Abstract
The image classification process is based on the assumption that pixels which have similar spatial distribution patterns, or statistical characteristics, belong to the same spectral class. In a previous study we have shown how we can improve the accuracy of classification of remotely sensed imagery data by incorporating contextual elevation knowledge in a form of a digital elevation model with the output of the classification process using Dempster-Shafer Theory of Evidence. A knowledge based approach is created for this purpose using suitable production rules derived from the elevation distributions and range of values for the elevation data attached to a particular satellite image. Production rules are the major part of knowledge representation and have the basic form: IF condition THEN Inference. Although the basic form of production rules has shown accuracy improvement, in general, in some cases accuracy can degrade. In this paper we propose a “refined” approach that takes into account the actual “distribution” of elevation values for each class rather than simply the “range” of values to solve the accuracy degradation. This approach is performed by refining the basic production rules used in the previous study taking into account the number of pixels at each elevation within the elevation distribution for each class.
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
Momani, B.M., Morrow, P.J., McClean, S.I.: Using Dempster-Shafer to incorporate knowledge into satellite image classification. Artif. Intell. Rev. 25, 161–178 (2006)
Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the EM algorithm. Royal Statistical Soc. B 39, 1–39 (1977)
Vatsavai, R.R., Shekhar, S., Burk, T.E.: A Semi-Supervised Learning Method for Remote Sensing Data Mining. In: Proc. ICTAI, pp. 207–211 (2005)
Benkhalifa, M., Bensaid, A., Mouradi, A.: Text categorization using the semi-supervised fuzzy c-means algorithm. NAFIPS, 561–565 (June 1999)
Huimin, G., Xutao, D., Bastola, D., Ali, H.: On clustering biological data using unsupervised and semi-supervised message passing. BIBE, 294–298 (2005)
Dempster, A.P.: A Generalisation of Bayesian Inference. J. of the Royal Statistical Society B 30, 205–247 (1968)
Guan, J.W., Bell, D.A.: Evidence Theory and its Applications. Elsevier Science Inc., New York (1991)
McClean, S.I., Scotney, B.W.: Using Evidence Theory for the Integration of Distributed Databases. Int. Journal of Intelligent Systems 12, 763–776 (1997)
Le Héegarat-Mascle, S., Richard, D., Ottl´e, C.: Multi-scale data fusion using Dempster-Shafer evidence theory. In: ICAE, vol. 10, pp. 9–22 (2003)
Yager, R.R., Engemann, K.J., Filev, D.P.: On the Concept of Immediate Probabilities. Int. Journal of Intelligent Systems 10, 373–397 (1995)
Muaralikrishna, I.V.: Image Classification and Performance Evaluation of IRS IC LISS – III Data. In: IEEE Conference on Geoscience and Remote Sensing, vol. 4(S), pp. 1772–1774 (1997)
The US Geological Survey, http://www.seamless.usgs.gov (cited January 10, 2011)
Congalton, R.G.: Accuracy assessment and validation of remotely sensed and other spatial information. Int. Journal of Wildland Fire 10, 321–328 (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Momani, B.A., Morrow, P., McClean, S. (2011). Fusion of Elevation Data into Satellite Image Classification Using Refined Production Rules. In: Kamel, M., Campilho, A. (eds) Image Analysis and Recognition. ICIAR 2011. Lecture Notes in Computer Science, vol 6753. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-21593-3_22
Download citation
DOI: https://doi.org/10.1007/978-3-642-21593-3_22
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-21592-6
Online ISBN: 978-3-642-21593-3
eBook Packages: Computer ScienceComputer Science (R0)