Article information
Resumen
El objetivo de este artículo es encontrar un extractor de características visuales que pueda ser utilizado en un proceso de SLAM (Simultaneous Localization and Mapping). Este extractor de características consiste en la combinación de un detector que extrae puntos significativos del entorno, y un descriptor local que caracteriza dichos puntos. Este artículo presenta la comparación de un conjunto de detectores de puntos de interés y de descriptores locales que se utilizan como marcas visuales en un proceso de SLAM. El análisis comparativo se divide en dos fases diferenciadas: detección y descripción. Se evalúa la repetibilidad de los detectores, así como la invariabilidad de los descriptores ante cambios de vista, escala e iluminación. Los experimentos se han realizado a partir de un conjunto de secuencias de imágenes tanto interiores (entorno de oficinas) como exteriores, con diversas variaciones en la imagen (iluminación y posición), representando así de una forma bastante general los entornos típicos de un robot. Se considera que los resultados de este trabajo pueden ser útiles a la hora de seleccionar una marca adecuada en SLAM visual, tanto para entornos interiores como exteriores.
Palabras clave:
SLAM visual
marcas visuales
detectores de puntos de interés
descriptores locales
Full text is only aviable in PDF
Referencias
[Ballesta et al., 2007]
Ballesta, M., A. Gil, O. MartínezMozos and O. Reinoso (2007). Local descriptors for visual SLAM. In: Workshop on Robotics and Mathematics (ROBOMAT07), Portugal. pp. 209-215.
[Bay et al., 2006]
Bay, Herbert, Tinne Tuytelaars, Luc Van Gool.
SURF: Speeded up robust features.
European Conference on Computer Vision, (2006),
[Biber et al., 2004]
P. Biber, H. Andreasson, T. Duckett, A. Schilling.
3D modelling of indoor environments by a mobile robot with a laser scanner and panoramic camera.
IEEE/RSJ Int. Conf. on Intelligent Robots & Systems, 4 (2004), pp. 3430-3435
[Burgard et al., 1998]
W. Burgard, A.B. Cremers, D. Fox, D. Hähnel, G. Lakemeyer, D. Schulz, W. Steiner, S. Thrun.
The interactive museum tour-guide robot.
Proc. of the National Conference on Artificial Intelligence, (1998),
[Béjar and Ollero, 2008]
M. Béjar, A. Ollero.
Modelado y control de helic ópteros autónomos. revisión del estado de la técnica.
RIAI, 5 (2008), pp. 5-16
[Davison et al., 2002]
Davison, J. Andrew, W. David, Murray.
Simultaneous localisation and map-building using active vision.
IEEE Transactions on Pattern Analysis and Machine Intelligence, (2002), pp. 735-758
[Eustice et al., 2005]
R. Eustice, H. Singh, J.J. Leonard.
Exactly sparse delayed-state filters.
IEEE Int. Conf. on Robotics & Automation, (2005), pp. 2417-2424
[Fraundorfer and Bischof, 2005]
F. Fraundorfer, H. Bischof.
A novel performance evaluation method of local detectors on non-planar scenes.
IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), (2005),
[Gil et al., 2009]
A. Gil, O. MartinezMozos, M. Ballesta, O. Reinoso.
A comparative evaluation of interest point detectors and local descriptors for visual slam.
Machine Vision and Applications Journal, (2009),
[Gil et al., 2006]
A. Gil, O. Reinoso, W. Burgard, C. Stachniss, O. Martínez Mozos.
Improving data association in rao-blackwellized visual SLAM.
IEEE/RSJ Int. Conf. on Intelligent Robots & Systems, (2006), pp. 2076-2081
[Grisetti et al., 2007]
G. Grisetti, C. Stachniss, W. Burgard.
Improved techniques for grid mapping with rao-blackwellized particle filters.
IEEE Transactions on Robotics, 23 (2007), pp. 34-46
[Hähnel et al., 2003]
D. Hähnel, W. Burgard, D. Fox, S. Thrun.
An efficient FastSLAM algorithm for generating maps of largescale cyclic environments from raw laser range measurements.
Las Vegas, (2003),
[Harris and Stephens, 1998]
C.G. Harris, M. Stephens.
A combined corner and edge detector.
Alvey Vision Conference, (1998), pp. 147-151
[Hygounenc et al., 2004]
Hygounenc, Emmanuel, Il-Kyun Jung, Philippe Souéres, Simon Lacroix.
The autonomous blimp project of laascnrs: Achievements in flight control and terrain mapping.
International Journal of Robotics Research, 23 (2004), pp. 473-511
[Jensfelt et al., 2006]
Jensfelt, Patric, Danica Kragic, John Folkesson, Mårten Björkman.
A framework for vision based bearing only 3D SLAM.
