Abstract
We present a novel method for estimation of articulated motion in depth scans. The method is based on a framework for regularization of vector- and matrix- valued functions on parametric surfaces.
We extend augmented-Lagrangian total variation regularization to smooth rigid motion cues on the scanned 3D surface obtained from a range scanner. We demonstrate the resulting smoothed motion maps to be a powerful tool in articulated scene understanding, providing a basis for rigid parts segmentation, with little prior assumptions on the scene, despite the noisy depth measurements that often appear in commodity depth scanners.
Keywords
References
Adiv, G.: Determining three-dimensional motion structure from optic flow generated by several moving object. IEEE Trans. PAMI 7(4), 384–401 (1985)
Anguelov, D., Koller, D., Pang, H.-C., Srinivasan, P., Thrun, S.: Recovering articulated object models from 3D range data. In: Proc. Conf. on Uncertainty in Artificial Intelligence, pp. 18–26. AUAI Press (2004)
Benhabiles, H., Lavoué, G., Vandeborre, J.-P., Daoudi, M.: Learning boundary edges for 3D-mesh segmentation. Comp. Graphics Forum (2011)
Besl, P.J., McKay, N.D.: A method for registration of 3D shapes. IEEE Trans. PAMI 14(2), 239–256 (1992)
Bronstein, A.M., Bronstein, M.M., Kimmel, R.: Generalized multidimensional scaling: a framework for isometry-invariant partial surface matching. Proc. Natl. Acad. Sci. USA 103(5), 1168–1172 (2006)
Brox, T., Rousson, M., Deriche Dr., R., Weickert, J.: Colour, texture, and motion in level set based segmentation and tracking. Image and Vision Computing 28(3), 376–390 (2010)
Celledoni, E., Owren, B.: Lie group methods for rigid body dynamics and time integration on manifolds. Computer Methods in Applied Mechanics and Engineering 19, 421–438 (1999)
Chen, H., Bhanu, B.: 3D free form object recognition in range images using local surface patches. Pattern Recognition Letters 28, 1252–1262 (2007)
Chen, Y., Medioni, G.: Object modelling by registration of multiple range images. Image Vision Comput. 10, 145–155 (1992)
Comaniciu, D., Meer, P.: Mean shift: A robust approach toward feature space analysis. IEEE Trans. PAMI 24, 603–619 (2002)
Combettes, P.L., Pesquet, J.-C.: Proximal splitting methods in signal processing (May 2010)
Cremers, D., Soatto, S.: Motion competition: A variational framework for piecewise parametric motion segmentation. IJCV 62(3), 249–265 (2005)
do Carmo, M.P.: Differential Geometry of Curves and Surfaces. Prentice-Hall (1976)
Fayad, J., Russell, C., de Agapito, L.: Automated articulated structure and 3D shape recovery from point correspondences. In: ICCV, pp. 431–438 (2011)
Hall, B.C.: Lie Groups, Lie Algebras,and Representations, An Elementary Introduction. Springer (2004)
Hesteness, M.R.: Multipliers and gradient methods. J. of Optimization Theory and Applications 4, 303–320 (1969)
Kim, E., Medioni, G.G.: 3D object recognition in range images using visibility context. In: IROS, pp. 3800–3807 (2011)
Kobilarov, M., Crane, K., Desbrun, M.: Lie group integrators for animation and control of vehicles. ACM Trans. Graph. 28(2), 1–14 (2009)
Lai, R., Chan, T.F.: A framework for intrinsic image processing on surfaces. Comput. Vis. Image Underst. 115, 1647–1661 (2011)
Larochelle, P.M., Murray, A.P., Angeles, J.: A Distance Metric for Finite Sets of Rigid-Body Displacements via the Polar Decomposition. Journal of Mechanical Design 129 (2007)
Li, H., Sumner, R.W., Pauly, M.: Global correspondence optimization for non-rigid registration of depth scans. Computer Graphics Forum 27(5) (July 2008)
Lin, D., Grimson, W., Fisher, J.: Learning visual flows: A Lie algebraic approach. In: CVPR, pp. 747–754 (2009)
