Advanced search
1 file | 1.60 MB

Multi-resolution ICP for the efficient registration of point clouds based on octrees

Michiel Vlaminck (UGent) , Hiep Luong (UGent) and Wilfried Philips (UGent)
Author
Organization
Abstract
In this paper we propose a multiresolution scheme based on hierarchical octrees for the registration of point clouds acquired by lidar scanners. The point density of these point clouds is generally sparse and inhomogeneous, a property that can yield a risk for correct alignment. Experiments demonstrate that our multiresolution technique is a lot faster than the traditional iterative closest point (ICP) algorithm while it is more robust, e.g. in case of abrupt movements of the sensor. We can report a speed-up factor of more than 30, without jeopardizing the level of accuracy. In scenarios for which the level of detail is less critical, e.g. in case of navigation for autonomous robots, we can even achieve a larger speed-up by trading speed for quality.

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 1.60 MB

Citation

Please use this url to cite or link to this publication:

Chicago
Vlaminck, Michiel, Hiep Luong, and Wilfried Philips. 2017. “Multi-resolution ICP for the Efficient Registration of Point Clouds Based on Octrees.” In PROCEEDINGS OF THE FIFTEENTH IAPR INTERNATIONAL CONFERENCE ON MACHINE VISION APPLICATIONS - MVA2017 , 334–337. IAPR.
APA
Vlaminck, M., Luong, H., & Philips, W. (2017). Multi-resolution ICP for the efficient registration of point clouds based on octrees. PROCEEDINGS OF THE FIFTEENTH IAPR INTERNATIONAL CONFERENCE ON MACHINE VISION APPLICATIONS - MVA2017 (pp. 334–337). Presented at the 15th IAPR International Conference on Machine Vision Applications (MVA) , IAPR.
Vancouver
1.
Vlaminck M, Luong H, Philips W. Multi-resolution ICP for the efficient registration of point clouds based on octrees. PROCEEDINGS OF THE FIFTEENTH IAPR INTERNATIONAL CONFERENCE ON MACHINE VISION APPLICATIONS - MVA2017 . IAPR; 2017. p. 334–7.
MLA
Vlaminck, Michiel, Hiep Luong, and Wilfried Philips. “Multi-resolution ICP for the Efficient Registration of Point Clouds Based on Octrees.” PROCEEDINGS OF THE FIFTEENTH IAPR INTERNATIONAL CONFERENCE ON MACHINE VISION APPLICATIONS - MVA2017 . IAPR, 2017. 334–337. Print.
@inproceedings{8511831,
  abstract     = {In this paper we propose a multiresolution scheme based on hierarchical octrees for the registration of point clouds acquired by lidar scanners. The point density of these point clouds is generally sparse and inhomogeneous, a property that can yield a risk for correct alignment. Experiments demonstrate that our multiresolution technique is a lot faster than the traditional iterative closest point (ICP) algorithm while it is more robust, e.g. in case of abrupt movements of the sensor. We can report a speed-up factor of more than 30, without jeopardizing the level of accuracy. In scenarios for which the level of detail is less critical, e.g. in case of navigation for autonomous robots, we can even achieve a larger speed-up by trading speed for quality.},
  author       = {Vlaminck, Michiel and Luong, Hiep and Philips, Wilfried},
  booktitle    = {PROCEEDINGS OF THE FIFTEENTH IAPR INTERNATIONAL CONFERENCE ON MACHINE VISION APPLICATIONS - MVA2017 },
  isbn         = {978-1-5386-0495-3},
  language     = {eng},
  location     = {Nagoya Univ, Nagoya, JAPAN },
  pages        = {334--337},
  publisher    = {IAPR},
  title        = {Multi-resolution ICP for the efficient registration of point clouds based on octrees},
  year         = {2017},
}

Web of Science
Times cited: