| | This Article | |
| |
| |
| | Share | |
| |
| |
| | Bibliographic References | |
| |
| |
| | Add to: | |
| |
 Digg
 Furl
 Spurl
 Blink
 Simpy
 Google
 Del.icio.us
 Y!MyWeb
| |
| | Search | |
| |
| |
| | |
Correspondence-Free Determination of the Affine Fundamental Matrix
January 2007 (vol. 29 no. 1)
pp. 82-97
Fundamental matrix estimation is a central problem in computer vision and forms the basis of tasks such as stereo imaging and structure from motion. Existing algorithms typically analyze the relative geometries of matched feature points identified in both projected views. Automated feature matching is itself a challenging problem. Results typically have a large number of false matches. Traditional fundamental matrix estimation methods are very sensitive to matching errors, which led naturally to the application of robust statistical estimation techniques to the problem. In this work, an entirely novel approach is proposed to the fundamental matrix estimation problem. Instead of analyzing the geometry of matched feature points, the problem is recast in the frequency domain through the use of Integral Projection, showing how this is a reasonable model for orthographic cameras. The problem now reduces to one of identifying matching lines in the frequency domain which, most importantly, requires no feature matching or correspondence information. Experimental results on both real and synthetic data are presented that demonstrate the algorithm is a practical technique for fundamental matrix estimation. The behavior of the proposed algorithm is additionally characterized with respect to input noise, feature counts, and other parameters of interest.
[1] 82 R. Hartley and A. Zisserman, Multiple View Geometry in Computer Vision. Cambridge Univ. Press, 2000.[2] P. Favaro, H. Jin, and S. Soatto, “A Semi-Direct Approach to Structure from Motion,” Proc. 11th Int'l Conf. Image Analysis and Processing, pp. 250-255, 2001.[3] F. Dellaert, S.M. Seitz, C.E. Thorpe, and S. Thrun, “Structure from Motion without Correspondences,” Proc. IEEE Int'l Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 557-564, June 2000.[4] G.P. Stein and A. Shashua, “Model-Based Brightness Constraints: On Direct Estimation of Structure and Motion,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no. 9, pp. 992-1015, Sept. 2000.[5] B.K.P. Horn and B.G. Schunck, “Determining Optical Flow,” Artifical Intelligence, vol. 17, pp. 185-203, 1981.[6] S. Negahdaripour and B.K.P. Horn, “A Direct Method for Locating the Focus of Expansion,” Computer Vision, Graphics, and Image Processing, vol. 46, no. 3, pp. 303-326, 1989.[7] Z. Zhang, “Determining the Epipolar Geometry and Its Uncertainty: A Review,” Int'l J. Computer Vision, vol. 27, no. 2, pp.161-198, 1998.[8] N. Gracias and J. Santos-Victor, “Robust Estimation of the Fundamental Matrix and Stereo Correspondences,” Proc. Fifth Int'l Symp. Intelligent Robotic Systems, July 1997.[9] R.M. Haralick, H. Joo, C.-N. Lee, X. Zhuang, V.G. Vaidya, and M.B. Kim, “Pose Estimation from Corresponding Point Data,” IEEE Trans. Systems, Man, and Cybernetics, vol. 19, no. 6, pp. 1426-1446, Nov. 1989.[10] S. Seitz and C. Dyer, “Complete Structure from Four Point Correspondences,” Proc. Fifth Int'l Conf. Computer Vision, pp. 330-337, 1995.[11] C. Tomasi and T. Kanade, “Shape and Motion from Image Streams under Orthography: A Factorization Method,” Int'l J. Computer Vision, vol. 9, no. 2, pp. 137-154, Nov. 1992.[12] M. Taalebinezhaad, “Direct Robot Motion Vision by Fixation,” Proc. IEEE Int'l Conf. Robotics and Automation, pp. 626-631, Apr. 1991.[13] E. WeldonJr. and H. Liu, “How Accurately Can Direct Motion Vision Determine Depth,” Proc. IEEE Int'l Conf. Computer Vision and Pattern Recognition, pp. 613-618, 1991.[14] S. Negahdaripour and B.K.P. Horn, “Direct Passive Navigation,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 9, no. 1, pp. 168-176, 1987.[15] S. Roy and I.J. Cox, “Motion without Structure,” Proc. IEEE Int'l Conf. Pattern Recognition, vol. 1, pp. 728-734, Aug. 1996.[16] C. Fermüller and Y. Aloimonos, “Global Rigidity Constraints in Image Displacement Fields,” Proc. IEEE Int'l Conf. Computer Vision, pp. 245-250, 1995.[17] C. Fermüller and Y. Aloimonos, “The Confounding of Translation and Rotation in Reconstruction from Multiple Views,” Proc. IEEE Int'l Conf. Computer Vision and Pattern Recognition, pp. 250-256, 1997.