Advertisement

Euclidean Structure Recovery from Motion in Perspective Image Sequences via Hankel Rank Minimization

  • Mustafa Ayazoglu
  • Mario Sznaier
  • Octavia Camps
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6312)

Abstract

In this paper we consider the problem of recovering 3D Euclidean structure from multi-frame point correspondence data in image sequences under perspective projection. Existing approaches rely either only on geometrical constraints reflecting the rigid nature of the object, or exploit temporal information by recasting the problem into a nonlinear filtering form. In contrast, here we introduce a new constraint that implicitly exploits the temporal ordering of the frames, leading to a provably correct algorithm to find Euclidean structure (up to a single scaling factor) without the need to alternate between projective depth and motion estimation, estimate the Fundamental matrices or assume a camera motion model. Finally, the proposed approach does not require an accurate calibration of the camera. The accuracy of the algorithm is illustrated using several examples involving both synthetic and real data.

Keywords

Ground Truth Data Perspective Projection Bundle Adjustment Hankel Matrix Linear Time Invariant 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Supplementary material

978-3-642-15552-9_6_MOESM1_ESM.avi (217 kb)
Electronic Supplementary Material (217 KB)
978-3-642-15552-9_6_MOESM2_ESM.avi (216 kb)
Electronic Supplementary Material (216 KB)
978-3-642-15552-9_6_MOESM3_ESM.avi (206 kb)
Electronic Supplementary Material (207 KB)
978-3-642-15552-9_6_MOESM4_ESM.avi (182 kb)
Electronic Supplementary Material (183 KB)
978-3-642-15552-9_6_MOESM5_ESM.avi (179 kb)
Electronic Supplementary Material (179 KB)
978-3-642-15552-9_6_MOESM6_ESM.avi (178 kb)
Electronic Supplementary Material (178 KB)
978-3-642-15552-9_6_MOESM7_ESM.avi (183 kb)
Electronic Supplementary Material (184 KB)
978-3-642-15552-9_6_MOESM8_ESM.avi (164 kb)
Electronic Supplementary Material (164 KB)
978-3-642-15552-9_6_MOESM9_ESM.avi (161 kb)
Electronic Supplementary Material (162 KB)
978-3-642-15552-9_6_MOESM10_ESM.avi (159 kb)
Electronic Supplementary Material (159 KB)
978-3-642-15552-9_6_MOESM11_ESM.avi (164 kb)
Electronic Supplementary Material (164 KB)
978-3-642-15552-9_6_MOESM12_ESM.avi (853 kb)
Electronic Supplementary Material (853 KB)
978-3-642-15552-9_6_MOESM13_ESM.avi (813 kb)
Electronic Supplementary Material (813 KB)
978-3-642-15552-9_6_MOESM14_ESM.avi (809 kb)
Electronic Supplementary Material (810 KB)
978-3-642-15552-9_6_MOESM15_ESM.avi (884 kb)
Electronic Supplementary Material (885 KB)

