Información del artículo
Resumen
En este trabajo se muestra un método para el reconocimiento de objetos de forma libre a partir de los datos de rango de una vista parcial. Para ello presentamos una nueva característica que denominamos Cono-Curvatura Ponderada (WCC), que mide el ángulo que sustenta cada uno de los nodos de la malla. Debido a que la información empleada no es completa, es necesario reforzar la búsqueda empleando una técnica basada en componentes principales, así como una basada en el algoritmo ICP. Debido a estas dos últimas fases del algoritmo, además del reconocimiento, se soluciona el problema de localización.
Palabras clave:
Reconocimiento
posicionamiento
datos de rango
visión 3D
El Texto completo está disponible en PDF
Referencias
[Adán et al., 2004]
Adán Antonio, Adán Miguel.
A flexible similarity measure for 3D shapes recognition.
IEEE Transactions on Pattern Analysis and Machine Intelligence, 26 (2004), pp. 1507-1520
[Adán et al., 2000]
Adán Antonio, Carlos Cerrada, Vicente Feliu.
Modeling wave set: Definition and application of a new topological organization of 3D object modeling.
Computer Vision and Image Understanding, 79 (2000), pp. 281-307
[Adán et al., 2006]
Adán Miguel, Adán Antonio.
Cone curvature in triangular meshes: an adaptable curvature measure for 3d shapes.
In: Interna-tional Congress of Mathematicians, (2006),
[Besl and Paul. McKay, 1992]
Paul.J. Besl, N.D. McKay.
A method for registration of 3-D shapes.
IEEE Transac-tions on Pattern Analysis and Machine Inte-lligence, 14 (1992), pp. 239-256
[Campbell et al., 1999]
Campbell Richard J., Patrick J. Flynn.
Eigenshapes for 3D object recognition in range data.
Proc. of the IEEE Conference on Computer Vision and Pattern Recognition., pp. 2505-2510
[Chua et al., 1997]
Chua Ching S., Jarvis Ray.
Point signatures: A new representation for 3D object recognition.
International Journal of Compu-ter Vision, 25 (1997), pp. 63-85
[Hebert et al., 1995]
M. Hebert, K. Ikeuchi, H. Delingette.
A spherical representation for recognition of free-form surfaces.
IEEE Transactions on Pattern Analysis and Machine Intelligence, 17 (1995), pp. 681-690
[Horn and Berthold, 1984]
Horn Berthold K.P..
Extended gaussian images.
Proceeding of the IEEE, 72 (1984), pp. 1656-1678
[Horn and Berthold, 1988]
Horn Berthold K.P..
Closed form solu-tions of absolute orientation using orthonor-mal matrices.
Journal of the Optical Society A, 5 (1988), pp. 1127-1135
[Johnson et al., 1999]
Johnson Andrew E., Martial Hebert.
Using spin images for efficient object recog-nition in cluttered 3d scenes.
IEEE Transac-tions on Pattern Analysis and Machine Inte-lligence, 21 (1999), pp. 433-449
[Merchán et al., 2006a]
Merchán Pilar, Antonio Adán, Santiago Sala-manca.
Recognition of free-form ob-ject in complex scenes using DGI-BS mo-dels.
Proc. of the International Sympo-sium on 3D Data, Processing, Visualization and Transmission, (2006),
[Merchán et al., 2006b]
Merchán Pilar, Antonio Adán, Santiago Sala-manca.
Revisión y análisis compara-tivo de técnicas de reconocimiento en entor-nos tridimensionales.
Actas de las XXVII Jornadas de Automática, (2006),
[Salamanca et al., 2000]
Salamanca Santiago, Carlos Cerrada, An-tonio Adán.
HWM: a new spherical representation structure for modeling par-tial views of an object.
Proc. of the In-ternational Conference on Pattern Recogni-tion (ICPR’2000), pp. 770-773
[Salamanca et al., 2004]
Salamanca Santiago, Carlos Cerrada, Antonio Adán, Miguel Adán.
Partial views matching using a method based on principal components.
Proc. of the First Interna-tional Conference on Informatics in Control, Automation and Robotics (ICINCO 2004), pp. 3-10
[Sato and Inokuchi, In press]
Sato, K. and S. Inokuchi (87). Range-imaging system utilizing nematic liquid crystal mask. In: International Conference on Computer Vision. pp. 657–661.
[Skočaj et al., 2001]
Skočaj Danijel, Aleš Leonardis.
Ro-bust recognition and pose determination of 3-D objects using range image in eigenspace approach.
Proc. of 3DIM’01, (2001), pp. 171-178
[Stein et al., 1992]
Stein Fridtjof, Gérard Medioni.
Structural indexing: Efficient 3-D object recogni-tion.
IEEE Transactions on Pattern Analysis and Machine Intelligence, 14 (1992), pp. 125-145
[Yamany et al., 2002]
Yamany Sameh, Aly Farag.
Surfacing signatures: An orientation independent free-form surface representation scheme for the purpose of objects registration and matching.
IEEE Transactions on Pattern Analysis and Machine Intelligence, 24 (2002), pp. 1105-1120
[Zhang et al., 1999]
Zhang Dongmei, Martial Hebert.
Har-monic maps and their applications in surface matching.
Proc. of the IEEE Conferen-ce on Computer Vision and Pattern Recogni-tion, pp. 524-530
Este trabajo se ha desarrollado gracias a la financiación del Ministerio de Educación y Ciencia, a través de los proyectos de la CICYT DPI2005-03769 y DPI2006-14794-C02.
Copyright © 2007. Elsevier España, S.L.. Todos los derechos reservados