Abstract
We combine two well-established mathematical morphology notions: watershed segmentation and morphological attribute profile (AP), a multilevel feature extraction method commonly applied to the analysis of remote sensing images. To convey spatial-spectral features of remote sensing images, APs were initially defined as sequences of filtering operators on the max- and min-trees computed from the original data. Since its appearance, the notion of APs has been extended to other hierarchical representations including tree-of-shapes and partition trees such as \(\alpha \)-tree and \(\omega \)-tree. In this article, we propose a novel extension of APs to hierarchical watersheds. Furthermore, we extend the proposed approach to consider prior knowledge from training samples, leading to a more meaningful hierarchy. More precisely, in the construction of hierarchical watersheds, we combine the original data with the semantic knowledge provided by labeled training pixels. We illustrate the relevance of the proposed method with an application in land cover classification using optical remote sensing images, showing that the new profiles outperform various existing features.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Aksoy, S., et al.: Performance evaluation of building detection and digital surface model extraction algorithms: outcomes of the PRRS 2008 algorithm performance contest. In: PRRS 2008, pp. 1–12. IEEE (2008)
Beucher, S., Meyer, F.: The morphological approach to segmentation: the watershed transformation. Math. Morphol. Image Process. 34, 433–481 (1993)
Bosilj, P., Damodaran, B.B., Aptoula, E., Dalla Mura, M., Lefèvre, S.: Attribute profiles from partitioning trees. In: ISMM, pp. 381–392 (2017)
Courty, N., Aptoula, E., Lefèvre, S.: A classwise supervised ordering approach for morphology based hyperspectral image classification. In: ICPR 2012, pp. 1997–2000. IEEE (2012)
Cousty, J., Bertrand, G., Najman, L., Couprie, M.: Watershed cuts: minimum spanning forests and the drop of water principle. IEEE PAMI 31(8), 1362–1374 (2008)
Cousty, J., Najman, L., Perret, B.: Constructive links between some morphological hierarchies on edge-weighted graphs. In: Hendriks, C.L.L., Borgefors, G., Strand, R. (eds.) ISMM 2013. LNCS, vol. 7883, pp. 86–97. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-38294-9_8
Dalla Mura, M., Benediktsson, J., Bruzzone, L.: Self-dual attribute profiles for the analysis of remote sensing images. In: ISMM, pp. 320–330 (2011)
Dalla Mura, M., Benediktsson, J.A., Waske, B., Bruzzone, L.: Morphological attribute profiles for the analysis of very high resolution images. IEEE TGRS 48(10), 3747–3762 (2010)
De Miranda, P.A., Falcão, A.X., Udupa, J.K.: Synergistic arc-weight estimation for interactive image segmentation using graphs. Comput. Vis. Image Underst. 114(1), 85–99 (2010)
Derivaux, S., Forestier, G., Wemmert, C., Lefèvre, S.: Supervised image segmentation using watershed transform, fuzzy classification and evolutionary computation. PRL 31(15), 2364–2374 (2010)
Derivaux, S., Lefevre, S., Wemmert, C., Korczak, J.: Watershed segmentation of remotely sensed images based on a supervised fuzzy pixel classification. In: IEEE IGARSS, pp. 3712–3715 (2006)
Fehri, A., Velasco-Forero, S., Meyer, F.: Prior-based hierarchical segmentation highlighting structures of interest. Math. Morphol. Theory Appl. 3(1), 29–44 (2019)
Ghamisi, P., Souza, R., Benediktsson, J.A., Zhu, X.X., Rittner, L., Lotufo, R.A.: Extinction profiles for the classification of remote sensing data. IEEE Trans. Geosci. Remote Sens. 54(10), 5631–5645 (2016)
Grimaud, M.: New measure of contrast: the dynamics. In: Image Algebra and Morphological Image Processing III,vol. 1769, pp. 292–305. International Society for Optics and Photonics (1992)
Lefèvre, S.: Knowledge from markers in watershed segmentation. In: Kropatsch, W.G., Kampel, M., Hanbury, A. (eds.) CAIP 2007. LNCS, vol. 4673, pp. 579–586. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-74272-2_72
Lefèvre, S., Chapel, L., Merciol, F.: Hyperspectral image classification from multiscale description with constrained connectivity and metric learning. In: 2014 WHISPERS, pp. 1–4. IEEE (2014)
Lefevre, S., Puissant, A., Levoy, F.: Weakly supervised image segmentation: application to mapping and monitoring of salt marsh vegetation in the mont-saint-michel bay from high resolution imagery. In: ESA-EUSC-JRC 2011, pp. 4-p (2011)
Maia, D.S., Pham, M.T., Aptoula, E., Guiotte, F., Lefèvre, S.: Classification of remote sensing data with morphological attributes profiles: a decade of advances. IEEE GRSM (2021)
Pham, M.T., Aptoula, E., Lefèvre, S.: Feature profiles from attribute filtering for classification of remote sensing images. IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens. 11(1), 249–256 (2017)
Soille, P., Pesaresi, M.: Advances in mathematical morphology applied to geoscience and remote sensing. IEEE TGRS 40(9), 2042–2055 (2002)
Tarabalka, Y., Tilton, J.C., Benediktsson, J.A., Chanussot, J.: Marker-based hierarchical segmentation and classification approach for hyperspectral imagery. In: 2011 ICASSP, pp. 1089–1092. IEEE (2011)
Vachier, C., Meyer, F.: Extinction value: a new measurement of persistence. In: IEEE Workshop on Nonlinear Signal and Image Processing, vol. 1, pp. 254–257 (1995)
Velasco-Forero, S., Angulo, J.: Supervised ordering in \(\mathbb{R}^p\): application to morphological processing of hyperspectral images. IEEE TIP 20(11), 3301–3308 (2011)
Volpi, M., Ferrari, V.: Semantic segmentation of urban scenes by learning local class interactions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 1–9 (2015)
Acknowledgements
This work was partially supported by the ANR Multiscale project under the reference ANR-18-CE23-0022. The authors would like to thank Prof. Jon Atli Benediktsson for making available the Reykjavik image.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Santana Maia, D., Pham, MT., Lefèvre, S. (2021). Watershed-Based Attribute Profiles for Pixel Classification of Remote Sensing Data. In: Lindblad, J., Malmberg, F., Sladoje, N. (eds) Discrete Geometry and Mathematical Morphology. DGMM 2021. Lecture Notes in Computer Science(), vol 12708. Springer, Cham. https://doi.org/10.1007/978-3-030-76657-3_8
Download citation
DOI: https://doi.org/10.1007/978-3-030-76657-3_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-76656-6
Online ISBN: 978-3-030-76657-3
eBook Packages: Computer ScienceComputer Science (R0)
