Exploiting Segmentation for Robust 3D Object Matching
RSE: Robotics and State Estimation Lab, Department of Computer Science and Engineering, University of Washington
ICRA, 2012
@article{krainin2012exploiting,
title={Exploiting Segmentation for Robust 3D Object Matching},
author={Krainin, M. and Konolige, K. and Fox, D.},
year={2012}
}
While Iterative Closest Point (ICP) algorithms have been successful at aligning 3D point clouds, they do not take into account constraints arising from sensor viewpoints. More recent beam-based models take into account sensor noise and viewpoint, but problems still remain. In particular, good optimization strategies are still lacking for the beam-based model. In situations of occlusion and clutter, both beam-based and ICP approaches can fail to find good solutions. In this paper, we present both an optimization method for beambased models and a novel framework for modeling observation dependencies in beam-based models using over-segmentations. This technique enables reasoning about object extents and works well in heavy clutter. We also make available a groundtruth 3D dataset for testing algorithms in this area.
February 18, 2012 by hgpu
