Intrinsic correspondence using statistical signature-based matching for 3D surfaces

A wide variety of applications including object recognition and terrain mapping, rely upon automatic three dimensional surface modelling. The automatic correspondence stage of the modelling process has proven challenging. Intrinsic correspondence methods determine matching segments of partially overlapping 3D surfaces, by using properties intrinsic to the surfaces. These methods do not require initial relative orientations to begin the matching procedures. Hence, intrinsic methods are well-suited for automatic matching. This paper introduces a novel intrinsic automatic correspondence algorithm. Local feature support regions are described using distance and angular metrics, which are used to construct cumulative distribution function signatures. Local correspondences are hypothesised by comparing the signatures of two surfaces. A geometric consistency test is then applied to select the best local correspondences. Finally, registrations are computed from the remaining correspondences and the best alignment is selected. Results demonstrating the algorithm’s accuracy in selecting correspondences for mutual partially overlapping surfaces, are presented. The algorithm’s parameters prove robust, with only the local region size being surface dependent.

[1]  Gerhard Roth Registering two overlapping range images , 1999, Second International Conference on 3-D Digital Imaging and Modeling (Cat. No.PR00062).

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

[3]  Bernard Chazelle,et al.  Matching 3D models with shape distributions , 2001, Proceedings International Conference on Shape Modeling and Applications.

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

[5]  George F. Estabrook,et al.  Practical Nonparametric Statistics.W. J. Conover , 1971 .

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

[7]  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..

[8]  John A. Williams,et al.  Simultaneous Registration of Multiple Corresponding Point Sets , 2001, Comput. Vis. Image Underst..

[9]  Mohammed Bennamoun,et al.  Automatic correspondence of range images , 2002 .

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

[11]  Pavel Krsek,et al.  Range Image Registration Driven By A Hierarchy Of Surface Differential Features , 1998 .

[12]  Hon-Son Don,et al.  A Graph Matching Approach to 3-d Point Correspondences , 1991, Int. J. Pattern Recognit. Artif. Intell..

[13]  Gérard G. Medioni,et al.  Object modeling by registration of multiple range images , 1991, Proceedings. 1991 IEEE International Conference on Robotics and Automation.

[14]  Martial Hebert,et al.  A new approach to 3-D terrain mapping , 1999, Proceedings 1999 IEEE/RSJ International Conference on Intelligent Robots and Systems. Human and Environment Friendly Robots with High Intelligence and Emotional Quotients (Cat. No.99CH36289).

[15]  Andrew E. Johnson,et al.  Surface registration by matching oriented points , 1997, Proceedings. International Conference on Recent Advances in 3-D Digital Imaging and Modeling (Cat. No.97TB100134).

[16]  M. F. Fuller,et al.  Practical Nonparametric Statistics; Nonparametric Statistical Inference , 1973 .