Abstract
In this paper, we use local feature transformations estimated in the matching process as initial seeds for 2D homography estimation. The number of testing hypotheses is equal to the number of matches, naturally enabling a full search over the hypothesis space. Using this property, we develop an iterative algorithm that clusters the matches under the common 2D homography into one group, i.e., features on a common plane. Our clustering algorithm is less affected by the proportion of inliers and as few as two features on the common plane can be clustered together; thus, the algorithm robustly detects multiple dominant scene planes. The knowledge of the dominant planes is used for robust fundamental matrix computation in the presence of quasi-degenerate data.
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.
References
Fishler, M.A., Bolles, R.C.: Random sampling Consensus: A paradigm for model fitting with application to image analysis and automated cartography. Communications of the ACM 24(6), 381–395 (1981)
Torr, P.H., Zisserman, A.: Robust Computation and Parameterization of Multiple View Relations. In: ICCV (1998)
Chum, O., Werner, T., Matas, J.: Two-view Geometry Estimation Unaffected by a Dominant Plane. In: CVPR (2005)
Frahm, J., Pollefeys, M.: RANSAC for (Quasi-)Degenerate data (QDEGSAC). In: CVPR (2006)
Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2000)
Torr, P.H.S.: Geometric Motion Segmentation and Model Selection. Philosophical Transactions of the Royal Society, pp. 1321–1340 (1998)
Bhat, P., Zheng, K.C., Snavely, N., Agarwala, A., Agrawala, M., Cohen, M.F., Curless, B.: Piecewise Image Registration in the Presence of Multiple Large Motions. In: CVPR (2006)
Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaffalitzky, F., Kadir, T., Van Gool, L.: A Comparison of Affine Region Detectors. IJCV 65(1-2), 43–72 (2005)
Ferrari, V., Tuytelaars, T., Van Gool, L.: Simultaneous Object Recognition and Segmentation from Single or Multiple Model Views. IJCV 67(2), 159–188 (2006)
Vedaldi, A., Soatto, S.: Local Features, All Grown Up. In: CVPR (2006)
Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust Wide Baseline Stereo from Maximally Stable Extremal Regions. In: BMVC, pp. 384–393 (2002)
Lowe, D.G.: Distinctive Image Features from Scale-Invariant Keypoints. IJCV 60(2), 91–110 (2004)
Kim, S.H., Yoon, K.J., Kweon, I.S.: Object Recognition using Generalized Robust Invariant Feature and Gestalt Law of Proximity and Similarity. In: CVPR 2006. 5th IEEE Workshop on Perceptual Organization in Computer Vision (2006)
Levenberg, K.: A Method for the Solution of Certain Problems in Least Squares. Quart. Appl. Math. 2, 164–168 (1944)
Marquardt, D.: An Algorithm for Least-Squares Estimation of Nonlinear Parameters. SIAM J. Appl. Math. 11, 431–441 (1963)
Kanatani, K., Ohta, N., Kanazawa, Y.: Optimal Homography Computation with a Reliability Measure. IEICE Trans. Information Systems E83-D(7), 1369–1374 (2000)
Kanatani, K., Sugaya, Y.: High Accuracy Fundamental Matrix Computation and its Performance Evaluation. In: BMVC (2006)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Choi, O., Kim, H., Kweon, I.S. (2007). Simultaneous Plane Extraction and 2D Homography Estimation Using Local Feature Transformations. In: Yagi, Y., Kang, S.B., Kweon, I.S., Zha, H. (eds) Computer Vision – ACCV 2007. ACCV 2007. Lecture Notes in Computer Science, vol 4844. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-76390-1_27
Download citation
DOI: https://doi.org/10.1007/978-3-540-76390-1_27
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-76389-5
Online ISBN: 978-3-540-76390-1
eBook Packages: Computer ScienceComputer Science (R0)