Abstract
In this paper we introduce constraint satisfaction framework suitable for the task of finding correspondences in computer vision. This task lies in the heart of many problems like stereovision, 3D model reconstruction, image stitching, camera autocalibration, recognition and image retrieval and a host of others. If the problem domain is general enough, the correspondence problem can seldom employ any well-structured prior knowledge. This leads to tasks that have to find maximum cardinality solutions satisfying some weak optimality condition and a set of constraints. To avoid artifacts, robustness is required to cope with decision under occlusion, uncertainty or insufficiency of data and local violations of prior model. The proposed framework is based on a robust modification of graph-theoretic notion known as digraph kernel.
Chapter PDF
Similar content being viewed by others
References
S. Baker, T. Sim, and T. Kanade. A characterization of inherent stereo ambiguities. In Proc ICCV, pp 428–435, 2001.
E. Boros and V. Gurvich. Perfect graphs, kernels, and cores of cooperative games. Rutcor Research Report RRR 12-2003, Rutgers University, 2003.
H. Cornelius et al. Towards complete free-form reconstruction of complex 3D scenes from an unordered set of uncalibrated images. In Proc ECCV Workshop Statistical Methods in Video Processing, vol LNCS 3247, pp 1–12, 2004.
I. J. Cox, S. Hingorani, B. M. Maggs, and S. B. Rao. Stereo without disparity gradient smoothing: a Bayesian sensor fusion solution. In Proc BMVC, pp 337–346, 1992.
K. Mikolajczyk et al. A comparison of affine region detectors. Int J Computer Vision, 65(1–2):43–72, 2005.
M. A. Fischler and R. C. Bolles. Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Comm ACM, 24(6):381–395, 1981.
B. Flach and M. I. Schlesinger. A class of solvable consistent labelling problems. In Joint IAPR Int Wkshps SSPR and SPR, vol LNCS 1876, pp 462–471, 2000.
M. Gong and Y. Yang. Unambiguous stereo matching using reliability-based dynamic programming. IEEE Trans PAMI, 27(6):998–1003, 2005.
R. Hartley and A. Zisserman. Multiple view geometry in computer vision. Cambridge University, 2003.
V. Kolmogorov and R. Zabih. What energy functions can be minimized via graph cuts? IEEE Trans PAMI, 26(2):147–159, 2004.
J. Kostkováa and R. Šára. Stratified dense matching for stereopsis in complex scenes. In Proc BMVC, pp 339–348, 2003.
K. Mikolajczyk and C. Schmid. A performance evaluation of local descriptors. IEEE Trans PAMI, 27(10):1615–1630, 2005.
R. Šára. Finding the largest unambiguous component of stereo matching. In Proc ECCV, vol LNCS 2352, pp 900–914, 2002.
R. Šára, I. S. Okatani, and A. Sugimoto. Globally convergent range image registration by graph kernel algorithm. In Proc Int Conf 3-D Digital Imaging and Modeling, pp 377–384, 2005.
D. Scharstein and R. Szeliski. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Int J Computer Vision, 47(1–3):7–42, 2002.
J. von Neumann and O. Morgenstern. Theory of Games and Economic Behaviour. Princeton University Press, 1944.
A. L. Yuille and T. Poggio. A generalized ordering constraint for stereo correspondence. AI Memo 777, MIT, 1984.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Physica-Verlag Heidelberg
About this paper
Cite this paper
Šára, R. (2006). Robust correspondence recognition for computer vision. In: Rizzi, A., Vichi, M. (eds) Compstat 2006 - Proceedings in Computational Statistics. Physica-Verlag HD. https://doi.org/10.1007/978-3-7908-1709-6_10
Download citation
DOI: https://doi.org/10.1007/978-3-7908-1709-6_10
Publisher Name: Physica-Verlag HD
Print ISBN: 978-3-7908-1708-9
Online ISBN: 978-3-7908-1709-6
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)