Iterative Estimation of Rigid-Body Transformations

Closed-form solutions are traditionally used in computer vision for estimating rigid body transformations. Here we suggest an iterative solution for estimating rigid body transformations and prove its global convergence. We show that for a number of applications involving repeated estimations of rigid body transformations, an iterative scheme is preferable to a closed-form solution. We illustrate this experimentally on two applications, 3D object tracking and image registration with Iterative Closest Point. Our results show that for those problems using an iterative and continuous estimation process is more robust than using many independent closed-form estimations.

[1]  Kenichi Kanatani,et al.  Analysis of 3-D Rotation Fitting , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Paul J. Besl,et al.  A Method for Registration of 3-D Shapes , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Allen R. Tannenbaum,et al.  Point Set Registration via Particle Filtering and Stochastic Dynamics , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Berthold K. P. Horn,et al.  Closed-form solution of absolute orientation using orthonormal matrices , 1988 .

[5]  David Hestenes.  New Foundations for Classical Mechanics , 1986 .

[6]  Sang Wook Lee,et al.  ICP Registration Using Invariant Features , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Robert B. Fisher,et al.  Estimating 3-D rigid body transformations: a comparison of four major algorithms , 1997, Machine Vision and Applications.

[8]  O. Bauchau,et al.  The Vectorial Parameterization of Rotation , 2003 .

[9]  Allan D. Jepson,et al.  A new closed-form solution for absolute orientation , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Nanning Zheng,et al.  Affine iterative closest point algorithm for point set registration , 2010, Pattern Recognit. Lett..

[11]  Berthold K. P. Horn,et al.  Closed-form solution of absolute orientation using unit quaternions , 1987 .

[12]  Jon Louis Bentley,et al.  Multidimensional binary search trees used for associative searching , 1975, CACM.

[13]  Mohamed A. Deriche,et al.  3D registration using a new implementation of the ICP algorithm based on a comprehensive lookup matrix: Application to medical imaging , 2007, Pattern Recognit. Lett..

[14]  S. H. Joseph.  Optimal Pose Estimation in Two and Three Dimensions , 1999, Comput. Vis. Image Underst..

[15]  Carl-Fredrik Westin,et al.  Robust Generalized Total Least Squares Iterative Closest Point Registration , 2004, MICCAI.

[16]  Richard A. Volz,et al.  Estimating 3-D location parameters using dual number quaternions , 1991, CVGIP Image Underst..

[17]  John Porrill,et al.  Optimal combination of multiple sensors including stereo vision , 1987, Image Vis. Comput..

[18]  S. Altmann.  Rotations, Quaternions, and Double Groups , 1986 .

[19]  Marc Levoy,et al.  Efficient variants of the ICP algorithm , 2001, Proceedings Third International Conference on 3-D Digital Imaging and Modeling.

[20]  David Fofi,et al.  A review of recent range image registration methods with accuracy evaluation , 2007, Image Vis. Comput..

[21]  Purang Abolmaesumi,et al.  Point-Based Rigid-Body Registration Using an Unscented Kalman Filter , 2007, IEEE Transactions on Medical Imaging.

[22]  Katsuhiko Sakaue,et al.  Registration and integration of multiple range images for 3-D model construction , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[23]  Pavel Krsek,et al.  Robust Euclidean alignment of 3D point sets: the trimmed iterative closest point algorithm , 2005, Image Vis. Comput..

[24]  K. S. Arun,et al.  Least-Squares Fitting of Two 3-D Point Sets , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[25]  Nicholas Ayache,et al.  Generation of a statistical shape model with probabilistic point correspondences and the expectation maximization- iterative closest point algorithm , 2007, International Journal of Computer Assisted Radiology and Surgery.

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

[27]  Thomas S. Huang,et al.  Motion and structure from feature correspondences: a review , 1994, Proc. IEEE.

[28]  Torsten Söderström,et al.  Using an extended kalman filter for rigid body pose estimation. , 2005, Journal of biomechanical engineering.