A computer-assisted range image registration system for nuclear waste cleanup

Building a three-dimensional (3-D) computer-based representation of a large or complex scene from a set of range images requires assembling the range images so that they are spatially registered. This paper will present a technique for finding a homogeneous transformation between a pair of range images while making use of both range and intensity information obtained using a laser range scanner. A demonstrated application featuring this technique consists of building a 3-D representation of a nuclear dumpsite, which then serves to help control a teleoperated nuclear waste remediation system.

[1]  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.

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

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

[4]  Francois Blais,et al.  Range imaging sensors development at NRC Laboratories , 1989, [1989] Proceedings. Workshop on Interpretation of 3D Scenes.

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

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