Fusion of Elevation Data into Satellite Image Classification Using Refined Production Rules

Bilal Al Momani, Philip Morrow, Sally McClean

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

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.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages211-220
Number of pages20
Volume6753
DOIs
Publication statusPublished - 22 Jun 2011
Event8th International Conference, ICIAR 2011 - Burnaby, BC, Canada
Duration: 22 Jun 2011 → …

Conference

Conference8th International Conference, ICIAR 2011
Period22/06/11 → …

Fingerprint

image classification
pixel
digital elevation model
satellite image
imagery
spatial distribution
distribution

Cite this

@inproceedings{479a401c9d2e4cb9b13f01ed44ae11a7,
title = "Fusion of Elevation Data into Satellite Image Classification Using Refined Production Rules",
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.",
author = "{Al Momani}, Bilal and Philip Morrow and Sally McClean",
year = "2011",
month = "6",
day = "22",
doi = "10.1007/978-3-642-21593-3_22",
language = "English",
volume = "6753",
pages = "211--220",
booktitle = "Unknown Host Publication",

}

Al Momani, B, Morrow, P & McClean, S 2011, Fusion of Elevation Data into Satellite Image Classification Using Refined Production Rules. in Unknown Host Publication. vol. 6753, pp. 211-220, 8th International Conference, ICIAR 2011, 22/06/11. https://doi.org/10.1007/978-3-642-21593-3_22

Fusion of Elevation Data into Satellite Image Classification Using Refined Production Rules. / Al Momani, Bilal; Morrow, Philip; McClean, Sally.

Unknown Host Publication. Vol. 6753 2011. p. 211-220.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Fusion of Elevation Data into Satellite Image Classification Using Refined Production Rules

AU - Al Momani, Bilal

AU - Morrow, Philip

AU - McClean, Sally

PY - 2011/6/22

Y1 - 2011/6/22

N2 - 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.

AB - 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.

U2 - 10.1007/978-3-642-21593-3_22

DO - 10.1007/978-3-642-21593-3_22

M3 - Conference contribution

VL - 6753

SP - 211

EP - 220

BT - Unknown Host Publication

ER -