×

Robust factorization methods using a Gaussian/uniform mixture model. (English) Zbl 1477.68445

Summary: We address the problem of building a class of robust factorization algorithms that solve for the shape and motion parameters with both affine (weak perspective) and perspective camera models. We introduce a Gaussian/uniform mixture model and its associated EM algorithm. This allows us to address parameter estimation within a data clustering approach. We propose a robust technique that works with any affine factorization method and makes it resilient to outliers. In addition, we show how such a framework can be further embedded into an iterative perspective factorization scheme. We carry out a large number of experiments to validate our algorithms and to compare them with existing ones. We also compare our approach with factorization methods that use M-estimators.

MSC:

68T45 Machine vision and scene understanding
62H12 Estimation in multivariate analysis
62H30 Classification and discrimination; cluster analysis (statistical aspects)

Software:

TransforMesh; PRMLT

References:

[1] Aanaes, H., Fisker, R., & Astrom, K. (2002). Robust factorization. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(9), 1215–1225. · doi:10.1109/TPAMI.2002.1033213
[2] Anandan, P., & Irani, M. (2002). Factorization with uncertainty. International Journal of Computer Vision, 49(2/3), 101–116. · Zbl 1012.68766 · doi:10.1023/A:1020137420717
[3] Bishop, C. M. (2006). Pattern recognition and machine learning. Berlin: Springer. · Zbl 1107.68072
[4] Bouguet, J.-Y. (2001). Pyramidal implementation of the affine lucas kanade feature tracker–description of the algorithm (Technical report). Intel Corporation.
[5] Brant, S. (2002). Closed-form solutions for affine reconstruction under missing data. In Proceedings of statistical methods for video processing (ECCV ’02 Workshop) (pp. 109–114).
[6] Christy, S., & Horaud, R. (1996). Euclidean shape and motion from multiple perspective views by affine iterations. IEEE Transactions on Pattern Analysis and Machine Intelligence, 18(11), 1098–1104. · doi:10.1109/34.544079
[7] Dempster, A. P., Laird, N. M., & Rubin, D. B. (1977). Maximum likelihood estimation from incomplete data via the EM algorithm (with discussion). Journal of the Royal Statistical Society, Series B, 39, 1–38. · Zbl 0364.62022
[8] Faugeras, O. (1993). Three dimensional computer vision: a geometric viewpoint. Cambridge: MIT Press.
[9] Fischler, M. A., & Bolles, R. C. (1981). Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM, 24(6), 381–395. · doi:10.1145/358669.358692
[10] Fraley, C., & Raftery, A. E. (2002). Model-based clustering, discriminant analysis, and density estimation. Journal of the American Statistical Association, 97, 611–631. · Zbl 1073.62545 · doi:10.1198/016214502760047131
[11] Golub, G. H., & Van Loan, C. F. (1989). Matrix computations. Baltimore: The Johns Hopkins University Press. · Zbl 0733.65016
[12] Gruber, A., & Weiss, Y. (2003). Factorization with uncertainty and missing data: exploring temporal coherence. In Proceedings neural information processing systems (NIPS’2003).
[13] Gruber, A., & Weiss, Y. (2004). Multibody factorization with uncertainty and missing data using the em algorithm. In Proceedings conference on computer vision and pattern recognition (pp. 707–714).
[14] Hajder, L., & Chetverikov, D. (2004). Robust structure from motion under weak perspective. In Proc. of the second international symposium on 3d data processing, visualization, and transmission, September 2004.
[15] Hartley, R., & Schaffalitzky, F. (2003). Powerfactorization: 3d reconstruction with missing or uncertain data (Technical report). Australian National University.
[16] Hartley, R., & Zisserman, A. (2000). Multiple view geometry in computer vision. Cambridge: Cambridge University Press. · Zbl 0956.68149
[17] Horn, B. K. P. (1987). Closed-form solution of absolute orientation using unit quaternions. Journal of Optical Society of America A, 4(4), 629–642. · doi:10.1364/JOSAA.4.000629
[18] Huynh, D. Q., Hartley, R., & Heyden, A. (2003). Outlier correction in image sequences for the affine camera. In Proceedings ICCV (Vol. 1, pp. 585–590).
[19] Huynh, D. Q., & Heyden, A. (2002). Robust factorization for the affine camera: Analysis and comparison. In Proc. seventh international conference on control, automation, robotics, and vision, Singapore, December 2002.
[20] Kanatani, K. (1998). Geometric information criterion for model selection. International Journal of Computer Vision, 26(3), 171–189. · doi:10.1023/A:1007948927139
[21] Kanatani, K. (2004). Uncertainty modeling and model selection for geometric inference. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(10), 1307–1319. · doi:10.1109/TPAMI.2004.93
[22] Luong, Q., & Faugeras, O. (1997). Self-calibration of a moving camera from point correspondences and fundamental matrices. International Journal of Computer Vision, 1, 5–40.
[23] Luong, Q.-T., & Faugeras, O. D. (2001). The geometry of multiple images. Boston: MIT Press. · Zbl 1002.68183
