Abstract
Topological maps are graph-like spatial representations. To mitigate the above drawbacks of existing image segmentation algorithms, we propose a general theory of topological maps based on the abstract data structure whereby sensory input, topological and local metrical information are combined to define the topological maps explaining such information. In order to put the theory here proposed into computational practice, we provide two improvement algorithms on conventional region-based and edge-based image segmentation methods, which aim to extract directly regional boundaries and topological maps from the pixel sets in the processing of remote sensing image segmentation. The experimental results show that the two algorithms support different exploration strategies and facilitates map disambiguation when perceptual aliasing arises, and remain well the geometric topology information.
Keywords
The research is supported by the Director Fund (IS201116002) from Institute of Seismology, China Earthquake Administration, and the National Science and Technology Support Project (2012BAH01F02) from Ministry of Science and Technology of the People’s Republic of China.
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
Bleau, A., Leon, L.J.: Watershed-based Segmentation and Region Merging. Computer Vision and Image Understanding 77(3), 317–370 (2000)
Makrogiannis, S., Economou, G., Fotopoulos, S.: A Region Dissimilarity Relation That Combines Feature-Space and Spatial Information for Color Image Segmentation. IEEE Transactions on Systems, Man, and Cybernetics, Part B 35(1), 44–53 (2005)
Marfil, R., Molina-Tanco, L., Bandera, A., et al.: Pyramid Segmentation Algorithms Revisited. Pattern Recognition 39(8), 1430–1451 (2006)
David, P., Les, K.: Soft Image Segmentation by Weighted Linked Pyramid. Pattern Recognition Letters 22(2), 123–132 (2001)
Bazin, P.-L., Pham, D.L.: Topology Smoothing for Segmentation and Surface Reconstruction. In: Barillot, C., Haynor, D.R., Hellier, P. (eds.) MICCAI 2004. LNCS, vol. 3216, pp. 111–118. Springer, Heidelberg (2004)
Liu, X., Zhu, G., Jia, Z., Li, Q.: Hierarchical Image Representation Based on Digital Topology for Bridging Remote Sensing and GIS. In: First International Congress on Image and Signal Processing, pp. 736–740 (2008)
Bertrand, G.: On Topological Watersheds. Journal of Mathematical Imaging and Vision 22, 217–230 (2005)
Lotufo, R., Silva, W.: Minimal Set of Markers for the Watershed Transform. In: International Symposium on Mathematical Morphology, pp. 359–368 (2002)
Zhu, G., Liu, X., Jia, Z.: A Multi-level Image Description Model Scheme Based on Digital Topology. In: PIA 2007, 36(3/W49B), International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, Munich, Germany, pp. 185–190 (2007)
Pavlidis, T., Liow, Y.-T.: Integrating Region Growing and Edge Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI 12, 225–233 (1990)
Baldacci, F., Braquelaire, A., Desbarats, P., Domenger, J.-P.: 3D Image Topological Structuring with an Oriented Boundary Graph for Split and Merge Segmentation. In: Coeurjolly, D., Sivignon, I., Tougne, L., Dupont, F. (eds.) DGCI 2008. LNCS, vol. 4992, pp. 541–552. Springer, Heidelberg (2008)
Sun, Y.F., Chen, Y., Zhang, Y.Z., Li, Y.X.: Automated Seeded Region Growing Method for Document Image Binarization Based on Topographic Features. In: Campilho, A.C., Kamel, M.S. (eds.) ICIAR 2004. LNCS, vol. 3212, pp. 200–208. Springer, Heidelberg (2004)
Hsieh, P.-F., Lee, L.C., Chen, N.-Y.: Effect of Spatial Resolution on Classification Errors of Pure and Mixed Pixels in Remote Sensing. IEEE Transactions on Geoscience and Remote Sensing 39(12), 2657–2663 (2001)
Weber, G.H., Scheuermann, G., Hamann, B.: Detecting critical regions in scalar fields. In: EUROGRAPHICS - IEEE TCVG Symposium on Visualization, pp. 1–11 (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Liu, X., Zhu, G., Li, X. (2013). Topological Relationship Extraction by Two Improved Image Segmentation Methods. In: Bian, F., Xie, Y., Cui, X., Zeng, Y. (eds) Geo-Informatics in Resource Management and Sustainable Ecosystem. Communications in Computer and Information Science, vol 398. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-45025-9_53
Download citation
DOI: https://doi.org/10.1007/978-3-642-45025-9_53
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-45024-2
Online ISBN: 978-3-642-45025-9
eBook Packages: Computer ScienceComputer Science (R0)