Abstract
We present an irregular image pyramid which is derived from multi-scale analysis of segmented watershed regions. Our framework is based on the development of regions in the Gaussian scale-space, which is represented by a region hierarchy graph. Using this structure, we are able to determine geometrically precise borders of our segmented regions using a region focusing. In order to handle the complexity, we select only stable regions and regions resulting from a merging event, which enables us to keep the hierarchical structure of the regions. Using this framework, we are able to detect objects of various scales in an image. Finally, the hierarchical structure is used for describing these detected regions as aggregations of their parts. We investigate the usefulness of the regions for interpreting images showing building facades with parts like windows, balconies or entrances.
This work has been done within the project Ontological scales for automated detection, efficient processing and fast visualization of landscape models which is funded by the German Research Council (DFG).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Akçay, H.G., Aksoy, S.: Automatic detection of geospatial objects using multiple hierarchical segmentations. Geoscience & Remote Sensing 46(7), 2097–2111 (2008)
Bergholm, F.: Edge focusing. PAMI 9(6), 726–741 (1987)
Brun, L., Mokhtari, M., Meyer, F.: Hierarchical watersheds within the combinatorial pyramid framework. In: Andrès, É., Damiand, G., Lienhardt, P. (eds.) DGCI 2005. LNCS, vol. 3429, pp. 34–44. Springer, Heidelberg (2005)
Drauschke, M., Förstner, W.: Selecting appropriate features for detecting buildings and building parts. In: Proc. 21st ISPRS Congress, IAPRS 37 (B3b-2), pp. 447–452 (2008)
Drauschke, M., Schuster, H.-F., Förstner, W.: Detectability of buildings in aerial images over scale space. PCV 2006, IAPRS 36(3), 7–12 (2006)
Epshtein, B., Ullman, S.: Feature hierarchies for object classification. In: Proc. 10th ICCV, pp. 220–227 (2005)
Everingham, M., Winn, J.: The pascal visual object classes challenge 2008 (voc2008) development kit (2008) (online publication)
Gauch, J.M.: Image segmentation and analysis via multiscale gradient watershed hierarchies. Image Processing 8(1), 69–79 (1999)
Goldstein, E.B.: Sensation and Perception (in German translation by Ritter, M), 6th edn. Wadsworth, Belmont (2002)
Guigues, L., Le Men, H., Cocquerez, J.-P.: The hierarchy of the cocoons of a graph and its application to image segmentation. Pattern Recognition Letters 24(8), 1059–1066 (2003)
Hartz, J., Neumann, B.: Learning a knowledge base of ontological concepts for high-level scene interpretation. In: Proc. ICMLA, pp. 436–443 (2007)
Harvey, R., Bangham, J.A., Bosson, A.: Scale-space filters and their robustness. In: ter Haar Romeny, B.M., Florack, L.M.J., Viergever, M.A. (eds.) Scale-Space 1997. LNCS, vol. 1252, pp. 341–344. Springer, Heidelberg (1997)
Lifschitz, I.: Image interpretation using bottom-up top-down cycle on fragment trees. Master’s thesis, Weizmann Institute of Science (2005)
Lindeberg, T.: Scale space theory in computer vision. Kluwer Academic, Dordrecht (1994)
Meer, P.: Stochastic image pyramids. CVGIP 45, 269–294 (1989)
Olsen, O.F., Nielsen, M.: Multiscale gradient magnitude watershed segmentation. In: Del Bimbo, A. (ed.) ICIAP 1997. LNCS, vol. 1310, pp. 9–13. Springer, Heidelberg (1997)
Perona, P., Malik, J.: Scale-space and edge detection using anisotropic diffussion. PAMI 12(7), 629–639 (1990)
Witkin, A.: Scale-space filtering. In: Proc. 8th IJCAI, pp. 1019–1022 (1983)
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
Drauschke, M. (2009). An Irregular Pyramid for Multi-scale Analysis of Objects and Their Parts. In: Torsello, A., Escolano, F., Brun, L. (eds) Graph-Based Representations in Pattern Recognition. GbRPR 2009. Lecture Notes in Computer Science, vol 5534. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-02124-4_30
Download citation
DOI: https://doi.org/10.1007/978-3-642-02124-4_30
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-02123-7
Online ISBN: 978-3-642-02124-4
eBook Packages: Computer ScienceComputer Science (R0)