Fully Automatic Registration of Multiple 3D Data Sets - Robotics Institute Carnegie Mellon University

Fully Automatic Registration of Multiple 3D Data Sets

Conference Paper, Proceedings of CVPR '01 Workshop on Computer Vision Beyond the Visible Spectrum (CVBVS '01), December, 2001

Abstract

This paper presents a method for automatically registering multiple three dimensional (3D) data sets. Previous approaches required manual specification of initial pose estimates or relied on external pose measurement systems. In contrast, our method does not assume any knowledge of initial poses or even which data sets overlap. Our automatic registration algorithm begins by converting the input data into surface meshes, which are pair-wise registered using a surface matching engine. The resulting matches are tested for surface consistency, but some incorrect matches may be locally undetectable. A global optimization process searches a graph constructed from these potentially faulty pair-wise matches for a connected sub-graph containing only correct matches, employing a global consistency measure to detect incorrect, but locally consistent matches. From this sub-graph, the final poses of all views can be computed directly. We apply our algorithm to the problem of 3D digital reconstruction of real world objects and show results for a collection of automatically digitized objects.

BibTeX

@conference{Huber-2001-8369,
author = {Daniel Huber and Martial Hebert},
title = {Fully Automatic Registration of Multiple 3D Data Sets},
booktitle = {Proceedings of CVPR '01 Workshop on Computer Vision Beyond the Visible Spectrum (CVBVS '01)},
year = {2001},
month = {December},
keywords = {registration, 3D modeling, visibility consistency, range images},
}