Exploiting Segmentation for Robust 3D Object Matching

Michael Krainin, Kurt Konolige, Dieter Fox
RSE: Robotics and State Estimation Lab, Department of Computer Science and Engineering, University of Washington
ICRA, 2012


   title={Exploiting Segmentation for Robust 3D Object Matching},

   author={Krainin, M. and Konolige, K. and Fox, D.},



Download Download (PDF)   View View   Source Source   Source codes Source codes




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.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2018 hgpu.org

All rights belong to the respective authors

Contact us: