Epipolar Geometry from Two Correspondences

A novel algorithm for robust RANSAC-like estimation of epipolar geometry (of uncalibrated camera pair) from two correspondences of local affine frames (LAFs) is presented. Each LAF is constructed from three points independently detected on a maximally stable extremal region. The algorithm assumes that a sufficiently accurate approximation of the fundamental matrix is obtained from two LAF correspondences by the 6-point algorithm of Stewenius et al. The so-far-the-best hypotheses are further processed by so-called local optimization to estimate the epipolar geometry. Special attention is paid to planar sample degeneracy, since the probability of drawing two coplanar LAF correspondences is not negligible. Combining the 6-point solver, local optimization, and the degeneracy test enables RANSAC to draw samples of only two LAFs to generate hypotheses and thus to reduce the number of samples drawn. We experimentally show that using the 6-point algorithm (approximating the real camera by camera with unit aspect ratio, zero skew, principal point in the center of image, and a common unknown focal length) generates hypotheses that are sufficient for EG estimation in LO-RANSAC framework

[1]  Luc Van Gool,et al.  Wide Baseline Stereo Matching based on Local, Affinely Invariant Regions , 2000, BMVC.

[2]  Richard I. Hartley,et al.  In defence of the 8-point algorithm , 1995, Proceedings of IEEE International Conference on Computer Vision.

[3]  Henrik Stewenius,et al.  Gröbner Basis Methods for Minimal Problems in Computer Vision , 2005 .

[4]  Jiri Matas,et al.  Robust wide-baseline stereo from maximally stable extremal regions , 2004, Image Vis. Comput..

[5]  Andrew Zisserman,et al.  Multiple View Geometry in Computer Vision (2nd ed) , 2003 .

[6]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[7]  Andrew Zisserman,et al.  MLESAC: A New Robust Estimator with Application to Estimating Image Geometry , 2000, Comput. Vis. Image Underst..

[8]  Jiri Matas,et al.  Locally Optimized RANSAC , 2003, DAGM-Symposium.

[9]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[10]  Jan Flusser,et al.  Convex Layers: A New Tool for Recognition of Projectively Deformed Point Sets , 1999, CAIP.

[11]  O. Chum,et al.  ENHANCING RANSAC BY GENERALIZED MODEL OPTIMIZATION Onďrej Chum, Jǐ , 2003 .

[12]  David W. Murray,et al.  Guided Sampling and Consensus for Motion Estimation , 2002, ECCV.

[13]  Andrew Zisserman,et al.  Robust Detection of Degenerate Configurations while Estimating the Fundamental Matrix , 1998, Comput. Vis. Image Underst..

[14]  H. Opower.  Multiple view geometry in computer vision , 2002 .

[15]  Andrew Zisserman,et al.  Wide baseline stereo matching , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[16]  Andrew Zisserman,et al.  Geometric invariance in computer vision , 1992 .

[17]  Andrew Zisserman,et al.  Viewpoint invariant texture matching and wide baseline stereo , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[18]  Stepán Obdrzálek,et al.  Local affine frames for wide-baseline stereo , 2002, Object recognition supported by user interaction for service robots.

[19]  Jiri Matas,et al.  Two-view geometry estimation unaffected by a dominant plane , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[20]  Frederik Schaffalitzky,et al.  A minimal solution for relative pose with unknown focal length , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).