Back to Top

Enabling Efficient Registration using Adaptive Iterative Closest Keypoint

J. Ekekrantz, A. Pronobis, J. Folkesson, P. Jensfelt

In IROS 2013 Workshop on Planning, Perception and Navigation for Intelligent Vehicles, 2013.

About

Registering frames of 3D sensor data is a key functionality in many robot applications, from multi-view 3D object recognition to SLAM. With the advent of cheap and widely available, so called, RGB-D sensors acquiring such data has become possible also from small robots or other mobile devices. Such robots and devices typically have limited resources and being able to perform registration in a computationally efficient manner is therefore very important. In our recent work, we proposed a fast and simple method for registering RGB-D data, building on the principle of the Iterative Closest Point (ICP) algorithm. This paper outlines this new method and shows how it can facilitate a significant reduction in computational cost while maintaining or even improving performance in terms of accuracy and convergence properties. As a contribution we present a method to efficiently measure the quality of a found registration.

BibTeX

@inproceedings{ekekrantz2013iros-ppniv,
  author =       {Ekekrantz, Johan and Pronobis, Andrzej and Folkesson, John and Jensfelt, Patric},
  title =        {Enabling Efficient Registration using Adaptive Iterative Closest Keypoint},
  booktitle =    {IROS 2013 Workshop on Planning, Perception and Navigation for Intelligent Vehicles},
  year =         2013,
  address =      {Tokyo, Japan},
  month =        nov,
  url =          {http://www.pronobis.pro/publications/ekekrantz2013iros-ppniv}
}
© 2018. Copyright Andrzej Pronobis
  • stackoverflow
  • scholar