Abstract
Within the nonlinearities of image structures occlusions play a particular role: additional scene views are needet to reconstruct the hidden parts of the scene. Furthermore the algorithmic complexity depends on the modeling of singularities like special views to the scene, which are not handled by a general position assumption. This paper presents an explicit modeling of special views and occlusions in polyhedral scenes due to the spatial arrangements of object components and the center of projection. The resulting taxonomies are applied within the search for consistent interpretations of line drawings from polyhedral scenes. Furthermore an iterative reconstruction process uses partial scene reconstructions and a generic scene model for predicting suitable scene views to complete the reconstruction process in an efficient way avoiding thereby occlusions and special views.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
M. Mäntylä, Solid Modeling, Computer Science Press, Rockville, 1988.
C. M. Hoffmann, Geometric and Solid Modeling, An Introd, Kaufmann, 1989.
M. B. Clowes, On Seeing Things, Artif. Intell. 2, 79–116, 1971.
D. A. Huffman, Impossible Objects as Nonsense Sentences, Machine Intelligence 6, B. Meltzer, D. M. Michie (eds.), 295–323, Edinburgh Univ., 1971.
D. L. Waltz, Understanding Line Drawings of Scenes with Shadows, The Psychology of Computer Vision, P. H. Winston (Ed.), 19–91, McGraw-Hill, 1975.
T. Kanade, Recovery of the Three-dimensional Shape of an Object from a Single View, Artif. Intell. 17, Nos. 1–3, 409–460, 1981.
K. Sugihara, Machine Interpretation of Line Drawings, MIT Press, 1986.
T. O. Binford, Inferring Surfaces from Images, Art. Int. 17, 205–244, 1981.
C. Müller, Verwendung von Bildauswertungsmethoden zur Erkennung und Lagebestimmung von generischen polyedrischen Objekten im Raum, infix, 1992.
T. Pavlidis, Algorithms for Graphics and Image Processing, Springer, 1982.
V. Steinhage, Verdeckungen und spezielle Sichten in der Rekonstruktion von Polyederszenen, PhD Thesis, University of Bonn, 1992.
J. Aloimonos, A. Bandyopadhyay, Active Vision, Proc. IEEE 1st Int. Conf. Comp. Vision, 35–54, 1987.
R. Bajcsy, Active Perception, Proc. IEEE, Vol. 76., No. 8, 996–1005, 1988.
D. H. Ballard, Animate Vision, Artificial Intelligence 48, 57–86, 1991.
V. Steinhage, I. Daniels, A. Schick, A Multi-View Stereovision Approach for Polyhedron Reconstruction, 4th Int. Conf. Comp. Anal. of Images and Patterns CAIP '91, Dresden, 33–41, 1991.
V. Steinhage, POLYOC: Photogrammetric Measurements of Buildings and Arch. Models via Multi-View Stereovision, Proc. 2nd Int. Conf. Exper. CAAD in Eur. ECAADE'91, Munich, 1991.
V. Steinhage, The General Position Assumption in the Practice of Stereovision, 7th Int. Symp. Microcomp.& Microproc. Applic., μP'92, Budapest, 377–386,1992.
V. Steinhage, Verification of the General Position Assumption in the Practice of Stereovision, 11. Int. Conf. Patt. Recog., ICPR 11, Den Haag, 746–749, 1992.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Steinhage, V. (1993). Occlusions and special views within the reconstruction of polyhedral scenes. In: Chetverikov, D., Kropatsch, W.G. (eds) Computer Analysis of Images and Patterns. CAIP 1993. Lecture Notes in Computer Science, vol 719. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-57233-3_65
Download citation
DOI: https://doi.org/10.1007/3-540-57233-3_65
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-57233-6
Online ISBN: 978-3-540-47980-2
eBook Packages: Springer Book Archive