Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Using GNG to improve 3D features extractio - Application to 6DoF Egomotion

Viejo, Diego ; Garcia, Jose ; Cazorla, Miguel ; Gil, David LU and Johnsson, Magnus LU (2012) In Neural Networks 32. p.138-146
Abstract
Abstract in Undetermined
Several recent works deal with 3D data in mobile robotic problems, e.g. mapping or egomotion. Data comes from any kind of sensor such as stereo vision systems, time of flight cameras or 3D lasers, providing a huge amount of unorganized 3D data. In this paper, we describe an efficient method to build complete 3D models from a Growing Neural Gas (GNG). The GNG is applied to the 3D raw data and it reduces both the subjacent error and the number of points, keeping the topology of the 3D data. The GNG output is then used in a 3D feature extraction method. We have performed a deep study in which we quantitatively show that the use of GNG improves the 3D feature extraction method. We also show that our method can be... (More)
Abstract in Undetermined
Several recent works deal with 3D data in mobile robotic problems, e.g. mapping or egomotion. Data comes from any kind of sensor such as stereo vision systems, time of flight cameras or 3D lasers, providing a huge amount of unorganized 3D data. In this paper, we describe an efficient method to build complete 3D models from a Growing Neural Gas (GNG). The GNG is applied to the 3D raw data and it reduces both the subjacent error and the number of points, keeping the topology of the 3D data. The GNG output is then used in a 3D feature extraction method. We have performed a deep study in which we quantitatively show that the use of GNG improves the 3D feature extraction method. We also show that our method can be applied to any kind of 3D data. The 3D features obtained are used as input in an Iterative Closest Point (ICP)-like method to compute the 6DoF movement performed by a mobile robot. A comparison with standard ICP is performed, showing that the use of GNG improves the results. Final results of 3D mapping from the egomotion calculated are also shown. (C) 2012 Elsevier Ltd. All rights reserved. (Less)
Please use this url to cite or link to this publication:
author
; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
GNG, Egomotion, 3D feature extraction, 6DoF registration
in
Neural Networks
volume
32
pages
138 - 146
publisher
Elsevier
external identifiers
  • wos:000306162600015
  • scopus:84863416782
  • pmid:22386789
ISSN
1879-2782
DOI
10.1016/j.neunet.2012.02.014
project
Thinking in Time: Cognition, Communication and Learning
language
English
LU publication?
yes
id
92b239f0-edc6-421e-8b26-664e2fef01ae (old id 2333991)
date added to LUP
2016-04-01 14:06:26
date last changed
2022-02-12 00:44:31
@article{92b239f0-edc6-421e-8b26-664e2fef01ae,
  abstract     = {{Abstract in Undetermined<br/>Several recent works deal with 3D data in mobile robotic problems, e.g. mapping or egomotion. Data comes from any kind of sensor such as stereo vision systems, time of flight cameras or 3D lasers, providing a huge amount of unorganized 3D data. In this paper, we describe an efficient method to build complete 3D models from a Growing Neural Gas (GNG). The GNG is applied to the 3D raw data and it reduces both the subjacent error and the number of points, keeping the topology of the 3D data. The GNG output is then used in a 3D feature extraction method. We have performed a deep study in which we quantitatively show that the use of GNG improves the 3D feature extraction method. We also show that our method can be applied to any kind of 3D data. The 3D features obtained are used as input in an Iterative Closest Point (ICP)-like method to compute the 6DoF movement performed by a mobile robot. A comparison with standard ICP is performed, showing that the use of GNG improves the results. Final results of 3D mapping from the egomotion calculated are also shown. (C) 2012 Elsevier Ltd. All rights reserved.}},
  author       = {{Viejo, Diego and Garcia, Jose and Cazorla, Miguel and Gil, David and Johnsson, Magnus}},
  issn         = {{1879-2782}},
  keywords     = {{GNG; Egomotion; 3D feature extraction; 6DoF registration}},
  language     = {{eng}},
  pages        = {{138--146}},
  publisher    = {{Elsevier}},
  series       = {{Neural Networks}},
  title        = {{Using GNG to improve 3D features extractio - Application to 6DoF Egomotion}},
  url          = {{http://dx.doi.org/10.1016/j.neunet.2012.02.014}},
  doi          = {{10.1016/j.neunet.2012.02.014}},
  volume       = {{32}},
  year         = {{2012}},
}