This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Simultaneous Two-View Epipolar Geometry Estimation and Motion Segmentation by 4D Tensor Voting
September 2004 (vol. 26 no. 9)
pp. 1167-1184
Wai-Shun Tong, IEEE Computer Society
Chi-Keung Tang, IEEE Computer Society
We address the problem of simultaneous two-view epipolar geometry estimation and motion segmentation from nonstatic scenes. Given a set of noisy image pairs containing matches of n objects, we propose an unconventional, efficient, and robust method, 4D tensor voting, for estimating the unknown n epipolar geometries, and segmenting the static and motion matching pairs into n independent motions. By considering the 4D isotropic and orthogonal joint image space, only two tensor voting passes are needed, and a very high noise to signal ratio (up to five) can be tolerated. Epipolar geometries corresponding to multiple, rigid motions are extracted in succession. Only two uncalibrated frames are needed, and no simplifying assumption (such as affine camera model or homographic model between images) other than the pin-hole camera model is made. Our novel approach consists of propagating a local geometric smoothness constraint in the 4D joint image space, followed by global consistency enforcement for extracting the fundamental matrices corresponding to independent motions. We have performed extensive experiments to compare our method with some representative algorithms to show that better performance on nonstatic scenes are achieved. Results on challenging data sets are presented.

[1] A. Adam, E. Rivlin, and I. Shimshoni, Ror: Rejection of Outliers by Rotations IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 23, no. 1, pp. 78-84, Jan. 2001.
[2] P. Anandan and S. Avidan, Integrating Local Affine into Global Projective Images in the Joint Image Space Proc. European Conf. Computer Vision, 2000.
[3] X. Armangué, J. Pags, J. Salvi, and J. Batlle, Comparative Survey on Estimating the Fundamental Matrix Proc. Ninth Simposium Nacional de Reconocimiento de Formas y Anlisis de Imgenes, pp. 227-232, June 2001.
[4] D.H. Ballard, Parameter Nets Artificial Intelligence, vol. 22, pp. 235-267, 1984.
[5] J. Davis, Mosaics of Scenes with Moving Objects IEEE CS Conf. Computer Vision and Pattern Recognition, pp. 354-360, June 1998.
[6] O.D. Faugeras, Q.T. Luong, and T. Papadopoulo, The Geometry of Multiple Images. MIT Press, 2001.
[7] R. Hartley and A. Zisserman, Multiple View Geometry in Computer Vision. Cambridge Univ. Press, 2000.
[8] R.I. Hartley, In Defense of the 8-Point Algorithm IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 19, no. 6, pp. 580-593, June 1997.
[9] R.I. Hartley and A. Zisserman, Multiple View Geometry in Computer Vision. Cambridge Univ. Press, 2000.
[10] H.C. Longuet-Higgins, A Computer Algorithm for Reconstructing a Scene from Two Projections Nature, vol. 293, pp. 133-135, 1981.
[11] Q.T. Luong and O.D. Faugeras, The Fundamental Matrix: Theory, Algorithms, and Stability Analysis Int'l J. Computer Vision, vol. 17, no. 1, pp. 43-75, Jan. 1996.
[12] G. Medioni, M.-S. Lee, and C.-K. Tang, A Computational Framework for Feature Extraction and Segmentation. Amsterdam: Elseviers Science, 2000.
[13] M. Nicolescu and G. Medioni, Perceptual Grouping from Motion Cues Using Tensor Voting in 4-D Proc. European Conf. Computer Vision, vol. III, pp. 423-437, 2002.
[14] M. Nicolescu and G. Medioni, Perceptual Grouping into Motion Layers Using Tensor Voting in 4-D Proc. Int'l Conf. Pattern Recognition, vol. III, pp. 303-308, 2002.
[15] P. Pritchett and A. Zisserman, Wide Baseline Stereo Matching IEEE Proc. Int'l Conf., pp. 754-760, Jan. 1998.
[16] J.G. Semple and G.T. Kneebone, Algebraic Projective Geometry. Oxford, England: Clarendon Press, 1952.
[17] R. Sturm, Das Problem der Projektivitat und Seine Anwendung auf die Flaachen Zweiten Grades Math. Ann, vol. 1, pp. 533-547, 1869.
[18] C.-K. Tang, G. Medioni, and M.-S. Lee, N-Dimensional Tensor Voting, and Application to Epipolar Geometry Estimation IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 23, no. 8, pp. 829-844, Aug. 2001.
[19] W.-S. Tong, An Enhanced Tensor Voting Formalism and Applications master's thesis, The Hong Kong Univ. of Science and Tech nology, June 2001.
[20] W.-S. Tong, C.-K. Tang, and G. Medioni, Epipolar Geometry Estimation by 4D Tensor Voting Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. I, pp. 926-933, 2001.
[21] P.H.S. Torr and D.W. Murray, Statistical Detection of Independent Movement of a Moving Camera Image and Vision Computing, vol. 1, no. 4, 1993.
[22] P.H.S. Torr and D.W. Murray, The Development and Comparison of Robust Methods for Estimating the Fundamental Matrix Int'l J. Computer Vision, vol. 24, no. 3, pp. 271-300, 1997.
[23] R. Vidal, Y. Ma, S. Hsu, and S. Sastry, Optimal Motion Estimation from Multiview Normalized Epipolar Constraint Proc. Int'l Conf. Computer Vision, vol. I, pp. 34-41, 2001.
[24] L. Wolf and A. Shashua, Two-Body Segmentation from Two Perspective Views Proc. Computer Vision and Pattern Recognition, vol. I, pp. 263-270, 2001.
[25] Z. Zhang, Determining the Epipolar Geometry and Its Uncertainty: A Review Two-Body Segmentation from Two Perspective Views Int'l J. Computer Vision, vol. 27, no. 2, pp. 161-195, 1998.

Index Terms:
Epipolar geometry, motion segmentation, nonstatic scene, robust estimation, higher dimensional inference.
Citation:
Wai-Shun Tong, Chi-Keung Tang, G?rard Medioni, "Simultaneous Two-View Epipolar Geometry Estimation and Motion Segmentation by 4D Tensor Voting," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 26, no. 9, pp. 1167-1184, Sept. 2004, doi:10.1109/TPAMI.2004.72
Usage of this product signifies your acceptance of the Terms of Use.