Geometrical Analysis of Two Sets of 3D Correspondence Data Patterns for the Registration of Free-Form Shapes

The iterative closest point (ICP) algorithm represents an efficient method to establish an initial set of possible correspondences between two overlapping range images. An inherent limitation of the algorithm is the introduction of false matches, a problem that has been tackled by a variety of schemes mainly based on local invariants described in a single coordinate frame. In this paper we propose using global rigid motion constraints to deal with false matches. Such constraints are derived from geometric properties of correspondence vectors bridging the points described in different coordinate frames before and after a rigid motion. In order to accurately and efficiently estimate the parameters of interest, the Monte Carlo resampling technique is used and motion parameter candidates are then synthesised by a median filter. The proposed algorithm is validated based on both synthetic data and real range images. Experimental results show that the proposed algorithm has advantages over existing registration methods concerning robustness, accuracy, and efficiency.

[1]  J.-M. Vezien,et al.  Multiple representation approach to geometric model construction from range data , 1994, Proceedings of 1994 IEEE 2nd CAD-Based Vision Workshop.

[2]  Cordelia Schmid,et al.  Comparing and evaluating interest points , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[3]  Reinhard Koch,et al.  Invariant-based registration of surface patches , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[4]  Hong-Tzong Yau,et al.  Automated precision measurement of surface profile in CAD-directed inspection , 1992, IEEE Trans. Robotics Autom..

[5]  Nicholas Ayache,et al.  Locally affine registration of free-form surfaces , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Andrew E. Johnson,et al.  Registration and integration of textured 3-D data , 1997, Proceedings. International Conference on Recent Advances in 3-D Digital Imaging and Modeling (Cat. No.97TB100134).

[7]  Nicholas Ayache,et al.  3D-2D Projective Registration of Free-Form Curves and Surfaces , 1997, Comput. Vis. Image Underst..

[8]  Ramesh C. Jain,et al.  Determining Motion Parameters for Scenes with Translation and Rotation , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Ross T. Whitaker,et al.  Indoor scene reconstruction from sets of noisy range images , 1999, Second International Conference on 3-D Digital Imaging and Modeling (Cat. No.PR00062).

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

[11]  Aly A. Farag,et al.  Free-form surface registration using surface signatures , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[12]  Nicholas Ayache,et al.  Extension of the ICP Algorithm to Nonrigid Intensity-Based Registration of 3D Volumes , 1997, Comput. Vis. Image Underst..

[13]  Marc Levoy,et al.  Zippered polygon meshes from range images , 1994, SIGGRAPH.

[14]  Martial Hebert,et al.  3D map reconstruction from range data , 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065).

[15]  Georg Glaeser,et al.  Open Geometry: OpenGL + Advanced Geometry with Disk , 1999 .

[16]  Marcos A. Rodrigues,et al.  Geometrical Analysis of Two Sets of 3D Correspondence Data Patterns for the Registration of Free-Form Shapes , 1999, Proceedings Shape Modeling International '99. International Conference on Shape Modeling and Applications.

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

[18]  Shahriar Negahdaripour,et al.  Multiple Interpretations of the Shape and Motion of Objects from Two Perspective Images , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[19]  Ales Leonardis,et al.  Registration of Range Images Based on Segmented Data , 1999, CAIP.

[20]  Gérard G. Medioni,et al.  Object modelling by registration of multiple range images , 1992, Image Vis. Comput..

[21]  Benoit M. Dawant,et al.  Registration of 3-D images using weighted geometrical features , 1996, IEEE Trans. Medical Imaging.

[22]  Sang Wook Lee,et al.  Invariant features and the registration of rigid bodies , 1999, Proceedings 1999 IEEE International Conference on Robotics and Automation (Cat. No.99CH36288C).

[23]  Georg Glaeser,et al.  Open geometry - OpenGL and advanced geometry , 1999 .

[24]  J. Thirion,et al.  The 3D marching lines algorithm and its application to crest lines extraction , 1992 .

[25]  Robert B. Fisher,et al.  Finding Surface Correspondance for Object Recognition and Registration Using Pairwise Geometric Histograms , 1998, ECCV.

[26]  Thomas S. Huang,et al.  FINDING 3-D POINT CORRESPONDENCES IN MOTION ESTIMATION. , 1986 .

[27]  Jean-Philippe Thirion,et al.  New feature points based on geometric invariants for 3D image registration , 1996, International Journal of Computer Vision.

[28]  Gene H. Golub,et al.  Matrix computations (3rd ed.) , 1996 .

[29]  Nicholas Ayache,et al.  Rigid, affine and locally affine registration of free-form surfaces , 1996, International Journal of Computer Vision.

[30]  Robert Bergevin,et al.  Towards a General Multi-View Registration Technique , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[31]  Martin D. Levine,et al.  Registering Multiview Range Data to Create 3D Computer Objects , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

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