Using 3D GNG-based reconstruction for 6DoF egomotion

Diego Viejo; Jose Garcia; Miguel Cazorla; David Gil; Magnus Johnsson

doi:10.1109/IJCNN.2011.6033337

Using 3D GNG-based reconstruction for 6DoF egomotion

Diego Viejo^*
, Jose Garcia
, Miguel Cazorla
, David Gil
, Magnus Johnsson

^*Huvudförfattare för detta arbete

Forskningsoutput: Konferensbidrag › Paper › Peer review

2 Citeringar (Scopus)

Sammanfattning

Several recent works deal with 3D data in mobile robotic problems, e.g. mapping. Data come from any kind of sensor (time of flight cameras and 3D lasers) providing a huge amount of unorganized 3D data. In this paper we detail an efficient method to build complete 3D models from a Growing Neural Gas (GNG). We show that the use of GNG provides better results than other approaches. The GNG obtained is then applied to a sequence. From GNG structure, we propose to calculate planar patches and thus obtaining a fast method to compute the movement performed by a mobile robot by means of a 3D models registration algorithm. Final results of 3D mapping are also shown.

Originalspråk	Engelska
Sidor	1042-1048
Antal sidor	7
DOI	https://doi.org/10.1109/IJCNN.2011.6033337
Status	Publicerad - 2011
Externt publicerad	Ja
Evenemang	2011 International Joint Conference on Neural Network, IJCNN 2011 - San Jose, CA, USA Varaktighet: 2011-juli-31 → 2011-aug.-05

Konferens

Konferens	2011 International Joint Conference on Neural Network, IJCNN 2011
Land/Territorium	USA
Ort	San Jose, CA
Period	11-07-31 → 11-08-05

Nationell ämneskategori

Elektroteknik och elektronik (202)

Åtkomst av dokument

10.1109/IJCNN.2011.6033337

Citera det här

@conference{871c03fb5e224bdc945de3ad2a98fda3,

title = "Using 3D GNG-based reconstruction for 6DoF egomotion",

abstract = "Several recent works deal with 3D data in mobile robotic problems, e.g. mapping. Data come from any kind of sensor (time of flight cameras and 3D lasers) providing a huge amount of unorganized 3D data. In this paper we detail an efficient method to build complete 3D models from a Growing Neural Gas (GNG). We show that the use of GNG provides better results than other approaches. The GNG obtained is then applied to a sequence. From GNG structure, we propose to calculate planar patches and thus obtaining a fast method to compute the movement performed by a mobile robot by means of a 3D models registration algorithm. Final results of 3D mapping are also shown.",

author = "Diego Viejo and Jose Garcia and Miguel Cazorla and David Gil and Magnus Johnsson",

year = "2011",

doi = "10.1109/IJCNN.2011.6033337",

language = "English",

pages = "1042--1048",

note = "2011 International Joint Conference on Neural Network, IJCNN 2011 ; Conference date: 31-07-2011 Through 05-08-2011",

}

TY - CONF

T1 - Using 3D GNG-based reconstruction for 6DoF egomotion

AU - Viejo, Diego

AU - Garcia, Jose

AU - Cazorla, Miguel

AU - Gil, David

AU - Johnsson, Magnus

PY - 2011

Y1 - 2011

N2 - Several recent works deal with 3D data in mobile robotic problems, e.g. mapping. Data come from any kind of sensor (time of flight cameras and 3D lasers) providing a huge amount of unorganized 3D data. In this paper we detail an efficient method to build complete 3D models from a Growing Neural Gas (GNG). We show that the use of GNG provides better results than other approaches. The GNG obtained is then applied to a sequence. From GNG structure, we propose to calculate planar patches and thus obtaining a fast method to compute the movement performed by a mobile robot by means of a 3D models registration algorithm. Final results of 3D mapping are also shown.

AB - Several recent works deal with 3D data in mobile robotic problems, e.g. mapping. Data come from any kind of sensor (time of flight cameras and 3D lasers) providing a huge amount of unorganized 3D data. In this paper we detail an efficient method to build complete 3D models from a Growing Neural Gas (GNG). We show that the use of GNG provides better results than other approaches. The GNG obtained is then applied to a sequence. From GNG structure, we propose to calculate planar patches and thus obtaining a fast method to compute the movement performed by a mobile robot by means of a 3D models registration algorithm. Final results of 3D mapping are also shown.

U2 - 10.1109/IJCNN.2011.6033337

DO - 10.1109/IJCNN.2011.6033337

M3 - Paper

AN - SCOPUS:80054736600

SP - 1042

EP - 1048

T2 - 2011 International Joint Conference on Neural Network, IJCNN 2011

Y2 - 31 July 2011 through 5 August 2011

ER -

Using 3D GNG-based reconstruction for 6DoF egomotion

Sammanfattning

Konferens

Nationell ämneskategori

Åtkomst av dokument

Fingeravtryck

Citera det här