DOI:
https://doi.org/10.14483/22487638.9250Publicado:
2014-12-01Número:
Vol. 18 (2014): Special Edition DoctorateSección:
ReflexiónTopological challenges in multispectral image segmentation
Retos topológicos en la segmentación de imágenes multiespectrales
Palabras clave:
multispectral images, segmentation, topologic space. (en).Palabras clave:
multispectral images, segmentation, topologic space. (es).Descargas
Resumen (en)
Land cover classification from remote sensing multispectral images has been traditionallyconducted by using mainly spectral information associated with discrete spatial units (i.e. pixels).Geometric and topological characteristics of the spatial context close to every pixel have been either not fully treated or completely ignored.This article provides a review of the strategies used by a number of researchers in order to include spatial and topological properties in image segmentation.It is shown how most of researchers have proposed to perform -previous to classification- a grouping or segmentation of nearby pixels by modeling neighborhood relationships as 4-connected, 8-connected and (a, b) – connected graphs.In this object-oriented approach, however, topological concepts such as neighborhood, contiguity, connectivity and boundary suffer from ambiguity since image elements (pixels) are two-dimensional entities composing a spatially uniform grid cell (i.e. there are not uni-dimensional nor zero-dimensional elements to build boundaries). In order to solve such topological paradoxes, a few proposals have been proposed. This review discusses how the alternative of digital images representation based on Cartesian complexes suggested by Kovalevsky (2008) for image segmentation in computer vision, does not present topological flaws, typical of conventional solutions based on grid cells. However, such a proposal has not been yet applied to multispectral image segmentation in remote sensing. This review is part of the PhD in Engineering research conducted by the first author under guidance of the second one. This review concludes suggesting the need to research on the potential of using Cartesian complexes for multispectral image segmentation.Resumen (es)
La clasificación de la cobertura terrestre a partir de imágenes multiespectrales de teledetección se ha llevado a cabo tradicionalmente utilizando información principalmente espectral asociada a unidades espaciales discretas (es decir, píxeles). Las características geométricas y topológicas del contexto espacial cercanas a cada píxel no se han tratado del todo o se han ignorado por completo. proporciona una revisión de las estrategias utilizadas por un número de investigadores para incluir propiedades espaciales y topológicas en la segmentación de imágenes. Se muestra cómo la mayoría de los investigadores han propuesto realizar, antes de la clasificación, una agrupación o segmentación de píxeles cercanos modelando el vecindario relaciones como 4 conectadas, 8 conectadas y (a, b) conectadas. Sin embargo, en este enfoque orientado a objetos, los conceptos topológicos como vecindad, contigüidad, conectividad y límite sufren de ambigüedad ya que los elementos de imagen (píxeles) son dos entidades tridimensionales que componen una celda de cuadrícula espacialmente uniforme (es decir, no hay uni-di elementos mensionales o de cero dimensiones para construir límites). Para resolver tales paradojas topológicas, se han propuesto algunas propuestas. Esta revisión discute cómo la alternativa de representación de imágenes digitales basada en complejos cartesianos sugerida por Kovalevsky (2008) para la segmentación de imágenes en visión artificial, no presenta fallas topológicas, típicas de soluciones convencionales basadas en celdas de grillas. Sin embargo, tal propuesta aún no se ha aplicado a la segmentación de imágenes multiespectrales en teledetección. Esta revisión es parte del doctorado en investigación de ingeniería conducida por el primer autor bajo la dirección del segundo. Esta revisión concluye sugiriendo la necesidad de investigar sobre el potencial del uso de complejos cartesianos para la segmentación de imágenes multiespectrales.
Referencias
Arbeláez, P., Maire, M., Fowlkes, C.,& Malik,J. (2009). “From Contoursto Regions: An Empirical Evaluation,” Proc. IEEE Conf. ComputerVision and Pattern Recognition.
Arbeláez, P.; Maire, M.; Fowlkes, C. & Malik, J. (2011). Contour Detection and Hierarchical Image Segmentation IEEE Trans. Pattern Anal. Mach. Intell., IEEE Computer Society,vol. 33, no 5,pp. 898-916.
Baatz, M., & Schape,A.(2000). Multiresolution segmentation:An optimization approach for high quality multi-scale imagesegmentation., Angewandte Geographische Informations-Verarbeitung XII (J. Strobl, T. Blaschke, and G. Griesebner,editors), Wichmann Verlag, Karlsruhe, pp. 12–23.
Benz, U., Hofmann,P., Willhauck,G., Lingenfelder,I.,& Heynen,M. (2004). Multi-resolution, object-oriented fuzzy analysisof remote sensing data for GIS-ready information, ISPRS Journalof Photogrammetry and Remote Sensing, 58(3–4), pp.239–258.
Blaschke, T. (2009). Object based image analysis for remote sensing. International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS). Published by Elsevier B.V. All rights reserved.
