Abstract
When a three dimensional scene is projected to the two dimensional receptive field of a camera or a biological vision system, all depth information is lost. Even without a knowledgebase, i. e. without knowing what object can be seen, it is possible to reconstruct the depth information. Beside stereoscopic depth cues, also a number of moncular depth cues can be used. One of the most important monocular depth cues ist the occlusion of object boundaries. Therefore one of the elaborated tasks for the low level image processing stage of a vision system is the completion of cluttered or occluded object boundaries and the depth assignment of overlapped boundaries. We describe a method for depth ordering and figure-ground segregation from monocular depth cues, namely the arrangement of so-called illusory contours at junctions in the edge map of an image. Therefore, a computational approach to the perception of illusory contours, based on the tensor voting technique, is introduced and compared with an alternative contour completion realized by spline interpolation. While most approaches assume, that the position of junctions and the orientations of associated contours are already known, we also consider the preprocessing steps that are necessary for a robust perception task. This implies the anisotropic diffusion of the input image in order to simplify the image contents while preserving the edge information.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Hansen, T.: A neural model of early vision: Contrast, contours, corners and surfaces. PhD thesis, Universität Ulm (2003)
Heitger, F., von der Heydt, R., Peterhans, E., Rosenthaler, L., Kübler, O.: Simulation of neural contour mechanisms: representing anomalous contours. Image Vision Comput. 16(6-7), 407–421 (1998)
Hund, M., Mertsching, B.: A Computational Approach to Illusory Contour Perception Based on the Tensor Voting Technique. In: Sanfeliu, A., Cortés, M.L. (eds.) CIARP 2005. LNCS, vol. 3773, pp. 71–80. Springer, Heidelberg (2005)
Hund, M., Mertsching, B.: Anisotropic Diffusion by Quadratic Regularization. In: 3rd International Conference on Computer Vision Theory and Applications (VISAPP 2008) (January 2008)
Kellman, P.J., Guttman, S.E., Wickens, T.D.: Geometric and neural models of object perception. In: Shipley, T.F., Kellman, P.J. (eds.) From fragments to objects: Segmentation and grouping in vision. Elsevier Science, Oxford (2001)
Massad, A., Babos, M., Mertsching, B.: Perceptual grouping in grey level images by combination of gabor filtering and tensor voting. In: Kasturi, R., Laurendeau, D., Suen, C. (eds.) ICPR, vol. 2, pp. 677–680 (2002)
Massad, A., Medioni, G.: 2-D Shape Decomposition into Overlapping Parts. In: Arcelli, C., Cordella, L.P., Sanniti di Baja, G. (eds.) IWVF 2001. LNCS, vol. 2059, pp. 398–409. Springer, Heidelberg (2001)
Medioni, G., Lee, M.-S., Tang, C.-K.: A Computational Framework for Segmentation and Grouping. Elsevier Science, Amsterdam (2000)
Neumann, H., Mingolla, E.: Computational neural models of spatial integration in perceptual grouping. In: Shipley, T., Kellman, P. (eds.) From fragments to units: Segmentation and grouping in vision, pp. 353–400. Elsevier Science, Oxford (2001)
Nieder, A.: Seeing more than meets the eye: processing of illusory contours in animals. Journal of Comparative Physiology A: Sensory, Neural, and Behavioral Physiology 188(4), 249–260 (2002)
Saund, E.: Perceptual organization of occluding contours of opaque surfaces. Comput. Vis. Image Underst. 76(1), 70–82 (1999)
Williams, L.R., Hanson, A.R.: Perceptual completion of occluded surfaces. Computer Vision and Image Understanding: CVIU 64(1), 1–20 (1996)
Zweck, J.W., Williams, L.R.: Euclidean group invariant computation of stochastic completion fields using shiftable-twistable functions. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1843, pp. 100–116. Springer, Heidelberg (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hund, M., Mertsching, B. (2009). Occlusion as a Monocular Depth Cue Derived from Illusory Contour Perception. In: Mertsching, B., Hund, M., Aziz, Z. (eds) KI 2009: Advances in Artificial Intelligence. KI 2009. Lecture Notes in Computer Science(), vol 5803. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-04617-9_13
Download citation
DOI: https://doi.org/10.1007/978-3-642-04617-9_13
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-04616-2
Online ISBN: 978-3-642-04617-9
eBook Packages: Computer ScienceComputer Science (R0)