IEEE Int. Conf. on Robotics & Automation, (2006), pp. 1944-1950
[Kosecka et al., 2003]
J. Kosecka, L. Zhou, P. Barber, Z. Duric.
Qualitative image based localization in indoor environments.
Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, (2003), pp. 3-8
[Little et al., 2002]
J. Little, S. Se, D.G. Lowe.
Global localization using distinctive visual features.
IEEE/RSJ Int. Conf. on Intelligent Robots & Systems, (2002), pp. 226-231
[Lowe, 2004]
D. Lowe.
Distinctive image features from scaleinvariant keypoints.
International Journal of Computer Vision, 2 (2004), pp. 91-110
[Lowe, 1999]
D.G. Lowe.
Object recognition from local scaleinvariant features.
Int. Conf. on Computer Vision., (1999), pp. 1150-1157
[Martínez Mozos et al., 2007]
O. Martínez Mozos, A. Gil, M. Ballesta, O. Reinoso.
Interest point detectors for visual slam.
Proc. of the XII Conference of the Spanish Association for Artificial Intelligence (CAEPIA), Salamanca, Spain., (2007), pp. 217-226
[Mikolajczyk and Schmid, 2001]
K. Mikolajczyk, C. Schmid.
Indexing based on scale invariant interest points.
Int. Conf. on Computer Vision, (2001), pp. p525
[Mikolajczyk and Schmid, 2005]
K. Mikolajczyk, C. Schmid.
A performance evaluation of local descriptors.
IEEE Transactions on Pattern Analysis and Machine Intelligence, 27 (2005), pp. 1615-1630
[Mikolajczyk et al., 2005]
K. Mikolajczyk, T. Tuytelaars, C. Schmid, A. Zisserman, J. Matas, F. Schaffalitzky, T. Kadir, L. Van Gool.
A comparison of affine region detectors.
International Journal of computer Vision, 65 (2005), pp. 43-72
[Murillo et al., 2007]
A.C. Murillo, J.J. Guerrero, C. Sagüés.
Surf features for efficient robot localization with omnidirectional images.
IEEE Int. Conf. on Robotics & Automation, (2007),
[Ribas et al., 2008]
D. Ribas, P. Ridao, J.D. Tardós, J. Ñeira.
Underwater slam in man-made structured environments.
Journal of Field Robotics, (2008), pp. 1-24
[Rodriguez-Losada et al., 2005]
D. Rodriguez-Losada, F. Matia, A. Jimenez, R. Galan, G. Lacey.
Guido, the robotic smartwalker for the frail visually impaired.
First International Congress on Domotics, Robotics and Remote Assistance for All. DRT4ALL’05. Madrid, Spain, (2005), pp. 155-169
[Schmid et al., 2000]
C. Schmid, R. Mohr, C. Bauckhage.
Evaluaton of interest point detectors.
International Journal of computer Vision, 37 (2000), pp. 151-172
[Se et al., 2001]
Se, Stephen, G. David, Lowe, Jim Little.
Visionbased mobile robot localization and mapping using scaleinvariant features.
IEEE Int. Conf. on Robotics & Automation, (2001), pp. 2051-2058
[Sim et al., 2005]
R. Sim, P. Elinas, M. Griffin, J. Little.
Vision-based slam using the rao-blackwellised particle filter.
IJCAI Workshop on Reasoning with Uncertainty in Robotics, (2005),
[Smith, 1992]
S.M. Smith.
A new class of corner finder.
British Machine Vision Conference, (1992), pp. 139-148
[Soria et al., 2008]
C. Soria, F. Roberti, R. Carelli, J.M. Sebastian.
Control servo-visual de un robot manipulador planar basado en pasividad.
RIAI, 5 (2008), pp. 54-61
[Triebel, 2005]
Triebel, R. and W. Burgard (2005). Improving simultaneous mapping and localization in 3D using global constraints. In: National Conference on Artificial Intelligence (AAAI).Vol. 3. pp. 1330-1335.
[Valls Miro and Zhou, 2006]
Valls Miro, J., W. Zhou and G. Dissanayake (2006). Towards vision based navigation in large indoor environments. In: IEEE/RSJ Int. Conf. on Intelligent Robots & Systems. pp. 2096-2102.
[Zernike, 1934]
F. Zernike.
Diffraction theory of the cut procedure and its improved form, the phase contrast method.
Physica, 1 (1934), pp. 689-704
[Zhang et al., 1995]
Z. Zhang, R. Deriche, O. Faugeras, Q. Luong.
A robust technique for matching two uncalibrated images through the recovery of the unknown epipolar geometry.
Artificial Intelligence, 78 (1995), pp. 87-119
Copyright © 2010. Elsevier España, S.L.. Todos los derechos reservados