Efficient Articulated Trajectory Reconstruction Using Dynamic Programming and Filters

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.

[1]  David J. Fleet,et al.  Stochastic Tracking of 3D Human Figures Using 2D Image Motion , 2000, ECCV.

[2]  Simon Lucey,et al.  3D motion reconstruction for real-world camera motion , 2011, CVPR 2011.

[3]  Branislav Micusík,et al.  Trajectory reconstruction from non-overlapping surveillance cameras with relative depth ordering constraints , 2011, 2011 International Conference on Computer Vision.

[4]  Cristian Sminchisescu,et al.  Kinematic jump processes for monocular 3D human tracking , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[5]  Yaser Sheikh,et al.  Bilinear spatiotemporal basis models , 2012, TOGS.

[6]  Camillo J. Taylor,et al.  Reconstruction of Articulated Objects from Point Correspondences in a Single Uncalibrated Image , 2000, Comput. Vis. Image Underst..

[7]  Henning Biermann,et al.  Recovering non-rigid 3D shape from image streams , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[8]  Stephen A. Martucci,et al.  Symmetric convolution and the discrete sine and cosine transforms , 1993, IEEE Trans. Signal Process..

[9]  Lourdes Agapito,et al.  Automated articulated structure and 3D shape recovery from point correspondences , 2011, 2011 International Conference on Computer Vision.

[10]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[11]  Yaser Sheikh,et al.  3D reconstruction of a smooth articulated trajectory from a monocular image sequence , 2011, 2011 International Conference on Computer Vision.

[12]  Jinxiang Chai,et al.  Modeling 3D human poses from uncalibrated monocular images , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[13]  Alessio Del Bue,et al.  Factorization for non-rigid and articulated structure using metric projections , 2009, CVPR.

[14]  Raquel Urtasun,et al.  Physically-based motion models for 3D tracking: A convex formulation , 2011, 2011 International Conference on Computer Vision.

[15]  Bernt Schiele,et al.  Monocular 3D pose estimation and tracking by detection , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[16]  Simon Lucey,et al.  General trajectory prior for Non-Rigid reconstruction , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  Jinxiang Chai,et al.  VideoMocap: modeling physically realistic human motion from monocular video sequences , 2010, ACM Trans. Graph..

[18]  Ian D. Reid,et al.  Articulated structure from motion by factorization , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[19]  Ankur Agarwal,et al.  Recovering 3D human pose from monocular images , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Hongdong Li,et al.  A simple prior-free method for non-rigid structure-from-motion factorization , 2012, CVPR.

[21]  Marc Pollefeys,et al.  A Factorization-Based Approach to Articulated Motion Recovery , 2005, CVPR.

[22]  R. Chellappa,et al.  View independent human body pose estimation from a single perspective image , 2004, CVPR 2004.

[23]  Yaser Sheikh,et al.  3D Reconstruction of a Moving Point from a Series of 2D Projections , 2010, ECCV.

[24]  David J. Fleet,et al.  The Kneed Walker for human pose tracking , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[25]  Rama Chellappa,et al.  View independent human body pose estimation from a single perspective image , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[26]  Ioannis A. Kakadiaris,et al.  Estimating Anthropometry and Pose from a Single Uncalibrated Image , 2001, Comput. Vis. Image Underst..

[27]  Aleix M. Martínez,et al.  Non-rigid structure from motion with complementary rank-3 spaces , 2011, CVPR 2011.

[28]  Ramin Zabih,et al.  Dynamic Programming and Graph Algorithms in Computer Vision , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[29]  David J. Fleet,et al.  3D People Tracking with Gaussian Process Dynamical Models , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[30]  Simon Lucey,et al.  Deterministic 3D Human Pose Estimation Using Rigid Structure , 2010, ECCV.

[31]  Takeo Kanade,et al.  Nonrigid Structure from Motion in Trajectory Space , 2008, NIPS.