Brice, R., & Fennema, C.L.(1970). Scene analysis using regions. Artificial Intelligence 1, pp. 205–226.
Brun, L., Mokhtari, M. & Domenger, J. P. (2003). Incremental modifications on segmented image defined by discrete maps. Journal of Visual Communication and Image Representation, vol. 14, no. 3, pp.251–290, September 2003.
Cantor, G. (1883). "Überunendliche, linearePunktmannigfaltigkeiten V" [On infinite, linear point-manifolds (sets)], MathematischeAnnalen, vol. 21, pp. 545–591.
Cracknell, A.P. (1998). Synergy in Remote Sensing –What's in a Pixel?, International Journal of Remote Sensing, Vol. 19, pp. 2025 –2047.
Chen, C., Freedman, D.,&Lampert, C. (2011).Enforcing topological constraints in random field image segmentation.2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2089- 2096.
Cheevasuvut, F., Maitre, H., & Vidal-Madjar, D. (1986). A robust method for picture segmentation based ona split and merge procedure. CVGIP 34, pp. 268–281.
de Berg, M., Cheong, O., Kreveld, M., &Overmars, M. (2008). Computational Geometry: Algorithms and Applications (3d ed.). Springer-Verlag Berlin Heidelberg.
de Jong, S.M., & van der Meer, F.D.(2004). Remote Sensing Image Analysis Including the Spatial Domain.Springer. Dordrecht, The Netherlands.
deLoera, J., Rambau, J.,& Santos, F. (2010). Triangulations: Structures for Algorithms and Applications. Springer-Verlag Berlin Heidelberg, pp 377-383.
Felzenszwalb, P. F.,&Huttenlocher, D. P. (2004).Efficient graph-based image segmentation. InternationalJournal of Computer Vision, vol. 59, no. 2, pp. 167–181. September 2004.
Grady, L. (2012).Targeted Image Segmentation Using GraphMethods.Image Processingand Analysiswith Graphs: Theory and Practice.CRC Press.Taylor & Francis Group, pp. 111-140.
Guigues, L., le Men, H., Cocquerez, J.-P., 2001. Graphs, cocoons and image segmentation.Third Workshop on Graph Based Representations in PatternRecognition (GbR’2001), Ischia, Italy, May 2001. IAPR-TC15, CUEN. ISBN 88 7146 579-2, pp. 22–31.
Horowitz, S.L., &Pavlidis, T.(1976).Picture segmentation by a tree traversal algorithm. J. Association for Computing Machinery 23 (2), pp. 368–388.
Ishikawa, H.(2012).Graph Cuts—Combinatorial Optimization in Vision. Image Processingand Analysiswith Graphs: Theory and Practice.CRC Press.Taylor & Francis Group, pp. 25-64.
Johansen, K., Coops, N.C., Gergel, S.E.,&Stange, J. (2007).Application of high spatial resolution satellite imagery for riparian and forest ecosystem classification.Remote Sensing of Environment 110 (1), pp. 29-44.
Knuth, D.(1992). Axioms and hulls. Berlin:Springer-Verlag. ISBN:9783540556114.
Kong, C., Xu, K., &Wu, C. (2006).Classification and extraction of urban land-use information from high-resolution image based on object multi-features. Journal of China University of Geosciences 17 (2), pp. 151-157.
Kong, T.Y. & Rosenfeld.(1991). Digital Topology, a Comparison of the graph based and Topological Approaches. In G.M. Reed, A.W. Ronscoe, and R.F. Wachter (eds): Topology and Category Theory in Computer Science, Oxford University press, Oxford, U.K, pp. 273-289.
Kovalevsky, V. A.(1984). Discrete topology and contour definition, Pattern Recognit.Lett. 2, No.5, pp. 281-288.
Kovalevsky, V. A. (1989). Finite Topology as Applied to Image Analysis. Computer Vision, Graphics, and Image Processing. V 45, No 2, pp. 141-161.
Kovalevsky, V. (2001).Algorithms and Data Structures for Computer Topology Digital and Image Geometry, Springer Berlin Heidelberg, vol. 2243, pp. 38-58
Kovalevsky, V. (2005). Algorithms in Digital Geometry Based on Cellular Topology Combinatorial Image Analysis, Springer Berlin Heidelberg, vol. 3322, pp. 366-393.
Kovalevsky, V. A. (2006). Axiomatic Digital Topology, Department of Computer Science, University of Applied Sciences Berlin, Luxemburger Str. 10, 13353 Berlin, Germany.
Kovalevsky, V. A. (2008). Geometry of Locally Finite Spaces, DrBaerbelKovalevskiVERLAG Berlin, Luxemburger Str. 10, 13353 Berlin, Germany.
