Efficient Articulated Trajectory Reconstruction Using Dynamic Programming and Filters

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7572)


This paper considers the problem of reconstructing the motion of a 3D articulated tree from 2D point correspondences subject to some temporal prior. Hitherto, smooth motion has been encouraged using a trajectory basis, yielding a hard combinatorial problem with time complexity growing exponentially in the number of frames. Branch and bound strategies have previously attempted to curb this complexity whilst maintaining global optimality. However, they provide no guarantee of being more efficient than exhaustive search. Inspired by recent work which reconstructs general trajectories using compact high-pass filters, we develop a dynamic programming approach which scales linearly in the number of frames, leveraging the intrinsically local nature of filter interactions. Extension to affine projection enables reconstruction without estimating cameras.


Basis Size Perspective Camera Articulation Constraint Trajectory Reconstruction Trajectory Basis 
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.


  1. 1.
    Park, H.S., Sheikh, Y.A.: 3D reconstruction of a smooth articulated trajectory from a monocular image sequence. In: ICCV, pp. 201–208. IEEE (2011)Google Scholar
  2. 2.
    Akhter, I., Sheikh, Y.A., Khan, S., Kanade, T.: Nonrigid structure from motion in trajectory space. In: NIPS. MIT Press (2008)Google Scholar
  3. 3.
    Park, H.S., Shiratori, T., Matthews, I., Sheikh, Y.: 3D Reconstruction of a Moving Point from a Series of 2D Projections. In: Daniilidis, K. (ed.) ECCV 2010, Part III. LNCS, vol. 6313, pp. 158–171. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  4. 4.
    Bregler, C., Hertzmann, A., Biermann, H.: Recovering non-rigid 3D shape from image streams. In: CVPR, vol. 2, pp. 690–696. IEEE (2000)Google Scholar
  5. 5.
    Valmadre, J., Lucey, S.: General trajectory prior for non-rigid reconstruction. In: CVPR. IEEE (2012)Google Scholar
  6. 6.
    Zhu, Y., Cox, M., Lucey, S.: 3D motion reconstruction for real-world camera motion. In: CVPR. IEEE (2011)Google Scholar
  7. 7.
    Gotardo, P.F.U., Martinez, A.M.: Non-rigid structure from motion with complementary rank-3 spaces. In: CVPR, pp. 3065–3072. IEEE (2011)Google Scholar
  8. 8.
    Akhter, I., Simon, T., Khan, S., Matthews, I., Sheikh, Y.A.: Bilinear spatiotemporal basis models. In: SIGGRAPH. ACM Press (2012)Google Scholar
  9. 9.
    Dai, Y., Li, H., He, M.: A simple prior-free method for non-rigid structure-from-motion factorization. In: CVPR (2012)Google Scholar
  10. 10.
    Tresadern, P.A., Reid, I.: Articulated structure from motion by factorization. In: CVPR, vol. 2, pp. 1110–1115. IEEE (2005)Google Scholar
  11. 11.
    Yan, J., Pollefeys, M.: A factorization-based approach to articulated motion recovery. In: CVPR, vol. 2, pp. 815–821. IEEE (2005)Google Scholar
  12. 12.
    Paladini, M., Del Bue, A., Stošić, M., Dodig, M., Xavier, J., Agapito, L.: Factorization for non-rigid and articulated structure using metric projections. In: CVPR, pp. 2898–2905. IEEE (2009)Google Scholar
  13. 13.
    Fayad, J., Russell, C., Agapito, L.: Automated articulated structure and 3D shape recovery from point correspondences. In: ICCV, pp. 431–438. IEEE (2011)Google Scholar
  14. 14.
    Sidenbladh, H., Black, M.J., Fleet, D.J.: Stochastic Tracking of 3D Human Figures Using 2D Image Motion. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1843, pp. 702–718. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  15. 15.
    Sminchisescu, C., Triggs, B.: Kinematic jump processes for monocular 3D human tracking. In: CVPR, vol. 1, pp. 69–76. IEEE (2003)Google Scholar
  16. 16.
    Urtasun, R., Fleet, D.J., Fua, P.: 3D people tracking with Gaussian Process Dynamical Models. In: CVPR, vol. 1, pp. 238–245. IEEE (2006)Google Scholar
  17. 17.
    Andriluka, M., Roth, S., Schiele, B.: Monocular 3D pose estimation and tracking by detection. In: CVPR, pp. 623–630. IEEE (2010)Google Scholar
  18. 18.
    Brubaker, M.A., Fleet, D.J.: The Kneed Walker for human pose tracking. In: CVPR. IEEE (2008)Google Scholar
  19. 19.
    Wei, X., Chai, J.: VideoMocap: Modeling physically realistic human motion from monocular video sequences. In: SIGGRAPH. ACM Press (2010)Google Scholar
  20. 20.
    Taylor, C.J.: Reconstruction of articulated objects from point correspondences in a single uncalibrated image. In: CVPR, pp. 677–684. IEEE (2000)Google Scholar
  21. 21.
    Parameswaran, V., Chellappa, R.: View independent human body pose estimation from a single perspective image. In: CVPR, pp. 16–22. IEEE (2004)Google Scholar
  22. 22.
    Barrón, C., Kakadiaris, I.A.: Estimating anthropometry and pose from a single uncalibrated image. Computer Vision and Image Understanding 81(3), 269–284 (2001)zbMATHCrossRefGoogle Scholar
  23. 23.
    Wei, X., Chai, J.: Modeling 3D human poses from uncalibrated monocular images. In: ICCV. IEEE (2009)Google Scholar
  24. 24.
    Agarwal, A., Triggs, B.: Recovering 3D human pose from monocular images. PAMI 28, 44–58 (2006)CrossRefGoogle Scholar
  25. 25.
    Salzmann, M., Urtasun, R.: Physically-based motion models for 3D tracking: A convex formulation. In: ICCV, pp. 2064–2071. IEEE (2011)Google Scholar
  26. 26.
    Micusik, B.: Trajectory reconstruction from non-overlapping surveillance cameras with relative depth ordering constraints. In: ICCV, pp. 922–928. IEEE (2011)Google Scholar
  27. 27.
    Martucci, S.A.: Symmetric convolution and the discrete sine and cosine transforms. IEEE Transactions on Signal Processing 42(5), 1038–1051 (1994)CrossRefGoogle Scholar
  28. 28.
    Bishop, C.M.: Pattern Recognition and Machine Learning. Springer (2007)Google Scholar
  29. 29.
    Felzenszwalb, P.F., Zabih, R.: Dynamic programming and graph algorithms in computer vision. PAMI 33(4), 721–740 (2011)CrossRefGoogle Scholar
  30. 30.
    Valmadre, J., Lucey, S.: Deterministic 3D Human Pose Estimation using Rigid Structure. In: Daniilidis, K. (ed.) ECCV 2010, Part III. LNCS, vol. 6313, pp. 467–480. Springer, Heidelberg (2010)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  1. 1.Queensland University of TechnologyAustralia
  2. 2.University of QueenslandAustralia
  3. 3.Commonwealth Scientific and Industrial Research OrganisationAustralia

Personalised recommendations