maybank, S. Theory of reconstruction from image motion, vol. 28 of Information Sciences. Springer-Verlag, 1992.
Mundy, J., and Zisserman, A-, Eds, Geometric invariance in computer vision. MIT Press, Cambridge, Mass., 1992.
Murray, R., Li, Z., and Sastry, S. A Mathematical Introduction to Robotic Manipulation. Preprint, 1993.
Oliensis, J., and Inigo-Thomas, J. Recursive multi-frame structure from motion incorporating motion error. Proc. DARPA Image Understanding Workshop (1992).
Soatto, S. Observability of rigid motion under perspective projection with application to visual motion estimation. Technical Report CIT-CDS 94-001, California Institute of Technology (1994).
Soatto, S., Frezza, R., and Perona, P. Recursive motion estimation on the essential manifold. Technical Report CIT-CDS 93-021 and CIT-CNS 32/93, California Institute of Technology (1993).
Soatto, S., and Perona, P. Three dimensional transparent structure segmentation and multiple 3d motion estimation from monocular perspective image sequences. Technical Report CIT-CDS 93-022, California Institute of Technology (1993).
Soatto, S., Perona, P., Frezza, R., and Picci, G. Recursive motion and structure estimation with complete error characterization. In Proc. IEEE Comput. Soc. Conf. Comput. Vision and Pattern Recogn. (New York, June 1993), pp. 428–433.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1994 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Soatto, S., Frezza, R., Perona, P. (1994). Motion estimation on the essential manifold. In: Eklundh, JO. (eds) Computer Vision — ECCV '94. ECCV 1994. Lecture Notes in Computer Science, vol 801. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0028335
Download citation
DOI: https://doi.org/10.1007/BFb0028335
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-57957-1
Online ISBN: 978-3-540-48400-4
eBook Packages: Springer Book Archive