Abstract
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.
Chapter PDF
References
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)
Akhter, I., Sheikh, Y.A., Khan, S., Kanade, T.: Nonrigid structure from motion in trajectory space. In: NIPS. MIT Press (2008)
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)
Bregler, C., Hertzmann, A., Biermann, H.: Recovering non-rigid 3D shape from image streams. In: CVPR, vol. 2, pp. 690–696. IEEE (2000)
Valmadre, J., Lucey, S.: General trajectory prior for non-rigid reconstruction. In: CVPR. IEEE (2012)
Zhu, Y., Cox, M., Lucey, S.: 3D motion reconstruction for real-world camera motion. In: CVPR. IEEE (2011)
Gotardo, P.F.U., Martinez, A.M.: Non-rigid structure from motion with complementary rank-3 spaces. In: CVPR, pp. 3065–3072. IEEE (2011)
Akhter, I., Simon, T., Khan, S., Matthews, I., Sheikh, Y.A.: Bilinear spatiotemporal basis models. In: SIGGRAPH. ACM Press (2012)
Dai, Y., Li, H., He, M.: A simple prior-free method for non-rigid structure-from-motion factorization. In: CVPR (2012)
Tresadern, P.A., Reid, I.: Articulated structure from motion by factorization. In: CVPR, vol. 2, pp. 1110–1115. IEEE (2005)
Yan, J., Pollefeys, M.: A factorization-based approach to articulated motion recovery. In: CVPR, vol. 2, pp. 815–821. IEEE (2005)
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)
Fayad, J., Russell, C., Agapito, L.: Automated articulated structure and 3D shape recovery from point correspondences. In: ICCV, pp. 431–438. IEEE (2011)
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)
Sminchisescu, C., Triggs, B.: Kinematic jump processes for monocular 3D human tracking. In: CVPR, vol. 1, pp. 69–76. IEEE (2003)
Urtasun, R., Fleet, D.J., Fua, P.: 3D people tracking with Gaussian Process Dynamical Models. In: CVPR, vol. 1, pp. 238–245. IEEE (2006)
Andriluka, M., Roth, S., Schiele, B.: Monocular 3D pose estimation and tracking by detection. In: CVPR, pp. 623–630. IEEE (2010)
Brubaker, M.A., Fleet, D.J.: The Kneed Walker for human pose tracking. In: CVPR. IEEE (2008)
Wei, X., Chai, J.: VideoMocap: Modeling physically realistic human motion from monocular video sequences. In: SIGGRAPH. ACM Press (2010)
Taylor, C.J.: Reconstruction of articulated objects from point correspondences in a single uncalibrated image. In: CVPR, pp. 677–684. IEEE (2000)
Parameswaran, V., Chellappa, R.: View independent human body pose estimation from a single perspective image. In: CVPR, pp. 16–22. IEEE (2004)
Barrón, C., Kakadiaris, I.A.: Estimating anthropometry and pose from a single uncalibrated image. Computer Vision and Image Understanding 81(3), 269–284 (2001)
Wei, X., Chai, J.: Modeling 3D human poses from uncalibrated monocular images. In: ICCV. IEEE (2009)
Agarwal, A., Triggs, B.: Recovering 3D human pose from monocular images. PAMI 28, 44–58 (2006)
Salzmann, M., Urtasun, R.: Physically-based motion models for 3D tracking: A convex formulation. In: ICCV, pp. 2064–2071. IEEE (2011)
Micusik, B.: Trajectory reconstruction from non-overlapping surveillance cameras with relative depth ordering constraints. In: ICCV, pp. 922–928. IEEE (2011)
Martucci, S.A.: Symmetric convolution and the discrete sine and cosine transforms. IEEE Transactions on Signal Processing 42(5), 1038–1051 (1994)
Bishop, C.M.: Pattern Recognition and Machine Learning. Springer (2007)
Felzenszwalb, P.F., Zabih, R.: Dynamic programming and graph algorithms in computer vision. PAMI 33(4), 721–740 (2011)
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)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Valmadre, J., Zhu, Y., Sridharan, S., Lucey, S. (2012). Efficient Articulated Trajectory Reconstruction Using Dynamic Programming and Filters. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds) Computer Vision – ECCV 2012. ECCV 2012. Lecture Notes in Computer Science, vol 7572. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33718-5_6
Download citation
DOI: https://doi.org/10.1007/978-3-642-33718-5_6
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33717-8
Online ISBN: 978-3-642-33718-5
eBook Packages: Computer ScienceComputer Science (R0)