Global Localization Based on 3D Planar Surface Segments Detected by a 3D Camera

Abstract

Global localization of a mobile robot using planar surface segments extracted from depth images is considered. The robot’s environment is represented by a topological map consisting of local models, each representing a particular location modeled by a set of planar surface segments. The discussed localization approach segments a depth image acquired by a 3D camera into planar surface segments which are then matched to model surface segments. The robot pose is estimated by the Extended Kalman Filter using surface segment pairs as measurements. The reliability and accuracy of the considered approach are experimentally evaluated using a mobile robot equipped by a Microsoft Kinect sensor.

Files

Full Paper as PDF

BibTeX Citation

DOI

10.20532/ccvw.2013.0008

https://doi.org/10.20532/ccvw.2013.0008

BibTeX

@InProceedings{10.20532/ccvw.2013.0008,
  author =       {Robert Cupec and Emmanuel Karlo Nyarko and Damir
                  Filko and Andrej Kitanov and Ivan Petrovi{\' c}},
  title =        {Global Localization Based on {3D} Planar Surface
                  Segments},
  booktitle =    {Proceedings of the Croatian Compter Vision Workshop,
                  Year 1},
  pages =        {31-36},
  year =         2013,
  editor =       {Lon{\v c}ari{\' c}, Sven and {\v S}egvi{\' c},
                  Sini{\v s}a},
  address =      {Zagreb},
  month =        {September},
  organization = {Center of Excellence for Computer Vision},
  publisher =    {University of Zagreb},
  abstract =     {Global localization of a mobile robot using planar
                  surface segments extracted from depth images is
                  considered. The robot’s environment is represented
                  by a topological map consisting of local models,
                  each representing a particular location modeled by a
                  set of planar surface segments. The discussed
                  localization approach segments a depth image
                  acquired by a 3D camera into planar surface segments
                  which are then matched to model surface
                  segments. The robot pose is estimated by the
                  Extended Kalman Filter using surface segment pairs
                  as measurements. The reliability and accuracy of the
                  considered approach are experimentally evaluated
                  using a mobile robot equipped by a Microsoft Kinect
                  sensor.},
  doi =          {10.20532/ccvw.2013.0008},
  url =          {https://doi.org/10.20532/ccvw.2013.0008}
}