Abstract
In its traditional formulation, stereo correspondence involves both searching and selecting. Given a feature in one scanline, the corresponding scanline in the other image is searched for the positions of similar features. Often more than one candidate is found, and the correct one must be selected. The problem of selection is unavoidable because different features look similar to each other. Search, on the other hand, is not inherent in the correspondence problem. We propose a representation of scanlines, called intrinsic curves, that avoids search over different disparities. The idea is to represent scanlines by means of local descriptor vectors, without regard for where in the image a descriptor is computed, but without losing information about the contiguity of image points. In fact, intrinsic curves are the paths that the descriptor vector traverses as an image scanline is traversed from left to right. Because the path in the space of descriptors ignores image position, intrinsic curves are invariant with respect to disparity under ideal circumstances. Establishing stereo correspondences is then reduced to the selection of one among few match candidates, a task simplified by the contiguity information carried by intrinsic curves. We analyze intrinsic curves both theoretically and for real images in the presence of noise, brightness bias, contrast fluctuations, and moderate geometric distortion. We report preliminary experiments.
This research was supported by the National Science Foundation under contract IRI-9496205.
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
R.D. Arnold and T.O. Binford. Geometric constraints in stereo vision. SPIE 238:281–292, 1978.
V.I. Arnold. Ordinary Differential Equations. MIT Press, 1990.
H.H. Baker and T.O. Binford. Depth from edge and intensity based stereo. IJCAI, 631–636, 1981.
P.N. Belhumeur and D. Mumford. A Bayesian treatment of the stereo correspondence problem using half-occluded regions. CVPR, 506–512, 1992.
A. Blake and C. Marinos. Shape from texture: Estimation, isotropy and moments. Artificial Intelligence, 45:323–380, 1990.
M. Campani and A. Verri. Motion analysis from first-order properties of optical flow. CVGIP: Image Understanding, 56(1):90–107, 1992.
D. Geiger, B. Ladendorf, and A. Yuille. Occlusions and binocular stereo. EECV, 425–433, 1992.
W.E.L. Grimson. Computational experiments with a feature based stereo algorithm. PAMI, 7(1):17–34, 1985.
W. Förstner. Image Matching. In R.M. Haralick and L.G. Shapiro, Computer and Robot Vision. Addison-Wesley, 1992.
S.S. Intille and A.F. Bobick. Disparity-space images and large occlusion stereo. ECCV, 179–186, 1994.
D.G. Jones and J. Malik. A computational framework for determining stereo correspondence from a set of linear spatial filters. EECV, 395–410, 1992.
D.G. Jones and J. Malik. Determining three-dimensional shape from orientation and spatial frequency disparities. EECV, 661–669, 1992.
K. Kanatani. Detection of surface orientation and motion from texture by a stereological technique. Artificial Intelligence, 23:213–237, 1984.
M.H. Kass. Computing stereo correspondence. Master's thesis, M.I.T., 1984.
J.J. Koenderink and A.J. Van Doorn. Geometry of binocular vision and a model for stereopsis. Biological Cybernetics, 21:29–35, 1976.
J.J. Little and W.E. Gillet. Direct evidence for occlusion in stereo and motion. ECCV, 336–340, 1990.
J. Malik and P. Perona. Preattentive texture discrimination with early vision mechanisms. JOSA — A, 7(5):923–932, 1990.
S.G. Mallat. A theory for multiresolution signal decomposition: The wavelet representation. PAMI, 11(7):674–693, 1989.
R. Manmatha. A framework for recovering affine transforms using points, lines or image brightness. CVPR, 141–146, 1994.
D. Marr and T. Poggio. Cooperative computation of stereo disparity. Science, 194:283–287, 1976.
G. Medioni and R. Nevatia. Segment-based stereo matching. CVGIP, 31:2–18, 1985.
Y. Ohta and T. Kanade. Stereo by intra-and inter-scanline search using dynamic programming. PAMI, 7(2):139–154, 1985.
S.B. Pollard, J.E. Mayhew, and G.P. Frisby. PMF: A stereo correspondence algorithm using a disparity gradient limit. Perception, 14:449–470, 1985.
J. Sato and R. Cipolla. Extracting the affine transformation from texture moments. ECCV, 165–172, 1994.
D.J. Struik. Lectures on Classical Differential Geometry. Dover, 1988.
B.J. Super and A.C. Bovik. Shape-from-texture by wavelet-based measurement of local spectral moments. CVPR, 296–301, 1992.
P.S. Toh and A.K. Forrest. Occlusion detection in early vision. ICCV, 126–132, 1990.
C. Tomasi and R. Manduchi. Stereo without search. Tech. Rep. STAN-CS-TR-95-1543, Stanford, 1995.
A. Verri and T. Poggio. Against quantitative optical flow. ICCV, 171–180, 1987.
J. Weng, N. Ahuja, and T.S. Huang. Matching two perspective views. PAMI, 14(8):806–825, 1992.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tomasi, C., Manduchi, R. (1996). Stereo without search. In: Buxton, B., Cipolla, R. (eds) Computer Vision — ECCV '96. ECCV 1996. Lecture Notes in Computer Science, vol 1064. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0015557
Download citation
DOI: https://doi.org/10.1007/BFb0015557
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61122-6
Online ISBN: 978-3-540-49949-7
eBook Packages: Springer Book Archive