Abstract
This paper surveys an approach to data fusion that makes use of computational physics. Partial, noisy, multisensory data acquired at different spatial positions, at different instants in time, and/or at different scales of resolution are transformed into nonlinear force fields. The force fields act on deformable models, whose physical behaviors are governed by the continuum mechanical equations of deformable bodies. Reacting dynamically to the net external forces, deformable models integrate, interpolate, and regularize all the incoming data into a globally consistent interpretation. Physically-based fusion has seen successful application to several vision problems: image contour extraction, stereo and motion matching, visual surface reconstruction, and the recovery of 3D shape and nonrigid motion from dynamic stereo imagery.
The author is a Fellow of the Canadian Institute for Advanced Research.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
Terzopoulos, D., and Fleischer, K., “Deformable Models,” The Visual Computer, 4, 1988, 306–331.
Terzopoulos, D., “Integrating visual information from multiple sources,” From Pixels to Predicates, A.P. Pentland (ed.), Ablex, Norwood, NJ, 1986.
Terzopoulos, D., “On matching deformable models to images,” Topical Meeting on Machine Vision, Technical Digest Series, Vol. 12., Optical Society of America, Washington, DC, 1987, 160–167; also TR No. 60, Schlumberger Palo Alto Research, Nov., 1986.
Terzopoulos, D., “Multilevel computational processes for visual surface reconstruction,” Computer Vision, Graphics, and Image Processing, 24, 1983, 52–96.
Terzopoulos, D., “The role of constraints and discontinuities in visible-surface reconstruction,” Proc. 8th Int. J. Conf. AI, Karlsruhe, W. Germany, 1983, 1073–1077.
Terzopoulos, D., “The computation of visible-surface representations,” IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI-10, 1988, 417–438.
Terzopoulos, D., “Regularization of inverse visual problems involving discontinuities,” IEEE Transactions on Pattern Analysis and Machine Intelligence,PAMI-8, 1986, 413424.
Terzopoulos, D., Witkin, A., and Kass, M., “Stereo matching as constrained optimization using scale continuation methods,” Optical and Digital Pattern Recognition (Proc. SPIE 754), 1I-K. Liu and P.S. Schenker (ed.), 1987, 92–99.
Witkin, A., Terzopoulos, D., and Kass, M., “Signal matching through scale space,” International Journal of Computer Vision, 1, 1987, 133–144.
Terzopoulos, D., Witkin, A., and Kass, M., “Symmetry-seeking models and 3D object reconstruction,” International Journal of Computer Vision, 1, 1987, 211–221.
Kass, M., Witkin, A., and Terzopoulos, D., “Snakes: Active contour models,” International Journal of Computer Vision, 1, 1987, 321–331.
Terzopoulos, D., Witkin, A., and Kass, M., “Constraints on deformable models: Recovering 3D shape and nonrigid motion,” Artificial Intelligence, 35, 1988, 91–123.
Terzopoulos, D., “Image analysis using multigrid relaxation methods,” IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI-8, 1986, 129–139.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Terzopoulos, D. (1993). Physically-Based Fusion of Visual Data over Space, Time, and Scale. In: Aggarwal, J.K. (eds) Multisensor Fusion for Computer Vision. NATO ASI Series, vol 99. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-02957-2_4
Download citation
DOI: https://doi.org/10.1007/978-3-662-02957-2_4
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-08135-4
Online ISBN: 978-3-662-02957-2
eBook Packages: Springer Book Archive