Lo, T.-W.R., Siebert, J.P.: Local feature extraction and matching on range images: 2.5D SIFT. Comput. Vis. Image Underst. 113, 1235–1250 (2009)
Myronenko, A., Song, X.B.: Point-set registration: Coherent point drift. CoRR, abs/0905.2635 (2009)
Nir, T., Bruckstein, A.M., Kimmel, R.: Over-parameterized variational optical flow. IJCV 76(2), 205–216 (2008)
Paladini, M., Del Bue, A., Xavier, J.a., Agapito, L., Stošić, M., Dodig, M.: Optimal metric projections for deformable and articulated Structure-from-Motion. IJCV, 1–25 (July 2011)
Park, F.C., Bobrow, J.E., Ploen, S.R.: A Lie group formulation of robot dynamics. Int. J. Rob. Res. 14, 609–618 (1995)
Powell, M.J.: A method for nonlinear constraints in minimization problems. In: Optimization. Academic Press (1969)
Rosman, G., Bronstein, M.M., Bronstein, A.M., Kimmel, R.: Articulated motion segmentation of point clouds by group-valued regularization. In: Eurographics Workshop on 3D Object Retrieval (2012)
Rosman, G., Shem-Tov, S., Bitton, D., Nir, T., Adiv, G., Kimmel, R., Feuer, A., Bruckstein, A.M.: Over-Parameterized Optical Flow Using a Stereoscopic Constraint. In: Bruckstein, A.M., ter Haar Romeny, B.M., Bronstein, A.M., Bronstein, M.M. (eds.) SSVM 2011. LNCS, vol. 6667, pp. 761–772. Springer, Heidelberg (2012)
Rosman, G., Wang, Y., Tai, X.-C., Kimmel, R., Bruckstein, A.M.: Fast Regularization of Matrix-Valued Images. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part III. LNCS, vol. 7574, pp. 173–186. Springer, Heidelberg (2012)
Rudin, L.I., Osher, S., Fatemi, E.: Nonlinear total variation based noise removal algorithms. Physica D Letters 60, 259–268 (1992)
Shotton, J., Fitzgibbon, A., Cook, M., Sharp, T., Finocchio, M., Moore, R., Kipman, A., Blake, A.: Real-Time human pose recognition in parts from single depth images (June 2011)
Spira, A., Kimmel, R.: Geometric curve flows on parametric manifolds. J. Comput. Phys. 223, 235–249 (2007)
Subbarao, R., Meer, P.: Nonlinear mean shift over Riemannian manifolds. IJCV 84(1), 1–20 (2009)
Tai, X.-C., Wu, C.: Augmented Lagrangian method, dual methods and split Bregman iteration for ROF model. In: SSVM, pp. 502–513 (2009)
Tuzel, O., Porikli, F., Meer, P.: Learning on Lie groups for invariant detection and tracking. In: CVPR (2008)
Žefran, M., Kumar, V., Croke, C.: On the generation of smooth three-dimensional rigid body motions. IEEE Transactions on Robotics and Automation 14(4), 576–589 (1998)
Wang, Y., Yang, J., Yin, W., Zhang, Y.: A new alternating minimization algorithm for total variation image reconstruction. SIAM J. Imag. Sci. 1(3), 248–272 (2008)
Wu, C., Zhang, J., Duan, Y., Tai, X.-C.: Augmented lagrangian method for total variation based image restoration and segmentation over triangulated surfaces. J. Sci. Comput. 50(1), 145–166 (2012)
Yacoob, Y., Davis, L.S.: Learned models for estimation of rigid and articulated human motion from stationary or moving camera. IJCV 36, 5–30 (2000)
Zhang, Y., Kambhamettu, C.: Integrated 3D scene flow and structure recovery from multiview image sequences. In: CVPR, vol. 2, p. 2674 (2000)
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
Rosman, G., Bronstein, A.M., Bronstein, M.M., Tai, XC., Kimmel, R. (2012). Group-Valued Regularization for Analysis of Articulated Motion. In: Fusiello, A., Murino, V., Cucchiara, R. (eds) Computer Vision – ECCV 2012. Workshops and Demonstrations. ECCV 2012. Lecture Notes in Computer Science, vol 7583. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33863-2_6
Download citation
DOI: https://doi.org/10.1007/978-3-642-33863-2_6
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33862-5
Online ISBN: 978-3-642-33863-2
eBook Packages: Computer ScienceComputer Science (R0)