[18] A.J. Yezzi and S. Soatto, “Structure from Motion for Scenes without Features,” Proc. IEEE Int'l Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 525-532, 2003.[19] M. Irani, “Multi-Frame Optical Flow Estimation Using Subspace Constraints,” Proc. IEEE Int'l Conf. Computer Vision, pp. 626-633, Sept. 1999.[20] M.E. Antone and S.J. Teller, “Automatic Recovery of Relative Camera Rotations for Urban Scenes,” Proc. IEEE Int'l Conf. Computer Vision and Pattern Recognition, pp. 2282-2289, 2000.[21] M.E. Antone and S.J. Teller, “Scalable Extrinsic Calibration of Omni-Directional Image Networks,” Int'l J. Computer Vision, vol. 49, no. 2-3, pp. 143-174, 2002.[22] C. Fermüller, P. Baker, and Y. Aloimonos, “Visual Space Time Geometry: A Tool for Perception and Imagination,” Proc. IEEE, vol. 90, no. 5, pp. 1113-1135, July 2002.[23] P. Baker and Y. Aloimonos, “Structure from Motion of Parallel Lines,” Proc. Eighth European Conf. Computer Vision, pp. 229-240, 2004.[24] C. Geyer, S. Sastry, and R. Bajcsy, “Euclid Meets Fourier: Applying Harmonic Analysis to Essential Matrix Estimation in Omnidirectional Cameras,” Proc. Workshop Omnidirectional Vision, 2004.[25] A. Makadia, C. Geyer, S. Sastry, and K. Daniilidis, “Radon-Based Structure from Motion without Correspondences,” Proc. IEEE Int'l Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 796-803, 2005.[26] A. Makadia and K. Daniilidis, “Direct 3D-Rotation Estimation from Spherical Images via a Generalized Shift Theorem,” Proc. IEEE Int'l Conf. Computer Vision and Pattern Recognition, vol. 2, pp.217-226, 2003.[27] A. Makadia, L. Sorgi, and K. Daniilidis, “Rotation Estimation from Spherical Images,” Proc. IEEE Int'l Conf. Pattern Recognition, vol. 3, pp. 590-593, 2004.[28] S. Lehmann, I.V.L. Clarkson, and P.J. Kootsookos, “An Integral Projection Approach to 3D Rigid Body Transformations,” Proc. 38th Asilomar Conf. Signals, Systems, and Computers, vol. 1, pp. 2089-2093, Nov. 2004.[29] J.-X. Chai and H.-Y. Shum, “Parallel Projections for Stereo Reconstruction,” Proc. IEEE Int'l Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 493-500, June 2000.[30] D.W. Watt and C.M. Vest, “Consistent Iterative Convolution: A Coupled Approach to Tomographic Reconstruction,” J. Optical Soc. Am. A, vol. 6, no. 1, pp. 44-51, Jan. 1989.[31] S.R. Deans, The Radon Transform and Some of Its Applications. Wiley, 1983.[32] R.N. Bracewell, Two-Dimensional Imaging. Prentice-Hall, 1995.[33] A.C. Kak and M. Slaney, Principles of Computerized Tomographic Imaging. SIAM, 2001.[34] G.W. Lank, I.S. Reed, and G.E. Pollon, “A Semicoherent Detection Statistic and Doppler Estimation Statistic,” IEEE Trans. Aerospace and Electronic Systems, vol. 9, no. 2, pp. 151-165, 1973.[35] L.A.D. Hutchison and W.A. Barrett, “Fast Registration of Tabular Document Images Using the Fourier-Mellin Transform,” Proc. First Int'l Workshop Document Image Analysis for Libraries, pp. 253-267, 2004.[36] R.I. Hartley, “In Defense of the Eight-Point Algorithm,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 19, no. 6, pp.580-593, June 1997.[37] 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, vol. 24, no. 6, pp. 381-395, 1981.[38] C.J. Harris and M. Stephens, “A Combined Corner and Edge Detector,” Proc. Fourth Alvey Vision Conf., pp. 147-151, 1988.[39] X.C. He and N.H.C. Yung, “Curvature Scale Space Corner Detector with Adaptive Threshold and Dynamic Region of Support,” Proc. IEEE Int'l Conf. Pattern Recognition, vol. 2, pp.791-794, 2004.[40] P.A. Beardsley, P.H.S. Torr, and A. Zisserman, “3D Model Acquisition from Extended Image Sequences,” Proc. Fourth European Conf. Computer Vision, vol. 2, pp. 683-695, 1996.[41] P.H.S. Torr, “A Structure and Motion Toolkit in Matlab: Interactive Adventures in s and m,” Technical Report MSR-TR-2002-56, Microsoft Research, 2002.[42] P. Leclercq and J. Morris, “Robustness to Noise of Stereo Matching,” Proc. 12th Int'l Conf. Image Analysis and Processing, pp. 606-611, 2003.
Index Terms:
Computer vision, epipolar geometry, fundamental matrix, robust estimation, projection-slice theorem, Radon transformation.
Citation:
Stefan Lehmann, Andrew P. Bradley, I. Vaughan L. Clarkson, John Williams, Peter J. Kootsookos, "Correspondence-Free Determination of the Affine Fundamental Matrix," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 29, no. 1, pp. 82-97, Jan. 2007, doi:10.1109/TPAMI.2007.5