[24] Mahamud, S., & Hebert, M. (2000). Iterative projective reconstruction from multiple views. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR ’00) (Vol. 2, pp. 430–437). June 2000.
[25] Mahamud, S., Hebert, M., Omori, Y., & Ponce, J. (2001). Provably-convergent iterative methods for projective structure from motion. In IEEE conf. on computer vision and pattern recognition (CVPR).
[26] McLachlan, G. J., & Krishnan, T. (1997). The EM algorithm and extensions. New York: Wiley. · Zbl 0882.62012
[27] Meer, P. (2004). Robust techniques for computer vision. In Emerging topics in computer vision. Prentice Hall.
[28] Miller, D. J., & Browning, J. (2003). A mixture model and em-based algorithm for class discovery, robust classification and outlier rejection in mixed labeled/unlabeled data sets. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25(11), 1468–1483. · doi:10.1109/TPAMI.2003.1240120
[29] Miyagawa, I., & Arakawa, K. (2006). Motion and shape recovery based on iterative stabilization for modest deviation from planar motion. IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(7), 1176–1181. · doi:10.1109/TPAMI.2006.147
[30] Morris, D., & Kanade, T. (1998). A unified factorization algorithm for points, line segments and planes with uncertainty models. In Proceedings of international conference of computer vision (pp. 696–702).
[31] Oliensis, J., & Hartley, R. (2007). Iterative extensions of the sturm/triggs algorithm: Convergence and nonconvergence. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(12), 2217–2233. · doi:10.1109/TPAMI.2007.1132
[32] Rousseeuw, P. J. (1984). Least median of squares regression. Journal of the American Statistical Association, 79, 871–880. · Zbl 0547.62046 · doi:10.2307/2288718
[33] Rousseeuw, P. J., & Van Aelst, S. (1999). Positive-breakdown robust methods in computer vision. In Berk, & Pourahmadi (Eds.), Computing science and statistics (Vol. 31, pp. 451–460). Interface Foundation of North America.
[34] Roweis, S. (1997). EM algorithm for PCA and SPCA. Proceedings NIPS, 10, 626–632.
[35] Shum, H., Ikeuchi, K., & Reddy, R. (1995). Principal component analysis with missing data and its application to polyhedral object modeling. IEEE Transactions on Pattern Analysis and Machine Intelligence, 17(9), 855–867. · doi:10.1109/34.406651
[36] Stewart, C. V. (1999). Robust parameter estimation in computer vision. SIAM Review, 41(3), 513–537. · Zbl 0933.68144 · doi:10.1137/S0036144598345802
[37] Sturm, P., & Triggs, W. (1996). A factorization based algorithm for multi-image projective structure and motion. In LNCS : Vol. 1065. Proceedings of the 4th European conference on computer vision (pp. 709–720). Cambridge, England. Berlin: Springer.
[38] Tardif, J.P., Bartoli, A., Trudeau, M., Guilbert, N., & Roy, S. (2007). Algorithms for batch matrix factorization with application to structure-from-motion. In Proc. of IEEE conference on computer vision and pattern recognition, Minneapolis, USA, June 2007.
[39] Tomasi, C., & Kanade, T. (1992). Shape and motion from image streams under orthography: a factorization method. International Journal of Computer Vision, 9(2), 137–154. · doi:10.1007/BF00129684
[40] Trajkovic, M., & Hedley, M. (2007). Robust recursive structure and motion recovery under affine projection. In Proc. of the British machine vision conference, September 1997.
[41] Triggs, W., McLauchlan, P., Hartley, R., & Fitzgibbon, A. (2000). Bundle adjustment–a modern synthesis. In LNCS. Vision algorithms: theory and practice (pp. 298–375).
[42] Vidal, R., & Hartley, R. (2004). Motion segmentation with missing data using powerfactorization and GPCA. In Proceedings CVPR (Vol. 2, pp. 310–316).
[43] Walker, M. W., Shao, L., & Volz, R. A. (1991). Estimating 3-d location parameters using dual number quaternions. CGVIP-Image Understanding, 54(3), 358–367. · Zbl 0777.68102 · doi:10.1016/1049-9660(91)90036-O
[44] Wiberg, T. (1976). Computation of principal components when data are missing. In Proceedings symposium of computational statistics (pp. 229–326). · Zbl 0385.62038
[45] Zaharescu, A., Horaud, R., Ronfard, R., & Lefort, L. (2006). Multiple camera calibration using robust perspective factorization. In Proceedings of the 3rd international symposium on 3d data processing, visualization and transmission, Chapel Hill, USA. IEEE Computer Society Press.
[46] Zaharescu, A., Boyer, E., & Horaud, R. P. (2007). Transformesh: a topology-adaptive mesh-based approach to surface evolution. In Proceedings of the eighth Asian conference on computer vision, LNCS, Tokyo, Japan, November 2007. Springer.
[47] Zhang, Z. (2000). A flexible new technique for camera calibration. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(11), 1330–1334. · doi:10.1109/34.888718
[48] Zhang, Z. (2004). Camera calibration with one-dimensional objects. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(7), 892–899. · doi:10.1109/TPAMI.2004.21
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.