A mean field annealing approach to accurate free form shape matching

The SoftAssign algorithm is an elegant free form shape matching algorithm. While its objective function can be interpreted as consisting of three desired terms: minimising a weighted sum of matching errors of combinations of all the points in the two free form shapes to be matched, equalising their weights (probabilities) of being real ones and also maximising the overlapping area between the free form shapes to be matched, the last term has no effect on the optimisation of the parameters of interest due to normalisation. In this paper, we reformulate the last two terms using the inequality about the geometric and algebraic averages and the sum of the powers of these probabilities. For the sake of computational efficiency, instead of considering combinations of all the points in the overlapping free form shapes to be matched, we employ the traditional closest point criterion to establish possible correspondences between the two overlapping free form shapes to be matched. The saddle point solution of the resulting objective function no longer yields a closed form solution to the parameters of interest. For easy computation, we then adopt a pseudo-linearisation method to linearise the first order derivative of the objective function, leading the parameters of interest to be tracked and estimated with a closed form solution. The parameters of interest are finally optimised using the efficient deterministic annealing scheme with the camera motion parameters estimated using the quaternion method in the weighted least squares sense. A comparative study based on both synthetic data and real images with partial overlap has shown that the proposed algorithm is promising for the automatic matching of overlapping 3D free form shapes subject to a large range of motions.

[1]  Richard Sinkhorn.  A Relationship Between Arbitrary Positive Matrices and Doubly Stochastic Matrices , 1964 .

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

[3]  Luc Van Gool,et al.  Matching of 3-D curves using semi-differential invariants , 1995, Proceedings of IEEE International Conference on Computer Vision.

[4]  Gang Wang,et al.  Registration and Integration of Multiple Object Views for 3D Model Construction , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Aly A. Farag,et al.  Surfacing Signatures: An Orientation Independent Free-Form Surface Representation Scheme for the Purpose of Objects Registration and Matching , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Kim L. Boyer,et al.  Precision range image registration using a robust surface interpenetration measure and enhanced genetic algorithms , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Guido M. Cortelazzo,et al.  Metrological analysis of a procedure for the automatic 3D modeling of dental plaster casts , 2004 .

[8]  Kostas Daniilidis,et al.  Fully Automatic Registration of 3D Point Clouds , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

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

[10]  Eric Mjolsness,et al.  New Algorithms for 2D and 3D Point Matching: Pose Estimation and Correspondence , 1998, NIPS.

[11]  Guido M. Cortelazzo,et al.  3D registration by textured spin-images , 2005, Fifth International Conference on 3-D Digital Imaging and Modeling (3DIM'05).

[12]  A. Ardeshir Goshtasby,et al.  A mechanism for range image integration without image registration , 2005, Fifth International Conference on 3-D Digital Imaging and Modeling (3DIM'05).

[13]  B. Ripley,et al.  Pattern Recognition , 1968, Nature.

[14]  Martial Hebert,et al.  Fully automatic registration of multiple 3D data sets , 2003, Image Vis. Comput..

[15]  Yi-Ping Hung,et al.  RANSAC-Based DARCES: A New Approach to Fast Automatic Registration of Partially Overlapping Range Images , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Xavier Pennec,et al.  Multi-scale EM-ICP: A Fast and Robust Approach for Surface Registration , 2002, ECCV.

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

[18]  Anikó Ekárt,et al.  Pre-registration of arbitrarily oriented 3D surfaces using a genetic algorithm , 2006, Pattern Recognit. Lett..

[19]  Radu Horaud,et al.  Hand Motion from 3D Point Trajectories and a Smooth Surface Model , 2004, ECCV.

[20]  Heinz Hügli,et al.  Multi-feature matching algorithm for free-form 3D surface registration , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).

[21]  E. Jaynes.  Information Theory and Statistical Mechanics , 1957 .

[22]  Chia-Ling Tsai,et al.  The dual-bootstrap iterative closest point algorithm with application to retinal image registration , 2003, IEEE Transactions on Medical Imaging.

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

[24]  Hong Zhou,et al.  Projecting registration error for accurate registration of overlapping range images , 2006, Robotics Auton. Syst..

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

[26]  Kari Pulli,et al.  Multiview registration for large data sets , 1999, Second International Conference on 3-D Digital Imaging and Modeling (Cat. No.PR00062).

[27]  Yonghuai Liu,et al.  Pseudo-linearizing collinearity constraint for accurate pose estimation from a single image , 2004, Pattern Recognit. Lett..

[28]  Richard Lepage,et al.  A non contact CAD based inspection system , 1999 .

[29]  Zhengyou Zhang,et al.  Iterative point matching for registration of free-form curves and surfaces , 1994, International Journal of Computer Vision.

[30]  Jon Louis Bentley,et al.  An Algorithm for Finding Best Matches in Logarithmic Expected Time , 1977, TOMS.

[31]  Sebastian Thrun,et al.  6D SLAM with an application in autonomous mine mapping , 2004, IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004.

[32]  Guido M. Cortelazzo,et al.  Automatic 3D modeling of textured cultural heritage objects , 2004, IEEE Transactions on Image Processing.

[33]  Philip David,et al.  Simultaneous pose and correspondence determination using line features , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[34]  David Nister,et al.  Alignment of continuous video onto 3D point clouds , 2004, CVPR 2004.

[35]  Ying Wang,et al.  Developing rigid motion constraints for the registration of free-form shapes , 2000, Proceedings. 2000 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2000) (Cat. No.00CH37113).

[36]  Ioannis Stamos,et al.  3D modeling of historic sites using range and image data , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[37]  Benjamin B. Kimia,et al.  3D shape registration using regularized medial scaffolds , 2004 .

[38]  Yonghuai Liu,et al.  Developing structural constraints for accurate registration of overlapping range images , 2004, Robotics Auton. Syst..

[39]  Constantino Tsallis,et al.  Fluxes of cosmic rays: a delicately balanced stationary state , 2002 .

[40]  Andrew E. Johnson,et al.  Using Spin Images for Efficient Object Recognition in Cluttered 3D Scenes , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

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

[42]  Yonghuai Liu,et al.  Automatic 3d free form shape matching using the graduated assignment algorithm , 2005, Pattern Recognit..