Letscher, D.,&Fritts, J. (2007).Image Segmentation Using Topological Persistence.Computer Analysis of Images and Patterns. Lecture Notes in Computer Science Volume 4673, pp. 587-595.
Li, C.,& Sun, Y. (2010). Active Image: A Shape And Topology Preserving Segmentation Method Using B-Spline Free Form Deformations. Proceedings of 2010 IEEE 17th International Conference on Image Processing,pp. 2221- 2224.
Listing, J. (1862).Der census räumlichercomplexe.Abhandlungen der KöniglichenGesellschaft der WissenschaftenzuGöttingen, vol. 10, pp. 97 – 182.
Lizarazo, I. &Elsner, P.(2009).Fuzzy segmentation for object‐based image classificationInternational Journal of Remote Sensing 30 (6), pp.1643-1649
Lizarazo, I. (2014). Accuracy assessment of object‐based image classification: another STEP. International Journal of Remote Sensing 35 (16), pp. 1-22.
Munkres, J. (1999) Topology. Prentice Hall, 2nd edition
Neubert, M.,Herold, H.,Meinel, G., &Blaschke, T.(2008).Assessing image segmentation quality concepts, methods and application Object-Based. Image Analysis, Springer Berlin Heidelberg, pp. 769-784.
Nunez, J., Kennedy, R., Parag, T., Shi, J., &Chklovskii, D. B. (2013).Machine learning of hierarchical clustering to segment 2D and 3D images.PLoS ONE 8:e71715. doi: 10.1371/journal.pone.0071715.
Oxley, J.(2003). What is a matroid? Cubo 5, pp 179–218. www.math.lsu.edu/~oxley/ survey4.pdf . [Consulta: 12-04-2011]
Pavlidis, T.(1977).Structural Pattern Recognition, Springer-Verlag, New York.
Pfeifle, J.,&Rambau, M. (2002). Computing Triangulations Using Oriented Matroids. ZIB-Report 02-02, Konrad-Zuse-ZentrumfürInformationstechnik Berlin.
Richter-Gebert, J.,&Ziegler, M.(2004).Oriented Matroids. Handbook of Discrete and Computational Geometry, 2nd Ed. Boca Raton: Chapman & Hall/CRCPress, pp. 129-151.
Rinow, W. (1975).Textbook of topology.VEBDeutscherVerlag der Wissenschaften, Berlin.
Rosenfeld, A.(1970). Connectivity in digital pictures, J. ACM 17, pp. 146-160.
Saeedi, N. B. (2012). On Fully Characterizing Terrain Visibility Graphs. A thesis submitted in partial fulfillment of the requirements for the degree of Master of Science. The University of British Columbia.
Schneider, M.(1997). Spatial Data Types for Database Systems: Finite Resolution Geometries for Geographic Information Systems. Lecture Notes in Computer Science, Vol. 1288. Berlin: Springer.
Stell, J., &Webster, J. (2007).Oriented Matroids as a Foundation for Space in GIS. Computers, Environment and Urban Systems, Vol. 31, Issue 4, July 2007, pp. 379-392
Stilwell, J. (1995). Classical topology and combinatorial group theory.Springer.
Tso, B., & Mather, P. (2009).Classification Methods for Remotely Sensed Data.CRC Press, Taylor & Francis Group. Boca Raton, FL.
Urquhart, R. (1982). Graph theoretical clustering based on limitedneighborhood sets. Pattern Recognition, 15(3), pp. 173–187.
Whitney, H.(1935). On the abstract properties of linear dependence. American Journal of Mathematics 57, pp. 509–533.
Worboys, M.,&Duckham, M.(2004). GIS: A Computing Perspective, Second Edition, CRC Press, pp. 90-113.
Yu, Q., Gong, P., Chinton, N., Biging, G., Kelly, M.,&Schirokauer, D. (2006). Objectbased detailed vegetation classification with airborne high spatial resolution remote sensing imagery. Photogrammetric Engineering & Remote Sensing 72 (7), pp. 799-811.
Zahn, C.T. (1971). Graph-theoretic methods for detecting and describinggestalt clusters. IEEE Transactions on Computing, 20, pp. 68–86.
Cómo citar
APA
ACM
ACS
ABNT
Chicago
Harvard
IEEE
MLA
Turabian
Vancouver
Descargar cita
Licencia
Esta licencia permite a otros remezclar, adaptar y desarrollar su trabajo incluso con fines comerciales, siempre que le den crédito y concedan licencias para sus nuevas creaciones bajo los mismos términos. Esta licencia a menudo se compara con las licencias de software libre y de código abierto “copyleft”. Todos los trabajos nuevos basados en el tuyo tendrán la misma licencia, por lo que cualquier derivado también permitirá el uso comercial. Esta es la licencia utilizada por Wikipedia y se recomienda para materiales que se beneficiarían al incorporar contenido de Wikipedia y proyectos con licencias similares.