References

  1. 1.
    Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge Univeristy Press, Cambridge (2003)Google Scholar
  2. 2.
    Faugeras, O.D., Luong, Q.T., Papadopoulo, T.: The Geometry of Multiple Images. MIT Press, Cambridge (2001)zbMATHGoogle Scholar
  3. 3.
    Tomasi, C., Kanade, T.: Shape and motion from image streams under orthography: a factorization method. International Journal of Computer Vision 9, 137–154 (1992)CrossRefGoogle Scholar
  4. 4.
    Morita, T., Kanade, T.: A paraperspective factorization method for recovering shape and motion from image sequences. IEEE Trans. on PAMI 19, 858–867 (1997)Google Scholar
  5. 5.
    Poelman, C.J., Kanade, T.: A paraperspective factorization method for shape and motion recovery. IEEE Transactions on PAMI 19, 206–218 (1997)Google Scholar
  6. 6.
    Sturm, P., Triggs, B.: A factorization based algorithm for multi-image projective structure and motion. In: Buxton, B.F., Cipolla, R. (eds.) ECCV 1996. LNCS, vol. 1065, pp. 709–720. Springer, Heidelberg (1996)Google Scholar
  7. 7.
    Triggs, B.: Factorization methods for projective structure and motion. In: IEEE CVPR (1996)Google Scholar
  8. 8.
    Sparr, G.: Simultaneous reconstruction of scene structure and camera locations from uncalibrated image sequences. In: Int. Conf. on Pattern Recognition (1996)Google Scholar
  9. 9.
    Chen, G., Medioni, G.: Efficient iterative solutions to m-view projective reconstruction problem. In: IEEE CVPR, vol. 2, pp. 55–61 (1999)Google Scholar
  10. 10.
    Mahamud, S., Hebert, M.: Iterative projective reconstruction from multiple views. In: IEEE CVPR, vol. 2, pp. 430–437 (2000)Google Scholar
  11. 11.
    Hung, Y., Tang, W.: Projective reconstruction from multiple views with minimization of 2d reprojection error. International Journal of Computer Vision 66, 305–317 (2006)CrossRefGoogle Scholar
  12. 12.
    Mohr, R., Veillon, F., Quan, L.: Relative 3d reconstruction using multiple uncalibrated images. In: IEEE CVPR, pp. 543–548 (1993)Google Scholar
  13. 13.
    Hartley, R.: Euclidean reconstruction from uncalibrated views. In: Mundy, J.L., Zisserman, A., Forsyth, D. (eds.) AICV 1993. LNCS, vol. 825, pp. 237–256. Springer, Heidelberg (1994)Google Scholar
  14. 14.
    Morris, D., Kanatani, K., Kanade, T.: Euclidean reconstruction from uncalibrated views. In: Triggs, B., Zisserman, A., Szeliski, R. (eds.) ICCV-WS 1999. LNCS, vol. 1883, pp. 298–375. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  15. 15.
    Shum, H.Y., Ke, Q., Zhang, Z.: Efficient bundle adjustment with virtual key frames: A hierarchical approach to multi-frame structure from motion. In: IEEE CVPR (1999)Google Scholar
  16. 16.
    Triggs, B., McLauchlan, P., Hartley, R., Fitzgibbon, A.: Bundle adjustment-a modern synthesis. In: Triggs, B., Zisserman, A., Szeliski, R. (eds.) ICCV-WS 1999. LNCS, vol. 1883, pp. 298–375. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  17. 17.
    Bartoli, A., Sturm, P.: Three new algorithms for projective bundle adjustment with minimum parameters. Technical Report 4236, INRIA (2001)Google Scholar
  18. 18.
    Oliensis, J.: Fast and accurate self-calibration. In: ICCV, pp. 745–752 (1996)Google Scholar
  19. 19.
    Mahamud, S., Hebert, M., Omori, Y., Ponce, J.: Provably convergent iterative methods for projective structure frommotion. In: IEEE CVPR, pp. 1018–1025 (2001)Google Scholar
  20. 20.
    Oliensis, J., Hartley, R.: Iterative extensions of the strum/triggs algorithm: convergence and nonconvergence. IEEE Trans. on PAMI 29, 2217–2233 (2007)Google Scholar
  21. 21.
    Davison, A.J., Reid, I.D., Molton, N.D., Stasse, O.: Monoslam: Real time single camera slam. IEEE Trans. on PAMI 29, 1052–1067 (2007)Google Scholar
  22. 22.
    Klein, G., Murray, D.: Parallel tracking and mapping for small AR workspaces. In: Proc. ISMAR 2007, Nara, Japan (November 2007)Google Scholar
  23. 23.
    Orsi, R.: LMIRank: software for rank constrained lmi problems (web page and software) (2005), http://rsise.anu.edu.au/robert/lmirank/
  24. 24.
    Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. ACM Comm. 24, 381–395 (1981)CrossRefMathSciNetGoogle Scholar
  25. 25.
    Kailath, T.: Linear Systems. Prentice-Hall, Englewood Cliffs (1980)zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Mustafa Ayazoglu
    • 1
  • Mario Sznaier
    • 1
  • Octavia Camps
    • 1
  1. 1.Department of Electrical and Computer EngineeringNortheastern UniversityBostonUSA

Personalised recommendations