Abstract
Computing a 1-dimensional linear subspace is an important problem in many computer vision algorithms. Its importance stems from the fact that maximizing a linear homogeneous equation system can be interpreted as subspace fitting problem. It is trivial to compute the solution if all coefficients of the equation system are known, yet for the case of incomplete data, only approximation methods based on variations of gradient descent have been developed.
In this work, an algorithm is presented in which the data is embedded in projective spaces. We prove that the intersection of these projective spaces is identical to the desired subspace. Whereas other algorithms approximate this subspace iteratively, computing the intersection of projective spaces defines a linear problem. This solution is therefore not an approximation but exact in the absence of noise. We derive an upper boundary on the number of missing entries the algorithm can handle. Experiments with synthetic data confirm that the proposed algorithm successfully fits subspaces to data even if more than 90% of the data is missing. We demonstrate an example application with real image sequences.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Ackermann, H., Rosenhahn, B.: Trajectory Reconstruction for Affine Structure-from-Motion by Global and Local Constraints. In: IEEE Computer Vision and Pattern Recognition (CVPR), Miami, Florida, USA (June 2009)
Aguiar, P., Xavier, J., Stosic, M.: Spectrally Optimal Factorization of Incomplete Matrices. In: IEEE Computer Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1–8 (2008)
Brand, M.: Incremental singular value decomposition of uncertain data with missing values. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 707–720. Springer, Heidelberg (2002)
Buchanan, A., Fitzgibbon, A.: Damped Newton Algorithms for Matrix Factorization with Missing Data. In: IEEE Computer Vision and Pattern Recognition (CVPR), Washington, DC, USA, pp. 316–322 (2005)
Cai, J.-F., Candès, E.J., Shen, Z.: A singular value thresholding algorithm for matrix completion. SIAM Journal on Optimization 20(4), 1956–1982 (2010)
Candès, E.J., Recht, B.: Exact matrix completion via convex optimization. Foundations of Computational Mathematics 9(6), 717–772 (2009)
Chen, P., Suter, D.: Recovering the Missing Components in a Large Noisy Low-Rank Matrix: Application to SFM. IEEE Transactions on Pattern Analyis and Machine Intelligence 26(8), 1051–1063 (2004)
Dempster, A., Laird, N., Rubin, D.: Maximum likelihood from incomplete data via the em algorithm. Journal of the Royal Statistical Society. Series B (Methodological) 39(1), 1–38 (1977)
Fazel, M.: Matrix Rank Minimization with Applications. PhD thesis, Dept. Electrical Engineering, Stanford University (March 2002)
Gabriel, K., Zamir, S.: Lower rank approximation of matrices by least squares with any choice of weights. Techonometrics 21(4), 489–498 (1979)
Hartley, R., Schaffalizky, F.: PowerFactorization: 3D Reconstruction with Missing or Uncertain Data. In: Australia-Japan Advanced Workshop on Computer Vision (June 2002)
Heyden, A., Berthilsson, R., Sparr, G.: An Iterative Factorization Method for Projective Structure and Motion from Image Sequences. Image and Vision Computing 17(13), 981–991 (1999)
Jacobs, D.W.: Linear fitting with missing data for structure-from-motion. Computer Vision and Image Understanding 82(1), 57–81 (2001)
Kanatani, K.: Statistical Optimization for Geometric Computation: Theory and Practice. Elsevier Science Inc., New York (1996)
Mahamud, S., Hebert, M.: Iterative Projective Reconstruction from Multiple Views. In: IEEE Computer Vision and Pattern Recognition (CVPR), Hilton Head, SC, USA, pp. 430–437 (June 2000)
Marquez, M., Costeira, J.: Optimal Shape from Motion Estimation with Missing and Degenerate Data. In: IEEE Workshop on Application of Computer Vision (WACV), Copper Mountain, CO, USA (January 2008)
Ruhe, A.: Numerical computation of principal components when several observations are missing. Technical report, Dept. Information Processing, University of Umeda, Umeda, Sweden (April 1974)
Ruhe, A., Wedin, P.: Algorithms for separable nonlinear least squares problems. Society for Industrial and Applied Mathematics Review 22(3), 318–337 (1980)
Sugaya, Y., Kanatani, K.: Extending interrupted feature point tracking for 3-D affine reconstruction. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3021, pp. 310–321. Springer, Heidelberg (2004)
Tomasi, C., Kanade, T.: Shape and motion from image streams under orthography: A factorization method. International Journal of Computer Vision 9(2), 137–154 (1992)
Tsai, R.: A versatile camera calibration technique for high-accuracy 3-d machine vision metrology using off-the-shelf cameras and lenses. IEEE Transaction on Robotics and Automation 3(4), 323–344 (1987)
Wiberg, T.: Computation of principal components when data are missing. In: Second Symp. on Computational Statistics, Berlin, Germany, pp. 229–236 (1976)
Wold, H.: Estimation of principal components and related models by iterative least squares. In: Krishnaiah (ed.) Multivariate Analysis, pp. 391–420 (1966)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ackermann, H., Rosenhahn, B. (2011). A Linear Solution to 1-Dimensional Subspace Fitting under Incomplete Data. In: Kimmel, R., Klette, R., Sugimoto, A. (eds) Computer Vision – ACCV 2010. ACCV 2010. Lecture Notes in Computer Science, vol 6493. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-19309-5_36
Download citation
DOI: https://doi.org/10.1007/978-3-642-19309-5_36
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-19308-8
Online ISBN: 978-3-642-19309-5
eBook Packages: Computer ScienceComputer Science (R0)