MULTIPLE VIEW REGISTRATION OF RANGE DATA USING SIGNATURE SEARCH

This paper presents a novel practical solution for registering a set of partial ly overlapping range images of an arbitrary scene. It was developed for appli cation in remote telerobotic operation in unstructured environments. The method is based on simple matching of 2-D range profil es extracted from two images. It handles all six degrees of freedom and does not rely on any particular geometric properties in the scene content. It can be used for combining multiple views of a scene taken from diff erent viewing directions to fil l in surfaces that are otherwise occluded. It can also be used for registering adjacent images to build up a mosaic from patches of a larger scene.

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

[2]  Marc Rioux,et al.  Design Of A Large Depth Of View Three-Dimensional Camera For Robot Vision , 1987 .

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

[4]  M. Hebert,et al.  The Representation, Recognition, and Locating of 3-D Objects , 1986 .

[5]  N. Burtnyk,et al.  Signature search method for 3-D pose refinement with range data , 1994, Proceedings of 1994 IEEE International Conference on MFI '94. Multisensor Fusion and Integration for Intelligent Systems.

[6]  Anil K. Jain,et al.  BONSAI: 3D Object Recognition Using Constrained Search , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Robert C. Bolles,et al.  3DPO: A Three- Dimensional Part Orientation System , 1986, IJCAI.

[8]  Azriel Rosenfeld,et al.  Registration of multiple overlapping range images: scenes without distinctive features , 1989, Proceedings CVPR '89: IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[9]  Richard Szeliski,et al.  Method for registering overlapping range images of arbitrarily shaped surfaces for 3D object reconstruction , 1993, Other Conferences.

[10]  Stefano Masciangelo,et al.  3-D Object Recognition: a Matching Paradigm Oriented to Data Fusion , 1989, IAS.