Abstract
In this report, a method for remote sensing data segmentation is proposed. For image approximation, the segments with minimal difference between adjusted threshold parameter and segment variance or entropy are selected. The generation of image hierarchical segmentation based on intensity gradient analysis and computation of object segments accounting for variance (entropy) are considered. For the algorithm generalization, the method of sequential image approximations within prescribed standard deviation values by means of image segments computed in merging/splitting technique is proposed. The peculiarities of data structures for optimization of computations are discussed. The comparison with known methods is outlined.
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 subscriptionsNotes
- 1.
Image 2.2.01. (San Diego) from University of Southern California’s Signal and Image Processing Institute image database. http://sipi.usc.edu/database/index.html.
- 2.
The term “standard deviation” is used as a synonym for “root mean square” referring to the square root of the mean squared deviation of an image from a given approximation (fit).
References
Berlant A., Coshcarev A. (1999) Geoinformatics. Definition dictionary. Publisher «GIS Association», Moscow.
Potapichev S. (2005). Architecture of intelligent GIS. Proceeding of workshop IF&GIS’05. Saint Petersburg.
Shapiro L., Stockman G.(2006). Computer vision. Publisher «Binom», Moscow.
Gonzalez R., Woods R. (2006). Digital image processing. Publisher «Technosphere», Moscow.
Selim Aksoy. Spatial Techniques for Image Classification. «Image Processing for Remote Sensing». Ed. Chi Hau Chen. CRC Press, Boca Raton, 2008.
«Intelligent images analysis in GIS». Philipp Galjano and Vasily Popovich. Ceминap Information Fusion and Geographic Information System 2007. Springer, New York.
Kharinov M.V. (2006) Storage and Adaptive Processing of Digital Image Information. St. Petersburg University Press, St. Petersburg — 138 p. (in Russian).
Robinson D. J., Redding N. J., Crisp D. J. (2002) Implementation of a fast algorithm for segmenting SAR imagery: Scientific and Technical Report, — Australia: Defense Science and Technology Organization. — 42 p.
ENVI Feature Extraction Module User’s Guide (2008). http://www.ittvis.com/portals/0/pdfs/envi/Feature_Extraction_Module.pdf
Kharinov M.V., Galiano P.R. (2009) Recognition of Images represented in Different Gradations of Pixel Values // Mathematical tools for Pattern Recognition / Proc. 14–th AllRussian Conf, Suzdal. — Moscow: MAKS Press,— P. 465–468. (in Russian).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Galiano, P., Kharinov, M., Kuzenny, V. (2011). Remote Sensing Data Analysis Based on Hierarchical Image Approximation with Previously Computed Segments. In: Popovich, V., Claramunt, C., Devogele, T., Schrenk, M., Korolenko, K. (eds) Information Fusion and Geographic Information Systems. Lecture Notes in Geoinformation and Cartography(), vol 5. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-19766-6_10
Download citation
DOI: https://doi.org/10.1007/978-3-642-19766-6_10
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-19765-9
Online ISBN: 978-3-642-19766-6
eBook Packages: Earth and Environmental ScienceEarth and Environmental Science (R0)