Abstract
Variational (cost minimization) and local constraint approaches are generally applicable to problems in low-level vision (e.g., computation of intrinsic images). Iterative relaxation algorithms are “natural” choices for implementation because they can be executed on highly parallel and locally connected processors. They may, however, require a very large number of iterations to attain convergence. Multilevel relaxation techniques converge much faster and are well suited to processing in cones or pyramids. These techniques are applied to the problem of computing optic flow from dynamic images.
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.
Similar content being viewed by others
References
K. A. Narayanan, D. P. O’Leary, A. Rosenfeld: Image smoothing and segmentation by cost minimization, IEEE Trans. Systems, Man, Cybernetics SMC-12. 91–96 (1982)
W. E. L. Grimson: “A Computational Theory of Visual Surface Interpolation”, Artificial Intelligence Laboratory Memo 613, MIT (1981)
K. Ikeuchi: “Numerical Shape from Shading and Occluding Contour in a Single View”, Artificial Intelligence Laboratory Memo 566, MIT (1980)
K. Ikeuchi, B. K. P. Horn: Numerical shape from shading and occluding boundaries. Artificial Intelligence 17, 141–184 (1981)
B. K. P. Horn, B. G. Schunck: Determining optical flow. Artificial Intelligence 17, 185–204 (1981)
L. A. Hageman, D. M, Young: Applied Iterative Methods (Academic Press, New York, 1981)
A. Brandt: “Multi-level adaptive techniques (MLAT) for partial differential equations: ideas and software”, in Mathematical Software III, ed. by J. R. Rice (Academic Press, New York, 1977), pp. 277–318
A. Brandt: Multi-level adaptive solutions to boundary-value problems. Mathematics of Computation 31, 333–390 (1977)
S. L. Tanimoto: “Regular hierarchical image and processing structures in machine vision”, in Computer Vision Systems, ed. by A. R. Hanson, E. M. Riseman (Academic Press, New York, 1978), pp. 165–174
S. Tanimoto, A. Klinger (eds.): Structured Computer Vision: Machine Perception through Hierarchical Computation Structures (Academic Press, New York, 1980)
A. R. Hanson, E. M. Riseman: “Processing cones: a computational structure for image analysis”, in Structured Computer Vision, ed. by S. Tanimoto, A. Klinger (Academic Press, New York, 1980), pp. 101–131
S. Tanimoto, T. Pavlidis: A hierarchical data structure for picture processing, Computer Graphics Image Processing 4, 104–119 (1975)
A. Klinger, C. R. Dyer: Experiments on picture representation using regular decomposition. Computer Graphics Image Processing 5, 68–105(1976)
M. D. Kelly: “Edge detection in pictures by computer using planning”, in Machine Intelligence 6, ed. by B. Meitzer, D. Michie (Edinburgh University Press, Edinburgh, UK, 1971), pp. 379–409
R. Y. Wong, E. L. Hall: Sequential hierarchical scene matching, IEEE Trans. Computers C-27, 359–366 (1978)
D. Marr, T. Poggio: A computational theory of human stereo vision, Proco Royal Society (London) B204, 301–328 (1979)
P. J. Burt: “Pyramid-based extraction of local image features with applications to motion and texture analysis,” in Proc. SPIE Conf. on Robotics and Industrial Inspection, San Diego, CA, 1982
D. G. Luenberger: Introduction to Linear and Nonlinear Programming (Addison-Wesley, Reading, MA, 1973)
R. Courant, D. Hilbert: Methods of Mathematical Physics Vol. 1 (Interscience, New York, 1953)
D. Terzopolous: “Multi-Level Reconstruction of Visual Surfaces: Variational Principles and Finite Element Representation”, Artificial Intelligence Laboratory Memo 671, MIT (1982)
M. Yachida: “Determining velocity map by 3-D iterative estimates”, in Proc. 7th Intl. Joint Conf. on Artificial Intelligence, Vancouver, BC, 1981, pp. 716–718
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1984 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Glazer, F. (1984). Multilevel Relaxation in Low-Level Computer Vision. In: Rosenfeld, A. (eds) Multiresolution Image Processing and Analysis. Springer Series in Information Sciences, vol 12. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-51590-3_18
Download citation
DOI: https://doi.org/10.1007/978-3-642-51590-3_18
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-51592-7
Online ISBN: 978-3-642-51590-3
eBook Packages: Springer Book Archive