Abstract
In this work we present a method to integrate driving model and depth for the identification of 3D models in a scene where they can be partially occluded. The method is based on the identification of objects through the identification of projective invariant features and the validation of them by means of geometric and depth information. The depth information is used in several stages of the identification process for reducing the number of candidates in the initial hypothesis process and to augment the reliability of other modules. Two examples are shown in order to show the goodness of the method.
This work has been partially supported by a grant from the Fundació Areces.
Preview
Unable to display preview. Download preview PDF.
References
Añaños M. y Sanfeliu A.; 1988 Posicionamiento y verificaciSn de objetos 3D parcialmente ocultos representados por fronteras conocidos 4 puntos de su proyeccibn. III Simposium Nacional de Reconocimiento de Formas y Anklisis de Imkgenes Oviedo 27–30, Sept..
Brooks R.; 1981 Model-based three dimensional interpretations of two dimensional images. Proc. 7th INt. Joint Conf. Artificial Intell., Vancouver, B.C., Canada, Aug., pp. 619–624.
Chen C.H. and Kak A.C.; 1989 A robot system for recognizing 3-D objects in low-order polynomial time. IEEE Transactions SMC (Special issue on Computer Vision).
Grimson W.E.L. and Lozano-Perez T.; 1985 Recognition abd location of overlapping parts from sparse data in two and three dimensions. IEEE Comput. Soc. Int. Conf. Robotics, St. Louis, MO, Mar..
Ikeuchi K.; 1987 Generating and interpreting tree from a CAD model for 3D object recognition in bin-picking tasks. International Journal of Computer Vision, Vol.1, No. 2.
Oshima M. and Shirai Y.; 1983 Object recognition using three dimensional information. IEEE Trans. on Pattern Analysis and Machine Intelligence VOL. PAMI-5 NO.4 Jul pp.353–361.
Sanfeliu A.; 1984 A distance measure based on tree-graph grammars• a way of recognizing hidden and deformed 3D complex objects. 7th Int. Conf. on Pattern Recognition Montreal Canada Jul. 30- Aug. 2 1984; also in Instituto de Cibernetica Technical Report IC-DT-1984.01.
Sanfeliu A.; 1987 Parallel straight segments in the recognition of 3D objects. Instituto de Cibernética Technical document IC-DT-1987.04.
Sanfeliu A.; 1988 Matching on complex structures: the cyclic tree representation (invited paper). IAPR Syntactic and Structural Pattern Recognition Workshop, Pont-a-Mousson, France, Sep. 12–14.
Sanfeliu A. and Ananos M.; 1989 A CAD based vision system for identifyng industrial work pieces. 6th IFACIIFIP/IFORSIIMACS Symposium on Information Control Problems in Manufacturing Technology Sept. 26–29 Madrid (Spain).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sanfeliu, A., Añaños, M., Dunjó, M.J. (1993). Integrating Driving Model and Depth for Identification of Partially Occluded 3D Models. In: Aggarwal, J.K. (eds) Multisensor Fusion for Computer Vision. NATO ASI Series, vol 99. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-02957-2_12
Download citation
DOI: https://doi.org/10.1007/978-3-662-02957-2_12
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-08135-4
Online ISBN: 978-3-662-02957-2
eBook Packages: Springer Book Archive