Classification for Landfast Ice Types in the Greenland of the Arctic by Using Multifrequency SAR images

Do-Hyun Hwang, Byonjun Hwang, Hong-Joo Yoon

Research output: Contribution to journalArticle

Abstract

To classify the landfast ice in the north of the Greenland, observation data, multifrequency Synthetic Aperture Radar (SAR) images and texture images were used. The total four types of sea ice are first year ice, highly deformed ice, ridge and moderately deformed ice. The texture images that were processed by K-means algorithm showed higher accuracy than the ones that were processed by SAR images; however, overall accuracy of maximum likelihood algorithm using texture images did not show the highest accuracy all the time. It turned out that when using K-means algorithm, the accuracy of the multi SAR images were higher than the single SAR image. When using the maximum likelihood algorithm, the results of single and multi SAR images are differ from each other, therefore, maximum likelihood algorithm method should be used properly.
Original languageEnglish
Pages (from-to)1-9
Number of pages9
JournalKorean Journal of Remote Sensing
Volume29
Issue number1
DOIs
Publication statusPublished - 2013
Externally publishedYes

Fingerprint

synthetic aperture radar
ice
texture
ice ridge
sea ice

Cite this

@article{f975ef9efe2345918aadf4c582df7cbc,
title = "Classification for Landfast Ice Types in the Greenland of the Arctic by Using Multifrequency SAR images",
abstract = "To classify the landfast ice in the north of the Greenland, observation data, multifrequency Synthetic Aperture Radar (SAR) images and texture images were used. The total four types of sea ice are first year ice, highly deformed ice, ridge and moderately deformed ice. The texture images that were processed by K-means algorithm showed higher accuracy than the ones that were processed by SAR images; however, overall accuracy of maximum likelihood algorithm using texture images did not show the highest accuracy all the time. It turned out that when using K-means algorithm, the accuracy of the multi SAR images were higher than the single SAR image. When using the maximum likelihood algorithm, the results of single and multi SAR images are differ from each other, therefore, maximum likelihood algorithm method should be used properly.",
keywords = "Arctic, Synthetic Aperture Radar (SAR), K-means, Maximum likelihood",
author = "Do-Hyun Hwang and Byonjun Hwang and Hong-Joo Yoon",
year = "2013",
doi = "10.7780/kjrs.2013.29.1.1",
language = "English",
volume = "29",
pages = "1--9",
journal = "Korean Journal of Remote Sensing",
issn = "1225-6161",
number = "1",

}

Classification for Landfast Ice Types in the Greenland of the Arctic by Using Multifrequency SAR images. / Hwang, Do-Hyun; Hwang, Byonjun; Yoon, Hong-Joo.

In: Korean Journal of Remote Sensing, Vol. 29, No. 1, 2013, p. 1-9.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Classification for Landfast Ice Types in the Greenland of the Arctic by Using Multifrequency SAR images

AU - Hwang, Do-Hyun

AU - Hwang, Byonjun

AU - Yoon, Hong-Joo

PY - 2013

Y1 - 2013

N2 - To classify the landfast ice in the north of the Greenland, observation data, multifrequency Synthetic Aperture Radar (SAR) images and texture images were used. The total four types of sea ice are first year ice, highly deformed ice, ridge and moderately deformed ice. The texture images that were processed by K-means algorithm showed higher accuracy than the ones that were processed by SAR images; however, overall accuracy of maximum likelihood algorithm using texture images did not show the highest accuracy all the time. It turned out that when using K-means algorithm, the accuracy of the multi SAR images were higher than the single SAR image. When using the maximum likelihood algorithm, the results of single and multi SAR images are differ from each other, therefore, maximum likelihood algorithm method should be used properly.

AB - To classify the landfast ice in the north of the Greenland, observation data, multifrequency Synthetic Aperture Radar (SAR) images and texture images were used. The total four types of sea ice are first year ice, highly deformed ice, ridge and moderately deformed ice. The texture images that were processed by K-means algorithm showed higher accuracy than the ones that were processed by SAR images; however, overall accuracy of maximum likelihood algorithm using texture images did not show the highest accuracy all the time. It turned out that when using K-means algorithm, the accuracy of the multi SAR images were higher than the single SAR image. When using the maximum likelihood algorithm, the results of single and multi SAR images are differ from each other, therefore, maximum likelihood algorithm method should be used properly.

KW - Arctic

KW - Synthetic Aperture Radar (SAR)

KW - K-means

KW - Maximum likelihood

UR - https://www.researchgate.net/publication/263438528_Classification_for_Landfast_Ice_Types_in_the_Greenland_of_the_Arctic_by_Using_Multifrequency_SAR_Images

U2 - 10.7780/kjrs.2013.29.1.1

DO - 10.7780/kjrs.2013.29.1.1

M3 - Article

VL - 29

SP - 1

EP - 9

JO - Korean Journal of Remote Sensing

JF - Korean Journal of Remote Sensing

SN - 1225-6161

IS - 1

ER -