Automatic Image Alignment for 3D Environment Modeling

Nathaniel Williams, Kok-Lim Low, Chad Hantak, Marc Pollefeys, Anselmo Lastra

Abstract

We describe an approach for automatically registering color images with 3D laser scanned models. We use the chi-square statistic to compare color images to polygonal models texture mapped with acquired laser reflectance values. In complicated scenes we find that the chi-square test is not robust enough to permit an automatic global registration approach. Therefore, we introduce two techniques for obtaining initial pose estimates that correspond to a coarse alignment of the data. The first method is based on rigidly attaching a camera to a laser scanner and the second utilizes object tracking to decouple these imaging devices. The pose estimates serve as an initial guess for our optimization method, which maximizes the chi-square statistic over a local space of transformations in order to automatically determine the proper alignment.
BibTeX
@inproceedings{williams2004automatic,
  author = {Nathaniel Williams and Kok-Lim Low and Chad Hantak and Marc Pollefeys and Anselmo Lastra},
  title = {{Automatic Image Alignment for 3D Environment Modeling}},
  booktitle = {SIBGRAPI},
  year = {2004},
  doi = {10.1109/sibgra.2004.1352985},
}

Loading related content...

Figure