Evaluating the efficiency of multisensor satellite data fusion based on the accuracy level of land cover/use classification

Ashraf Sami Elkotb, Shih Jen Huang, Chen Chih Lin, Dong-Jiing Doong

Research output: Contribution to journalArticle

Abstract

The term imagery fusion has been used to describe a variety of combining operations performed to increase the ground resolution of multispectral data. The objective of this study was to characterize and evaluate the impact of different pixellevel fusion methods on the accuracy level of land cover/use classification. Panchromatic FORMOSAT-2 data and multispectral SPOT-6 data were considered, and Brovey, Ehlers, and principal component analysis (PCA) algorithms were used as pixel-level fusion algorithms. The improvement in the accuracy of the fused images relative to the original images was determined. The land cover/use categories were classified into five groups by using a maximum likelihood algorithm. To verify and assess the accuracy of classification, training sites were selected for all land cover/use themes. The classification accuracy was calculated for all images by using error matrices. The greatest improvement in land cover/use classification was obtained by using the Brovey algorithm; the overall accuracy was 93.68% and the kappa coefficient was 0.9115. The next greatest improvement was obtained using the Ehlers algorithm, and the overall accuracy and kappa coefficient were 89.54% and 0.8620, respectively. Finally, the least accurate classification was obtained by using the PCA algorithm; the overall accuracy was 88.36% and the kappa coefficient was 0.8247. Comparing the fused images with the original images, the overall accuracy of 86.36% and kappa coefficient value of 0.8036, which were obtained for the original images, were used as benchmarks.

Original languageEnglish
Pages (from-to)800-806
Number of pages7
JournalJournal of Marine Science and Technology (Taiwan)
Volume23
Issue number5
DOIs
Publication statusPublished - 2015 Jan 1

Fingerprint

Data fusion
satellite data
land cover
Satellites
Principal component analysis
principal component analysis
SPOT
Maximum likelihood
pixel
imagery
Pixels
matrix

All Science Journal Classification (ASJC) codes

  • Oceanography
  • Ocean Engineering
  • Mechanics of Materials
  • Mechanical Engineering

Cite this

@article{51ab35fbd11a47afa5629a9782664712,
title = "Evaluating the efficiency of multisensor satellite data fusion based on the accuracy level of land cover/use classification",
abstract = "The term imagery fusion has been used to describe a variety of combining operations performed to increase the ground resolution of multispectral data. The objective of this study was to characterize and evaluate the impact of different pixellevel fusion methods on the accuracy level of land cover/use classification. Panchromatic FORMOSAT-2 data and multispectral SPOT-6 data were considered, and Brovey, Ehlers, and principal component analysis (PCA) algorithms were used as pixel-level fusion algorithms. The improvement in the accuracy of the fused images relative to the original images was determined. The land cover/use categories were classified into five groups by using a maximum likelihood algorithm. To verify and assess the accuracy of classification, training sites were selected for all land cover/use themes. The classification accuracy was calculated for all images by using error matrices. The greatest improvement in land cover/use classification was obtained by using the Brovey algorithm; the overall accuracy was 93.68{\%} and the kappa coefficient was 0.9115. The next greatest improvement was obtained using the Ehlers algorithm, and the overall accuracy and kappa coefficient were 89.54{\%} and 0.8620, respectively. Finally, the least accurate classification was obtained by using the PCA algorithm; the overall accuracy was 88.36{\%} and the kappa coefficient was 0.8247. Comparing the fused images with the original images, the overall accuracy of 86.36{\%} and kappa coefficient value of 0.8036, which were obtained for the original images, were used as benchmarks.",
author = "Elkotb, {Ashraf Sami} and Huang, {Shih Jen} and Lin, {Chen Chih} and Dong-Jiing Doong",
year = "2015",
month = "1",
day = "1",
doi = "10.6119/JMST-014-1202-1",
language = "English",
volume = "23",
pages = "800--806",
journal = "Journal of Marine Science and Technology",
issn = "1023-2796",
publisher = "National Taiwan Ocean University",
number = "5",

}

Evaluating the efficiency of multisensor satellite data fusion based on the accuracy level of land cover/use classification. / Elkotb, Ashraf Sami; Huang, Shih Jen; Lin, Chen Chih; Doong, Dong-Jiing.

In: Journal of Marine Science and Technology (Taiwan), Vol. 23, No. 5, 01.01.2015, p. 800-806.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Evaluating the efficiency of multisensor satellite data fusion based on the accuracy level of land cover/use classification

AU - Elkotb, Ashraf Sami

AU - Huang, Shih Jen

AU - Lin, Chen Chih

AU - Doong, Dong-Jiing

PY - 2015/1/1

Y1 - 2015/1/1

N2 - The term imagery fusion has been used to describe a variety of combining operations performed to increase the ground resolution of multispectral data. The objective of this study was to characterize and evaluate the impact of different pixellevel fusion methods on the accuracy level of land cover/use classification. Panchromatic FORMOSAT-2 data and multispectral SPOT-6 data were considered, and Brovey, Ehlers, and principal component analysis (PCA) algorithms were used as pixel-level fusion algorithms. The improvement in the accuracy of the fused images relative to the original images was determined. The land cover/use categories were classified into five groups by using a maximum likelihood algorithm. To verify and assess the accuracy of classification, training sites were selected for all land cover/use themes. The classification accuracy was calculated for all images by using error matrices. The greatest improvement in land cover/use classification was obtained by using the Brovey algorithm; the overall accuracy was 93.68% and the kappa coefficient was 0.9115. The next greatest improvement was obtained using the Ehlers algorithm, and the overall accuracy and kappa coefficient were 89.54% and 0.8620, respectively. Finally, the least accurate classification was obtained by using the PCA algorithm; the overall accuracy was 88.36% and the kappa coefficient was 0.8247. Comparing the fused images with the original images, the overall accuracy of 86.36% and kappa coefficient value of 0.8036, which were obtained for the original images, were used as benchmarks.

AB - The term imagery fusion has been used to describe a variety of combining operations performed to increase the ground resolution of multispectral data. The objective of this study was to characterize and evaluate the impact of different pixellevel fusion methods on the accuracy level of land cover/use classification. Panchromatic FORMOSAT-2 data and multispectral SPOT-6 data were considered, and Brovey, Ehlers, and principal component analysis (PCA) algorithms were used as pixel-level fusion algorithms. The improvement in the accuracy of the fused images relative to the original images was determined. The land cover/use categories were classified into five groups by using a maximum likelihood algorithm. To verify and assess the accuracy of classification, training sites were selected for all land cover/use themes. The classification accuracy was calculated for all images by using error matrices. The greatest improvement in land cover/use classification was obtained by using the Brovey algorithm; the overall accuracy was 93.68% and the kappa coefficient was 0.9115. The next greatest improvement was obtained using the Ehlers algorithm, and the overall accuracy and kappa coefficient were 89.54% and 0.8620, respectively. Finally, the least accurate classification was obtained by using the PCA algorithm; the overall accuracy was 88.36% and the kappa coefficient was 0.8247. Comparing the fused images with the original images, the overall accuracy of 86.36% and kappa coefficient value of 0.8036, which were obtained for the original images, were used as benchmarks.

UR - http://www.scopus.com/inward/record.url?scp=84946849255&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84946849255&partnerID=8YFLogxK

U2 - 10.6119/JMST-014-1202-1

DO - 10.6119/JMST-014-1202-1

M3 - Article

VL - 23

SP - 800

EP - 806

JO - Journal of Marine Science and Technology

JF - Journal of Marine Science and Technology

SN - 1023-2796

IS - 5

ER -