Fitting smoothing splines to time-indexed, noisy points on nonlinear manifolds

We address the problem of estimating full curves/paths on certain nonlinear manifolds using only a set of time-indexed points, for use in interpolation, smoothing, and prediction of dynamic systems. These curves are analogous to smoothing splines in Euclidean spaces as they are optimal under a similar objective function, which is a weighted sum of a fitting-related (data term) and a regularity-related (smoothing term) cost functions. The search for smoothing splines on manifolds is based on a Palais metric-based steepest-decent algorithm developed in Samir et al. [38]. Using three representative manifolds: the rotation group for pose tracking, the space of symmetric positive-definite matrices for DTI image analysis, and Kendall's shape space for video-based activity recognition, we demonstrate the effectiveness of the proposed algorithm for optimal curve fitting. This paper derives certain geometrical elements, namely the exponential map and its inverse, parallel transport of tangents, and the curvature tensor, on these manifolds, that are needed in the gradient-based search for smoothing splines. These ideas are illustrated using experimental results involving both simulated and real data, and comparing the results to some current algorithms such as piecewise geodesic curves and splines on tangent spaces, including the method by Kume et al. [24].

[1]  F. Tompkins,et al.  Bayesian Filtering on the Stiefel Manifold , 2007, 2007 2nd IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing.

[2]  Hong Qin,et al.  Manifold splines , 2006, Graph. Model..

[3]  Anuj Srivastava,et al.  A Gradient-Descent Method for Curve Fitting on Riemannian Manifolds , 2011, Foundations of Computational Mathematics.

[4]  C. Altafini The de casteljau algorithm on SE(3) , 2001 .

[5]  I. Dryden,et al.  Non-Euclidean statistics for covariance matrices, with applications to diffusion tensor imaging , 2009, 0910.1656.

[6]  David J. Kriegman,et al.  Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection , 1996, ECCV.

[7]  Lyle Noakes,et al.  Bézier curves and C2 interpolation in Riemannian manifolds , 2007, J. Approx. Theory.

[8]  Namrata Vaswani,et al.  Tracking Deforming Objects Using Particle Filtering for Geometric Active Contours , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Rama Chellappa,et al.  "Shape Activity": a continuous-state HMM for moving/deforming shapes with application to abnormal activity detection , 2005, IEEE Transactions on Image Processing.

[10]  Victor Solo,et al.  On nonlinear state estimation in a Riemannian manifold , 2009, Proceedings of the 48h IEEE Conference on Decision and Control (CDC) held jointly with 2009 28th Chinese Control Conference.

[11]  Frank Chongwoo Park,et al.  Smooth invariant interpolation of rotations , 1997, TOGS.

[12]  Vijay Kumar,et al.  On the generation of smooth three-dimensional rigid body motions , 1998, IEEE Trans. Robotics Autom..

[13]  R. Palais Morse theory on Hilbert manifolds , 1963 .

[14]  F. Leite,et al.  Riemannian Means as Solutions of Variational Problems , 2006 .

[15]  T. K. Carne,et al.  Shape and Shape Theory , 1999 .

[16]  H. Pottmann,et al.  Energy-minimizing splines in manifolds , 2004, SIGGRAPH 2004.

[17]  Maher Moakher,et al.  To appear in: SIAM J. MATRIX ANAL. APPL. MEANS AND AVERAGING IN THE GROUP OF ROTATIONS∗ , 2002 .

[18]  Namrata Vaswani,et al.  Nonstationary Shape Activities: Dynamic Models for Landmark Shape Change and Applications , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  P. Crouch,et al.  The De Casteljau Algorithm on Lie Groups and Spheres , 1999 .

[20]  P. Crouch,et al.  The dynamic interpolation problem: On Riemannian manifolds, Lie groups, and symmetric spaces , 1995 .

[21]  F. Silva Leite,et al.  Geometry and the Dynamic Interpolation Problem , 1991, 1991 American Control Conference.

[22]  Anuj Srivastava,et al.  Optimal linear representations of images for object recognition , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[23]  Michael I. Miller,et al.  Hilbert-Schmidt Lower Bounds for Estimators on Matrix Lie Groups for ATR , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[24]  P. Crouch,et al.  Splines of class Ck on non-euclidean spaces , 1995 .

[25]  Rama Chellappa,et al.  Rate-Invariant Recognition of Humans and Their Activities , 2009, IEEE Transactions on Image Processing.

[26]  Namrata Vaswani,et al.  Deform PF-MT: Particle Filter With Mode Tracker for Tracking Nonaffine Contour Deformations , 2010, IEEE Transactions on Image Processing.

[27]  P. Jupp,et al.  Fitting Smooth Paths to Spherical Data , 1987 .

[28]  I. Dryden,et al.  Shape-space smoothing splines for planar landmark data , 2007 .

[29]  P. Thomas Fletcher,et al.  Riemannian geometry for the statistical analysis of diffusion tensor data , 2007, Signal Process..

[30]  Anuj Srivastava,et al.  Riemannian Analysis of Probability Density Functions with Applications in Vision , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[31]  Thomas B. Moeslund,et al.  Long-Term Occupancy Analysis Using Graph-Based Optimisation in Thermal Imagery , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[32]  F. Leite,et al.  Fitting Smooth Paths on Riemannian Manifolds , 2004 .

[33]  W. Boothby An introduction to differentiable manifolds and Riemannian geometry , 1975 .

[34]  I. Dryden,et al.  Shape curves and geodesic modelling , 2010 .

[35]  Lyle Noakes,et al.  Cubic Splines on Curved Spaces , 1989 .

[36]  K. Mardia,et al.  Statistical Shape Analysis , 1998 .

[37]  Max Donath,et al.  American Control Conference , 1993 .

[38]  D. Kendall SHAPE MANIFOLDS, PROCRUSTEAN METRICS, AND COMPLEX PROJECTIVE SPACES , 1984 .

[39]  Samuel R. Buss,et al.  Spherical averages and applications to spherical splines and interpolation , 2001, TOGS.

[40]  J. Jost Riemannian geometry and geometric analysis , 1995 .

[41]  Maher Moakher,et al.  A Differential Geometric Approach to the Geometric Mean of Symmetric Positive-Definite Matrices , 2005, SIAM J. Matrix Anal. Appl..

[42]  S. R. Jammalamadaka,et al.  Directional Statistics, I , 2011 .

[43]  K. Mardia,et al.  Functional models of growth for landmark data , 2010 .

[44]  Anuj Srivastava,et al.  Bayesian and geometric subspace tracking , 2004, Advances in Applied Probability.

[45]  Anuj Srivastava,et al.  Shape Analysis of Elastic Curves in Euclidean Spaces , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[46]  R. C. Rodrigues,et al.  A two-step algorithm of smooth spline generation on Riemannian manifolds , 2006 .

[47]  K. Hüper,et al.  On the Geometry of Rolling and Interpolation Curves on Sn, SOn, and Grassmann Manifolds , 2007 .

[48]  Xavier Pennec,et al.  A Riemannian Framework for Tensor Computing , 2005, International Journal of Computer Vision.